Commit
·
6cb6113
1
Parent(s):
b1775c3
upload
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- llama2_13b_peft/paragraph_segmentation/README.md +94 -0
- llama2_13b_peft/paragraph_segmentation/adapter_config.json +34 -0
- llama2_13b_peft/paragraph_segmentation/adapter_model.safetensors +3 -0
- llama2_13b_peft/paragraph_segmentation/all_results.json +12 -0
- llama2_13b_peft/paragraph_segmentation/eval_results.json +7 -0
- llama2_13b_peft/paragraph_segmentation/special_tokens_map.json +24 -0
- llama2_13b_peft/paragraph_segmentation/tokenizer.model +3 -0
- llama2_13b_peft/paragraph_segmentation/tokenizer_config.json +45 -0
- llama2_13b_peft/paragraph_segmentation/train_results.json +8 -0
- llama2_13b_peft/paragraph_segmentation/trainer_log.jsonl +321 -0
- llama2_13b_peft/paragraph_segmentation/trainer_state.json +2292 -0
- llama2_13b_peft/paragraph_segmentation/training_args.bin +3 -0
- llama2_13b_peft/paragraph_segmentation/training_eval_loss.png +0 -0
- llama2_13b_peft/paragraph_segmentation/training_loss.png +0 -0
- llama2_13b_peft/play_dialog_same_or_different/README.md +73 -0
- llama2_13b_peft/play_dialog_same_or_different/adapter_config.json +34 -0
- llama2_13b_peft/play_dialog_same_or_different/adapter_model.safetensors +3 -0
- llama2_13b_peft/play_dialog_same_or_different/all_results.json +12 -0
- llama2_13b_peft/play_dialog_same_or_different/eval_results.json +7 -0
- llama2_13b_peft/play_dialog_same_or_different/special_tokens_map.json +24 -0
- llama2_13b_peft/play_dialog_same_or_different/tokenizer.model +3 -0
- llama2_13b_peft/play_dialog_same_or_different/tokenizer_config.json +45 -0
- llama2_13b_peft/play_dialog_same_or_different/train_results.json +8 -0
- llama2_13b_peft/play_dialog_same_or_different/trainer_log.jsonl +90 -0
- llama2_13b_peft/play_dialog_same_or_different/trainer_state.json +654 -0
- llama2_13b_peft/play_dialog_same_or_different/training_args.bin +3 -0
- llama2_13b_peft/play_dialog_same_or_different/training_eval_loss.png +0 -0
- llama2_13b_peft/play_dialog_same_or_different/training_loss.png +0 -0
- llama2_13b_peft/question_selection/README.md +69 -0
- llama2_13b_peft/question_selection/adapter_config.json +33 -0
- llama2_13b_peft/question_selection/adapter_model.safetensors +3 -0
- llama2_13b_peft/question_selection/all_results.json +11 -0
- llama2_13b_peft/question_selection/eval_results.json +7 -0
- llama2_13b_peft/question_selection/special_tokens_map.json +24 -0
- llama2_13b_peft/question_selection/tokenizer.model +3 -0
- llama2_13b_peft/question_selection/tokenizer_config.json +45 -0
- llama2_13b_peft/question_selection/train_results.json +7 -0
- llama2_13b_peft/question_selection/trainer_log.jsonl +51 -0
- llama2_13b_peft/question_selection/trainer_state.json +377 -0
- llama2_13b_peft/question_selection/training_args.bin +3 -0
- llama2_13b_peft/question_selection/training_eval_loss.png +0 -0
- llama2_13b_peft/question_selection/training_loss.png +0 -0
- llama2_13b_peft/reasoning_about_colored_objects/README.md +69 -0
- llama2_13b_peft/reasoning_about_colored_objects/adapter_config.json +34 -0
- llama2_13b_peft/reasoning_about_colored_objects/adapter_model.safetensors +3 -0
- llama2_13b_peft/reasoning_about_colored_objects/all_results.json +12 -0
- llama2_13b_peft/reasoning_about_colored_objects/eval_results.json +7 -0
- llama2_13b_peft/reasoning_about_colored_objects/special_tokens_map.json +24 -0
- llama2_13b_peft/reasoning_about_colored_objects/tokenizer.model +3 -0
- llama2_13b_peft/reasoning_about_colored_objects/tokenizer_config.json +45 -0
llama2_13b_peft/paragraph_segmentation/README.md
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: /data1/model/llama2/meta-llama/Llama2-13b
|
| 9 |
+
model-index:
|
| 10 |
+
- name: paragraph_segmentation_no_sys
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# paragraph_segmentation_no_sys
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the paragraph_segmentation_no_sys dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1180
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 2
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- total_eval_batch_size: 8
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_steps: 20
|
| 51 |
+
- num_epochs: 5.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 57 |
+
| 0.2344 | 0.1170 | 100 | 0.2354 |
|
| 58 |
+
| 0.2247 | 0.2339 | 200 | 0.2296 |
|
| 59 |
+
| 0.2009 | 0.3509 | 300 | 0.2020 |
|
| 60 |
+
| 0.2097 | 0.4678 | 400 | 0.1956 |
|
| 61 |
+
| 0.185 | 0.5848 | 500 | 0.1874 |
|
| 62 |
+
| 0.1804 | 0.7018 | 600 | 0.1784 |
|
| 63 |
+
| 0.1647 | 0.8187 | 700 | 0.1701 |
|
| 64 |
+
| 0.1663 | 0.9357 | 800 | 0.1684 |
|
| 65 |
+
| 0.1553 | 1.0526 | 900 | 0.1524 |
|
| 66 |
+
| 0.1665 | 1.1696 | 1000 | 0.1584 |
|
| 67 |
+
| 0.1424 | 1.2865 | 1100 | 0.1660 |
|
| 68 |
+
| 0.1163 | 1.4035 | 1200 | 0.1442 |
|
| 69 |
+
| 0.1593 | 1.5205 | 1300 | 0.1365 |
|
| 70 |
+
| 0.1529 | 1.6374 | 1400 | 0.1444 |
|
| 71 |
+
| 0.1321 | 1.7544 | 1500 | 0.1334 |
|
| 72 |
+
| 0.135 | 1.8713 | 1600 | 0.1293 |
|
| 73 |
+
| 0.1322 | 1.9883 | 1700 | 0.1401 |
|
| 74 |
+
| 0.1355 | 2.1053 | 1800 | 0.1292 |
|
| 75 |
+
| 0.1227 | 2.2222 | 1900 | 0.1354 |
|
| 76 |
+
| 0.1061 | 2.3392 | 2000 | 0.1234 |
|
| 77 |
+
| 0.1164 | 2.4561 | 2100 | 0.1263 |
|
| 78 |
+
| 0.1038 | 2.5731 | 2200 | 0.1236 |
|
| 79 |
+
| 0.1196 | 2.6901 | 2300 | 0.1217 |
|
| 80 |
+
| 0.1058 | 2.8070 | 2400 | 0.1206 |
|
| 81 |
+
| 0.1177 | 2.9240 | 2500 | 0.1204 |
|
| 82 |
+
| 0.1009 | 3.0409 | 2600 | 0.1180 |
|
| 83 |
+
| 0.1024 | 3.1579 | 2700 | 0.1185 |
|
| 84 |
+
| 0.0953 | 3.2749 | 2800 | 0.1236 |
|
| 85 |
+
| 0.0905 | 3.3918 | 2900 | 0.1202 |
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
### Framework versions
|
| 89 |
+
|
| 90 |
+
- PEFT 0.10.0
|
| 91 |
+
- Transformers 4.40.0
|
| 92 |
+
- Pytorch 2.2.1
|
| 93 |
+
- Datasets 2.18.0
|
| 94 |
+
- Tokenizers 0.19.1
|
llama2_13b_peft/paragraph_segmentation/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"o_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
llama2_13b_peft/paragraph_segmentation/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4aac6fb5909f3aa5cf0aeb90a4e4e745847e28d213cda4ccbdd852fe680ae7b
|
| 3 |
+
size 125248064
|
llama2_13b_peft/paragraph_segmentation/all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.391812865497076,
|
| 3 |
+
"eval_loss": 0.11801114678382874,
|
| 4 |
+
"eval_runtime": 70.3409,
|
| 5 |
+
"eval_samples_per_second": 5.118,
|
| 6 |
+
"eval_steps_per_second": 0.64,
|
| 7 |
+
"total_flos": 5.067618607815459e+18,
|
| 8 |
+
"train_loss": 0.14973004334959492,
|
| 9 |
+
"train_runtime": 17301.2227,
|
| 10 |
+
"train_samples_per_second": 1.977,
|
| 11 |
+
"train_steps_per_second": 0.247
|
| 12 |
+
}
|
llama2_13b_peft/paragraph_segmentation/eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.391812865497076,
|
| 3 |
+
"eval_loss": 0.11801114678382874,
|
| 4 |
+
"eval_runtime": 70.3409,
|
| 5 |
+
"eval_samples_per_second": 5.118,
|
| 6 |
+
"eval_steps_per_second": 0.64
|
| 7 |
+
}
|
llama2_13b_peft/paragraph_segmentation/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
llama2_13b_peft/paragraph_segmentation/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
llama2_13b_peft/paragraph_segmentation/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false
|
| 45 |
+
}
|
llama2_13b_peft/paragraph_segmentation/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.391812865497076,
|
| 3 |
+
"total_flos": 5.067618607815459e+18,
|
| 4 |
+
"train_loss": 0.14973004334959492,
|
| 5 |
+
"train_runtime": 17301.2227,
|
| 6 |
+
"train_samples_per_second": 1.977,
|
| 7 |
+
"train_steps_per_second": 0.247
|
| 8 |
+
}
|
llama2_13b_peft/paragraph_segmentation/trainer_log.jsonl
ADDED
|
@@ -0,0 +1,321 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 4275, "loss": 0.781, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5e-05, "epoch": 0.011695906432748537, "percentage": 0.23, "elapsed_time": "0:00:53", "remaining_time": "6:16:58"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 4275, "loss": 0.5723, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5e-05, "epoch": 0.023391812865497075, "percentage": 0.47, "elapsed_time": "0:01:43", "remaining_time": "6:06:17"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 4275, "loss": 0.378, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.999931858975852e-05, "epoch": 0.03508771929824561, "percentage": 0.7, "elapsed_time": "0:02:38", "remaining_time": "6:13:33"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 4275, "loss": 0.2932, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.999727439617963e-05, "epoch": 0.04678362573099415, "percentage": 0.94, "elapsed_time": "0:03:29", "remaining_time": "6:09:17"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 4275, "loss": 0.2703, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.999386753069811e-05, "epoch": 0.05847953216374269, "percentage": 1.17, "elapsed_time": "0:04:25", "remaining_time": "6:14:10"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 4275, "loss": 0.2844, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9989098179031804e-05, "epoch": 0.07017543859649122, "percentage": 1.4, "elapsed_time": "0:05:25", "remaining_time": "6:20:48"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 4275, "loss": 0.249, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.998296660117151e-05, "epoch": 0.08187134502923976, "percentage": 1.64, "elapsed_time": "0:06:09", "remaining_time": "6:10:23"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 4275, "loss": 0.2521, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.997547313136682e-05, "epoch": 0.0935672514619883, "percentage": 1.87, "elapsed_time": "0:07:05", "remaining_time": "6:12:14"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 4275, "loss": 0.2647, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.996661817810791e-05, "epoch": 0.10526315789473684, "percentage": 2.11, "elapsed_time": "0:07:59", "remaining_time": "6:11:55"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 4275, "loss": 0.2344, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.995640222410324e-05, "epoch": 0.11695906432748537, "percentage": 2.34, "elapsed_time": "0:08:47", "remaining_time": "6:07:16"}
|
| 11 |
+
{"current_steps": 100, "total_steps": 4275, "loss": null, "eval_loss": 0.23539581894874573, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.11695906432748537, "percentage": 2.34, "elapsed_time": "0:08:47", "remaining_time": "6:07:16"}
|
| 12 |
+
{"current_steps": 110, "total_steps": 4275, "loss": 0.2274, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.994482582625327e-05, "epoch": 0.1286549707602339, "percentage": 2.57, "elapsed_time": "0:10:46", "remaining_time": "6:47:48"}
|
| 13 |
+
{"current_steps": 120, "total_steps": 4275, "loss": 0.2664, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9931889615620075e-05, "epoch": 0.14035087719298245, "percentage": 2.81, "elapsed_time": "0:11:42", "remaining_time": "6:45:36"}
|
| 14 |
+
{"current_steps": 130, "total_steps": 4275, "loss": 0.2483, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.991759429739298e-05, "epoch": 0.15204678362573099, "percentage": 3.04, "elapsed_time": "0:12:36", "remaining_time": "6:41:56"}
|
| 15 |
+
{"current_steps": 140, "total_steps": 4275, "loss": 0.2269, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9901940650850074e-05, "epoch": 0.16374269005847952, "percentage": 3.27, "elapsed_time": "0:13:27", "remaining_time": "6:37:32"}
|
| 16 |
+
{"current_steps": 150, "total_steps": 4275, "loss": 0.2249, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9884929529315774e-05, "epoch": 0.17543859649122806, "percentage": 3.51, "elapsed_time": "0:14:21", "remaining_time": "6:34:55"}
|
| 17 |
+
{"current_steps": 160, "total_steps": 4275, "loss": 0.2232, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.986656186011426e-05, "epoch": 0.1871345029239766, "percentage": 3.74, "elapsed_time": "0:15:21", "remaining_time": "6:35:11"}
|
| 18 |
+
{"current_steps": 170, "total_steps": 4275, "loss": 0.2274, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.984683864451898e-05, "epoch": 0.19883040935672514, "percentage": 3.98, "elapsed_time": "0:16:10", "remaining_time": "6:30:41"}
|
| 19 |
+
{"current_steps": 180, "total_steps": 4275, "loss": 0.2153, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.982576095769801e-05, "epoch": 0.21052631578947367, "percentage": 4.21, "elapsed_time": "0:17:06", "remaining_time": "6:29:21"}
|
| 20 |
+
{"current_steps": 190, "total_steps": 4275, "loss": 0.2123, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.980332994865549e-05, "epoch": 0.2222222222222222, "percentage": 4.44, "elapsed_time": "0:17:56", "remaining_time": "6:25:36"}
|
| 21 |
+
{"current_steps": 200, "total_steps": 4275, "loss": 0.2247, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9779546840168964e-05, "epoch": 0.23391812865497075, "percentage": 4.68, "elapsed_time": "0:18:50", "remaining_time": "6:23:50"}
|
| 22 |
+
{"current_steps": 200, "total_steps": 4275, "loss": null, "eval_loss": 0.2295626550912857, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.23391812865497075, "percentage": 4.68, "elapsed_time": "0:18:50", "remaining_time": "6:23:50"}
|
| 23 |
+
{"current_steps": 210, "total_steps": 4275, "loss": 0.2358, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9754412928722714e-05, "epoch": 0.24561403508771928, "percentage": 4.91, "elapsed_time": "0:20:47", "remaining_time": "6:42:19"}
|
| 24 |
+
{"current_steps": 220, "total_steps": 4275, "loss": 0.2187, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9727929584437136e-05, "epoch": 0.2573099415204678, "percentage": 5.15, "elapsed_time": "0:21:46", "remaining_time": "6:41:18"}
|
| 25 |
+
{"current_steps": 230, "total_steps": 4275, "loss": 0.2077, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.970009825099398e-05, "epoch": 0.26900584795321636, "percentage": 5.38, "elapsed_time": "0:22:37", "remaining_time": "6:37:51"}
|
| 26 |
+
{"current_steps": 240, "total_steps": 4275, "loss": 0.2458, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.967092044555769e-05, "epoch": 0.2807017543859649, "percentage": 5.61, "elapsed_time": "0:23:25", "remaining_time": "6:33:46"}
|
| 27 |
+
{"current_steps": 250, "total_steps": 4275, "loss": 0.1873, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9640397758692715e-05, "epoch": 0.29239766081871343, "percentage": 5.85, "elapsed_time": "0:24:22", "remaining_time": "6:32:19"}
|
| 28 |
+
{"current_steps": 260, "total_steps": 4275, "loss": 0.1758, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.960853185427676e-05, "epoch": 0.30409356725146197, "percentage": 6.08, "elapsed_time": "0:25:18", "remaining_time": "6:30:42"}
|
| 29 |
+
{"current_steps": 270, "total_steps": 4275, "loss": 0.2229, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.957532446941012e-05, "epoch": 0.3157894736842105, "percentage": 6.32, "elapsed_time": "0:26:14", "remaining_time": "6:29:08"}
|
| 30 |
+
{"current_steps": 280, "total_steps": 4275, "loss": 0.2043, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.954077741432097e-05, "epoch": 0.32748538011695905, "percentage": 6.55, "elapsed_time": "0:27:10", "remaining_time": "6:27:47"}
|
| 31 |
+
{"current_steps": 290, "total_steps": 4275, "loss": 0.1949, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.950489257226667e-05, "epoch": 0.3391812865497076, "percentage": 6.78, "elapsed_time": "0:28:01", "remaining_time": "6:25:09"}
|
| 32 |
+
{"current_steps": 300, "total_steps": 4275, "loss": 0.2009, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9467671899431145e-05, "epoch": 0.3508771929824561, "percentage": 7.02, "elapsed_time": "0:28:53", "remaining_time": "6:22:51"}
|
| 33 |
+
{"current_steps": 300, "total_steps": 4275, "loss": null, "eval_loss": 0.20195595920085907, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.3508771929824561, "percentage": 7.02, "elapsed_time": "0:28:53", "remaining_time": "6:22:51"}
|
| 34 |
+
{"current_steps": 310, "total_steps": 4275, "loss": 0.1841, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.942911742481819e-05, "epoch": 0.36257309941520466, "percentage": 7.25, "elapsed_time": "0:30:56", "remaining_time": "6:35:48"}
|
| 35 |
+
{"current_steps": 320, "total_steps": 4275, "loss": 0.2091, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.938923125014094e-05, "epoch": 0.3742690058479532, "percentage": 7.49, "elapsed_time": "0:31:49", "remaining_time": "6:33:14"}
|
| 36 |
+
{"current_steps": 330, "total_steps": 4275, "loss": 0.2032, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.93480155497072e-05, "epoch": 0.38596491228070173, "percentage": 7.72, "elapsed_time": "0:32:44", "remaining_time": "6:31:27"}
|
| 37 |
+
{"current_steps": 340, "total_steps": 4275, "loss": 0.1952, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.930547257030102e-05, "epoch": 0.39766081871345027, "percentage": 7.95, "elapsed_time": "0:33:39", "remaining_time": "6:29:37"}
|
| 38 |
+
{"current_steps": 350, "total_steps": 4275, "loss": 0.1926, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.926160463106015e-05, "epoch": 0.4093567251461988, "percentage": 8.19, "elapsed_time": "0:34:37", "remaining_time": "6:28:14"}
|
| 39 |
+
{"current_steps": 360, "total_steps": 4275, "loss": 0.2085, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.921641412334963e-05, "epoch": 0.42105263157894735, "percentage": 8.42, "elapsed_time": "0:35:32", "remaining_time": "6:26:26"}
|
| 40 |
+
{"current_steps": 370, "total_steps": 4275, "loss": 0.199, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9169903510631434e-05, "epoch": 0.4327485380116959, "percentage": 8.65, "elapsed_time": "0:36:31", "remaining_time": "6:25:25"}
|
| 41 |
+
{"current_steps": 380, "total_steps": 4275, "loss": 0.1874, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.91220753283302e-05, "epoch": 0.4444444444444444, "percentage": 8.89, "elapsed_time": "0:37:28", "remaining_time": "6:24:06"}
|
| 42 |
+
{"current_steps": 390, "total_steps": 4275, "loss": 0.1775, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.907293218369499e-05, "epoch": 0.45614035087719296, "percentage": 9.12, "elapsed_time": "0:38:22", "remaining_time": "6:22:11"}
|
| 43 |
+
{"current_steps": 400, "total_steps": 4275, "loss": 0.2097, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9022476755657155e-05, "epoch": 0.4678362573099415, "percentage": 9.36, "elapsed_time": "0:39:19", "remaining_time": "6:20:53"}
|
| 44 |
+
{"current_steps": 400, "total_steps": 4275, "loss": null, "eval_loss": 0.19560903310775757, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.4678362573099415, "percentage": 9.36, "elapsed_time": "0:39:19", "remaining_time": "6:20:53"}
|
| 45 |
+
{"current_steps": 410, "total_steps": 4275, "loss": 0.1872, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8970711794684345e-05, "epoch": 0.47953216374269003, "percentage": 9.59, "elapsed_time": "0:41:17", "remaining_time": "6:29:12"}
|
| 46 |
+
{"current_steps": 420, "total_steps": 4275, "loss": 0.1936, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8917640122630506e-05, "epoch": 0.49122807017543857, "percentage": 9.82, "elapsed_time": "0:42:09", "remaining_time": "6:26:55"}
|
| 47 |
+
{"current_steps": 430, "total_steps": 4275, "loss": 0.1933, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.886326463258212e-05, "epoch": 0.5029239766081871, "percentage": 10.06, "elapsed_time": "0:43:01", "remaining_time": "6:24:39"}
|
| 48 |
+
{"current_steps": 440, "total_steps": 4275, "loss": 0.1874, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.880758828870045e-05, "epoch": 0.5146198830409356, "percentage": 10.29, "elapsed_time": "0:43:55", "remaining_time": "6:22:51"}
|
| 49 |
+
{"current_steps": 450, "total_steps": 4275, "loss": 0.184, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.875061412605997e-05, "epoch": 0.5263157894736842, "percentage": 10.53, "elapsed_time": "0:44:50", "remaining_time": "6:21:11"}
|
| 50 |
+
{"current_steps": 460, "total_steps": 4275, "loss": 0.1901, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8692345250482914e-05, "epoch": 0.5380116959064327, "percentage": 10.76, "elapsed_time": "0:45:46", "remaining_time": "6:19:39"}
|
| 51 |
+
{"current_steps": 470, "total_steps": 4275, "loss": 0.1803, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.863278483836996e-05, "epoch": 0.5497076023391813, "percentage": 10.99, "elapsed_time": "0:46:43", "remaining_time": "6:18:18"}
|
| 52 |
+
{"current_steps": 480, "total_steps": 4275, "loss": 0.1688, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.857193613652711e-05, "epoch": 0.5614035087719298, "percentage": 11.23, "elapsed_time": "0:47:39", "remaining_time": "6:16:50"}
|
| 53 |
+
{"current_steps": 490, "total_steps": 4275, "loss": 0.1757, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8509802461988635e-05, "epoch": 0.5730994152046783, "percentage": 11.46, "elapsed_time": "0:48:38", "remaining_time": "6:15:41"}
|
| 54 |
+
{"current_steps": 500, "total_steps": 4275, "loss": 0.185, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.844638720183632e-05, "epoch": 0.5847953216374269, "percentage": 11.7, "elapsed_time": "0:49:26", "remaining_time": "6:13:20"}
|
| 55 |
+
{"current_steps": 500, "total_steps": 4275, "loss": null, "eval_loss": 0.1873869150876999, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.5847953216374269, "percentage": 11.7, "elapsed_time": "0:49:26", "remaining_time": "6:13:20"}
|
| 56 |
+
{"current_steps": 510, "total_steps": 4275, "loss": 0.1864, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8381693813014775e-05, "epoch": 0.5964912280701754, "percentage": 11.93, "elapsed_time": "0:51:29", "remaining_time": "6:20:08"}
|
| 57 |
+
{"current_steps": 520, "total_steps": 4275, "loss": 0.1723, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8315725822143024e-05, "epoch": 0.6081871345029239, "percentage": 12.16, "elapsed_time": "0:52:23", "remaining_time": "6:18:19"}
|
| 58 |
+
{"current_steps": 530, "total_steps": 4275, "loss": 0.161, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.824848682532224e-05, "epoch": 0.6198830409356725, "percentage": 12.4, "elapsed_time": "0:53:16", "remaining_time": "6:16:23"}
|
| 59 |
+
{"current_steps": 540, "total_steps": 4275, "loss": 0.1908, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.817998048793969e-05, "epoch": 0.631578947368421, "percentage": 12.63, "elapsed_time": "0:54:01", "remaining_time": "6:13:43"}
|
| 60 |
+
{"current_steps": 550, "total_steps": 4275, "loss": 0.1888, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.811021054446897e-05, "epoch": 0.6432748538011696, "percentage": 12.87, "elapsed_time": "0:54:45", "remaining_time": "6:10:54"}
|
| 61 |
+
{"current_steps": 560, "total_steps": 4275, "loss": 0.1944, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.803918079826641e-05, "epoch": 0.6549707602339181, "percentage": 13.1, "elapsed_time": "0:55:34", "remaining_time": "6:08:42"}
|
| 62 |
+
{"current_steps": 570, "total_steps": 4275, "loss": 0.1819, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7966895121363744e-05, "epoch": 0.6666666666666666, "percentage": 13.33, "elapsed_time": "0:56:27", "remaining_time": "6:07:00"}
|
| 63 |
+
{"current_steps": 580, "total_steps": 4275, "loss": 0.177, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.789335745425698e-05, "epoch": 0.6783625730994152, "percentage": 13.57, "elapsed_time": "0:57:19", "remaining_time": "6:05:09"}
|
| 64 |
+
{"current_steps": 590, "total_steps": 4275, "loss": 0.1756, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.781857180569171e-05, "epoch": 0.6900584795321637, "percentage": 13.8, "elapsed_time": "0:58:08", "remaining_time": "6:03:10"}
|
| 65 |
+
{"current_steps": 600, "total_steps": 4275, "loss": 0.1804, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.774254225244447e-05, "epoch": 0.7017543859649122, "percentage": 14.04, "elapsed_time": "0:59:05", "remaining_time": "6:01:57"}
|
| 66 |
+
{"current_steps": 600, "total_steps": 4275, "loss": null, "eval_loss": 0.17837749421596527, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.7017543859649122, "percentage": 14.04, "elapsed_time": "0:59:05", "remaining_time": "6:01:57"}
|
| 67 |
+
{"current_steps": 610, "total_steps": 4275, "loss": 0.182, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.766527293910056e-05, "epoch": 0.7134502923976608, "percentage": 14.27, "elapsed_time": "1:01:15", "remaining_time": "6:08:03"}
|
| 68 |
+
{"current_steps": 620, "total_steps": 4275, "loss": 0.1955, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.75867680778281e-05, "epoch": 0.7251461988304093, "percentage": 14.5, "elapsed_time": "1:02:07", "remaining_time": "6:06:16"}
|
| 69 |
+
{"current_steps": 630, "total_steps": 4275, "loss": 0.1685, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.750703194814841e-05, "epoch": 0.7368421052631579, "percentage": 14.74, "elapsed_time": "1:02:52", "remaining_time": "6:03:43"}
|
| 70 |
+
{"current_steps": 640, "total_steps": 4275, "loss": 0.1852, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7426068896702704e-05, "epoch": 0.7485380116959064, "percentage": 14.97, "elapsed_time": "1:03:38", "remaining_time": "6:01:26"}
|
| 71 |
+
{"current_steps": 650, "total_steps": 4275, "loss": 0.1782, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.734388333701519e-05, "epoch": 0.7602339181286549, "percentage": 15.2, "elapsed_time": "1:04:23", "remaining_time": "5:59:06"}
|
| 72 |
+
{"current_steps": 660, "total_steps": 4275, "loss": 0.1661, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.726047974925244e-05, "epoch": 0.7719298245614035, "percentage": 15.44, "elapsed_time": "1:05:11", "remaining_time": "5:57:04"}
|
| 73 |
+
{"current_steps": 670, "total_steps": 4275, "loss": 0.1638, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.717586267997916e-05, "epoch": 0.783625730994152, "percentage": 15.67, "elapsed_time": "1:06:05", "remaining_time": "5:55:35"}
|
| 74 |
+
{"current_steps": 680, "total_steps": 4275, "loss": 0.1733, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.709003674191035e-05, "epoch": 0.7953216374269005, "percentage": 15.91, "elapsed_time": "1:06:57", "remaining_time": "5:54:02"}
|
| 75 |
+
{"current_steps": 690, "total_steps": 4275, "loss": 0.1798, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7003006613659866e-05, "epoch": 0.8070175438596491, "percentage": 16.14, "elapsed_time": "1:07:52", "remaining_time": "5:52:39"}
|
| 76 |
+
{"current_steps": 700, "total_steps": 4275, "loss": 0.1647, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.691477703948537e-05, "epoch": 0.8187134502923976, "percentage": 16.37, "elapsed_time": "1:08:46", "remaining_time": "5:51:13"}
|
| 77 |
+
{"current_steps": 700, "total_steps": 4275, "loss": null, "eval_loss": 0.1701304167509079, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.8187134502923976, "percentage": 16.37, "elapsed_time": "1:08:46", "remaining_time": "5:51:13"}
|
| 78 |
+
{"current_steps": 710, "total_steps": 4275, "loss": 0.1569, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6825352829029705e-05, "epoch": 0.8304093567251462, "percentage": 16.61, "elapsed_time": "1:10:49", "remaining_time": "5:55:37"}
|
| 79 |
+
{"current_steps": 720, "total_steps": 4275, "loss": 0.1748, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.673473885705869e-05, "epoch": 0.8421052631578947, "percentage": 16.84, "elapsed_time": "1:11:45", "remaining_time": "5:54:19"}
|
| 80 |
+
{"current_steps": 730, "total_steps": 4275, "loss": 0.2056, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.66429400631954e-05, "epoch": 0.8538011695906432, "percentage": 17.08, "elapsed_time": "1:12:39", "remaining_time": "5:52:50"}
|
| 81 |
+
{"current_steps": 740, "total_steps": 4275, "loss": 0.1772, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.654996145165092e-05, "epoch": 0.8654970760233918, "percentage": 17.31, "elapsed_time": "1:13:33", "remaining_time": "5:51:21"}
|
| 82 |
+
{"current_steps": 750, "total_steps": 4275, "loss": 0.1655, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.645580809095147e-05, "epoch": 0.8771929824561403, "percentage": 17.54, "elapsed_time": "1:14:26", "remaining_time": "5:49:51"}
|
| 83 |
+
{"current_steps": 760, "total_steps": 4275, "loss": 0.1826, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6360485113662216e-05, "epoch": 0.8888888888888888, "percentage": 17.78, "elapsed_time": "1:15:14", "remaining_time": "5:48:00"}
|
| 84 |
+
{"current_steps": 770, "total_steps": 4275, "loss": 0.155, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.626399771610739e-05, "epoch": 0.9005847953216374, "percentage": 18.01, "elapsed_time": "1:16:05", "remaining_time": "5:46:21"}
|
| 85 |
+
{"current_steps": 780, "total_steps": 4275, "loss": 0.1791, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.616635115808705e-05, "epoch": 0.9122807017543859, "percentage": 18.25, "elapsed_time": "1:16:58", "remaining_time": "5:44:52"}
|
| 86 |
+
{"current_steps": 790, "total_steps": 4275, "loss": 0.167, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.606755076259039e-05, "epoch": 0.9239766081871345, "percentage": 18.48, "elapsed_time": "1:17:42", "remaining_time": "5:42:47"}
|
| 87 |
+
{"current_steps": 800, "total_steps": 4275, "loss": 0.1663, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.5967601915505505e-05, "epoch": 0.935672514619883, "percentage": 18.71, "elapsed_time": "1:18:33", "remaining_time": "5:41:16"}
|
| 88 |
+
{"current_steps": 800, "total_steps": 4275, "loss": null, "eval_loss": 0.1684267818927765, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.935672514619883, "percentage": 18.71, "elapsed_time": "1:18:33", "remaining_time": "5:41:16"}
|
| 89 |
+
{"current_steps": 810, "total_steps": 4275, "loss": 0.1783, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.5866510065325837e-05, "epoch": 0.9473684210526315, "percentage": 18.95, "elapsed_time": "1:20:35", "remaining_time": "5:44:46"}
|
| 90 |
+
{"current_steps": 820, "total_steps": 4275, "loss": 0.1765, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.576428072285316e-05, "epoch": 0.9590643274853801, "percentage": 19.18, "elapsed_time": "1:21:25", "remaining_time": "5:43:06"}
|
| 91 |
+
{"current_steps": 830, "total_steps": 4275, "loss": 0.1485, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.5660919460897136e-05, "epoch": 0.9707602339181286, "percentage": 19.42, "elapsed_time": "1:22:22", "remaining_time": "5:41:55"}
|
| 92 |
+
{"current_steps": 840, "total_steps": 4275, "loss": 0.1719, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.5556431913971564e-05, "epoch": 0.9824561403508771, "percentage": 19.65, "elapsed_time": "1:23:20", "remaining_time": "5:40:48"}
|
| 93 |
+
{"current_steps": 850, "total_steps": 4275, "loss": 0.1671, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.5450823777987224e-05, "epoch": 0.9941520467836257, "percentage": 19.88, "elapsed_time": "1:24:15", "remaining_time": "5:39:32"}
|
| 94 |
+
{"current_steps": 860, "total_steps": 4275, "loss": 0.1546, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.534410080994134e-05, "epoch": 1.0058479532163742, "percentage": 20.12, "elapsed_time": "1:25:08", "remaining_time": "5:38:05"}
|
| 95 |
+
{"current_steps": 870, "total_steps": 4275, "loss": 0.1423, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.523626882760379e-05, "epoch": 1.0175438596491229, "percentage": 20.35, "elapsed_time": "1:26:04", "remaining_time": "5:36:53"}
|
| 96 |
+
{"current_steps": 880, "total_steps": 4275, "loss": 0.1596, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.512733370919994e-05, "epoch": 1.0292397660818713, "percentage": 20.58, "elapsed_time": "1:26:52", "remaining_time": "5:35:09"}
|
| 97 |
+
{"current_steps": 890, "total_steps": 4275, "loss": 0.1554, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.5017301393090226e-05, "epoch": 1.04093567251462, "percentage": 20.82, "elapsed_time": "1:27:52", "remaining_time": "5:34:12"}
|
| 98 |
+
{"current_steps": 900, "total_steps": 4275, "loss": 0.1553, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.490617787744641e-05, "epoch": 1.0526315789473684, "percentage": 21.05, "elapsed_time": "1:28:43", "remaining_time": "5:32:42"}
|
| 99 |
+
{"current_steps": 900, "total_steps": 4275, "loss": null, "eval_loss": 0.15236565470695496, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.0526315789473684, "percentage": 21.05, "elapsed_time": "1:28:43", "remaining_time": "5:32:42"}
|
| 100 |
+
{"current_steps": 910, "total_steps": 4275, "loss": 0.1656, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.479396921992462e-05, "epoch": 1.064327485380117, "percentage": 21.29, "elapsed_time": "1:30:51", "remaining_time": "5:35:57"}
|
| 101 |
+
{"current_steps": 920, "total_steps": 4275, "loss": 0.1604, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.4680681537335125e-05, "epoch": 1.0760233918128654, "percentage": 21.52, "elapsed_time": "1:31:47", "remaining_time": "5:34:44"}
|
| 102 |
+
{"current_steps": 930, "total_steps": 4275, "loss": 0.1695, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.456632100530891e-05, "epoch": 1.087719298245614, "percentage": 21.75, "elapsed_time": "1:32:38", "remaining_time": "5:33:12"}
|
| 103 |
+
{"current_steps": 940, "total_steps": 4275, "loss": 0.1528, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.445089385796099e-05, "epoch": 1.0994152046783625, "percentage": 21.99, "elapsed_time": "1:33:29", "remaining_time": "5:31:43"}
|
| 104 |
+
{"current_steps": 950, "total_steps": 4275, "loss": 0.1409, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.4334406387550584e-05, "epoch": 1.1111111111111112, "percentage": 22.22, "elapsed_time": "1:34:25", "remaining_time": "5:30:30"}
|
| 105 |
+
{"current_steps": 960, "total_steps": 4275, "loss": 0.151, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.4216864944138134e-05, "epoch": 1.1228070175438596, "percentage": 22.46, "elapsed_time": "1:35:10", "remaining_time": "5:28:40"}
|
| 106 |
+
{"current_steps": 970, "total_steps": 4275, "loss": 0.1443, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.4098275935239105e-05, "epoch": 1.1345029239766082, "percentage": 22.69, "elapsed_time": "1:36:05", "remaining_time": "5:27:22"}
|
| 107 |
+
{"current_steps": 980, "total_steps": 4275, "loss": 0.1723, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.39786458254747e-05, "epoch": 1.1461988304093567, "percentage": 22.92, "elapsed_time": "1:36:58", "remaining_time": "5:26:03"}
|
| 108 |
+
{"current_steps": 990, "total_steps": 4275, "loss": 0.1642, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.385798113621949e-05, "epoch": 1.1578947368421053, "percentage": 23.16, "elapsed_time": "1:37:54", "remaining_time": "5:24:54"}
|
| 109 |
+
{"current_steps": 1000, "total_steps": 4275, "loss": 0.1665, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.373628844524587e-05, "epoch": 1.1695906432748537, "percentage": 23.39, "elapsed_time": "1:38:53", "remaining_time": "5:23:51"}
|
| 110 |
+
{"current_steps": 1000, "total_steps": 4275, "loss": null, "eval_loss": 0.15835003554821014, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.1695906432748537, "percentage": 23.39, "elapsed_time": "1:38:53", "remaining_time": "5:23:51"}
|
| 111 |
+
{"current_steps": 1010, "total_steps": 4275, "loss": 0.149, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.361357438636552e-05, "epoch": 1.1812865497076024, "percentage": 23.63, "elapsed_time": "1:40:48", "remaining_time": "5:25:53"}
|
| 112 |
+
{"current_steps": 1020, "total_steps": 4275, "loss": 0.1487, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.3489845649067756e-05, "epoch": 1.1929824561403508, "percentage": 23.86, "elapsed_time": "1:41:32", "remaining_time": "5:24:00"}
|
| 113 |
+
{"current_steps": 1030, "total_steps": 4275, "loss": 0.1722, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.336510897815489e-05, "epoch": 1.2046783625730995, "percentage": 24.09, "elapsed_time": "1:42:21", "remaining_time": "5:22:27"}
|
| 114 |
+
{"current_steps": 1040, "total_steps": 4275, "loss": 0.1586, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.323937117337451e-05, "epoch": 1.2163742690058479, "percentage": 24.33, "elapsed_time": "1:43:16", "remaining_time": "5:21:13"}
|
| 115 |
+
{"current_steps": 1050, "total_steps": 4275, "loss": 0.1372, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.3112639089048856e-05, "epoch": 1.2280701754385965, "percentage": 24.56, "elapsed_time": "1:44:17", "remaining_time": "5:20:18"}
|
| 116 |
+
{"current_steps": 1060, "total_steps": 4275, "loss": 0.1375, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.298491963370115e-05, "epoch": 1.239766081871345, "percentage": 24.8, "elapsed_time": "1:45:11", "remaining_time": "5:19:03"}
|
| 117 |
+
{"current_steps": 1070, "total_steps": 4275, "loss": 0.1429, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.285621976967898e-05, "epoch": 1.2514619883040936, "percentage": 25.03, "elapsed_time": "1:45:56", "remaining_time": "5:17:19"}
|
| 118 |
+
{"current_steps": 1080, "total_steps": 4275, "loss": 0.1464, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.272654651277478e-05, "epoch": 1.263157894736842, "percentage": 25.26, "elapsed_time": "1:46:45", "remaining_time": "5:15:49"}
|
| 119 |
+
{"current_steps": 1090, "total_steps": 4275, "loss": 0.143, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.259590693184337e-05, "epoch": 1.2748538011695907, "percentage": 25.5, "elapsed_time": "1:47:29", "remaining_time": "5:14:04"}
|
| 120 |
+
{"current_steps": 1100, "total_steps": 4275, "loss": 0.1424, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.2464308148416626e-05, "epoch": 1.286549707602339, "percentage": 25.73, "elapsed_time": "1:48:29", "remaining_time": "5:13:07"}
|
| 121 |
+
{"current_steps": 1100, "total_steps": 4275, "loss": null, "eval_loss": 0.16600148379802704, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.286549707602339, "percentage": 25.73, "elapsed_time": "1:48:29", "remaining_time": "5:13:07"}
|
| 122 |
+
{"current_steps": 1110, "total_steps": 4275, "loss": 0.147, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.233175733631525e-05, "epoch": 1.2982456140350878, "percentage": 25.96, "elapsed_time": "1:50:36", "remaining_time": "5:15:22"}
|
| 123 |
+
{"current_steps": 1120, "total_steps": 4275, "loss": 0.1373, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.2198261721257715e-05, "epoch": 1.3099415204678362, "percentage": 26.2, "elapsed_time": "1:51:26", "remaining_time": "5:13:56"}
|
| 124 |
+
{"current_steps": 1130, "total_steps": 4275, "loss": 0.1439, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.206382858046636e-05, "epoch": 1.3216374269005848, "percentage": 26.43, "elapsed_time": "1:52:24", "remaining_time": "5:12:50"}
|
| 125 |
+
{"current_steps": 1140, "total_steps": 4275, "loss": 0.1372, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.1928465242270696e-05, "epoch": 1.3333333333333333, "percentage": 26.67, "elapsed_time": "1:53:17", "remaining_time": "5:11:34"}
|
| 126 |
+
{"current_steps": 1150, "total_steps": 4275, "loss": 0.1561, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.1792179085707935e-05, "epoch": 1.345029239766082, "percentage": 26.9, "elapsed_time": "1:54:11", "remaining_time": "5:10:18"}
|
| 127 |
+
{"current_steps": 1160, "total_steps": 4275, "loss": 0.1354, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.1654977540120686e-05, "epoch": 1.3567251461988303, "percentage": 27.13, "elapsed_time": "1:55:04", "remaining_time": "5:08:59"}
|
| 128 |
+
{"current_steps": 1170, "total_steps": 4275, "loss": 0.1372, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.151686808475204e-05, "epoch": 1.368421052631579, "percentage": 27.37, "elapsed_time": "1:55:52", "remaining_time": "5:07:30"}
|
| 129 |
+
{"current_steps": 1180, "total_steps": 4275, "loss": 0.1776, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.137785824833776e-05, "epoch": 1.3801169590643274, "percentage": 27.6, "elapsed_time": "1:56:51", "remaining_time": "5:06:31"}
|
| 130 |
+
{"current_steps": 1190, "total_steps": 4275, "loss": 0.1475, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.123795560869595e-05, "epoch": 1.391812865497076, "percentage": 27.84, "elapsed_time": "1:57:45", "remaining_time": "5:05:15"}
|
| 131 |
+
{"current_steps": 1200, "total_steps": 4275, "loss": 0.1163, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.109716779231393e-05, "epoch": 1.4035087719298245, "percentage": 28.07, "elapsed_time": "1:58:32", "remaining_time": "5:03:46"}
|
| 132 |
+
{"current_steps": 1200, "total_steps": 4275, "loss": null, "eval_loss": 0.14416372776031494, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.4035087719298245, "percentage": 28.07, "elapsed_time": "1:58:32", "remaining_time": "5:03:46"}
|
| 133 |
+
{"current_steps": 1210, "total_steps": 4275, "loss": 0.1398, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.0955502473932495e-05, "epoch": 1.4152046783625731, "percentage": 28.3, "elapsed_time": "2:00:36", "remaining_time": "5:05:30"}
|
| 134 |
+
{"current_steps": 1220, "total_steps": 4275, "loss": 0.1424, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.0812967376127555e-05, "epoch": 1.4269005847953216, "percentage": 28.54, "elapsed_time": "2:01:32", "remaining_time": "5:04:20"}
|
| 135 |
+
{"current_steps": 1230, "total_steps": 4275, "loss": 0.125, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.0669570268889124e-05, "epoch": 1.4385964912280702, "percentage": 28.77, "elapsed_time": "2:02:24", "remaining_time": "5:03:03"}
|
| 136 |
+
{"current_steps": 1240, "total_steps": 4275, "loss": 0.1474, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.0525318969197825e-05, "epoch": 1.4502923976608186, "percentage": 29.01, "elapsed_time": "2:03:10", "remaining_time": "5:01:29"}
|
| 137 |
+
{"current_steps": 1250, "total_steps": 4275, "loss": 0.1405, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.038022134059868e-05, "epoch": 1.4619883040935673, "percentage": 29.24, "elapsed_time": "2:04:06", "remaining_time": "5:00:21"}
|
| 138 |
+
{"current_steps": 1260, "total_steps": 4275, "loss": 0.1226, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.02342852927725e-05, "epoch": 1.4736842105263157, "percentage": 29.47, "elapsed_time": "2:05:01", "remaining_time": "4:59:10"}
|
| 139 |
+
{"current_steps": 1270, "total_steps": 4275, "loss": 0.1362, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.00875187811047e-05, "epoch": 1.4853801169590644, "percentage": 29.71, "elapsed_time": "2:05:55", "remaining_time": "4:57:58"}
|
| 140 |
+
{"current_steps": 1280, "total_steps": 4275, "loss": 0.1541, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.993992980625161e-05, "epoch": 1.4970760233918128, "percentage": 29.94, "elapsed_time": "2:06:45", "remaining_time": "4:56:34"}
|
| 141 |
+
{"current_steps": 1290, "total_steps": 4275, "loss": 0.1429, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.979152641370434e-05, "epoch": 1.5087719298245614, "percentage": 30.18, "elapsed_time": "2:07:37", "remaining_time": "4:55:20"}
|
| 142 |
+
{"current_steps": 1300, "total_steps": 4275, "loss": 0.1593, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.964231669335023e-05, "epoch": 1.52046783625731, "percentage": 30.41, "elapsed_time": "2:08:30", "remaining_time": "4:54:05"}
|
| 143 |
+
{"current_steps": 1300, "total_steps": 4275, "loss": null, "eval_loss": 0.136515274643898, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.52046783625731, "percentage": 30.41, "elapsed_time": "2:08:30", "remaining_time": "4:54:05"}
|
| 144 |
+
{"current_steps": 1310, "total_steps": 4275, "loss": 0.1437, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.94923087790318e-05, "epoch": 1.5321637426900585, "percentage": 30.64, "elapsed_time": "2:10:32", "remaining_time": "4:55:28"}
|
| 145 |
+
{"current_steps": 1320, "total_steps": 4275, "loss": 0.135, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.934151084810338e-05, "epoch": 1.543859649122807, "percentage": 30.88, "elapsed_time": "2:11:13", "remaining_time": "4:53:45"}
|
| 146 |
+
{"current_steps": 1330, "total_steps": 4275, "loss": 0.1278, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.918993112098532e-05, "epoch": 1.5555555555555556, "percentage": 31.11, "elapsed_time": "2:12:08", "remaining_time": "4:52:35"}
|
| 147 |
+
{"current_steps": 1340, "total_steps": 4275, "loss": 0.1384, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.9037577860715915e-05, "epoch": 1.5672514619883042, "percentage": 31.35, "elapsed_time": "2:13:05", "remaining_time": "4:51:31"}
|
| 148 |
+
{"current_steps": 1350, "total_steps": 4275, "loss": 0.1262, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.888445937250091e-05, "epoch": 1.5789473684210527, "percentage": 31.58, "elapsed_time": "2:13:59", "remaining_time": "4:50:19"}
|
| 149 |
+
{"current_steps": 1360, "total_steps": 4275, "loss": 0.1419, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.873058400326078e-05, "epoch": 1.590643274853801, "percentage": 31.81, "elapsed_time": "2:14:51", "remaining_time": "4:49:03"}
|
| 150 |
+
{"current_steps": 1370, "total_steps": 4275, "loss": 0.1429, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.8575960141175735e-05, "epoch": 1.6023391812865497, "percentage": 32.05, "elapsed_time": "2:15:45", "remaining_time": "4:47:51"}
|
| 151 |
+
{"current_steps": 1380, "total_steps": 4275, "loss": 0.1402, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.842059621522843e-05, "epoch": 1.6140350877192984, "percentage": 32.28, "elapsed_time": "2:16:33", "remaining_time": "4:46:27"}
|
| 152 |
+
{"current_steps": 1390, "total_steps": 4275, "loss": 0.1295, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.826450069474447e-05, "epoch": 1.6257309941520468, "percentage": 32.51, "elapsed_time": "2:17:29", "remaining_time": "4:45:22"}
|
| 153 |
+
{"current_steps": 1400, "total_steps": 4275, "loss": 0.1529, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.8107682088930794e-05, "epoch": 1.6374269005847952, "percentage": 32.75, "elapsed_time": "2:18:24", "remaining_time": "4:44:13"}
|
| 154 |
+
{"current_steps": 1400, "total_steps": 4275, "loss": null, "eval_loss": 0.14436422288417816, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.6374269005847952, "percentage": 32.75, "elapsed_time": "2:18:24", "remaining_time": "4:44:13"}
|
| 155 |
+
{"current_steps": 1410, "total_steps": 4275, "loss": 0.1212, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.7950148946411703e-05, "epoch": 1.6491228070175439, "percentage": 32.98, "elapsed_time": "2:20:19", "remaining_time": "4:45:07"}
|
| 156 |
+
{"current_steps": 1420, "total_steps": 4275, "loss": 0.1284, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.779190985476294e-05, "epoch": 1.6608187134502925, "percentage": 33.22, "elapsed_time": "2:21:09", "remaining_time": "4:43:48"}
|
| 157 |
+
{"current_steps": 1430, "total_steps": 4275, "loss": 0.1386, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.763297344004352e-05, "epoch": 1.672514619883041, "percentage": 33.45, "elapsed_time": "2:21:55", "remaining_time": "4:42:22"}
|
| 158 |
+
{"current_steps": 1440, "total_steps": 4275, "loss": 0.1426, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.747334836632549e-05, "epoch": 1.6842105263157894, "percentage": 33.68, "elapsed_time": "2:22:46", "remaining_time": "4:41:05"}
|
| 159 |
+
{"current_steps": 1450, "total_steps": 4275, "loss": 0.1362, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.7313043335221655e-05, "epoch": 1.695906432748538, "percentage": 33.92, "elapsed_time": "2:23:36", "remaining_time": "4:39:48"}
|
| 160 |
+
{"current_steps": 1460, "total_steps": 4275, "loss": 0.1498, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.715206708541122e-05, "epoch": 1.7076023391812867, "percentage": 34.15, "elapsed_time": "2:24:31", "remaining_time": "4:38:38"}
|
| 161 |
+
{"current_steps": 1470, "total_steps": 4275, "loss": 0.1371, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.69904283921634e-05, "epoch": 1.719298245614035, "percentage": 34.39, "elapsed_time": "2:25:28", "remaining_time": "4:37:34"}
|
| 162 |
+
{"current_steps": 1480, "total_steps": 4275, "loss": 0.1343, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.682813606685908e-05, "epoch": 1.7309941520467835, "percentage": 34.62, "elapsed_time": "2:26:15", "remaining_time": "4:36:12"}
|
| 163 |
+
{"current_steps": 1490, "total_steps": 4275, "loss": 0.1344, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.666519895651046e-05, "epoch": 1.7426900584795322, "percentage": 34.85, "elapsed_time": "2:27:07", "remaining_time": "4:34:59"}
|
| 164 |
+
{"current_steps": 1500, "total_steps": 4275, "loss": 0.1321, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.6501625943278805e-05, "epoch": 1.7543859649122808, "percentage": 35.09, "elapsed_time": "2:27:56", "remaining_time": "4:33:42"}
|
| 165 |
+
{"current_steps": 1500, "total_steps": 4275, "loss": null, "eval_loss": 0.13336236774921417, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.7543859649122808, "percentage": 35.09, "elapsed_time": "2:27:56", "remaining_time": "4:33:42"}
|
| 166 |
+
{"current_steps": 1510, "total_steps": 4275, "loss": 0.1102, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.6337425943990224e-05, "epoch": 1.7660818713450293, "percentage": 35.32, "elapsed_time": "2:29:55", "remaining_time": "4:34:32"}
|
| 167 |
+
{"current_steps": 1520, "total_steps": 4275, "loss": 0.1352, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.6172607909649606e-05, "epoch": 1.7777777777777777, "percentage": 35.56, "elapsed_time": "2:30:47", "remaining_time": "4:33:18"}
|
| 168 |
+
{"current_steps": 1530, "total_steps": 4275, "loss": 0.1296, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.600718082495269e-05, "epoch": 1.7894736842105263, "percentage": 35.79, "elapsed_time": "2:31:43", "remaining_time": "4:32:13"}
|
| 169 |
+
{"current_steps": 1540, "total_steps": 4275, "loss": 0.1427, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.5841153707796245e-05, "epoch": 1.801169590643275, "percentage": 36.02, "elapsed_time": "2:32:33", "remaining_time": "4:30:56"}
|
| 170 |
+
{"current_steps": 1550, "total_steps": 4275, "loss": 0.1426, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.567453560878652e-05, "epoch": 1.8128654970760234, "percentage": 36.26, "elapsed_time": "2:33:30", "remaining_time": "4:29:53"}
|
| 171 |
+
{"current_steps": 1560, "total_steps": 4275, "loss": 0.1342, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.550733561074582e-05, "epoch": 1.8245614035087718, "percentage": 36.49, "elapsed_time": "2:34:26", "remaining_time": "4:28:47"}
|
| 172 |
+
{"current_steps": 1570, "total_steps": 4275, "loss": 0.1337, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.533956282821746e-05, "epoch": 1.8362573099415205, "percentage": 36.73, "elapsed_time": "2:35:20", "remaining_time": "4:27:38"}
|
| 173 |
+
{"current_steps": 1580, "total_steps": 4275, "loss": 0.1306, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.51712264069688e-05, "epoch": 1.8479532163742691, "percentage": 36.96, "elapsed_time": "2:36:10", "remaining_time": "4:26:23"}
|
| 174 |
+
{"current_steps": 1590, "total_steps": 4275, "loss": 0.1299, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.500233552349276e-05, "epoch": 1.8596491228070176, "percentage": 37.19, "elapsed_time": "2:37:03", "remaining_time": "4:25:13"}
|
| 175 |
+
{"current_steps": 1600, "total_steps": 4275, "loss": 0.135, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.483289938450755e-05, "epoch": 1.871345029239766, "percentage": 37.43, "elapsed_time": "2:37:53", "remaining_time": "4:23:59"}
|
| 176 |
+
{"current_steps": 1600, "total_steps": 4275, "loss": null, "eval_loss": 0.12928339838981628, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.871345029239766, "percentage": 37.43, "elapsed_time": "2:37:53", "remaining_time": "4:23:59"}
|
| 177 |
+
{"current_steps": 1610, "total_steps": 4275, "loss": 0.1304, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.466292722645481e-05, "epoch": 1.8830409356725146, "percentage": 37.66, "elapsed_time": "2:39:55", "remaining_time": "4:24:43"}
|
| 178 |
+
{"current_steps": 1620, "total_steps": 4275, "loss": 0.1203, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.449242831499608e-05, "epoch": 1.8947368421052633, "percentage": 37.89, "elapsed_time": "2:40:50", "remaining_time": "4:23:35"}
|
| 179 |
+
{"current_steps": 1630, "total_steps": 4275, "loss": 0.1323, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.432141194450772e-05, "epoch": 1.9064327485380117, "percentage": 38.13, "elapsed_time": "2:41:35", "remaining_time": "4:22:13"}
|
| 180 |
+
{"current_steps": 1640, "total_steps": 4275, "loss": 0.1159, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.4149887437574226e-05, "epoch": 1.9181286549707601, "percentage": 38.36, "elapsed_time": "2:42:28", "remaining_time": "4:21:03"}
|
| 181 |
+
{"current_steps": 1650, "total_steps": 4275, "loss": 0.1272, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.397786414448004e-05, "epoch": 1.9298245614035088, "percentage": 38.6, "elapsed_time": "2:43:23", "remaining_time": "4:19:55"}
|
| 182 |
+
{"current_steps": 1660, "total_steps": 4275, "loss": 0.124, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.3805351442699885e-05, "epoch": 1.9415204678362574, "percentage": 38.83, "elapsed_time": "2:44:21", "remaining_time": "4:18:54"}
|
| 183 |
+
{"current_steps": 1670, "total_steps": 4275, "loss": 0.1259, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.363235873638749e-05, "epoch": 1.9532163742690059, "percentage": 39.06, "elapsed_time": "2:45:17", "remaining_time": "4:17:49"}
|
| 184 |
+
{"current_steps": 1680, "total_steps": 4275, "loss": 0.1223, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.345889545586301e-05, "epoch": 1.9649122807017543, "percentage": 39.3, "elapsed_time": "2:46:11", "remaining_time": "4:16:41"}
|
| 185 |
+
{"current_steps": 1690, "total_steps": 4275, "loss": 0.1312, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.328497105709888e-05, "epoch": 1.976608187134503, "percentage": 39.53, "elapsed_time": "2:47:03", "remaining_time": "4:15:31"}
|
| 186 |
+
{"current_steps": 1700, "total_steps": 4275, "loss": 0.1322, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.311059502120446e-05, "epoch": 1.9883040935672516, "percentage": 39.77, "elapsed_time": "2:47:58", "remaining_time": "4:14:25"}
|
| 187 |
+
{"current_steps": 1700, "total_steps": 4275, "loss": null, "eval_loss": 0.14009280502796173, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.9883040935672516, "percentage": 39.77, "elapsed_time": "2:47:58", "remaining_time": "4:14:25"}
|
| 188 |
+
{"current_steps": 1710, "total_steps": 4275, "loss": 0.1407, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.293577685390907e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "2:50:00", "remaining_time": "4:15:00"}
|
| 189 |
+
{"current_steps": 1720, "total_steps": 4275, "loss": 0.1053, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.2760526085043894e-05, "epoch": 2.0116959064327484, "percentage": 40.23, "elapsed_time": "2:50:43", "remaining_time": "4:13:36"}
|
| 190 |
+
{"current_steps": 1730, "total_steps": 4275, "loss": 0.1356, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.258485226802242e-05, "epoch": 2.023391812865497, "percentage": 40.47, "elapsed_time": "2:51:44", "remaining_time": "4:12:39"}
|
| 191 |
+
{"current_steps": 1740, "total_steps": 4275, "loss": 0.1009, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.2408764979319695e-05, "epoch": 2.0350877192982457, "percentage": 40.7, "elapsed_time": "2:52:38", "remaining_time": "4:11:30"}
|
| 192 |
+
{"current_steps": 1750, "total_steps": 4275, "loss": 0.1134, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.2232273817950273e-05, "epoch": 2.046783625730994, "percentage": 40.94, "elapsed_time": "2:53:30", "remaining_time": "4:10:20"}
|
| 193 |
+
{"current_steps": 1760, "total_steps": 4275, "loss": 0.1108, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.205538840494494e-05, "epoch": 2.0584795321637426, "percentage": 41.17, "elapsed_time": "2:54:28", "remaining_time": "4:09:19"}
|
| 194 |
+
{"current_steps": 1770, "total_steps": 4275, "loss": 0.1126, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.187811838282627e-05, "epoch": 2.0701754385964914, "percentage": 41.4, "elapsed_time": "2:55:26", "remaining_time": "4:08:17"}
|
| 195 |
+
{"current_steps": 1780, "total_steps": 4275, "loss": 0.1284, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.170047341508293e-05, "epoch": 2.08187134502924, "percentage": 41.64, "elapsed_time": "2:56:14", "remaining_time": "4:07:02"}
|
| 196 |
+
{"current_steps": 1790, "total_steps": 4275, "loss": 0.1202, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.1522463185642965e-05, "epoch": 2.0935672514619883, "percentage": 41.87, "elapsed_time": "2:57:08", "remaining_time": "4:05:55"}
|
| 197 |
+
{"current_steps": 1800, "total_steps": 4275, "loss": 0.1355, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.134409739834584e-05, "epoch": 2.1052631578947367, "percentage": 42.11, "elapsed_time": "2:58:02", "remaining_time": "4:04:48"}
|
| 198 |
+
{"current_steps": 1800, "total_steps": 4275, "loss": null, "eval_loss": 0.12916673719882965, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.1052631578947367, "percentage": 42.11, "elapsed_time": "2:58:02", "remaining_time": "4:04:48"}
|
| 199 |
+
{"current_steps": 1810, "total_steps": 4275, "loss": 0.1225, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.11653857764135e-05, "epoch": 2.116959064327485, "percentage": 42.34, "elapsed_time": "3:00:10", "remaining_time": "4:05:22"}
|
| 200 |
+
{"current_steps": 1820, "total_steps": 4275, "loss": 0.1103, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.098633806192029e-05, "epoch": 2.128654970760234, "percentage": 42.57, "elapsed_time": "3:01:07", "remaining_time": "4:04:19"}
|
| 201 |
+
{"current_steps": 1830, "total_steps": 4275, "loss": 0.1042, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.080696401526193e-05, "epoch": 2.1403508771929824, "percentage": 42.81, "elapsed_time": "3:02:04", "remaining_time": "4:03:16"}
|
| 202 |
+
{"current_steps": 1840, "total_steps": 4275, "loss": 0.1336, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.062727341462342e-05, "epoch": 2.152046783625731, "percentage": 43.04, "elapsed_time": "3:03:05", "remaining_time": "4:02:17"}
|
| 203 |
+
{"current_steps": 1850, "total_steps": 4275, "loss": 0.1212, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.0447276055445984e-05, "epoch": 2.1637426900584797, "percentage": 43.27, "elapsed_time": "3:04:00", "remaining_time": "4:01:12"}
|
| 204 |
+
{"current_steps": 1860, "total_steps": 4275, "loss": 0.1079, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.0266981749893157e-05, "epoch": 2.175438596491228, "percentage": 43.51, "elapsed_time": "3:04:58", "remaining_time": "4:00:10"}
|
| 205 |
+
{"current_steps": 1870, "total_steps": 4275, "loss": 0.1505, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.008640032631585e-05, "epoch": 2.1871345029239766, "percentage": 43.74, "elapsed_time": "3:05:45", "remaining_time": "3:58:54"}
|
| 206 |
+
{"current_steps": 1880, "total_steps": 4275, "loss": 0.1306, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.990554162871656e-05, "epoch": 2.198830409356725, "percentage": 43.98, "elapsed_time": "3:06:44", "remaining_time": "3:57:53"}
|
| 207 |
+
{"current_steps": 1890, "total_steps": 4275, "loss": 0.1184, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.97244155162128e-05, "epoch": 2.2105263157894735, "percentage": 44.21, "elapsed_time": "3:07:34", "remaining_time": "3:56:41"}
|
| 208 |
+
{"current_steps": 1900, "total_steps": 4275, "loss": 0.1227, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.954303186249962e-05, "epoch": 2.2222222222222223, "percentage": 44.44, "elapsed_time": "3:08:20", "remaining_time": "3:55:25"}
|
| 209 |
+
{"current_steps": 1900, "total_steps": 4275, "loss": null, "eval_loss": 0.13539400696754456, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.2222222222222223, "percentage": 44.44, "elapsed_time": "3:08:20", "remaining_time": "3:55:25"}
|
| 210 |
+
{"current_steps": 1910, "total_steps": 4275, "loss": 0.1208, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.936140055531135e-05, "epoch": 2.2339181286549707, "percentage": 44.68, "elapsed_time": "3:10:22", "remaining_time": "3:55:44"}
|
| 211 |
+
{"current_steps": 1920, "total_steps": 4275, "loss": 0.1231, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9179531495882644e-05, "epoch": 2.245614035087719, "percentage": 44.91, "elapsed_time": "3:11:12", "remaining_time": "3:54:31"}
|
| 212 |
+
{"current_steps": 1930, "total_steps": 4275, "loss": 0.123, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.8997434598408653e-05, "epoch": 2.257309941520468, "percentage": 45.15, "elapsed_time": "3:12:07", "remaining_time": "3:53:26"}
|
| 213 |
+
{"current_steps": 1940, "total_steps": 4275, "loss": 0.1132, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.8815119789504658e-05, "epoch": 2.2690058479532165, "percentage": 45.38, "elapsed_time": "3:12:59", "remaining_time": "3:52:17"}
|
| 214 |
+
{"current_steps": 1950, "total_steps": 4275, "loss": 0.1049, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.8632597007664895e-05, "epoch": 2.280701754385965, "percentage": 45.61, "elapsed_time": "3:13:53", "remaining_time": "3:51:10"}
|
| 215 |
+
{"current_steps": 1960, "total_steps": 4275, "loss": 0.111, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.8449876202720793e-05, "epoch": 2.2923976608187133, "percentage": 45.85, "elapsed_time": "3:14:46", "remaining_time": "3:50:03"}
|
| 216 |
+
{"current_steps": 1970, "total_steps": 4275, "loss": 0.1012, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.8266967335298584e-05, "epoch": 2.3040935672514617, "percentage": 46.08, "elapsed_time": "3:15:33", "remaining_time": "3:48:49"}
|
| 217 |
+
{"current_steps": 1980, "total_steps": 4275, "loss": 0.1121, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.8083880376276307e-05, "epoch": 2.3157894736842106, "percentage": 46.32, "elapsed_time": "3:16:24", "remaining_time": "3:47:38"}
|
| 218 |
+
{"current_steps": 1990, "total_steps": 4275, "loss": 0.1222, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7900625306240263e-05, "epoch": 2.327485380116959, "percentage": 46.55, "elapsed_time": "3:17:20", "remaining_time": "3:46:36"}
|
| 219 |
+
{"current_steps": 2000, "total_steps": 4275, "loss": 0.1061, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7717212114940988e-05, "epoch": 2.3391812865497075, "percentage": 46.78, "elapsed_time": "3:18:17", "remaining_time": "3:45:33"}
|
| 220 |
+
{"current_steps": 2000, "total_steps": 4275, "loss": null, "eval_loss": 0.12341146171092987, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.3391812865497075, "percentage": 46.78, "elapsed_time": "3:18:17", "remaining_time": "3:45:33"}
|
| 221 |
+
{"current_steps": 2010, "total_steps": 4275, "loss": 0.1144, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7533650800748645e-05, "epoch": 2.3508771929824563, "percentage": 47.02, "elapsed_time": "3:20:18", "remaining_time": "3:45:43"}
|
| 222 |
+
{"current_steps": 2020, "total_steps": 4275, "loss": 0.1077, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7349951370107983e-05, "epoch": 2.3625730994152048, "percentage": 47.25, "elapsed_time": "3:21:11", "remaining_time": "3:44:35"}
|
| 223 |
+
{"current_steps": 2030, "total_steps": 4275, "loss": 0.1088, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7166123836992873e-05, "epoch": 2.374269005847953, "percentage": 47.49, "elapsed_time": "3:22:05", "remaining_time": "3:43:29"}
|
| 224 |
+
{"current_steps": 2040, "total_steps": 4275, "loss": 0.1268, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.698217822236041e-05, "epoch": 2.3859649122807016, "percentage": 47.72, "elapsed_time": "3:22:55", "remaining_time": "3:42:18"}
|
| 225 |
+
{"current_steps": 2050, "total_steps": 4275, "loss": 0.1175, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.6798124553604653e-05, "epoch": 2.39766081871345, "percentage": 47.95, "elapsed_time": "3:23:51", "remaining_time": "3:41:16"}
|
| 226 |
+
{"current_steps": 2060, "total_steps": 4275, "loss": 0.1177, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.6613972864009994e-05, "epoch": 2.409356725146199, "percentage": 48.19, "elapsed_time": "3:24:40", "remaining_time": "3:40:04"}
|
| 227 |
+
{"current_steps": 2070, "total_steps": 4275, "loss": 0.1343, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.642973319220422e-05, "epoch": 2.4210526315789473, "percentage": 48.42, "elapsed_time": "3:25:33", "remaining_time": "3:38:57"}
|
| 228 |
+
{"current_steps": 2080, "total_steps": 4275, "loss": 0.1335, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.624541558161125e-05, "epoch": 2.4327485380116958, "percentage": 48.65, "elapsed_time": "3:26:33", "remaining_time": "3:37:58"}
|
| 229 |
+
{"current_steps": 2090, "total_steps": 4275, "loss": 0.1208, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.606103007990371e-05, "epoch": 2.4444444444444446, "percentage": 48.89, "elapsed_time": "3:27:30", "remaining_time": "3:36:56"}
|
| 230 |
+
{"current_steps": 2100, "total_steps": 4275, "loss": 0.1164, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.587658673845513e-05, "epoch": 2.456140350877193, "percentage": 49.12, "elapsed_time": "3:28:18", "remaining_time": "3:35:44"}
|
| 231 |
+
{"current_steps": 2100, "total_steps": 4275, "loss": null, "eval_loss": 0.12629590928554535, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.456140350877193, "percentage": 49.12, "elapsed_time": "3:28:18", "remaining_time": "3:35:44"}
|
| 232 |
+
{"current_steps": 2110, "total_steps": 4275, "loss": 0.1408, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.569209561179206e-05, "epoch": 2.4678362573099415, "percentage": 49.36, "elapsed_time": "3:30:24", "remaining_time": "3:35:53"}
|
| 233 |
+
{"current_steps": 2120, "total_steps": 4275, "loss": 0.1203, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.550756675704596e-05, "epoch": 2.47953216374269, "percentage": 49.59, "elapsed_time": "3:31:21", "remaining_time": "3:34:51"}
|
| 234 |
+
{"current_steps": 2130, "total_steps": 4275, "loss": 0.1187, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5323010233404925e-05, "epoch": 2.4912280701754383, "percentage": 49.82, "elapsed_time": "3:32:19", "remaining_time": "3:33:49"}
|
| 235 |
+
{"current_steps": 2140, "total_steps": 4275, "loss": 0.1105, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5138436101565405e-05, "epoch": 2.502923976608187, "percentage": 50.06, "elapsed_time": "3:33:05", "remaining_time": "3:32:35"}
|
| 236 |
+
{"current_steps": 2150, "total_steps": 4275, "loss": 0.1263, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.4953854423183694e-05, "epoch": 2.5146198830409356, "percentage": 50.29, "elapsed_time": "3:33:56", "remaining_time": "3:31:27"}
|
| 237 |
+
{"current_steps": 2160, "total_steps": 4275, "loss": 0.1402, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.4769275260327474e-05, "epoch": 2.526315789473684, "percentage": 50.53, "elapsed_time": "3:34:47", "remaining_time": "3:30:19"}
|
| 238 |
+
{"current_steps": 2170, "total_steps": 4275, "loss": 0.1254, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.4584708674927308e-05, "epoch": 2.538011695906433, "percentage": 50.76, "elapsed_time": "3:35:36", "remaining_time": "3:29:08"}
|
| 239 |
+
{"current_steps": 2180, "total_steps": 4275, "loss": 0.1069, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.44001647282281e-05, "epoch": 2.5497076023391814, "percentage": 50.99, "elapsed_time": "3:36:20", "remaining_time": "3:27:54"}
|
| 240 |
+
{"current_steps": 2190, "total_steps": 4275, "loss": 0.1203, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.4215653480240685e-05, "epoch": 2.56140350877193, "percentage": 51.23, "elapsed_time": "3:37:08", "remaining_time": "3:26:44"}
|
| 241 |
+
{"current_steps": 2200, "total_steps": 4275, "loss": 0.1038, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.4031184989193384e-05, "epoch": 2.573099415204678, "percentage": 51.46, "elapsed_time": "3:38:02", "remaining_time": "3:25:39"}
|
| 242 |
+
{"current_steps": 2200, "total_steps": 4275, "loss": null, "eval_loss": 0.12356504052877426, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.573099415204678, "percentage": 51.46, "elapsed_time": "3:38:02", "remaining_time": "3:25:39"}
|
| 243 |
+
{"current_steps": 2210, "total_steps": 4275, "loss": 0.1315, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3846769310983727e-05, "epoch": 2.5847953216374266, "percentage": 51.7, "elapsed_time": "3:40:00", "remaining_time": "3:25:33"}
|
| 244 |
+
{"current_steps": 2220, "total_steps": 4275, "loss": 0.1228, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3662416498630257e-05, "epoch": 2.5964912280701755, "percentage": 51.93, "elapsed_time": "3:40:56", "remaining_time": "3:24:31"}
|
| 245 |
+
{"current_steps": 2230, "total_steps": 4275, "loss": 0.115, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3478136601724515e-05, "epoch": 2.608187134502924, "percentage": 52.16, "elapsed_time": "3:41:56", "remaining_time": "3:23:31"}
|
| 246 |
+
{"current_steps": 2240, "total_steps": 4275, "loss": 0.0981, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.329393966588323e-05, "epoch": 2.6198830409356724, "percentage": 52.4, "elapsed_time": "3:42:37", "remaining_time": "3:22:15"}
|
| 247 |
+
{"current_steps": 2250, "total_steps": 4275, "loss": 0.0954, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3109835732200686e-05, "epoch": 2.6315789473684212, "percentage": 52.63, "elapsed_time": "3:43:30", "remaining_time": "3:21:09"}
|
| 248 |
+
{"current_steps": 2260, "total_steps": 4275, "loss": 0.1046, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.292583483670136e-05, "epoch": 2.6432748538011697, "percentage": 52.87, "elapsed_time": "3:44:31", "remaining_time": "3:20:11"}
|
| 249 |
+
{"current_steps": 2270, "total_steps": 4275, "loss": 0.1245, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.2741947009792817e-05, "epoch": 2.654970760233918, "percentage": 53.1, "elapsed_time": "3:45:20", "remaining_time": "3:19:02"}
|
| 250 |
+
{"current_steps": 2280, "total_steps": 4275, "loss": 0.1303, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.2558182275718953e-05, "epoch": 2.6666666666666665, "percentage": 53.33, "elapsed_time": "3:46:15", "remaining_time": "3:17:58"}
|
| 251 |
+
{"current_steps": 2290, "total_steps": 4275, "loss": 0.1142, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.2374550652013492e-05, "epoch": 2.678362573099415, "percentage": 53.57, "elapsed_time": "3:47:09", "remaining_time": "3:16:54"}
|
| 252 |
+
{"current_steps": 2300, "total_steps": 4275, "loss": 0.1196, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.219106214895397e-05, "epoch": 2.690058479532164, "percentage": 53.8, "elapsed_time": "3:48:10", "remaining_time": "3:15:55"}
|
| 253 |
+
{"current_steps": 2300, "total_steps": 4275, "loss": null, "eval_loss": 0.12174443155527115, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.690058479532164, "percentage": 53.8, "elapsed_time": "3:48:10", "remaining_time": "3:15:55"}
|
| 254 |
+
{"current_steps": 2310, "total_steps": 4275, "loss": 0.1071, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.2007726769016006e-05, "epoch": 2.7017543859649122, "percentage": 54.04, "elapsed_time": "3:50:14", "remaining_time": "3:15:51"}
|
| 255 |
+
{"current_steps": 2320, "total_steps": 4275, "loss": 0.1246, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.182455450632803e-05, "epoch": 2.7134502923976607, "percentage": 54.27, "elapsed_time": "3:51:05", "remaining_time": "3:14:43"}
|
| 256 |
+
{"current_steps": 2330, "total_steps": 4275, "loss": 0.1188, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.1641555346126512e-05, "epoch": 2.7251461988304095, "percentage": 54.5, "elapsed_time": "3:52:00", "remaining_time": "3:13:40"}
|
| 257 |
+
{"current_steps": 2340, "total_steps": 4275, "loss": 0.101, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.1458739264211618e-05, "epoch": 2.736842105263158, "percentage": 54.74, "elapsed_time": "3:52:52", "remaining_time": "3:12:33"}
|
| 258 |
+
{"current_steps": 2350, "total_steps": 4275, "loss": 0.1068, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.127611622640336e-05, "epoch": 2.7485380116959064, "percentage": 54.97, "elapsed_time": "3:53:37", "remaining_time": "3:11:22"}
|
| 259 |
+
{"current_steps": 2360, "total_steps": 4275, "loss": 0.1196, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.1093696187998424e-05, "epoch": 2.760233918128655, "percentage": 55.2, "elapsed_time": "3:54:28", "remaining_time": "3:10:15"}
|
| 260 |
+
{"current_steps": 2370, "total_steps": 4275, "loss": 0.1076, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.0911489093227395e-05, "epoch": 2.7719298245614032, "percentage": 55.44, "elapsed_time": "3:55:21", "remaining_time": "3:09:10"}
|
| 261 |
+
{"current_steps": 2380, "total_steps": 4275, "loss": 0.111, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.0729504874712713e-05, "epoch": 2.783625730994152, "percentage": 55.67, "elapsed_time": "3:56:15", "remaining_time": "3:08:07"}
|
| 262 |
+
{"current_steps": 2390, "total_steps": 4275, "loss": 0.1079, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.0547753452927197e-05, "epoch": 2.7953216374269005, "percentage": 55.91, "elapsed_time": "3:57:05", "remaining_time": "3:06:59"}
|
| 263 |
+
{"current_steps": 2400, "total_steps": 4275, "loss": 0.1058, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.036624473565328e-05, "epoch": 2.807017543859649, "percentage": 56.14, "elapsed_time": "3:57:51", "remaining_time": "3:05:49"}
|
| 264 |
+
{"current_steps": 2400, "total_steps": 4275, "loss": null, "eval_loss": 0.1205640360713005, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.807017543859649, "percentage": 56.14, "elapsed_time": "3:57:51", "remaining_time": "3:05:49"}
|
| 265 |
+
{"current_steps": 2410, "total_steps": 4275, "loss": 0.1111, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.0184988617442852e-05, "epoch": 2.818713450292398, "percentage": 56.37, "elapsed_time": "3:59:59", "remaining_time": "3:05:43"}
|
| 266 |
+
{"current_steps": 2420, "total_steps": 4275, "loss": 0.1069, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.0003994979077937e-05, "epoch": 2.8304093567251463, "percentage": 56.61, "elapsed_time": "4:00:52", "remaining_time": "3:04:38"}
|
| 267 |
+
{"current_steps": 2430, "total_steps": 4275, "loss": 0.1153, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.9823273687032045e-05, "epoch": 2.8421052631578947, "percentage": 56.84, "elapsed_time": "4:01:41", "remaining_time": "3:03:30"}
|
| 268 |
+
{"current_steps": 2440, "total_steps": 4275, "loss": 0.1097, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.964283459293232e-05, "epoch": 2.853801169590643, "percentage": 57.08, "elapsed_time": "4:02:32", "remaining_time": "3:02:24"}
|
| 269 |
+
{"current_steps": 2450, "total_steps": 4275, "loss": 0.1123, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.94626875330225e-05, "epoch": 2.8654970760233915, "percentage": 57.31, "elapsed_time": "4:03:35", "remaining_time": "3:01:27"}
|
| 270 |
+
{"current_steps": 2460, "total_steps": 4275, "loss": 0.1194, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.92828423276267e-05, "epoch": 2.8771929824561404, "percentage": 57.54, "elapsed_time": "4:04:18", "remaining_time": "3:00:15"}
|
| 271 |
+
{"current_steps": 2470, "total_steps": 4275, "loss": 0.1041, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.9103308780614118e-05, "epoch": 2.888888888888889, "percentage": 57.78, "elapsed_time": "4:05:16", "remaining_time": "2:59:14"}
|
| 272 |
+
{"current_steps": 2480, "total_steps": 4275, "loss": 0.1155, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.8924096678864557e-05, "epoch": 2.9005847953216373, "percentage": 58.01, "elapsed_time": "4:06:06", "remaining_time": "2:58:08"}
|
| 273 |
+
{"current_steps": 2490, "total_steps": 4275, "loss": 0.1073, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.8745215791734942e-05, "epoch": 2.912280701754386, "percentage": 58.25, "elapsed_time": "4:06:54", "remaining_time": "2:56:59"}
|
| 274 |
+
{"current_steps": 2500, "total_steps": 4275, "loss": 0.1177, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.8566675870526756e-05, "epoch": 2.9239766081871346, "percentage": 58.48, "elapsed_time": "4:07:48", "remaining_time": "2:55:56"}
|
| 275 |
+
{"current_steps": 2500, "total_steps": 4275, "loss": null, "eval_loss": 0.12042708694934845, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.9239766081871346, "percentage": 58.48, "elapsed_time": "4:07:48", "remaining_time": "2:55:56"}
|
| 276 |
+
{"current_steps": 2510, "total_steps": 4275, "loss": 0.1073, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.838848664795447e-05, "epoch": 2.935672514619883, "percentage": 58.71, "elapsed_time": "4:09:49", "remaining_time": "2:55:40"}
|
| 277 |
+
{"current_steps": 2520, "total_steps": 4275, "loss": 0.11, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.8210657837614965e-05, "epoch": 2.9473684210526314, "percentage": 58.95, "elapsed_time": "4:10:40", "remaining_time": "2:54:34"}
|
| 278 |
+
{"current_steps": 2530, "total_steps": 4275, "loss": 0.112, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.803319913345805e-05, "epoch": 2.95906432748538, "percentage": 59.18, "elapsed_time": "4:11:27", "remaining_time": "2:53:26"}
|
| 279 |
+
{"current_steps": 2540, "total_steps": 4275, "loss": 0.0969, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.785612020925801e-05, "epoch": 2.9707602339181287, "percentage": 59.42, "elapsed_time": "4:12:18", "remaining_time": "2:52:20"}
|
| 280 |
+
{"current_steps": 2550, "total_steps": 4275, "loss": 0.1006, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.7679430718086243e-05, "epoch": 2.982456140350877, "percentage": 59.65, "elapsed_time": "4:13:08", "remaining_time": "2:51:14"}
|
| 281 |
+
{"current_steps": 2560, "total_steps": 4275, "loss": 0.1041, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.7503140291785054e-05, "epoch": 2.9941520467836256, "percentage": 59.88, "elapsed_time": "4:13:56", "remaining_time": "2:50:07"}
|
| 282 |
+
{"current_steps": 2570, "total_steps": 4275, "loss": 0.0973, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.732725854044261e-05, "epoch": 3.0058479532163744, "percentage": 60.12, "elapsed_time": "4:14:51", "remaining_time": "2:49:04"}
|
| 283 |
+
{"current_steps": 2580, "total_steps": 4275, "loss": 0.1181, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.7151795051869025e-05, "epoch": 3.017543859649123, "percentage": 60.35, "elapsed_time": "4:15:48", "remaining_time": "2:48:03"}
|
| 284 |
+
{"current_steps": 2590, "total_steps": 4275, "loss": 0.1177, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.6976759391073758e-05, "epoch": 3.0292397660818713, "percentage": 60.58, "elapsed_time": "4:16:49", "remaining_time": "2:47:05"}
|
| 285 |
+
{"current_steps": 2600, "total_steps": 4275, "loss": 0.1009, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.6802161099744164e-05, "epoch": 3.0409356725146197, "percentage": 60.82, "elapsed_time": "4:17:37", "remaining_time": "2:45:58"}
|
| 286 |
+
{"current_steps": 2600, "total_steps": 4275, "loss": null, "eval_loss": 0.11801114678382874, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 3.0409356725146197, "percentage": 60.82, "elapsed_time": "4:17:37", "remaining_time": "2:45:58"}
|
| 287 |
+
{"current_steps": 2610, "total_steps": 4275, "loss": 0.0869, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.6628009695725346e-05, "epoch": 3.0526315789473686, "percentage": 61.05, "elapsed_time": "4:19:38", "remaining_time": "2:45:38"}
|
| 288 |
+
{"current_steps": 2620, "total_steps": 4275, "loss": 0.1067, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.645431467250134e-05, "epoch": 3.064327485380117, "percentage": 61.29, "elapsed_time": "4:20:30", "remaining_time": "2:44:33"}
|
| 289 |
+
{"current_steps": 2630, "total_steps": 4275, "loss": 0.1065, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.628108549867754e-05, "epoch": 3.0760233918128654, "percentage": 61.52, "elapsed_time": "4:21:24", "remaining_time": "2:43:30"}
|
| 290 |
+
{"current_steps": 2640, "total_steps": 4275, "loss": 0.1046, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.610833161746461e-05, "epoch": 3.087719298245614, "percentage": 61.75, "elapsed_time": "4:22:15", "remaining_time": "2:42:25"}
|
| 291 |
+
{"current_steps": 2650, "total_steps": 4275, "loss": 0.102, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.5936062446163666e-05, "epoch": 3.0994152046783627, "percentage": 61.99, "elapsed_time": "4:23:13", "remaining_time": "2:41:24"}
|
| 292 |
+
{"current_steps": 2660, "total_steps": 4275, "loss": 0.0921, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.576428737565292e-05, "epoch": 3.111111111111111, "percentage": 62.22, "elapsed_time": "4:24:03", "remaining_time": "2:40:19"}
|
| 293 |
+
{"current_steps": 2670, "total_steps": 4275, "loss": 0.0966, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.5593015769875746e-05, "epoch": 3.1228070175438596, "percentage": 62.46, "elapsed_time": "4:24:51", "remaining_time": "2:39:12"}
|
| 294 |
+
{"current_steps": 2680, "total_steps": 4275, "loss": 0.1179, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.5422256965330263e-05, "epoch": 3.134502923976608, "percentage": 62.69, "elapsed_time": "4:25:45", "remaining_time": "2:38:10"}
|
| 295 |
+
{"current_steps": 2690, "total_steps": 4275, "loss": 0.095, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.52520202705603e-05, "epoch": 3.146198830409357, "percentage": 62.92, "elapsed_time": "4:26:36", "remaining_time": "2:37:05"}
|
| 296 |
+
{"current_steps": 2700, "total_steps": 4275, "loss": 0.1024, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.508231496564806e-05, "epoch": 3.1578947368421053, "percentage": 63.16, "elapsed_time": "4:27:30", "remaining_time": "2:36:03"}
|
| 297 |
+
{"current_steps": 2700, "total_steps": 4275, "loss": null, "eval_loss": 0.11845976859331131, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 3.1578947368421053, "percentage": 63.16, "elapsed_time": "4:27:30", "remaining_time": "2:36:03"}
|
| 298 |
+
{"current_steps": 2710, "total_steps": 4275, "loss": 0.1048, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.4913150301708162e-05, "epoch": 3.1695906432748537, "percentage": 63.39, "elapsed_time": "4:29:40", "remaining_time": "2:35:44"}
|
| 299 |
+
{"current_steps": 2720, "total_steps": 4275, "loss": 0.1227, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.4744535500383372e-05, "epoch": 3.181286549707602, "percentage": 63.63, "elapsed_time": "4:30:25", "remaining_time": "2:34:36"}
|
| 300 |
+
{"current_steps": 2730, "total_steps": 4275, "loss": 0.1155, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.4576479753341882e-05, "epoch": 3.192982456140351, "percentage": 63.86, "elapsed_time": "4:31:20", "remaining_time": "2:33:33"}
|
| 301 |
+
{"current_steps": 2740, "total_steps": 4275, "loss": 0.1116, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.4408992221776282e-05, "epoch": 3.2046783625730995, "percentage": 64.09, "elapsed_time": "4:32:12", "remaining_time": "2:32:29"}
|
| 302 |
+
{"current_steps": 2750, "total_steps": 4275, "loss": 0.1168, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.4242082035904086e-05, "epoch": 3.216374269005848, "percentage": 64.33, "elapsed_time": "4:33:02", "remaining_time": "2:31:25"}
|
| 303 |
+
{"current_steps": 2760, "total_steps": 4275, "loss": 0.0942, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.4075758294470132e-05, "epoch": 3.2280701754385963, "percentage": 64.56, "elapsed_time": "4:33:56", "remaining_time": "2:30:22"}
|
| 304 |
+
{"current_steps": 2770, "total_steps": 4275, "loss": 0.103, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.3910030064250462e-05, "epoch": 3.239766081871345, "percentage": 64.8, "elapsed_time": "4:34:51", "remaining_time": "2:29:19"}
|
| 305 |
+
{"current_steps": 2780, "total_steps": 4275, "loss": 0.1246, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.3744906379558165e-05, "epoch": 3.2514619883040936, "percentage": 65.03, "elapsed_time": "4:35:46", "remaining_time": "2:28:18"}
|
| 306 |
+
{"current_steps": 2790, "total_steps": 4275, "loss": 0.1054, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.3580396241750823e-05, "epoch": 3.263157894736842, "percentage": 65.26, "elapsed_time": "4:36:36", "remaining_time": "2:27:13"}
|
| 307 |
+
{"current_steps": 2800, "total_steps": 4275, "loss": 0.0953, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.3416508618739854e-05, "epoch": 3.2748538011695905, "percentage": 65.5, "elapsed_time": "4:37:30", "remaining_time": "2:26:11"}
|
| 308 |
+
{"current_steps": 2800, "total_steps": 4275, "loss": null, "eval_loss": 0.1236434280872345, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 3.2748538011695905, "percentage": 65.5, "elapsed_time": "4:37:30", "remaining_time": "2:26:11"}
|
| 309 |
+
{"current_steps": 2810, "total_steps": 4275, "loss": 0.0891, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.3253252444501635e-05, "epoch": 3.2865497076023393, "percentage": 65.73, "elapsed_time": "4:39:22", "remaining_time": "2:25:39"}
|
| 310 |
+
{"current_steps": 2820, "total_steps": 4275, "loss": 0.0942, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.309063661859049e-05, "epoch": 3.2982456140350878, "percentage": 65.96, "elapsed_time": "4:40:07", "remaining_time": "2:24:31"}
|
| 311 |
+
{"current_steps": 2830, "total_steps": 4275, "loss": 0.0966, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.2928670005653576e-05, "epoch": 3.309941520467836, "percentage": 66.2, "elapsed_time": "4:41:02", "remaining_time": "2:23:30"}
|
| 312 |
+
{"current_steps": 2840, "total_steps": 4275, "loss": 0.0863, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.2767361434947584e-05, "epoch": 3.3216374269005846, "percentage": 66.43, "elapsed_time": "4:41:55", "remaining_time": "2:22:27"}
|
| 313 |
+
{"current_steps": 2850, "total_steps": 4275, "loss": 0.0938, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.2606719699857489e-05, "epoch": 3.3333333333333335, "percentage": 66.67, "elapsed_time": "4:42:48", "remaining_time": "2:21:24"}
|
| 314 |
+
{"current_steps": 2860, "total_steps": 4275, "loss": 0.1161, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.244675355741717e-05, "epoch": 3.345029239766082, "percentage": 66.9, "elapsed_time": "4:43:44", "remaining_time": "2:20:23"}
|
| 315 |
+
{"current_steps": 2870, "total_steps": 4275, "loss": 0.1082, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.228747172783204e-05, "epoch": 3.3567251461988303, "percentage": 67.13, "elapsed_time": "4:44:29", "remaining_time": "2:19:16"}
|
| 316 |
+
{"current_steps": 2880, "total_steps": 4275, "loss": 0.0982, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.212888289400371e-05, "epoch": 3.3684210526315788, "percentage": 67.37, "elapsed_time": "4:45:25", "remaining_time": "2:18:15"}
|
| 317 |
+
{"current_steps": 2890, "total_steps": 4275, "loss": 0.1026, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.1970995701056615e-05, "epoch": 3.3801169590643276, "percentage": 67.6, "elapsed_time": "4:46:13", "remaining_time": "2:17:10"}
|
| 318 |
+
{"current_steps": 2900, "total_steps": 4275, "loss": 0.0905, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.181381875586677e-05, "epoch": 3.391812865497076, "percentage": 67.84, "elapsed_time": "4:47:04", "remaining_time": "2:16:06"}
|
| 319 |
+
{"current_steps": 2900, "total_steps": 4275, "loss": null, "eval_loss": 0.12022969871759415, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 3.391812865497076, "percentage": 67.84, "elapsed_time": "4:47:04", "remaining_time": "2:16:06"}
|
| 320 |
+
{"current_steps": 2900, "total_steps": 4275, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 3.391812865497076, "percentage": 67.84, "elapsed_time": "4:47:04", "remaining_time": "2:16:06"}
|
| 321 |
+
{"current_steps": 45, "total_steps": 45, "loss": null, "eval_loss": 0.11801114678382874, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 3.391812865497076, "percentage": 100.0, "elapsed_time": "4:49:35", "remaining_time": "0:00:00"}
|
llama2_13b_peft/paragraph_segmentation/trainer_state.json
ADDED
|
@@ -0,0 +1,2292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.11801114678382874,
|
| 3 |
+
"best_model_checkpoint": "ckpt/llama2_13b_other/paragraph_segmentation_no_sys/checkpoint-2600",
|
| 4 |
+
"epoch": 3.391812865497076,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 2900,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.011695906432748537,
|
| 13 |
+
"grad_norm": 0.6690150499343872,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 0.781,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.023391812865497075,
|
| 20 |
+
"grad_norm": 0.3248962163925171,
|
| 21 |
+
"learning_rate": 5e-05,
|
| 22 |
+
"loss": 0.5723,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03508771929824561,
|
| 27 |
+
"grad_norm": 0.4461202621459961,
|
| 28 |
+
"learning_rate": 4.999931858975852e-05,
|
| 29 |
+
"loss": 0.378,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04678362573099415,
|
| 34 |
+
"grad_norm": 0.4027818739414215,
|
| 35 |
+
"learning_rate": 4.999727439617963e-05,
|
| 36 |
+
"loss": 0.2932,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05847953216374269,
|
| 41 |
+
"grad_norm": 0.17189592123031616,
|
| 42 |
+
"learning_rate": 4.999386753069811e-05,
|
| 43 |
+
"loss": 0.2703,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07017543859649122,
|
| 48 |
+
"grad_norm": 0.2007831186056137,
|
| 49 |
+
"learning_rate": 4.9989098179031804e-05,
|
| 50 |
+
"loss": 0.2844,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.08187134502923976,
|
| 55 |
+
"grad_norm": 0.21012109518051147,
|
| 56 |
+
"learning_rate": 4.998296660117151e-05,
|
| 57 |
+
"loss": 0.249,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0935672514619883,
|
| 62 |
+
"grad_norm": 0.3014354109764099,
|
| 63 |
+
"learning_rate": 4.997547313136682e-05,
|
| 64 |
+
"loss": 0.2521,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.10526315789473684,
|
| 69 |
+
"grad_norm": 0.3537119925022125,
|
| 70 |
+
"learning_rate": 4.996661817810791e-05,
|
| 71 |
+
"loss": 0.2647,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.11695906432748537,
|
| 76 |
+
"grad_norm": 0.3879987597465515,
|
| 77 |
+
"learning_rate": 4.995640222410324e-05,
|
| 78 |
+
"loss": 0.2344,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.11695906432748537,
|
| 83 |
+
"eval_loss": 0.23539581894874573,
|
| 84 |
+
"eval_runtime": 70.7724,
|
| 85 |
+
"eval_samples_per_second": 5.087,
|
| 86 |
+
"eval_steps_per_second": 0.636,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1286549707602339,
|
| 91 |
+
"grad_norm": 0.658244788646698,
|
| 92 |
+
"learning_rate": 4.994482582625327e-05,
|
| 93 |
+
"loss": 0.2274,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.14035087719298245,
|
| 98 |
+
"grad_norm": 1.490973949432373,
|
| 99 |
+
"learning_rate": 4.9931889615620075e-05,
|
| 100 |
+
"loss": 0.2664,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.15204678362573099,
|
| 105 |
+
"grad_norm": 0.39017337560653687,
|
| 106 |
+
"learning_rate": 4.991759429739298e-05,
|
| 107 |
+
"loss": 0.2483,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.16374269005847952,
|
| 112 |
+
"grad_norm": 1.4655972719192505,
|
| 113 |
+
"learning_rate": 4.9901940650850074e-05,
|
| 114 |
+
"loss": 0.2269,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.17543859649122806,
|
| 119 |
+
"grad_norm": 0.4164131283760071,
|
| 120 |
+
"learning_rate": 4.9884929529315774e-05,
|
| 121 |
+
"loss": 0.2249,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.1871345029239766,
|
| 126 |
+
"grad_norm": 0.43179380893707275,
|
| 127 |
+
"learning_rate": 4.986656186011426e-05,
|
| 128 |
+
"loss": 0.2232,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.19883040935672514,
|
| 133 |
+
"grad_norm": 0.9226874709129333,
|
| 134 |
+
"learning_rate": 4.984683864451898e-05,
|
| 135 |
+
"loss": 0.2274,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.21052631578947367,
|
| 140 |
+
"grad_norm": 0.5234158039093018,
|
| 141 |
+
"learning_rate": 4.982576095769801e-05,
|
| 142 |
+
"loss": 0.2153,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2222222222222222,
|
| 147 |
+
"grad_norm": 0.9352672696113586,
|
| 148 |
+
"learning_rate": 4.980332994865549e-05,
|
| 149 |
+
"loss": 0.2123,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.23391812865497075,
|
| 154 |
+
"grad_norm": 0.7342891693115234,
|
| 155 |
+
"learning_rate": 4.9779546840168964e-05,
|
| 156 |
+
"loss": 0.2247,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.23391812865497075,
|
| 161 |
+
"eval_loss": 0.2295626550912857,
|
| 162 |
+
"eval_runtime": 70.735,
|
| 163 |
+
"eval_samples_per_second": 5.089,
|
| 164 |
+
"eval_steps_per_second": 0.636,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.24561403508771928,
|
| 169 |
+
"grad_norm": 0.19036857783794403,
|
| 170 |
+
"learning_rate": 4.9754412928722714e-05,
|
| 171 |
+
"loss": 0.2358,
|
| 172 |
+
"step": 210
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.2573099415204678,
|
| 176 |
+
"grad_norm": 0.4506204426288605,
|
| 177 |
+
"learning_rate": 4.9727929584437136e-05,
|
| 178 |
+
"loss": 0.2187,
|
| 179 |
+
"step": 220
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.26900584795321636,
|
| 183 |
+
"grad_norm": 0.5454403162002563,
|
| 184 |
+
"learning_rate": 4.970009825099398e-05,
|
| 185 |
+
"loss": 0.2077,
|
| 186 |
+
"step": 230
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.2807017543859649,
|
| 190 |
+
"grad_norm": 0.6654325127601624,
|
| 191 |
+
"learning_rate": 4.967092044555769e-05,
|
| 192 |
+
"loss": 0.2458,
|
| 193 |
+
"step": 240
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.29239766081871343,
|
| 197 |
+
"grad_norm": 0.30863338708877563,
|
| 198 |
+
"learning_rate": 4.9640397758692715e-05,
|
| 199 |
+
"loss": 0.1873,
|
| 200 |
+
"step": 250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.30409356725146197,
|
| 204 |
+
"grad_norm": 0.4261077642440796,
|
| 205 |
+
"learning_rate": 4.960853185427676e-05,
|
| 206 |
+
"loss": 0.1758,
|
| 207 |
+
"step": 260
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.3157894736842105,
|
| 211 |
+
"grad_norm": 1.0026551485061646,
|
| 212 |
+
"learning_rate": 4.957532446941012e-05,
|
| 213 |
+
"loss": 0.2229,
|
| 214 |
+
"step": 270
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.32748538011695905,
|
| 218 |
+
"grad_norm": 0.20305348932743073,
|
| 219 |
+
"learning_rate": 4.954077741432097e-05,
|
| 220 |
+
"loss": 0.2043,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.3391812865497076,
|
| 225 |
+
"grad_norm": 0.20843225717544556,
|
| 226 |
+
"learning_rate": 4.950489257226667e-05,
|
| 227 |
+
"loss": 0.1949,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.3508771929824561,
|
| 232 |
+
"grad_norm": 1.1773661375045776,
|
| 233 |
+
"learning_rate": 4.9467671899431145e-05,
|
| 234 |
+
"loss": 0.2009,
|
| 235 |
+
"step": 300
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.3508771929824561,
|
| 239 |
+
"eval_loss": 0.20195595920085907,
|
| 240 |
+
"eval_runtime": 70.7382,
|
| 241 |
+
"eval_samples_per_second": 5.089,
|
| 242 |
+
"eval_steps_per_second": 0.636,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.36257309941520466,
|
| 247 |
+
"grad_norm": 0.6430270075798035,
|
| 248 |
+
"learning_rate": 4.942911742481819e-05,
|
| 249 |
+
"loss": 0.1841,
|
| 250 |
+
"step": 310
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.3742690058479532,
|
| 254 |
+
"grad_norm": 0.6599162220954895,
|
| 255 |
+
"learning_rate": 4.938923125014094e-05,
|
| 256 |
+
"loss": 0.2091,
|
| 257 |
+
"step": 320
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.38596491228070173,
|
| 261 |
+
"grad_norm": 0.49684128165245056,
|
| 262 |
+
"learning_rate": 4.93480155497072e-05,
|
| 263 |
+
"loss": 0.2032,
|
| 264 |
+
"step": 330
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.39766081871345027,
|
| 268 |
+
"grad_norm": 0.43949800729751587,
|
| 269 |
+
"learning_rate": 4.930547257030102e-05,
|
| 270 |
+
"loss": 0.1952,
|
| 271 |
+
"step": 340
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.4093567251461988,
|
| 275 |
+
"grad_norm": 0.18739910423755646,
|
| 276 |
+
"learning_rate": 4.926160463106015e-05,
|
| 277 |
+
"loss": 0.1926,
|
| 278 |
+
"step": 350
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.42105263157894735,
|
| 282 |
+
"grad_norm": 0.42857053875923157,
|
| 283 |
+
"learning_rate": 4.921641412334963e-05,
|
| 284 |
+
"loss": 0.2085,
|
| 285 |
+
"step": 360
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.4327485380116959,
|
| 289 |
+
"grad_norm": 0.3196578621864319,
|
| 290 |
+
"learning_rate": 4.9169903510631434e-05,
|
| 291 |
+
"loss": 0.199,
|
| 292 |
+
"step": 370
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.4444444444444444,
|
| 296 |
+
"grad_norm": 0.8997694849967957,
|
| 297 |
+
"learning_rate": 4.91220753283302e-05,
|
| 298 |
+
"loss": 0.1874,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.45614035087719296,
|
| 303 |
+
"grad_norm": 0.6457922458648682,
|
| 304 |
+
"learning_rate": 4.907293218369499e-05,
|
| 305 |
+
"loss": 0.1775,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.4678362573099415,
|
| 310 |
+
"grad_norm": 1.4266046285629272,
|
| 311 |
+
"learning_rate": 4.9022476755657155e-05,
|
| 312 |
+
"loss": 0.2097,
|
| 313 |
+
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.4678362573099415,
|
| 317 |
+
"eval_loss": 0.19560903310775757,
|
| 318 |
+
"eval_runtime": 70.7773,
|
| 319 |
+
"eval_samples_per_second": 5.086,
|
| 320 |
+
"eval_steps_per_second": 0.636,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.47953216374269003,
|
| 325 |
+
"grad_norm": 0.8755818009376526,
|
| 326 |
+
"learning_rate": 4.8970711794684345e-05,
|
| 327 |
+
"loss": 0.1872,
|
| 328 |
+
"step": 410
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.49122807017543857,
|
| 332 |
+
"grad_norm": 0.41280242800712585,
|
| 333 |
+
"learning_rate": 4.8917640122630506e-05,
|
| 334 |
+
"loss": 0.1936,
|
| 335 |
+
"step": 420
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.5029239766081871,
|
| 339 |
+
"grad_norm": 0.4296826422214508,
|
| 340 |
+
"learning_rate": 4.886326463258212e-05,
|
| 341 |
+
"loss": 0.1933,
|
| 342 |
+
"step": 430
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.5146198830409356,
|
| 346 |
+
"grad_norm": 0.6381562948226929,
|
| 347 |
+
"learning_rate": 4.880758828870045e-05,
|
| 348 |
+
"loss": 0.1874,
|
| 349 |
+
"step": 440
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.5263157894736842,
|
| 353 |
+
"grad_norm": 0.2770218849182129,
|
| 354 |
+
"learning_rate": 4.875061412605997e-05,
|
| 355 |
+
"loss": 0.184,
|
| 356 |
+
"step": 450
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.5380116959064327,
|
| 360 |
+
"grad_norm": 0.23563164472579956,
|
| 361 |
+
"learning_rate": 4.8692345250482914e-05,
|
| 362 |
+
"loss": 0.1901,
|
| 363 |
+
"step": 460
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.5497076023391813,
|
| 367 |
+
"grad_norm": 0.3889436721801758,
|
| 368 |
+
"learning_rate": 4.863278483836996e-05,
|
| 369 |
+
"loss": 0.1803,
|
| 370 |
+
"step": 470
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.5614035087719298,
|
| 374 |
+
"grad_norm": 0.23517946898937225,
|
| 375 |
+
"learning_rate": 4.857193613652711e-05,
|
| 376 |
+
"loss": 0.1688,
|
| 377 |
+
"step": 480
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.5730994152046783,
|
| 381 |
+
"grad_norm": 1.0376458168029785,
|
| 382 |
+
"learning_rate": 4.8509802461988635e-05,
|
| 383 |
+
"loss": 0.1757,
|
| 384 |
+
"step": 490
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.5847953216374269,
|
| 388 |
+
"grad_norm": 0.3648129999637604,
|
| 389 |
+
"learning_rate": 4.844638720183632e-05,
|
| 390 |
+
"loss": 0.185,
|
| 391 |
+
"step": 500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.5847953216374269,
|
| 395 |
+
"eval_loss": 0.1873869150876999,
|
| 396 |
+
"eval_runtime": 70.7709,
|
| 397 |
+
"eval_samples_per_second": 5.087,
|
| 398 |
+
"eval_steps_per_second": 0.636,
|
| 399 |
+
"step": 500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.5964912280701754,
|
| 403 |
+
"grad_norm": 0.1653483510017395,
|
| 404 |
+
"learning_rate": 4.8381693813014775e-05,
|
| 405 |
+
"loss": 0.1864,
|
| 406 |
+
"step": 510
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.6081871345029239,
|
| 410 |
+
"grad_norm": 0.6757428050041199,
|
| 411 |
+
"learning_rate": 4.8315725822143024e-05,
|
| 412 |
+
"loss": 0.1723,
|
| 413 |
+
"step": 520
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.6198830409356725,
|
| 417 |
+
"grad_norm": 0.8670457601547241,
|
| 418 |
+
"learning_rate": 4.824848682532224e-05,
|
| 419 |
+
"loss": 0.161,
|
| 420 |
+
"step": 530
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.631578947368421,
|
| 424 |
+
"grad_norm": 0.7731683254241943,
|
| 425 |
+
"learning_rate": 4.817998048793969e-05,
|
| 426 |
+
"loss": 0.1908,
|
| 427 |
+
"step": 540
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.6432748538011696,
|
| 431 |
+
"grad_norm": 1.1844624280929565,
|
| 432 |
+
"learning_rate": 4.811021054446897e-05,
|
| 433 |
+
"loss": 0.1888,
|
| 434 |
+
"step": 550
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.6549707602339181,
|
| 438 |
+
"grad_norm": 0.14377599954605103,
|
| 439 |
+
"learning_rate": 4.803918079826641e-05,
|
| 440 |
+
"loss": 0.1944,
|
| 441 |
+
"step": 560
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.6666666666666666,
|
| 445 |
+
"grad_norm": 0.44051724672317505,
|
| 446 |
+
"learning_rate": 4.7966895121363744e-05,
|
| 447 |
+
"loss": 0.1819,
|
| 448 |
+
"step": 570
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.6783625730994152,
|
| 452 |
+
"grad_norm": 0.9713970422744751,
|
| 453 |
+
"learning_rate": 4.789335745425698e-05,
|
| 454 |
+
"loss": 0.177,
|
| 455 |
+
"step": 580
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.6900584795321637,
|
| 459 |
+
"grad_norm": 0.6856667995452881,
|
| 460 |
+
"learning_rate": 4.781857180569171e-05,
|
| 461 |
+
"loss": 0.1756,
|
| 462 |
+
"step": 590
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.7017543859649122,
|
| 466 |
+
"grad_norm": 0.9721100330352783,
|
| 467 |
+
"learning_rate": 4.774254225244447e-05,
|
| 468 |
+
"loss": 0.1804,
|
| 469 |
+
"step": 600
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.7017543859649122,
|
| 473 |
+
"eval_loss": 0.17837749421596527,
|
| 474 |
+
"eval_runtime": 70.7185,
|
| 475 |
+
"eval_samples_per_second": 5.091,
|
| 476 |
+
"eval_steps_per_second": 0.636,
|
| 477 |
+
"step": 600
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.7134502923976608,
|
| 481 |
+
"grad_norm": 0.9976054430007935,
|
| 482 |
+
"learning_rate": 4.766527293910056e-05,
|
| 483 |
+
"loss": 0.182,
|
| 484 |
+
"step": 610
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.7251461988304093,
|
| 488 |
+
"grad_norm": 0.209353506565094,
|
| 489 |
+
"learning_rate": 4.75867680778281e-05,
|
| 490 |
+
"loss": 0.1955,
|
| 491 |
+
"step": 620
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.7368421052631579,
|
| 495 |
+
"grad_norm": 0.6750498414039612,
|
| 496 |
+
"learning_rate": 4.750703194814841e-05,
|
| 497 |
+
"loss": 0.1685,
|
| 498 |
+
"step": 630
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.7485380116959064,
|
| 502 |
+
"grad_norm": 0.8396773934364319,
|
| 503 |
+
"learning_rate": 4.7426068896702704e-05,
|
| 504 |
+
"loss": 0.1852,
|
| 505 |
+
"step": 640
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.7602339181286549,
|
| 509 |
+
"grad_norm": 0.5944289565086365,
|
| 510 |
+
"learning_rate": 4.734388333701519e-05,
|
| 511 |
+
"loss": 0.1782,
|
| 512 |
+
"step": 650
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.7719298245614035,
|
| 516 |
+
"grad_norm": 1.576680064201355,
|
| 517 |
+
"learning_rate": 4.726047974925244e-05,
|
| 518 |
+
"loss": 0.1661,
|
| 519 |
+
"step": 660
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.783625730994152,
|
| 523 |
+
"grad_norm": 0.5593374371528625,
|
| 524 |
+
"learning_rate": 4.717586267997916e-05,
|
| 525 |
+
"loss": 0.1638,
|
| 526 |
+
"step": 670
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.7953216374269005,
|
| 530 |
+
"grad_norm": 0.38532885909080505,
|
| 531 |
+
"learning_rate": 4.709003674191035e-05,
|
| 532 |
+
"loss": 0.1733,
|
| 533 |
+
"step": 680
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.8070175438596491,
|
| 537 |
+
"grad_norm": 0.8050347566604614,
|
| 538 |
+
"learning_rate": 4.7003006613659866e-05,
|
| 539 |
+
"loss": 0.1798,
|
| 540 |
+
"step": 690
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.8187134502923976,
|
| 544 |
+
"grad_norm": 1.1473042964935303,
|
| 545 |
+
"learning_rate": 4.691477703948537e-05,
|
| 546 |
+
"loss": 0.1647,
|
| 547 |
+
"step": 700
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.8187134502923976,
|
| 551 |
+
"eval_loss": 0.1701304167509079,
|
| 552 |
+
"eval_runtime": 70.7628,
|
| 553 |
+
"eval_samples_per_second": 5.087,
|
| 554 |
+
"eval_steps_per_second": 0.636,
|
| 555 |
+
"step": 700
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.8304093567251462,
|
| 559 |
+
"grad_norm": 0.6047437191009521,
|
| 560 |
+
"learning_rate": 4.6825352829029705e-05,
|
| 561 |
+
"loss": 0.1569,
|
| 562 |
+
"step": 710
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8421052631578947,
|
| 566 |
+
"grad_norm": 0.7595338225364685,
|
| 567 |
+
"learning_rate": 4.673473885705869e-05,
|
| 568 |
+
"loss": 0.1748,
|
| 569 |
+
"step": 720
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.8538011695906432,
|
| 573 |
+
"grad_norm": 1.2969980239868164,
|
| 574 |
+
"learning_rate": 4.66429400631954e-05,
|
| 575 |
+
"loss": 0.2056,
|
| 576 |
+
"step": 730
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.8654970760233918,
|
| 580 |
+
"grad_norm": 0.30272266268730164,
|
| 581 |
+
"learning_rate": 4.654996145165092e-05,
|
| 582 |
+
"loss": 0.1772,
|
| 583 |
+
"step": 740
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.8771929824561403,
|
| 587 |
+
"grad_norm": 0.6495968103408813,
|
| 588 |
+
"learning_rate": 4.645580809095147e-05,
|
| 589 |
+
"loss": 0.1655,
|
| 590 |
+
"step": 750
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.8888888888888888,
|
| 594 |
+
"grad_norm": 1.118062973022461,
|
| 595 |
+
"learning_rate": 4.6360485113662216e-05,
|
| 596 |
+
"loss": 0.1826,
|
| 597 |
+
"step": 760
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9005847953216374,
|
| 601 |
+
"grad_norm": 0.432836651802063,
|
| 602 |
+
"learning_rate": 4.626399771610739e-05,
|
| 603 |
+
"loss": 0.155,
|
| 604 |
+
"step": 770
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.9122807017543859,
|
| 608 |
+
"grad_norm": 1.9067554473876953,
|
| 609 |
+
"learning_rate": 4.616635115808705e-05,
|
| 610 |
+
"loss": 0.1791,
|
| 611 |
+
"step": 780
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.9239766081871345,
|
| 615 |
+
"grad_norm": 0.18835797905921936,
|
| 616 |
+
"learning_rate": 4.606755076259039e-05,
|
| 617 |
+
"loss": 0.167,
|
| 618 |
+
"step": 790
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.935672514619883,
|
| 622 |
+
"grad_norm": 0.27169495820999146,
|
| 623 |
+
"learning_rate": 4.5967601915505505e-05,
|
| 624 |
+
"loss": 0.1663,
|
| 625 |
+
"step": 800
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.935672514619883,
|
| 629 |
+
"eval_loss": 0.1684267818927765,
|
| 630 |
+
"eval_runtime": 70.7679,
|
| 631 |
+
"eval_samples_per_second": 5.087,
|
| 632 |
+
"eval_steps_per_second": 0.636,
|
| 633 |
+
"step": 800
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.9473684210526315,
|
| 637 |
+
"grad_norm": 0.5899501442909241,
|
| 638 |
+
"learning_rate": 4.5866510065325837e-05,
|
| 639 |
+
"loss": 0.1783,
|
| 640 |
+
"step": 810
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.9590643274853801,
|
| 644 |
+
"grad_norm": 2.2824106216430664,
|
| 645 |
+
"learning_rate": 4.576428072285316e-05,
|
| 646 |
+
"loss": 0.1765,
|
| 647 |
+
"step": 820
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.9707602339181286,
|
| 651 |
+
"grad_norm": 1.454735517501831,
|
| 652 |
+
"learning_rate": 4.5660919460897136e-05,
|
| 653 |
+
"loss": 0.1485,
|
| 654 |
+
"step": 830
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.9824561403508771,
|
| 658 |
+
"grad_norm": 0.3752526342868805,
|
| 659 |
+
"learning_rate": 4.5556431913971564e-05,
|
| 660 |
+
"loss": 0.1719,
|
| 661 |
+
"step": 840
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.9941520467836257,
|
| 665 |
+
"grad_norm": 0.4948273301124573,
|
| 666 |
+
"learning_rate": 4.5450823777987224e-05,
|
| 667 |
+
"loss": 0.1671,
|
| 668 |
+
"step": 850
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.0058479532163742,
|
| 672 |
+
"grad_norm": 0.39168354868888855,
|
| 673 |
+
"learning_rate": 4.534410080994134e-05,
|
| 674 |
+
"loss": 0.1546,
|
| 675 |
+
"step": 860
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.0175438596491229,
|
| 679 |
+
"grad_norm": 0.664540708065033,
|
| 680 |
+
"learning_rate": 4.523626882760379e-05,
|
| 681 |
+
"loss": 0.1423,
|
| 682 |
+
"step": 870
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.0292397660818713,
|
| 686 |
+
"grad_norm": 0.6726405024528503,
|
| 687 |
+
"learning_rate": 4.512733370919994e-05,
|
| 688 |
+
"loss": 0.1596,
|
| 689 |
+
"step": 880
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.04093567251462,
|
| 693 |
+
"grad_norm": 0.236578568816185,
|
| 694 |
+
"learning_rate": 4.5017301393090226e-05,
|
| 695 |
+
"loss": 0.1554,
|
| 696 |
+
"step": 890
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.0526315789473684,
|
| 700 |
+
"grad_norm": 0.3968108892440796,
|
| 701 |
+
"learning_rate": 4.490617787744641e-05,
|
| 702 |
+
"loss": 0.1553,
|
| 703 |
+
"step": 900
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.0526315789473684,
|
| 707 |
+
"eval_loss": 0.15236565470695496,
|
| 708 |
+
"eval_runtime": 70.7203,
|
| 709 |
+
"eval_samples_per_second": 5.09,
|
| 710 |
+
"eval_steps_per_second": 0.636,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.064327485380117,
|
| 715 |
+
"grad_norm": 0.25147774815559387,
|
| 716 |
+
"learning_rate": 4.479396921992462e-05,
|
| 717 |
+
"loss": 0.1656,
|
| 718 |
+
"step": 910
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.0760233918128654,
|
| 722 |
+
"grad_norm": 0.32600972056388855,
|
| 723 |
+
"learning_rate": 4.4680681537335125e-05,
|
| 724 |
+
"loss": 0.1604,
|
| 725 |
+
"step": 920
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.087719298245614,
|
| 729 |
+
"grad_norm": 1.188389778137207,
|
| 730 |
+
"learning_rate": 4.456632100530891e-05,
|
| 731 |
+
"loss": 0.1695,
|
| 732 |
+
"step": 930
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.0994152046783625,
|
| 736 |
+
"grad_norm": 0.3761911392211914,
|
| 737 |
+
"learning_rate": 4.445089385796099e-05,
|
| 738 |
+
"loss": 0.1528,
|
| 739 |
+
"step": 940
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 1.1111111111111112,
|
| 743 |
+
"grad_norm": 0.3615463972091675,
|
| 744 |
+
"learning_rate": 4.4334406387550584e-05,
|
| 745 |
+
"loss": 0.1409,
|
| 746 |
+
"step": 950
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.1228070175438596,
|
| 750 |
+
"grad_norm": 1.164436936378479,
|
| 751 |
+
"learning_rate": 4.4216864944138134e-05,
|
| 752 |
+
"loss": 0.151,
|
| 753 |
+
"step": 960
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.1345029239766082,
|
| 757 |
+
"grad_norm": 0.6423844695091248,
|
| 758 |
+
"learning_rate": 4.4098275935239105e-05,
|
| 759 |
+
"loss": 0.1443,
|
| 760 |
+
"step": 970
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.1461988304093567,
|
| 764 |
+
"grad_norm": 0.5043056011199951,
|
| 765 |
+
"learning_rate": 4.39786458254747e-05,
|
| 766 |
+
"loss": 0.1723,
|
| 767 |
+
"step": 980
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 1.1578947368421053,
|
| 771 |
+
"grad_norm": 0.6203618049621582,
|
| 772 |
+
"learning_rate": 4.385798113621949e-05,
|
| 773 |
+
"loss": 0.1642,
|
| 774 |
+
"step": 990
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.1695906432748537,
|
| 778 |
+
"grad_norm": 1.9213874340057373,
|
| 779 |
+
"learning_rate": 4.373628844524587e-05,
|
| 780 |
+
"loss": 0.1665,
|
| 781 |
+
"step": 1000
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.1695906432748537,
|
| 785 |
+
"eval_loss": 0.15835003554821014,
|
| 786 |
+
"eval_runtime": 70.7527,
|
| 787 |
+
"eval_samples_per_second": 5.088,
|
| 788 |
+
"eval_steps_per_second": 0.636,
|
| 789 |
+
"step": 1000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.1812865497076024,
|
| 793 |
+
"grad_norm": 0.5596243143081665,
|
| 794 |
+
"learning_rate": 4.361357438636552e-05,
|
| 795 |
+
"loss": 0.149,
|
| 796 |
+
"step": 1010
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.1929824561403508,
|
| 800 |
+
"grad_norm": 1.6553308963775635,
|
| 801 |
+
"learning_rate": 4.3489845649067756e-05,
|
| 802 |
+
"loss": 0.1487,
|
| 803 |
+
"step": 1020
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.2046783625730995,
|
| 807 |
+
"grad_norm": 1.0848426818847656,
|
| 808 |
+
"learning_rate": 4.336510897815489e-05,
|
| 809 |
+
"loss": 0.1722,
|
| 810 |
+
"step": 1030
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.2163742690058479,
|
| 814 |
+
"grad_norm": 0.7038739919662476,
|
| 815 |
+
"learning_rate": 4.323937117337451e-05,
|
| 816 |
+
"loss": 0.1586,
|
| 817 |
+
"step": 1040
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.2280701754385965,
|
| 821 |
+
"grad_norm": 0.2612368166446686,
|
| 822 |
+
"learning_rate": 4.3112639089048856e-05,
|
| 823 |
+
"loss": 0.1372,
|
| 824 |
+
"step": 1050
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.239766081871345,
|
| 828 |
+
"grad_norm": 1.2697585821151733,
|
| 829 |
+
"learning_rate": 4.298491963370115e-05,
|
| 830 |
+
"loss": 0.1375,
|
| 831 |
+
"step": 1060
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.2514619883040936,
|
| 835 |
+
"grad_norm": 0.5513612031936646,
|
| 836 |
+
"learning_rate": 4.285621976967898e-05,
|
| 837 |
+
"loss": 0.1429,
|
| 838 |
+
"step": 1070
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.263157894736842,
|
| 842 |
+
"grad_norm": 1.0210371017456055,
|
| 843 |
+
"learning_rate": 4.272654651277478e-05,
|
| 844 |
+
"loss": 0.1464,
|
| 845 |
+
"step": 1080
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.2748538011695907,
|
| 849 |
+
"grad_norm": 2.7657597064971924,
|
| 850 |
+
"learning_rate": 4.259590693184337e-05,
|
| 851 |
+
"loss": 0.143,
|
| 852 |
+
"step": 1090
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 1.286549707602339,
|
| 856 |
+
"grad_norm": 0.8804309964179993,
|
| 857 |
+
"learning_rate": 4.2464308148416626e-05,
|
| 858 |
+
"loss": 0.1424,
|
| 859 |
+
"step": 1100
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 1.286549707602339,
|
| 863 |
+
"eval_loss": 0.16600148379802704,
|
| 864 |
+
"eval_runtime": 70.6234,
|
| 865 |
+
"eval_samples_per_second": 5.097,
|
| 866 |
+
"eval_steps_per_second": 0.637,
|
| 867 |
+
"step": 1100
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.2982456140350878,
|
| 871 |
+
"grad_norm": 1.1973798274993896,
|
| 872 |
+
"learning_rate": 4.233175733631525e-05,
|
| 873 |
+
"loss": 0.147,
|
| 874 |
+
"step": 1110
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.3099415204678362,
|
| 878 |
+
"grad_norm": 0.6619781851768494,
|
| 879 |
+
"learning_rate": 4.2198261721257715e-05,
|
| 880 |
+
"loss": 0.1373,
|
| 881 |
+
"step": 1120
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.3216374269005848,
|
| 885 |
+
"grad_norm": 1.0239554643630981,
|
| 886 |
+
"learning_rate": 4.206382858046636e-05,
|
| 887 |
+
"loss": 0.1439,
|
| 888 |
+
"step": 1130
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 1.3333333333333333,
|
| 892 |
+
"grad_norm": 0.7170116901397705,
|
| 893 |
+
"learning_rate": 4.1928465242270696e-05,
|
| 894 |
+
"loss": 0.1372,
|
| 895 |
+
"step": 1140
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 1.345029239766082,
|
| 899 |
+
"grad_norm": 0.5151202082633972,
|
| 900 |
+
"learning_rate": 4.1792179085707935e-05,
|
| 901 |
+
"loss": 0.1561,
|
| 902 |
+
"step": 1150
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 1.3567251461988303,
|
| 906 |
+
"grad_norm": 0.5788434147834778,
|
| 907 |
+
"learning_rate": 4.1654977540120686e-05,
|
| 908 |
+
"loss": 0.1354,
|
| 909 |
+
"step": 1160
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.368421052631579,
|
| 913 |
+
"grad_norm": 3.5275087356567383,
|
| 914 |
+
"learning_rate": 4.151686808475204e-05,
|
| 915 |
+
"loss": 0.1372,
|
| 916 |
+
"step": 1170
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.3801169590643274,
|
| 920 |
+
"grad_norm": 1.1060805320739746,
|
| 921 |
+
"learning_rate": 4.137785824833776e-05,
|
| 922 |
+
"loss": 0.1776,
|
| 923 |
+
"step": 1180
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.391812865497076,
|
| 927 |
+
"grad_norm": 0.46970221400260925,
|
| 928 |
+
"learning_rate": 4.123795560869595e-05,
|
| 929 |
+
"loss": 0.1475,
|
| 930 |
+
"step": 1190
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.4035087719298245,
|
| 934 |
+
"grad_norm": 1.331180214881897,
|
| 935 |
+
"learning_rate": 4.109716779231393e-05,
|
| 936 |
+
"loss": 0.1163,
|
| 937 |
+
"step": 1200
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.4035087719298245,
|
| 941 |
+
"eval_loss": 0.14416372776031494,
|
| 942 |
+
"eval_runtime": 70.7419,
|
| 943 |
+
"eval_samples_per_second": 5.089,
|
| 944 |
+
"eval_steps_per_second": 0.636,
|
| 945 |
+
"step": 1200
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.4152046783625731,
|
| 949 |
+
"grad_norm": 0.3912939131259918,
|
| 950 |
+
"learning_rate": 4.0955502473932495e-05,
|
| 951 |
+
"loss": 0.1398,
|
| 952 |
+
"step": 1210
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 1.4269005847953216,
|
| 956 |
+
"grad_norm": 1.8457322120666504,
|
| 957 |
+
"learning_rate": 4.0812967376127555e-05,
|
| 958 |
+
"loss": 0.1424,
|
| 959 |
+
"step": 1220
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.4385964912280702,
|
| 963 |
+
"grad_norm": 1.9205797910690308,
|
| 964 |
+
"learning_rate": 4.0669570268889124e-05,
|
| 965 |
+
"loss": 0.125,
|
| 966 |
+
"step": 1230
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 1.4502923976608186,
|
| 970 |
+
"grad_norm": 0.6593519449234009,
|
| 971 |
+
"learning_rate": 4.0525318969197825e-05,
|
| 972 |
+
"loss": 0.1474,
|
| 973 |
+
"step": 1240
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 1.4619883040935673,
|
| 977 |
+
"grad_norm": 0.9120498895645142,
|
| 978 |
+
"learning_rate": 4.038022134059868e-05,
|
| 979 |
+
"loss": 0.1405,
|
| 980 |
+
"step": 1250
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 1.4736842105263157,
|
| 984 |
+
"grad_norm": 0.6781203746795654,
|
| 985 |
+
"learning_rate": 4.02342852927725e-05,
|
| 986 |
+
"loss": 0.1226,
|
| 987 |
+
"step": 1260
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 1.4853801169590644,
|
| 991 |
+
"grad_norm": 0.927740216255188,
|
| 992 |
+
"learning_rate": 4.00875187811047e-05,
|
| 993 |
+
"loss": 0.1362,
|
| 994 |
+
"step": 1270
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.4970760233918128,
|
| 998 |
+
"grad_norm": 0.7272914052009583,
|
| 999 |
+
"learning_rate": 3.993992980625161e-05,
|
| 1000 |
+
"loss": 0.1541,
|
| 1001 |
+
"step": 1280
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.5087719298245614,
|
| 1005 |
+
"grad_norm": 0.3226785957813263,
|
| 1006 |
+
"learning_rate": 3.979152641370434e-05,
|
| 1007 |
+
"loss": 0.1429,
|
| 1008 |
+
"step": 1290
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 1.52046783625731,
|
| 1012 |
+
"grad_norm": 0.9942995309829712,
|
| 1013 |
+
"learning_rate": 3.964231669335023e-05,
|
| 1014 |
+
"loss": 0.1593,
|
| 1015 |
+
"step": 1300
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 1.52046783625731,
|
| 1019 |
+
"eval_loss": 0.136515274643898,
|
| 1020 |
+
"eval_runtime": 70.6872,
|
| 1021 |
+
"eval_samples_per_second": 5.093,
|
| 1022 |
+
"eval_steps_per_second": 0.637,
|
| 1023 |
+
"step": 1300
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.5321637426900585,
|
| 1027 |
+
"grad_norm": 1.0689057111740112,
|
| 1028 |
+
"learning_rate": 3.94923087790318e-05,
|
| 1029 |
+
"loss": 0.1437,
|
| 1030 |
+
"step": 1310
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.543859649122807,
|
| 1034 |
+
"grad_norm": 0.9869856834411621,
|
| 1035 |
+
"learning_rate": 3.934151084810338e-05,
|
| 1036 |
+
"loss": 0.135,
|
| 1037 |
+
"step": 1320
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.5555555555555556,
|
| 1041 |
+
"grad_norm": 0.7283734679222107,
|
| 1042 |
+
"learning_rate": 3.918993112098532e-05,
|
| 1043 |
+
"loss": 0.1278,
|
| 1044 |
+
"step": 1330
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.5672514619883042,
|
| 1048 |
+
"grad_norm": 0.5857880115509033,
|
| 1049 |
+
"learning_rate": 3.9037577860715915e-05,
|
| 1050 |
+
"loss": 0.1384,
|
| 1051 |
+
"step": 1340
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.5789473684210527,
|
| 1055 |
+
"grad_norm": 1.0862607955932617,
|
| 1056 |
+
"learning_rate": 3.888445937250091e-05,
|
| 1057 |
+
"loss": 0.1262,
|
| 1058 |
+
"step": 1350
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.590643274853801,
|
| 1062 |
+
"grad_norm": 0.7065826058387756,
|
| 1063 |
+
"learning_rate": 3.873058400326078e-05,
|
| 1064 |
+
"loss": 0.1419,
|
| 1065 |
+
"step": 1360
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.6023391812865497,
|
| 1069 |
+
"grad_norm": 2.3313534259796143,
|
| 1070 |
+
"learning_rate": 3.8575960141175735e-05,
|
| 1071 |
+
"loss": 0.1429,
|
| 1072 |
+
"step": 1370
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.6140350877192984,
|
| 1076 |
+
"grad_norm": 1.8919905424118042,
|
| 1077 |
+
"learning_rate": 3.842059621522843e-05,
|
| 1078 |
+
"loss": 0.1402,
|
| 1079 |
+
"step": 1380
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.6257309941520468,
|
| 1083 |
+
"grad_norm": 0.48003846406936646,
|
| 1084 |
+
"learning_rate": 3.826450069474447e-05,
|
| 1085 |
+
"loss": 0.1295,
|
| 1086 |
+
"step": 1390
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.6374269005847952,
|
| 1090 |
+
"grad_norm": 1.175875186920166,
|
| 1091 |
+
"learning_rate": 3.8107682088930794e-05,
|
| 1092 |
+
"loss": 0.1529,
|
| 1093 |
+
"step": 1400
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.6374269005847952,
|
| 1097 |
+
"eval_loss": 0.14436422288417816,
|
| 1098 |
+
"eval_runtime": 70.6551,
|
| 1099 |
+
"eval_samples_per_second": 5.095,
|
| 1100 |
+
"eval_steps_per_second": 0.637,
|
| 1101 |
+
"step": 1400
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.6491228070175439,
|
| 1105 |
+
"grad_norm": 0.714869499206543,
|
| 1106 |
+
"learning_rate": 3.7950148946411703e-05,
|
| 1107 |
+
"loss": 0.1212,
|
| 1108 |
+
"step": 1410
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.6608187134502925,
|
| 1112 |
+
"grad_norm": 0.5298812985420227,
|
| 1113 |
+
"learning_rate": 3.779190985476294e-05,
|
| 1114 |
+
"loss": 0.1284,
|
| 1115 |
+
"step": 1420
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.672514619883041,
|
| 1119 |
+
"grad_norm": 0.49085694551467896,
|
| 1120 |
+
"learning_rate": 3.763297344004352e-05,
|
| 1121 |
+
"loss": 0.1386,
|
| 1122 |
+
"step": 1430
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.6842105263157894,
|
| 1126 |
+
"grad_norm": 0.5542166829109192,
|
| 1127 |
+
"learning_rate": 3.747334836632549e-05,
|
| 1128 |
+
"loss": 0.1426,
|
| 1129 |
+
"step": 1440
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.695906432748538,
|
| 1133 |
+
"grad_norm": 1.5810950994491577,
|
| 1134 |
+
"learning_rate": 3.7313043335221655e-05,
|
| 1135 |
+
"loss": 0.1362,
|
| 1136 |
+
"step": 1450
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.7076023391812867,
|
| 1140 |
+
"grad_norm": 0.910664975643158,
|
| 1141 |
+
"learning_rate": 3.715206708541122e-05,
|
| 1142 |
+
"loss": 0.1498,
|
| 1143 |
+
"step": 1460
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.719298245614035,
|
| 1147 |
+
"grad_norm": 0.7230697870254517,
|
| 1148 |
+
"learning_rate": 3.69904283921634e-05,
|
| 1149 |
+
"loss": 0.1371,
|
| 1150 |
+
"step": 1470
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.7309941520467835,
|
| 1154 |
+
"grad_norm": 0.5364117622375488,
|
| 1155 |
+
"learning_rate": 3.682813606685908e-05,
|
| 1156 |
+
"loss": 0.1343,
|
| 1157 |
+
"step": 1480
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.7426900584795322,
|
| 1161 |
+
"grad_norm": 1.2777420282363892,
|
| 1162 |
+
"learning_rate": 3.666519895651046e-05,
|
| 1163 |
+
"loss": 0.1344,
|
| 1164 |
+
"step": 1490
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.7543859649122808,
|
| 1168 |
+
"grad_norm": 1.1144359111785889,
|
| 1169 |
+
"learning_rate": 3.6501625943278805e-05,
|
| 1170 |
+
"loss": 0.1321,
|
| 1171 |
+
"step": 1500
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.7543859649122808,
|
| 1175 |
+
"eval_loss": 0.13336236774921417,
|
| 1176 |
+
"eval_runtime": 70.7727,
|
| 1177 |
+
"eval_samples_per_second": 5.087,
|
| 1178 |
+
"eval_steps_per_second": 0.636,
|
| 1179 |
+
"step": 1500
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.7660818713450293,
|
| 1183 |
+
"grad_norm": 1.9565575122833252,
|
| 1184 |
+
"learning_rate": 3.6337425943990224e-05,
|
| 1185 |
+
"loss": 0.1102,
|
| 1186 |
+
"step": 1510
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.7777777777777777,
|
| 1190 |
+
"grad_norm": 0.40069296956062317,
|
| 1191 |
+
"learning_rate": 3.6172607909649606e-05,
|
| 1192 |
+
"loss": 0.1352,
|
| 1193 |
+
"step": 1520
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.7894736842105263,
|
| 1197 |
+
"grad_norm": 0.9928420186042786,
|
| 1198 |
+
"learning_rate": 3.600718082495269e-05,
|
| 1199 |
+
"loss": 0.1296,
|
| 1200 |
+
"step": 1530
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.801169590643275,
|
| 1204 |
+
"grad_norm": 0.3943164050579071,
|
| 1205 |
+
"learning_rate": 3.5841153707796245e-05,
|
| 1206 |
+
"loss": 0.1427,
|
| 1207 |
+
"step": 1540
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.8128654970760234,
|
| 1211 |
+
"grad_norm": 0.4923238754272461,
|
| 1212 |
+
"learning_rate": 3.567453560878652e-05,
|
| 1213 |
+
"loss": 0.1426,
|
| 1214 |
+
"step": 1550
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.8245614035087718,
|
| 1218 |
+
"grad_norm": 0.944096028804779,
|
| 1219 |
+
"learning_rate": 3.550733561074582e-05,
|
| 1220 |
+
"loss": 0.1342,
|
| 1221 |
+
"step": 1560
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.8362573099415205,
|
| 1225 |
+
"grad_norm": 0.7152662873268127,
|
| 1226 |
+
"learning_rate": 3.533956282821746e-05,
|
| 1227 |
+
"loss": 0.1337,
|
| 1228 |
+
"step": 1570
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.8479532163742691,
|
| 1232 |
+
"grad_norm": 0.7894164323806763,
|
| 1233 |
+
"learning_rate": 3.51712264069688e-05,
|
| 1234 |
+
"loss": 0.1306,
|
| 1235 |
+
"step": 1580
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.8596491228070176,
|
| 1239 |
+
"grad_norm": 0.4547712206840515,
|
| 1240 |
+
"learning_rate": 3.500233552349276e-05,
|
| 1241 |
+
"loss": 0.1299,
|
| 1242 |
+
"step": 1590
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.871345029239766,
|
| 1246 |
+
"grad_norm": 2.5272104740142822,
|
| 1247 |
+
"learning_rate": 3.483289938450755e-05,
|
| 1248 |
+
"loss": 0.135,
|
| 1249 |
+
"step": 1600
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.871345029239766,
|
| 1253 |
+
"eval_loss": 0.12928339838981628,
|
| 1254 |
+
"eval_runtime": 70.7709,
|
| 1255 |
+
"eval_samples_per_second": 5.087,
|
| 1256 |
+
"eval_steps_per_second": 0.636,
|
| 1257 |
+
"step": 1600
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.8830409356725146,
|
| 1261 |
+
"grad_norm": 0.702826738357544,
|
| 1262 |
+
"learning_rate": 3.466292722645481e-05,
|
| 1263 |
+
"loss": 0.1304,
|
| 1264 |
+
"step": 1610
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 1.8947368421052633,
|
| 1268 |
+
"grad_norm": 2.502329111099243,
|
| 1269 |
+
"learning_rate": 3.449242831499608e-05,
|
| 1270 |
+
"loss": 0.1203,
|
| 1271 |
+
"step": 1620
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 1.9064327485380117,
|
| 1275 |
+
"grad_norm": 0.8610795140266418,
|
| 1276 |
+
"learning_rate": 3.432141194450772e-05,
|
| 1277 |
+
"loss": 0.1323,
|
| 1278 |
+
"step": 1630
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 1.9181286549707601,
|
| 1282 |
+
"grad_norm": 1.4722447395324707,
|
| 1283 |
+
"learning_rate": 3.4149887437574226e-05,
|
| 1284 |
+
"loss": 0.1159,
|
| 1285 |
+
"step": 1640
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 1.9298245614035088,
|
| 1289 |
+
"grad_norm": 1.3295050859451294,
|
| 1290 |
+
"learning_rate": 3.397786414448004e-05,
|
| 1291 |
+
"loss": 0.1272,
|
| 1292 |
+
"step": 1650
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 1.9415204678362574,
|
| 1296 |
+
"grad_norm": 0.8509026765823364,
|
| 1297 |
+
"learning_rate": 3.3805351442699885e-05,
|
| 1298 |
+
"loss": 0.124,
|
| 1299 |
+
"step": 1660
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.9532163742690059,
|
| 1303 |
+
"grad_norm": 0.3647763729095459,
|
| 1304 |
+
"learning_rate": 3.363235873638749e-05,
|
| 1305 |
+
"loss": 0.1259,
|
| 1306 |
+
"step": 1670
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.9649122807017543,
|
| 1310 |
+
"grad_norm": 1.6972521543502808,
|
| 1311 |
+
"learning_rate": 3.345889545586301e-05,
|
| 1312 |
+
"loss": 0.1223,
|
| 1313 |
+
"step": 1680
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.976608187134503,
|
| 1317 |
+
"grad_norm": 0.6397933959960938,
|
| 1318 |
+
"learning_rate": 3.328497105709888e-05,
|
| 1319 |
+
"loss": 0.1312,
|
| 1320 |
+
"step": 1690
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.9883040935672516,
|
| 1324 |
+
"grad_norm": 1.981067419052124,
|
| 1325 |
+
"learning_rate": 3.311059502120446e-05,
|
| 1326 |
+
"loss": 0.1322,
|
| 1327 |
+
"step": 1700
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.9883040935672516,
|
| 1331 |
+
"eval_loss": 0.14009280502796173,
|
| 1332 |
+
"eval_runtime": 70.745,
|
| 1333 |
+
"eval_samples_per_second": 5.089,
|
| 1334 |
+
"eval_steps_per_second": 0.636,
|
| 1335 |
+
"step": 1700
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 2.0,
|
| 1339 |
+
"grad_norm": 1.1901209354400635,
|
| 1340 |
+
"learning_rate": 3.293577685390907e-05,
|
| 1341 |
+
"loss": 0.1407,
|
| 1342 |
+
"step": 1710
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.0116959064327484,
|
| 1346 |
+
"grad_norm": 3.512953758239746,
|
| 1347 |
+
"learning_rate": 3.2760526085043894e-05,
|
| 1348 |
+
"loss": 0.1053,
|
| 1349 |
+
"step": 1720
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 2.023391812865497,
|
| 1353 |
+
"grad_norm": 0.8400770425796509,
|
| 1354 |
+
"learning_rate": 3.258485226802242e-05,
|
| 1355 |
+
"loss": 0.1356,
|
| 1356 |
+
"step": 1730
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.0350877192982457,
|
| 1360 |
+
"grad_norm": 0.9668805599212646,
|
| 1361 |
+
"learning_rate": 3.2408764979319695e-05,
|
| 1362 |
+
"loss": 0.1009,
|
| 1363 |
+
"step": 1740
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 2.046783625730994,
|
| 1367 |
+
"grad_norm": 0.7382619380950928,
|
| 1368 |
+
"learning_rate": 3.2232273817950273e-05,
|
| 1369 |
+
"loss": 0.1134,
|
| 1370 |
+
"step": 1750
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 2.0584795321637426,
|
| 1374 |
+
"grad_norm": 0.5820582509040833,
|
| 1375 |
+
"learning_rate": 3.205538840494494e-05,
|
| 1376 |
+
"loss": 0.1108,
|
| 1377 |
+
"step": 1760
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.0701754385964914,
|
| 1381 |
+
"grad_norm": 1.1828213930130005,
|
| 1382 |
+
"learning_rate": 3.187811838282627e-05,
|
| 1383 |
+
"loss": 0.1126,
|
| 1384 |
+
"step": 1770
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 2.08187134502924,
|
| 1388 |
+
"grad_norm": 0.654548168182373,
|
| 1389 |
+
"learning_rate": 3.170047341508293e-05,
|
| 1390 |
+
"loss": 0.1284,
|
| 1391 |
+
"step": 1780
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 2.0935672514619883,
|
| 1395 |
+
"grad_norm": 1.204846978187561,
|
| 1396 |
+
"learning_rate": 3.1522463185642965e-05,
|
| 1397 |
+
"loss": 0.1202,
|
| 1398 |
+
"step": 1790
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 2.1052631578947367,
|
| 1402 |
+
"grad_norm": 1.97409987449646,
|
| 1403 |
+
"learning_rate": 3.134409739834584e-05,
|
| 1404 |
+
"loss": 0.1355,
|
| 1405 |
+
"step": 1800
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 2.1052631578947367,
|
| 1409 |
+
"eval_loss": 0.12916673719882965,
|
| 1410 |
+
"eval_runtime": 70.7041,
|
| 1411 |
+
"eval_samples_per_second": 5.092,
|
| 1412 |
+
"eval_steps_per_second": 0.636,
|
| 1413 |
+
"step": 1800
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.116959064327485,
|
| 1417 |
+
"grad_norm": 2.286799907684326,
|
| 1418 |
+
"learning_rate": 3.11653857764135e-05,
|
| 1419 |
+
"loss": 0.1225,
|
| 1420 |
+
"step": 1810
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.128654970760234,
|
| 1424 |
+
"grad_norm": 0.6355563402175903,
|
| 1425 |
+
"learning_rate": 3.098633806192029e-05,
|
| 1426 |
+
"loss": 0.1103,
|
| 1427 |
+
"step": 1820
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 2.1403508771929824,
|
| 1431 |
+
"grad_norm": 0.6370256543159485,
|
| 1432 |
+
"learning_rate": 3.080696401526193e-05,
|
| 1433 |
+
"loss": 0.1042,
|
| 1434 |
+
"step": 1830
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 2.152046783625731,
|
| 1438 |
+
"grad_norm": 1.668946385383606,
|
| 1439 |
+
"learning_rate": 3.062727341462342e-05,
|
| 1440 |
+
"loss": 0.1336,
|
| 1441 |
+
"step": 1840
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.1637426900584797,
|
| 1445 |
+
"grad_norm": 4.8773722648620605,
|
| 1446 |
+
"learning_rate": 3.0447276055445984e-05,
|
| 1447 |
+
"loss": 0.1212,
|
| 1448 |
+
"step": 1850
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 2.175438596491228,
|
| 1452 |
+
"grad_norm": 0.7208726406097412,
|
| 1453 |
+
"learning_rate": 3.0266981749893157e-05,
|
| 1454 |
+
"loss": 0.1079,
|
| 1455 |
+
"step": 1860
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 2.1871345029239766,
|
| 1459 |
+
"grad_norm": 11.563030242919922,
|
| 1460 |
+
"learning_rate": 3.008640032631585e-05,
|
| 1461 |
+
"loss": 0.1505,
|
| 1462 |
+
"step": 1870
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 2.198830409356725,
|
| 1466 |
+
"grad_norm": 0.6635209918022156,
|
| 1467 |
+
"learning_rate": 2.990554162871656e-05,
|
| 1468 |
+
"loss": 0.1306,
|
| 1469 |
+
"step": 1880
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 2.2105263157894735,
|
| 1473 |
+
"grad_norm": 0.8239225149154663,
|
| 1474 |
+
"learning_rate": 2.97244155162128e-05,
|
| 1475 |
+
"loss": 0.1184,
|
| 1476 |
+
"step": 1890
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 2.2222222222222223,
|
| 1480 |
+
"grad_norm": 1.2284820079803467,
|
| 1481 |
+
"learning_rate": 2.954303186249962e-05,
|
| 1482 |
+
"loss": 0.1227,
|
| 1483 |
+
"step": 1900
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 2.2222222222222223,
|
| 1487 |
+
"eval_loss": 0.13539400696754456,
|
| 1488 |
+
"eval_runtime": 70.7773,
|
| 1489 |
+
"eval_samples_per_second": 5.086,
|
| 1490 |
+
"eval_steps_per_second": 0.636,
|
| 1491 |
+
"step": 1900
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 2.2339181286549707,
|
| 1495 |
+
"grad_norm": 0.5749723315238953,
|
| 1496 |
+
"learning_rate": 2.936140055531135e-05,
|
| 1497 |
+
"loss": 0.1208,
|
| 1498 |
+
"step": 1910
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 2.245614035087719,
|
| 1502 |
+
"grad_norm": 0.5214797854423523,
|
| 1503 |
+
"learning_rate": 2.9179531495882644e-05,
|
| 1504 |
+
"loss": 0.1231,
|
| 1505 |
+
"step": 1920
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 2.257309941520468,
|
| 1509 |
+
"grad_norm": 0.6751307249069214,
|
| 1510 |
+
"learning_rate": 2.8997434598408653e-05,
|
| 1511 |
+
"loss": 0.123,
|
| 1512 |
+
"step": 1930
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 2.2690058479532165,
|
| 1516 |
+
"grad_norm": 1.2597579956054688,
|
| 1517 |
+
"learning_rate": 2.8815119789504658e-05,
|
| 1518 |
+
"loss": 0.1132,
|
| 1519 |
+
"step": 1940
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 2.280701754385965,
|
| 1523 |
+
"grad_norm": 1.2100732326507568,
|
| 1524 |
+
"learning_rate": 2.8632597007664895e-05,
|
| 1525 |
+
"loss": 0.1049,
|
| 1526 |
+
"step": 1950
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 2.2923976608187133,
|
| 1530 |
+
"grad_norm": 0.6096538305282593,
|
| 1531 |
+
"learning_rate": 2.8449876202720793e-05,
|
| 1532 |
+
"loss": 0.111,
|
| 1533 |
+
"step": 1960
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 2.3040935672514617,
|
| 1537 |
+
"grad_norm": 1.1623386144638062,
|
| 1538 |
+
"learning_rate": 2.8266967335298584e-05,
|
| 1539 |
+
"loss": 0.1012,
|
| 1540 |
+
"step": 1970
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 2.3157894736842106,
|
| 1544 |
+
"grad_norm": 1.5342446565628052,
|
| 1545 |
+
"learning_rate": 2.8083880376276307e-05,
|
| 1546 |
+
"loss": 0.1121,
|
| 1547 |
+
"step": 1980
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 2.327485380116959,
|
| 1551 |
+
"grad_norm": 0.9902574419975281,
|
| 1552 |
+
"learning_rate": 2.7900625306240263e-05,
|
| 1553 |
+
"loss": 0.1222,
|
| 1554 |
+
"step": 1990
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 2.3391812865497075,
|
| 1558 |
+
"grad_norm": 0.4937221109867096,
|
| 1559 |
+
"learning_rate": 2.7717212114940988e-05,
|
| 1560 |
+
"loss": 0.1061,
|
| 1561 |
+
"step": 2000
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 2.3391812865497075,
|
| 1565 |
+
"eval_loss": 0.12341146171092987,
|
| 1566 |
+
"eval_runtime": 70.7503,
|
| 1567 |
+
"eval_samples_per_second": 5.088,
|
| 1568 |
+
"eval_steps_per_second": 0.636,
|
| 1569 |
+
"step": 2000
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 2.3508771929824563,
|
| 1573 |
+
"grad_norm": 1.1475658416748047,
|
| 1574 |
+
"learning_rate": 2.7533650800748645e-05,
|
| 1575 |
+
"loss": 0.1144,
|
| 1576 |
+
"step": 2010
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 2.3625730994152048,
|
| 1580 |
+
"grad_norm": 2.0592291355133057,
|
| 1581 |
+
"learning_rate": 2.7349951370107983e-05,
|
| 1582 |
+
"loss": 0.1077,
|
| 1583 |
+
"step": 2020
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 2.374269005847953,
|
| 1587 |
+
"grad_norm": 1.3138481378555298,
|
| 1588 |
+
"learning_rate": 2.7166123836992873e-05,
|
| 1589 |
+
"loss": 0.1088,
|
| 1590 |
+
"step": 2030
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 2.3859649122807016,
|
| 1594 |
+
"grad_norm": 0.8791354894638062,
|
| 1595 |
+
"learning_rate": 2.698217822236041e-05,
|
| 1596 |
+
"loss": 0.1268,
|
| 1597 |
+
"step": 2040
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 2.39766081871345,
|
| 1601 |
+
"grad_norm": 1.7546913623809814,
|
| 1602 |
+
"learning_rate": 2.6798124553604653e-05,
|
| 1603 |
+
"loss": 0.1175,
|
| 1604 |
+
"step": 2050
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 2.409356725146199,
|
| 1608 |
+
"grad_norm": 3.894958972930908,
|
| 1609 |
+
"learning_rate": 2.6613972864009994e-05,
|
| 1610 |
+
"loss": 0.1177,
|
| 1611 |
+
"step": 2060
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 2.4210526315789473,
|
| 1615 |
+
"grad_norm": 0.649161696434021,
|
| 1616 |
+
"learning_rate": 2.642973319220422e-05,
|
| 1617 |
+
"loss": 0.1343,
|
| 1618 |
+
"step": 2070
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 2.4327485380116958,
|
| 1622 |
+
"grad_norm": 1.5214674472808838,
|
| 1623 |
+
"learning_rate": 2.624541558161125e-05,
|
| 1624 |
+
"loss": 0.1335,
|
| 1625 |
+
"step": 2080
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 2.4444444444444446,
|
| 1629 |
+
"grad_norm": 4.411988735198975,
|
| 1630 |
+
"learning_rate": 2.606103007990371e-05,
|
| 1631 |
+
"loss": 0.1208,
|
| 1632 |
+
"step": 2090
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 2.456140350877193,
|
| 1636 |
+
"grad_norm": 2.7257485389709473,
|
| 1637 |
+
"learning_rate": 2.587658673845513e-05,
|
| 1638 |
+
"loss": 0.1164,
|
| 1639 |
+
"step": 2100
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 2.456140350877193,
|
| 1643 |
+
"eval_loss": 0.12629590928554535,
|
| 1644 |
+
"eval_runtime": 70.7902,
|
| 1645 |
+
"eval_samples_per_second": 5.085,
|
| 1646 |
+
"eval_steps_per_second": 0.636,
|
| 1647 |
+
"step": 2100
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 2.4678362573099415,
|
| 1651 |
+
"grad_norm": 1.7000402212142944,
|
| 1652 |
+
"learning_rate": 2.569209561179206e-05,
|
| 1653 |
+
"loss": 0.1408,
|
| 1654 |
+
"step": 2110
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 2.47953216374269,
|
| 1658 |
+
"grad_norm": 1.0611385107040405,
|
| 1659 |
+
"learning_rate": 2.550756675704596e-05,
|
| 1660 |
+
"loss": 0.1203,
|
| 1661 |
+
"step": 2120
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 2.4912280701754383,
|
| 1665 |
+
"grad_norm": 0.5716353058815002,
|
| 1666 |
+
"learning_rate": 2.5323010233404925e-05,
|
| 1667 |
+
"loss": 0.1187,
|
| 1668 |
+
"step": 2130
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 2.502923976608187,
|
| 1672 |
+
"grad_norm": 1.7797589302062988,
|
| 1673 |
+
"learning_rate": 2.5138436101565405e-05,
|
| 1674 |
+
"loss": 0.1105,
|
| 1675 |
+
"step": 2140
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 2.5146198830409356,
|
| 1679 |
+
"grad_norm": 1.4636850357055664,
|
| 1680 |
+
"learning_rate": 2.4953854423183694e-05,
|
| 1681 |
+
"loss": 0.1263,
|
| 1682 |
+
"step": 2150
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 2.526315789473684,
|
| 1686 |
+
"grad_norm": 1.3921252489089966,
|
| 1687 |
+
"learning_rate": 2.4769275260327474e-05,
|
| 1688 |
+
"loss": 0.1402,
|
| 1689 |
+
"step": 2160
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.538011695906433,
|
| 1693 |
+
"grad_norm": 3.662224292755127,
|
| 1694 |
+
"learning_rate": 2.4584708674927308e-05,
|
| 1695 |
+
"loss": 0.1254,
|
| 1696 |
+
"step": 2170
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.5497076023391814,
|
| 1700 |
+
"grad_norm": 1.0201853513717651,
|
| 1701 |
+
"learning_rate": 2.44001647282281e-05,
|
| 1702 |
+
"loss": 0.1069,
|
| 1703 |
+
"step": 2180
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 2.56140350877193,
|
| 1707 |
+
"grad_norm": 3.211782217025757,
|
| 1708 |
+
"learning_rate": 2.4215653480240685e-05,
|
| 1709 |
+
"loss": 0.1203,
|
| 1710 |
+
"step": 2190
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.573099415204678,
|
| 1714 |
+
"grad_norm": 0.7115254402160645,
|
| 1715 |
+
"learning_rate": 2.4031184989193384e-05,
|
| 1716 |
+
"loss": 0.1038,
|
| 1717 |
+
"step": 2200
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 2.573099415204678,
|
| 1721 |
+
"eval_loss": 0.12356504052877426,
|
| 1722 |
+
"eval_runtime": 70.7673,
|
| 1723 |
+
"eval_samples_per_second": 5.087,
|
| 1724 |
+
"eval_steps_per_second": 0.636,
|
| 1725 |
+
"step": 2200
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.5847953216374266,
|
| 1729 |
+
"grad_norm": 0.9516447186470032,
|
| 1730 |
+
"learning_rate": 2.3846769310983727e-05,
|
| 1731 |
+
"loss": 0.1315,
|
| 1732 |
+
"step": 2210
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.5964912280701755,
|
| 1736 |
+
"grad_norm": 0.743248701095581,
|
| 1737 |
+
"learning_rate": 2.3662416498630257e-05,
|
| 1738 |
+
"loss": 0.1228,
|
| 1739 |
+
"step": 2220
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.608187134502924,
|
| 1743 |
+
"grad_norm": 0.5412260890007019,
|
| 1744 |
+
"learning_rate": 2.3478136601724515e-05,
|
| 1745 |
+
"loss": 0.115,
|
| 1746 |
+
"step": 2230
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.6198830409356724,
|
| 1750 |
+
"grad_norm": 0.5550256371498108,
|
| 1751 |
+
"learning_rate": 2.329393966588323e-05,
|
| 1752 |
+
"loss": 0.0981,
|
| 1753 |
+
"step": 2240
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.6315789473684212,
|
| 1757 |
+
"grad_norm": 1.205012321472168,
|
| 1758 |
+
"learning_rate": 2.3109835732200686e-05,
|
| 1759 |
+
"loss": 0.0954,
|
| 1760 |
+
"step": 2250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.6432748538011697,
|
| 1764 |
+
"grad_norm": 0.8034434914588928,
|
| 1765 |
+
"learning_rate": 2.292583483670136e-05,
|
| 1766 |
+
"loss": 0.1046,
|
| 1767 |
+
"step": 2260
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.654970760233918,
|
| 1771 |
+
"grad_norm": 0.41518068313598633,
|
| 1772 |
+
"learning_rate": 2.2741947009792817e-05,
|
| 1773 |
+
"loss": 0.1245,
|
| 1774 |
+
"step": 2270
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.6666666666666665,
|
| 1778 |
+
"grad_norm": 1.7158474922180176,
|
| 1779 |
+
"learning_rate": 2.2558182275718953e-05,
|
| 1780 |
+
"loss": 0.1303,
|
| 1781 |
+
"step": 2280
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.678362573099415,
|
| 1785 |
+
"grad_norm": 2.198917865753174,
|
| 1786 |
+
"learning_rate": 2.2374550652013492e-05,
|
| 1787 |
+
"loss": 0.1142,
|
| 1788 |
+
"step": 2290
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.690058479532164,
|
| 1792 |
+
"grad_norm": 2.116436719894409,
|
| 1793 |
+
"learning_rate": 2.219106214895397e-05,
|
| 1794 |
+
"loss": 0.1196,
|
| 1795 |
+
"step": 2300
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.690058479532164,
|
| 1799 |
+
"eval_loss": 0.12174443155527115,
|
| 1800 |
+
"eval_runtime": 70.7411,
|
| 1801 |
+
"eval_samples_per_second": 5.089,
|
| 1802 |
+
"eval_steps_per_second": 0.636,
|
| 1803 |
+
"step": 2300
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 2.7017543859649122,
|
| 1807 |
+
"grad_norm": 1.5849992036819458,
|
| 1808 |
+
"learning_rate": 2.2007726769016006e-05,
|
| 1809 |
+
"loss": 0.1071,
|
| 1810 |
+
"step": 2310
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 2.7134502923976607,
|
| 1814 |
+
"grad_norm": 3.807744026184082,
|
| 1815 |
+
"learning_rate": 2.182455450632803e-05,
|
| 1816 |
+
"loss": 0.1246,
|
| 1817 |
+
"step": 2320
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 2.7251461988304095,
|
| 1821 |
+
"grad_norm": 1.429018497467041,
|
| 1822 |
+
"learning_rate": 2.1641555346126512e-05,
|
| 1823 |
+
"loss": 0.1188,
|
| 1824 |
+
"step": 2330
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 2.736842105263158,
|
| 1828 |
+
"grad_norm": 0.38770321011543274,
|
| 1829 |
+
"learning_rate": 2.1458739264211618e-05,
|
| 1830 |
+
"loss": 0.101,
|
| 1831 |
+
"step": 2340
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 2.7485380116959064,
|
| 1835 |
+
"grad_norm": 1.6713892221450806,
|
| 1836 |
+
"learning_rate": 2.127611622640336e-05,
|
| 1837 |
+
"loss": 0.1068,
|
| 1838 |
+
"step": 2350
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 2.760233918128655,
|
| 1842 |
+
"grad_norm": 1.5625298023223877,
|
| 1843 |
+
"learning_rate": 2.1093696187998424e-05,
|
| 1844 |
+
"loss": 0.1196,
|
| 1845 |
+
"step": 2360
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 2.7719298245614032,
|
| 1849 |
+
"grad_norm": 0.6439236402511597,
|
| 1850 |
+
"learning_rate": 2.0911489093227395e-05,
|
| 1851 |
+
"loss": 0.1076,
|
| 1852 |
+
"step": 2370
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 2.783625730994152,
|
| 1856 |
+
"grad_norm": 0.947961151599884,
|
| 1857 |
+
"learning_rate": 2.0729504874712713e-05,
|
| 1858 |
+
"loss": 0.111,
|
| 1859 |
+
"step": 2380
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 2.7953216374269005,
|
| 1863 |
+
"grad_norm": 0.6834493279457092,
|
| 1864 |
+
"learning_rate": 2.0547753452927197e-05,
|
| 1865 |
+
"loss": 0.1079,
|
| 1866 |
+
"step": 2390
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 2.807017543859649,
|
| 1870 |
+
"grad_norm": 0.9059198498725891,
|
| 1871 |
+
"learning_rate": 2.036624473565328e-05,
|
| 1872 |
+
"loss": 0.1058,
|
| 1873 |
+
"step": 2400
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 2.807017543859649,
|
| 1877 |
+
"eval_loss": 0.1205640360713005,
|
| 1878 |
+
"eval_runtime": 70.758,
|
| 1879 |
+
"eval_samples_per_second": 5.088,
|
| 1880 |
+
"eval_steps_per_second": 0.636,
|
| 1881 |
+
"step": 2400
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 2.818713450292398,
|
| 1885 |
+
"grad_norm": 1.0221079587936401,
|
| 1886 |
+
"learning_rate": 2.0184988617442852e-05,
|
| 1887 |
+
"loss": 0.1111,
|
| 1888 |
+
"step": 2410
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 2.8304093567251463,
|
| 1892 |
+
"grad_norm": 1.409433126449585,
|
| 1893 |
+
"learning_rate": 2.0003994979077937e-05,
|
| 1894 |
+
"loss": 0.1069,
|
| 1895 |
+
"step": 2420
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 2.8421052631578947,
|
| 1899 |
+
"grad_norm": 3.338195562362671,
|
| 1900 |
+
"learning_rate": 1.9823273687032045e-05,
|
| 1901 |
+
"loss": 0.1153,
|
| 1902 |
+
"step": 2430
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 2.853801169590643,
|
| 1906 |
+
"grad_norm": 1.3215330839157104,
|
| 1907 |
+
"learning_rate": 1.964283459293232e-05,
|
| 1908 |
+
"loss": 0.1097,
|
| 1909 |
+
"step": 2440
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 2.8654970760233915,
|
| 1913 |
+
"grad_norm": 0.9754563570022583,
|
| 1914 |
+
"learning_rate": 1.94626875330225e-05,
|
| 1915 |
+
"loss": 0.1123,
|
| 1916 |
+
"step": 2450
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 2.8771929824561404,
|
| 1920 |
+
"grad_norm": 1.7067068815231323,
|
| 1921 |
+
"learning_rate": 1.92828423276267e-05,
|
| 1922 |
+
"loss": 0.1194,
|
| 1923 |
+
"step": 2460
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 2.888888888888889,
|
| 1927 |
+
"grad_norm": 0.7298212051391602,
|
| 1928 |
+
"learning_rate": 1.9103308780614118e-05,
|
| 1929 |
+
"loss": 0.1041,
|
| 1930 |
+
"step": 2470
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 2.9005847953216373,
|
| 1934 |
+
"grad_norm": 2.4480433464050293,
|
| 1935 |
+
"learning_rate": 1.8924096678864557e-05,
|
| 1936 |
+
"loss": 0.1155,
|
| 1937 |
+
"step": 2480
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 2.912280701754386,
|
| 1941 |
+
"grad_norm": 0.9016093611717224,
|
| 1942 |
+
"learning_rate": 1.8745215791734942e-05,
|
| 1943 |
+
"loss": 0.1073,
|
| 1944 |
+
"step": 2490
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 2.9239766081871346,
|
| 1948 |
+
"grad_norm": 1.3098756074905396,
|
| 1949 |
+
"learning_rate": 1.8566675870526756e-05,
|
| 1950 |
+
"loss": 0.1177,
|
| 1951 |
+
"step": 2500
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 2.9239766081871346,
|
| 1955 |
+
"eval_loss": 0.12042708694934845,
|
| 1956 |
+
"eval_runtime": 70.7595,
|
| 1957 |
+
"eval_samples_per_second": 5.088,
|
| 1958 |
+
"eval_steps_per_second": 0.636,
|
| 1959 |
+
"step": 2500
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 2.935672514619883,
|
| 1963 |
+
"grad_norm": 0.7243450284004211,
|
| 1964 |
+
"learning_rate": 1.838848664795447e-05,
|
| 1965 |
+
"loss": 0.1073,
|
| 1966 |
+
"step": 2510
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 2.9473684210526314,
|
| 1970 |
+
"grad_norm": 0.7760084271430969,
|
| 1971 |
+
"learning_rate": 1.8210657837614965e-05,
|
| 1972 |
+
"loss": 0.11,
|
| 1973 |
+
"step": 2520
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 2.95906432748538,
|
| 1977 |
+
"grad_norm": 3.328228712081909,
|
| 1978 |
+
"learning_rate": 1.803319913345805e-05,
|
| 1979 |
+
"loss": 0.112,
|
| 1980 |
+
"step": 2530
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 2.9707602339181287,
|
| 1984 |
+
"grad_norm": 2.186782121658325,
|
| 1985 |
+
"learning_rate": 1.785612020925801e-05,
|
| 1986 |
+
"loss": 0.0969,
|
| 1987 |
+
"step": 2540
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 2.982456140350877,
|
| 1991 |
+
"grad_norm": 0.893616259098053,
|
| 1992 |
+
"learning_rate": 1.7679430718086243e-05,
|
| 1993 |
+
"loss": 0.1006,
|
| 1994 |
+
"step": 2550
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 2.9941520467836256,
|
| 1998 |
+
"grad_norm": 3.7202115058898926,
|
| 1999 |
+
"learning_rate": 1.7503140291785054e-05,
|
| 2000 |
+
"loss": 0.1041,
|
| 2001 |
+
"step": 2560
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 3.0058479532163744,
|
| 2005 |
+
"grad_norm": 1.9740840196609497,
|
| 2006 |
+
"learning_rate": 1.732725854044261e-05,
|
| 2007 |
+
"loss": 0.0973,
|
| 2008 |
+
"step": 2570
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 3.017543859649123,
|
| 2012 |
+
"grad_norm": 3.9907517433166504,
|
| 2013 |
+
"learning_rate": 1.7151795051869025e-05,
|
| 2014 |
+
"loss": 0.1181,
|
| 2015 |
+
"step": 2580
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 3.0292397660818713,
|
| 2019 |
+
"grad_norm": 0.8175060153007507,
|
| 2020 |
+
"learning_rate": 1.6976759391073758e-05,
|
| 2021 |
+
"loss": 0.1177,
|
| 2022 |
+
"step": 2590
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 3.0409356725146197,
|
| 2026 |
+
"grad_norm": 1.1770973205566406,
|
| 2027 |
+
"learning_rate": 1.6802161099744164e-05,
|
| 2028 |
+
"loss": 0.1009,
|
| 2029 |
+
"step": 2600
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 3.0409356725146197,
|
| 2033 |
+
"eval_loss": 0.11801114678382874,
|
| 2034 |
+
"eval_runtime": 70.7625,
|
| 2035 |
+
"eval_samples_per_second": 5.087,
|
| 2036 |
+
"eval_steps_per_second": 0.636,
|
| 2037 |
+
"step": 2600
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 3.0526315789473686,
|
| 2041 |
+
"grad_norm": 0.982765793800354,
|
| 2042 |
+
"learning_rate": 1.6628009695725346e-05,
|
| 2043 |
+
"loss": 0.0869,
|
| 2044 |
+
"step": 2610
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 3.064327485380117,
|
| 2048 |
+
"grad_norm": 1.3147976398468018,
|
| 2049 |
+
"learning_rate": 1.645431467250134e-05,
|
| 2050 |
+
"loss": 0.1067,
|
| 2051 |
+
"step": 2620
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 3.0760233918128654,
|
| 2055 |
+
"grad_norm": 2.452866315841675,
|
| 2056 |
+
"learning_rate": 1.628108549867754e-05,
|
| 2057 |
+
"loss": 0.1065,
|
| 2058 |
+
"step": 2630
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 3.087719298245614,
|
| 2062 |
+
"grad_norm": 1.246812105178833,
|
| 2063 |
+
"learning_rate": 1.610833161746461e-05,
|
| 2064 |
+
"loss": 0.1046,
|
| 2065 |
+
"step": 2640
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 3.0994152046783627,
|
| 2069 |
+
"grad_norm": 2.475942611694336,
|
| 2070 |
+
"learning_rate": 1.5936062446163666e-05,
|
| 2071 |
+
"loss": 0.102,
|
| 2072 |
+
"step": 2650
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 3.111111111111111,
|
| 2076 |
+
"grad_norm": 2.2378146648406982,
|
| 2077 |
+
"learning_rate": 1.576428737565292e-05,
|
| 2078 |
+
"loss": 0.0921,
|
| 2079 |
+
"step": 2660
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 3.1228070175438596,
|
| 2083 |
+
"grad_norm": 1.563463807106018,
|
| 2084 |
+
"learning_rate": 1.5593015769875746e-05,
|
| 2085 |
+
"loss": 0.0966,
|
| 2086 |
+
"step": 2670
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 3.134502923976608,
|
| 2090 |
+
"grad_norm": 2.7009105682373047,
|
| 2091 |
+
"learning_rate": 1.5422256965330263e-05,
|
| 2092 |
+
"loss": 0.1179,
|
| 2093 |
+
"step": 2680
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 3.146198830409357,
|
| 2097 |
+
"grad_norm": 0.5407319664955139,
|
| 2098 |
+
"learning_rate": 1.52520202705603e-05,
|
| 2099 |
+
"loss": 0.095,
|
| 2100 |
+
"step": 2690
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 3.1578947368421053,
|
| 2104 |
+
"grad_norm": 1.054494857788086,
|
| 2105 |
+
"learning_rate": 1.508231496564806e-05,
|
| 2106 |
+
"loss": 0.1024,
|
| 2107 |
+
"step": 2700
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 3.1578947368421053,
|
| 2111 |
+
"eval_loss": 0.11845976859331131,
|
| 2112 |
+
"eval_runtime": 70.8082,
|
| 2113 |
+
"eval_samples_per_second": 5.084,
|
| 2114 |
+
"eval_steps_per_second": 0.636,
|
| 2115 |
+
"step": 2700
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 3.1695906432748537,
|
| 2119 |
+
"grad_norm": 1.0297489166259766,
|
| 2120 |
+
"learning_rate": 1.4913150301708162e-05,
|
| 2121 |
+
"loss": 0.1048,
|
| 2122 |
+
"step": 2710
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 3.181286549707602,
|
| 2126 |
+
"grad_norm": 7.1104254722595215,
|
| 2127 |
+
"learning_rate": 1.4744535500383372e-05,
|
| 2128 |
+
"loss": 0.1227,
|
| 2129 |
+
"step": 2720
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 3.192982456140351,
|
| 2133 |
+
"grad_norm": 1.7294998168945312,
|
| 2134 |
+
"learning_rate": 1.4576479753341882e-05,
|
| 2135 |
+
"loss": 0.1155,
|
| 2136 |
+
"step": 2730
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 3.2046783625730995,
|
| 2140 |
+
"grad_norm": 1.502966046333313,
|
| 2141 |
+
"learning_rate": 1.4408992221776282e-05,
|
| 2142 |
+
"loss": 0.1116,
|
| 2143 |
+
"step": 2740
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 3.216374269005848,
|
| 2147 |
+
"grad_norm": 1.003847360610962,
|
| 2148 |
+
"learning_rate": 1.4242082035904086e-05,
|
| 2149 |
+
"loss": 0.1168,
|
| 2150 |
+
"step": 2750
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 3.2280701754385963,
|
| 2154 |
+
"grad_norm": 1.5059524774551392,
|
| 2155 |
+
"learning_rate": 1.4075758294470132e-05,
|
| 2156 |
+
"loss": 0.0942,
|
| 2157 |
+
"step": 2760
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 3.239766081871345,
|
| 2161 |
+
"grad_norm": 0.9065340161323547,
|
| 2162 |
+
"learning_rate": 1.3910030064250462e-05,
|
| 2163 |
+
"loss": 0.103,
|
| 2164 |
+
"step": 2770
|
| 2165 |
+
},
|
| 2166 |
+
{
|
| 2167 |
+
"epoch": 3.2514619883040936,
|
| 2168 |
+
"grad_norm": 1.1417133808135986,
|
| 2169 |
+
"learning_rate": 1.3744906379558165e-05,
|
| 2170 |
+
"loss": 0.1246,
|
| 2171 |
+
"step": 2780
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 3.263157894736842,
|
| 2175 |
+
"grad_norm": 1.5030591487884521,
|
| 2176 |
+
"learning_rate": 1.3580396241750823e-05,
|
| 2177 |
+
"loss": 0.1054,
|
| 2178 |
+
"step": 2790
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 3.2748538011695905,
|
| 2182 |
+
"grad_norm": 2.610001564025879,
|
| 2183 |
+
"learning_rate": 1.3416508618739854e-05,
|
| 2184 |
+
"loss": 0.0953,
|
| 2185 |
+
"step": 2800
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 3.2748538011695905,
|
| 2189 |
+
"eval_loss": 0.1236434280872345,
|
| 2190 |
+
"eval_runtime": 70.7784,
|
| 2191 |
+
"eval_samples_per_second": 5.086,
|
| 2192 |
+
"eval_steps_per_second": 0.636,
|
| 2193 |
+
"step": 2800
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 3.2865497076023393,
|
| 2197 |
+
"grad_norm": 1.7465177774429321,
|
| 2198 |
+
"learning_rate": 1.3253252444501635e-05,
|
| 2199 |
+
"loss": 0.0891,
|
| 2200 |
+
"step": 2810
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 3.2982456140350878,
|
| 2204 |
+
"grad_norm": 1.5508021116256714,
|
| 2205 |
+
"learning_rate": 1.309063661859049e-05,
|
| 2206 |
+
"loss": 0.0942,
|
| 2207 |
+
"step": 2820
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 3.309941520467836,
|
| 2211 |
+
"grad_norm": 0.9697007536888123,
|
| 2212 |
+
"learning_rate": 1.2928670005653576e-05,
|
| 2213 |
+
"loss": 0.0966,
|
| 2214 |
+
"step": 2830
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 3.3216374269005846,
|
| 2218 |
+
"grad_norm": 1.3551596403121948,
|
| 2219 |
+
"learning_rate": 1.2767361434947584e-05,
|
| 2220 |
+
"loss": 0.0863,
|
| 2221 |
+
"step": 2840
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 3.3333333333333335,
|
| 2225 |
+
"grad_norm": 2.1799612045288086,
|
| 2226 |
+
"learning_rate": 1.2606719699857489e-05,
|
| 2227 |
+
"loss": 0.0938,
|
| 2228 |
+
"step": 2850
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 3.345029239766082,
|
| 2232 |
+
"grad_norm": 3.5059502124786377,
|
| 2233 |
+
"learning_rate": 1.244675355741717e-05,
|
| 2234 |
+
"loss": 0.1161,
|
| 2235 |
+
"step": 2860
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 3.3567251461988303,
|
| 2239 |
+
"grad_norm": 1.9047223329544067,
|
| 2240 |
+
"learning_rate": 1.228747172783204e-05,
|
| 2241 |
+
"loss": 0.1082,
|
| 2242 |
+
"step": 2870
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 3.3684210526315788,
|
| 2246 |
+
"grad_norm": 0.8077034950256348,
|
| 2247 |
+
"learning_rate": 1.212888289400371e-05,
|
| 2248 |
+
"loss": 0.0982,
|
| 2249 |
+
"step": 2880
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 3.3801169590643276,
|
| 2253 |
+
"grad_norm": 4.194718360900879,
|
| 2254 |
+
"learning_rate": 1.1970995701056615e-05,
|
| 2255 |
+
"loss": 0.1026,
|
| 2256 |
+
"step": 2890
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 3.391812865497076,
|
| 2260 |
+
"grad_norm": 1.0910911560058594,
|
| 2261 |
+
"learning_rate": 1.181381875586677e-05,
|
| 2262 |
+
"loss": 0.0905,
|
| 2263 |
+
"step": 2900
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 3.391812865497076,
|
| 2267 |
+
"eval_loss": 0.12022969871759415,
|
| 2268 |
+
"eval_runtime": 70.7539,
|
| 2269 |
+
"eval_samples_per_second": 5.088,
|
| 2270 |
+
"eval_steps_per_second": 0.636,
|
| 2271 |
+
"step": 2900
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 3.391812865497076,
|
| 2275 |
+
"step": 2900,
|
| 2276 |
+
"total_flos": 5.067618607815459e+18,
|
| 2277 |
+
"train_loss": 0.14973004334959492,
|
| 2278 |
+
"train_runtime": 17301.2227,
|
| 2279 |
+
"train_samples_per_second": 1.977,
|
| 2280 |
+
"train_steps_per_second": 0.247
|
| 2281 |
+
}
|
| 2282 |
+
],
|
| 2283 |
+
"logging_steps": 10,
|
| 2284 |
+
"max_steps": 4275,
|
| 2285 |
+
"num_input_tokens_seen": 0,
|
| 2286 |
+
"num_train_epochs": 5,
|
| 2287 |
+
"save_steps": 100,
|
| 2288 |
+
"total_flos": 5.067618607815459e+18,
|
| 2289 |
+
"train_batch_size": 4,
|
| 2290 |
+
"trial_name": null,
|
| 2291 |
+
"trial_params": null
|
| 2292 |
+
}
|
llama2_13b_peft/paragraph_segmentation/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b46a67d8364305ef66b05e699b604996db4a79a12ca30354ea647391b8a5316d
|
| 3 |
+
size 5176
|
llama2_13b_peft/paragraph_segmentation/training_eval_loss.png
ADDED
|
llama2_13b_peft/paragraph_segmentation/training_loss.png
ADDED
|
llama2_13b_peft/play_dialog_same_or_different/README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: /data1/model/llama2/meta-llama/Llama2-13b
|
| 9 |
+
model-index:
|
| 10 |
+
- name: play_dialog_same_or_different_no_sys
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# play_dialog_same_or_different_no_sys
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the play_dialog_same_or_different_no_sys dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.3175
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 2
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- total_eval_batch_size: 8
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_steps: 20
|
| 51 |
+
- num_epochs: 5.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 57 |
+
| 0.3588 | 0.3215 | 100 | 0.3202 |
|
| 58 |
+
| 0.321 | 0.6431 | 200 | 0.3241 |
|
| 59 |
+
| 0.3268 | 0.9646 | 300 | 0.3193 |
|
| 60 |
+
| 0.34 | 1.2862 | 400 | 0.3250 |
|
| 61 |
+
| 0.3221 | 1.6077 | 500 | 0.3175 |
|
| 62 |
+
| 0.3193 | 1.9293 | 600 | 0.3194 |
|
| 63 |
+
| 0.339 | 2.2508 | 700 | 0.3211 |
|
| 64 |
+
| 0.3347 | 2.5723 | 800 | 0.3262 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- PEFT 0.10.0
|
| 70 |
+
- Transformers 4.40.0
|
| 71 |
+
- Pytorch 2.2.1
|
| 72 |
+
- Datasets 2.18.0
|
| 73 |
+
- Tokenizers 0.19.1
|
llama2_13b_peft/play_dialog_same_or_different/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
llama2_13b_peft/play_dialog_same_or_different/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c8c83ac7a47be01b3b27a6d3b9aae775e94b660b6e0717369fa2c9340ce3144
|
| 3 |
+
size 125248064
|
llama2_13b_peft/play_dialog_same_or_different/all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.572347266881029,
|
| 3 |
+
"eval_loss": 0.31748995184898376,
|
| 4 |
+
"eval_runtime": 2.9141,
|
| 5 |
+
"eval_samples_per_second": 44.953,
|
| 6 |
+
"eval_steps_per_second": 5.834,
|
| 7 |
+
"total_flos": 1.4161342881595392e+17,
|
| 8 |
+
"train_loss": 0.5724774128198624,
|
| 9 |
+
"train_runtime": 490.2786,
|
| 10 |
+
"train_samples_per_second": 25.302,
|
| 11 |
+
"train_steps_per_second": 3.172
|
| 12 |
+
}
|
llama2_13b_peft/play_dialog_same_or_different/eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.572347266881029,
|
| 3 |
+
"eval_loss": 0.31748995184898376,
|
| 4 |
+
"eval_runtime": 2.9141,
|
| 5 |
+
"eval_samples_per_second": 44.953,
|
| 6 |
+
"eval_steps_per_second": 5.834
|
| 7 |
+
}
|
llama2_13b_peft/play_dialog_same_or_different/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
llama2_13b_peft/play_dialog_same_or_different/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
llama2_13b_peft/play_dialog_same_or_different/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false
|
| 45 |
+
}
|
llama2_13b_peft/play_dialog_same_or_different/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.572347266881029,
|
| 3 |
+
"total_flos": 1.4161342881595392e+17,
|
| 4 |
+
"train_loss": 0.5724774128198624,
|
| 5 |
+
"train_runtime": 490.2786,
|
| 6 |
+
"train_samples_per_second": 25.302,
|
| 7 |
+
"train_steps_per_second": 3.172
|
| 8 |
+
}
|
llama2_13b_peft/play_dialog_same_or_different/trainer_log.jsonl
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 1555, "loss": 10.7274, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5e-05, "epoch": 0.03215434083601286, "percentage": 0.64, "elapsed_time": "0:00:07", "remaining_time": "0:18:20"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 1555, "loss": 7.7527, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5e-05, "epoch": 0.06430868167202572, "percentage": 1.29, "elapsed_time": "0:00:12", "remaining_time": "0:16:00"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 1555, "loss": 1.1271, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.999476426280588e-05, "epoch": 0.09646302250803858, "percentage": 1.93, "elapsed_time": "0:00:18", "remaining_time": "0:15:22"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 1555, "loss": 0.4741, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.997905924425903e-05, "epoch": 0.12861736334405144, "percentage": 2.57, "elapsed_time": "0:00:23", "remaining_time": "0:14:57"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 1555, "loss": 0.3836, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.995289152254744e-05, "epoch": 0.1607717041800643, "percentage": 3.22, "elapsed_time": "0:00:29", "remaining_time": "0:14:45"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 1555, "loss": 0.3745, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.991627205825621e-05, "epoch": 0.19292604501607716, "percentage": 3.86, "elapsed_time": "0:00:34", "remaining_time": "0:14:30"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 1555, "loss": 0.3658, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.986921618977664e-05, "epoch": 0.22508038585209003, "percentage": 4.5, "elapsed_time": "0:00:40", "remaining_time": "0:14:27"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 1555, "loss": 0.346, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.981174362688158e-05, "epoch": 0.2572347266881029, "percentage": 5.14, "elapsed_time": "0:00:46", "remaining_time": "0:14:19"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 1555, "loss": 0.3624, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.974387844246987e-05, "epoch": 0.28938906752411575, "percentage": 5.79, "elapsed_time": "0:00:52", "remaining_time": "0:14:06"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 1555, "loss": 0.3588, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9665649062483115e-05, "epoch": 0.3215434083601286, "percentage": 6.43, "elapsed_time": "0:00:57", "remaining_time": "0:13:56"}
|
| 11 |
+
{"current_steps": 100, "total_steps": 1555, "loss": null, "eval_loss": 0.3202289044857025, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.3215434083601286, "percentage": 6.43, "elapsed_time": "0:00:57", "remaining_time": "0:13:56"}
|
| 12 |
+
{"current_steps": 110, "total_steps": 1555, "loss": 0.341, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.957708825399927e-05, "epoch": 0.3536977491961415, "percentage": 7.07, "elapsed_time": "0:01:06", "remaining_time": "0:14:34"}
|
| 13 |
+
{"current_steps": 120, "total_steps": 1555, "loss": 0.3741, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9478233111507856e-05, "epoch": 0.3858520900321543, "percentage": 7.72, "elapsed_time": "0:01:12", "remaining_time": "0:14:21"}
|
| 14 |
+
{"current_steps": 130, "total_steps": 1555, "loss": 0.3254, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.936912504137257e-05, "epoch": 0.4180064308681672, "percentage": 8.36, "elapsed_time": "0:01:17", "remaining_time": "0:14:09"}
|
| 15 |
+
{"current_steps": 140, "total_steps": 1555, "loss": 0.3496, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.924980974448791e-05, "epoch": 0.45016077170418006, "percentage": 9.0, "elapsed_time": "0:01:23", "remaining_time": "0:14:01"}
|
| 16 |
+
{"current_steps": 150, "total_steps": 1555, "loss": 0.3569, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.912033719713687e-05, "epoch": 0.48231511254019294, "percentage": 9.65, "elapsed_time": "0:01:28", "remaining_time": "0:13:51"}
|
| 17 |
+
{"current_steps": 160, "total_steps": 1555, "loss": 0.3066, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8980761630058014e-05, "epoch": 0.5144694533762058, "percentage": 10.29, "elapsed_time": "0:01:34", "remaining_time": "0:13:42"}
|
| 18 |
+
{"current_steps": 170, "total_steps": 1555, "loss": 0.356, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.883114150573037e-05, "epoch": 0.5466237942122186, "percentage": 10.93, "elapsed_time": "0:01:40", "remaining_time": "0:13:37"}
|
| 19 |
+
{"current_steps": 180, "total_steps": 1555, "loss": 0.3955, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8671539493885934e-05, "epoch": 0.5787781350482315, "percentage": 11.58, "elapsed_time": "0:01:46", "remaining_time": "0:13:29"}
|
| 20 |
+
{"current_steps": 190, "total_steps": 1555, "loss": 0.3876, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.850202244525987e-05, "epoch": 0.6109324758842444, "percentage": 12.22, "elapsed_time": "0:01:51", "remaining_time": "0:13:22"}
|
| 21 |
+
{"current_steps": 200, "total_steps": 1555, "loss": 0.321, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8322661363589507e-05, "epoch": 0.6430868167202572, "percentage": 12.86, "elapsed_time": "0:01:57", "remaining_time": "0:13:15"}
|
| 22 |
+
{"current_steps": 200, "total_steps": 1555, "loss": null, "eval_loss": 0.32409238815307617, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.6430868167202572, "percentage": 12.86, "elapsed_time": "0:01:57", "remaining_time": "0:13:15"}
|
| 23 |
+
{"current_steps": 210, "total_steps": 1555, "loss": 0.39, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.813353137587377e-05, "epoch": 0.6752411575562701, "percentage": 13.5, "elapsed_time": "0:02:06", "remaining_time": "0:13:29"}
|
| 24 |
+
{"current_steps": 220, "total_steps": 1555, "loss": 0.3429, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.793471170090555e-05, "epoch": 0.707395498392283, "percentage": 14.15, "elapsed_time": "0:02:12", "remaining_time": "0:13:22"}
|
| 25 |
+
{"current_steps": 230, "total_steps": 1555, "loss": 0.3208, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.772628561609022e-05, "epoch": 0.7395498392282959, "percentage": 14.79, "elapsed_time": "0:02:17", "remaining_time": "0:13:13"}
|
| 26 |
+
{"current_steps": 240, "total_steps": 1555, "loss": 0.344, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7508340422564134e-05, "epoch": 0.7717041800643086, "percentage": 15.43, "elapsed_time": "0:02:23", "remaining_time": "0:13:05"}
|
| 27 |
+
{"current_steps": 250, "total_steps": 1555, "loss": 0.2976, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.728096740862778e-05, "epoch": 0.8038585209003215, "percentage": 16.08, "elapsed_time": "0:02:29", "remaining_time": "0:12:59"}
|
| 28 |
+
{"current_steps": 260, "total_steps": 1555, "loss": 0.3684, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.704426181150884e-05, "epoch": 0.8360128617363344, "percentage": 16.72, "elapsed_time": "0:02:34", "remaining_time": "0:12:51"}
|
| 29 |
+
{"current_steps": 270, "total_steps": 1555, "loss": 0.3398, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6798322777471216e-05, "epoch": 0.8681672025723473, "percentage": 17.36, "elapsed_time": "0:02:40", "remaining_time": "0:12:43"}
|
| 30 |
+
{"current_steps": 280, "total_steps": 1555, "loss": 0.3236, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.654325332028676e-05, "epoch": 0.9003215434083601, "percentage": 18.01, "elapsed_time": "0:02:46", "remaining_time": "0:12:37"}
|
| 31 |
+
{"current_steps": 290, "total_steps": 1555, "loss": 0.2567, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6279160278086994e-05, "epoch": 0.932475884244373, "percentage": 18.65, "elapsed_time": "0:02:51", "remaining_time": "0:12:30"}
|
| 32 |
+
{"current_steps": 300, "total_steps": 1555, "loss": 0.3268, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6006154268613014e-05, "epoch": 0.9646302250803859, "percentage": 19.29, "elapsed_time": "0:02:57", "remaining_time": "0:12:22"}
|
| 33 |
+
{"current_steps": 300, "total_steps": 1555, "loss": null, "eval_loss": 0.3192877471446991, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.9646302250803859, "percentage": 19.29, "elapsed_time": "0:02:57", "remaining_time": "0:12:22"}
|
| 34 |
+
{"current_steps": 310, "total_steps": 1555, "loss": 0.3136, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.572434964288226e-05, "epoch": 0.9967845659163987, "percentage": 19.94, "elapsed_time": "0:03:06", "remaining_time": "0:12:28"}
|
| 35 |
+
{"current_steps": 320, "total_steps": 1555, "loss": 0.3386, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.543386443729157e-05, "epoch": 1.0289389067524115, "percentage": 20.58, "elapsed_time": "0:03:11", "remaining_time": "0:12:20"}
|
| 36 |
+
{"current_steps": 330, "total_steps": 1555, "loss": 0.3385, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.513482032417656e-05, "epoch": 1.0610932475884245, "percentage": 21.22, "elapsed_time": "0:03:17", "remaining_time": "0:12:14"}
|
| 37 |
+
{"current_steps": 340, "total_steps": 1555, "loss": 0.3345, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.48273425608481e-05, "epoch": 1.0932475884244373, "percentage": 21.86, "elapsed_time": "0:03:23", "remaining_time": "0:12:07"}
|
| 38 |
+
{"current_steps": 350, "total_steps": 1555, "loss": 0.3515, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.451155993712711e-05, "epoch": 1.1254019292604502, "percentage": 22.51, "elapsed_time": "0:03:29", "remaining_time": "0:11:59"}
|
| 39 |
+
{"current_steps": 360, "total_steps": 1555, "loss": 0.3363, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.4187604721399877e-05, "epoch": 1.157556270096463, "percentage": 23.15, "elapsed_time": "0:03:34", "remaining_time": "0:11:53"}
|
| 40 |
+
{"current_steps": 370, "total_steps": 1555, "loss": 0.3453, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.3855612605216174e-05, "epoch": 1.189710610932476, "percentage": 23.79, "elapsed_time": "0:03:40", "remaining_time": "0:11:46"}
|
| 41 |
+
{"current_steps": 380, "total_steps": 1555, "loss": 0.3297, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.351572264645366e-05, "epoch": 1.2218649517684887, "percentage": 24.44, "elapsed_time": "0:03:46", "remaining_time": "0:11:39"}
|
| 42 |
+
{"current_steps": 390, "total_steps": 1555, "loss": 0.3453, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.3168077211072263e-05, "epoch": 1.2540192926045015, "percentage": 25.08, "elapsed_time": "0:03:51", "remaining_time": "0:11:31"}
|
| 43 |
+
{"current_steps": 400, "total_steps": 1555, "loss": 0.34, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.281282191348289e-05, "epoch": 1.2861736334405145, "percentage": 25.72, "elapsed_time": "0:03:57", "remaining_time": "0:11:25"}
|
| 44 |
+
{"current_steps": 400, "total_steps": 1555, "loss": null, "eval_loss": 0.32504987716674805, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.2861736334405145, "percentage": 25.72, "elapsed_time": "0:03:57", "remaining_time": "0:11:25"}
|
| 45 |
+
{"current_steps": 410, "total_steps": 1555, "loss": 0.3324, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.245010555555554e-05, "epoch": 1.3183279742765273, "percentage": 26.37, "elapsed_time": "0:04:06", "remaining_time": "0:11:28"}
|
| 46 |
+
{"current_steps": 420, "total_steps": 1555, "loss": 0.3564, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.2080080064292304e-05, "epoch": 1.3504823151125402, "percentage": 27.01, "elapsed_time": "0:04:12", "remaining_time": "0:11:21"}
|
| 47 |
+
{"current_steps": 430, "total_steps": 1555, "loss": 0.3105, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.1702900428191374e-05, "epoch": 1.382636655948553, "percentage": 27.65, "elapsed_time": "0:04:17", "remaining_time": "0:11:14"}
|
| 48 |
+
{"current_steps": 440, "total_steps": 1555, "loss": 0.2817, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.131872463232872e-05, "epoch": 1.414790996784566, "percentage": 28.3, "elapsed_time": "0:04:23", "remaining_time": "0:11:07"}
|
| 49 |
+
{"current_steps": 450, "total_steps": 1555, "loss": 0.3865, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.092771359218461e-05, "epoch": 1.4469453376205788, "percentage": 28.94, "elapsed_time": "0:04:29", "remaining_time": "0:11:00"}
|
| 50 |
+
{"current_steps": 460, "total_steps": 1555, "loss": 0.3358, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.053003108624276e-05, "epoch": 1.4790996784565915, "percentage": 29.58, "elapsed_time": "0:04:34", "remaining_time": "0:10:54"}
|
| 51 |
+
{"current_steps": 470, "total_steps": 1555, "loss": 0.3586, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.0125843687390166e-05, "epoch": 1.5112540192926045, "percentage": 30.23, "elapsed_time": "0:04:40", "remaining_time": "0:10:47"}
|
| 52 |
+
{"current_steps": 480, "total_steps": 1555, "loss": 0.3285, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.9715320693146655e-05, "epoch": 1.5434083601286175, "percentage": 30.87, "elapsed_time": "0:04:46", "remaining_time": "0:10:41"}
|
| 53 |
+
{"current_steps": 490, "total_steps": 1555, "loss": 0.3437, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.9298634054753026e-05, "epoch": 1.5755627009646302, "percentage": 31.51, "elapsed_time": "0:04:51", "remaining_time": "0:10:34"}
|
| 54 |
+
{"current_steps": 500, "total_steps": 1555, "loss": 0.3221, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.887595830514775e-05, "epoch": 1.607717041800643, "percentage": 32.15, "elapsed_time": "0:04:57", "remaining_time": "0:10:26"}
|
| 55 |
+
{"current_steps": 500, "total_steps": 1555, "loss": null, "eval_loss": 0.31748995184898376, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.607717041800643, "percentage": 32.15, "elapsed_time": "0:04:57", "remaining_time": "0:10:26"}
|
| 56 |
+
{"current_steps": 510, "total_steps": 1555, "loss": 0.3011, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.844747048586228e-05, "epoch": 1.639871382636656, "percentage": 32.8, "elapsed_time": "0:05:06", "remaining_time": "0:10:27"}
|
| 57 |
+
{"current_steps": 520, "total_steps": 1555, "loss": 0.3461, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.801335007286564e-05, "epoch": 1.6720257234726688, "percentage": 33.44, "elapsed_time": "0:05:12", "remaining_time": "0:10:21"}
|
| 58 |
+
{"current_steps": 530, "total_steps": 1555, "loss": 0.3477, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.757377890138927e-05, "epoch": 1.7041800643086815, "percentage": 34.08, "elapsed_time": "0:05:18", "remaining_time": "0:10:15"}
|
| 59 |
+
{"current_steps": 540, "total_steps": 1555, "loss": 0.3507, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.712894108976372e-05, "epoch": 1.7363344051446945, "percentage": 34.73, "elapsed_time": "0:05:23", "remaining_time": "0:10:08"}
|
| 60 |
+
{"current_steps": 550, "total_steps": 1555, "loss": 0.3327, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.667902296229905e-05, "epoch": 1.7684887459807075, "percentage": 35.37, "elapsed_time": "0:05:29", "remaining_time": "0:10:01"}
|
| 61 |
+
{"current_steps": 560, "total_steps": 1555, "loss": 0.3312, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.622421297124122e-05, "epoch": 1.8006430868167203, "percentage": 36.01, "elapsed_time": "0:05:35", "remaining_time": "0:09:55"}
|
| 62 |
+
{"current_steps": 570, "total_steps": 1555, "loss": 0.3659, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.576470161783712e-05, "epoch": 1.832797427652733, "percentage": 36.66, "elapsed_time": "0:05:40", "remaining_time": "0:09:49"}
|
| 63 |
+
{"current_steps": 580, "total_steps": 1555, "loss": 0.3347, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.5300681372541476e-05, "epoch": 1.864951768488746, "percentage": 37.3, "elapsed_time": "0:05:46", "remaining_time": "0:09:42"}
|
| 64 |
+
{"current_steps": 590, "total_steps": 1555, "loss": 0.3146, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.483234659439889e-05, "epoch": 1.897106109324759, "percentage": 37.94, "elapsed_time": "0:05:52", "remaining_time": "0:09:35"}
|
| 65 |
+
{"current_steps": 600, "total_steps": 1555, "loss": 0.3193, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.435989344963471e-05, "epoch": 1.9292604501607717, "percentage": 38.59, "elapsed_time": "0:05:57", "remaining_time": "0:09:29"}
|
| 66 |
+
{"current_steps": 600, "total_steps": 1555, "loss": null, "eval_loss": 0.3193986415863037, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.9292604501607717, "percentage": 38.59, "elapsed_time": "0:05:57", "remaining_time": "0:09:29"}
|
| 67 |
+
{"current_steps": 610, "total_steps": 1555, "loss": 0.3494, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.3883519829489154e-05, "epoch": 1.9614147909967845, "percentage": 39.23, "elapsed_time": "0:06:06", "remaining_time": "0:09:27"}
|
| 68 |
+
{"current_steps": 620, "total_steps": 1555, "loss": 0.2765, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.3403425267328715e-05, "epoch": 1.9935691318327975, "percentage": 39.87, "elapsed_time": "0:06:12", "remaining_time": "0:09:21"}
|
| 69 |
+
{"current_steps": 630, "total_steps": 1555, "loss": 0.327, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.2919810855069864e-05, "epoch": 2.0257234726688105, "percentage": 40.51, "elapsed_time": "0:06:18", "remaining_time": "0:09:15"}
|
| 70 |
+
{"current_steps": 640, "total_steps": 1555, "loss": 0.362, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.243287915894987e-05, "epoch": 2.057877813504823, "percentage": 41.16, "elapsed_time": "0:06:23", "remaining_time": "0:09:08"}
|
| 71 |
+
{"current_steps": 650, "total_steps": 1555, "loss": 0.3393, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.1942834134680124e-05, "epoch": 2.090032154340836, "percentage": 41.8, "elapsed_time": "0:06:29", "remaining_time": "0:09:02"}
|
| 72 |
+
{"current_steps": 660, "total_steps": 1555, "loss": 0.3322, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.144988104201745e-05, "epoch": 2.122186495176849, "percentage": 42.44, "elapsed_time": "0:06:35", "remaining_time": "0:08:55"}
|
| 73 |
+
{"current_steps": 670, "total_steps": 1555, "loss": 0.3191, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.095422635878923e-05, "epoch": 2.154340836012862, "percentage": 43.09, "elapsed_time": "0:06:40", "remaining_time": "0:08:49"}
|
| 74 |
+
{"current_steps": 680, "total_steps": 1555, "loss": 0.3311, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.045607769440829e-05, "epoch": 2.1864951768488745, "percentage": 43.73, "elapsed_time": "0:06:46", "remaining_time": "0:08:43"}
|
| 75 |
+
{"current_steps": 690, "total_steps": 1555, "loss": 0.3412, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9955643702913865e-05, "epoch": 2.2186495176848875, "percentage": 44.37, "elapsed_time": "0:06:52", "remaining_time": "0:08:36"}
|
| 76 |
+
{"current_steps": 700, "total_steps": 1555, "loss": 0.339, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9453133995574955e-05, "epoch": 2.2508038585209005, "percentage": 45.02, "elapsed_time": "0:06:57", "remaining_time": "0:08:30"}
|
| 77 |
+
{"current_steps": 700, "total_steps": 1555, "loss": null, "eval_loss": 0.32114845514297485, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.2508038585209005, "percentage": 45.02, "elapsed_time": "0:06:57", "remaining_time": "0:08:30"}
|
| 78 |
+
{"current_steps": 710, "total_steps": 1555, "loss": 0.3128, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.8948759053092754e-05, "epoch": 2.282958199356913, "percentage": 45.66, "elapsed_time": "0:07:06", "remaining_time": "0:08:27"}
|
| 79 |
+
{"current_steps": 720, "total_steps": 1555, "loss": 0.3448, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.844273013743896e-05, "epoch": 2.315112540192926, "percentage": 46.3, "elapsed_time": "0:07:12", "remaining_time": "0:08:21"}
|
| 80 |
+
{"current_steps": 730, "total_steps": 1555, "loss": 0.3295, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7935259203366777e-05, "epoch": 2.347266881028939, "percentage": 46.95, "elapsed_time": "0:07:18", "remaining_time": "0:08:15"}
|
| 81 |
+
{"current_steps": 740, "total_steps": 1555, "loss": 0.3249, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7426558809631748e-05, "epoch": 2.379421221864952, "percentage": 47.59, "elapsed_time": "0:07:23", "remaining_time": "0:08:08"}
|
| 82 |
+
{"current_steps": 750, "total_steps": 1555, "loss": 0.3213, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.691684202995966e-05, "epoch": 2.4115755627009645, "percentage": 48.23, "elapsed_time": "0:07:29", "remaining_time": "0:08:02"}
|
| 83 |
+
{"current_steps": 760, "total_steps": 1555, "loss": 0.3157, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.6406322363798657e-05, "epoch": 2.4437299035369775, "percentage": 48.87, "elapsed_time": "0:07:35", "remaining_time": "0:07:56"}
|
| 84 |
+
{"current_steps": 770, "total_steps": 1555, "loss": 0.3537, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.589521364689308e-05, "epoch": 2.4758842443729905, "percentage": 49.52, "elapsed_time": "0:07:40", "remaining_time": "0:07:49"}
|
| 85 |
+
{"current_steps": 780, "total_steps": 1555, "loss": 0.3344, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5383729961716483e-05, "epoch": 2.508038585209003, "percentage": 50.16, "elapsed_time": "0:07:46", "remaining_time": "0:07:43"}
|
| 86 |
+
{"current_steps": 790, "total_steps": 1555, "loss": 0.3398, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.487208554780125e-05, "epoch": 2.540192926045016, "percentage": 50.8, "elapsed_time": "0:07:51", "remaining_time": "0:07:36"}
|
| 87 |
+
{"current_steps": 800, "total_steps": 1555, "loss": 0.3347, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.4360494712002423e-05, "epoch": 2.572347266881029, "percentage": 51.45, "elapsed_time": "0:07:57", "remaining_time": "0:07:30"}
|
| 88 |
+
{"current_steps": 800, "total_steps": 1555, "loss": null, "eval_loss": 0.3262169659137726, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.572347266881029, "percentage": 51.45, "elapsed_time": "0:07:57", "remaining_time": "0:07:30"}
|
| 89 |
+
{"current_steps": 800, "total_steps": 1555, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.572347266881029, "percentage": 51.45, "elapsed_time": "0:07:57", "remaining_time": "0:07:30"}
|
| 90 |
+
{"current_steps": 17, "total_steps": 17, "loss": null, "eval_loss": 0.31748995184898376, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.572347266881029, "percentage": 100.0, "elapsed_time": "0:08:12", "remaining_time": "0:00:00"}
|
llama2_13b_peft/play_dialog_same_or_different/trainer_state.json
ADDED
|
@@ -0,0 +1,654 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.31748995184898376,
|
| 3 |
+
"best_model_checkpoint": "ckpt/llama2_13b_fuze27_no_sys/play_dialog_same_or_different_no_sys/checkpoint-500",
|
| 4 |
+
"epoch": 2.572347266881029,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03215434083601286,
|
| 13 |
+
"grad_norm": 11.316423416137695,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 10.7274,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06430868167202572,
|
| 20 |
+
"grad_norm": 13.179275512695312,
|
| 21 |
+
"learning_rate": 5e-05,
|
| 22 |
+
"loss": 7.7527,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09646302250803858,
|
| 27 |
+
"grad_norm": 2.945481777191162,
|
| 28 |
+
"learning_rate": 4.999476426280588e-05,
|
| 29 |
+
"loss": 1.1271,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12861736334405144,
|
| 34 |
+
"grad_norm": 0.8495484590530396,
|
| 35 |
+
"learning_rate": 4.997905924425903e-05,
|
| 36 |
+
"loss": 0.4741,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1607717041800643,
|
| 41 |
+
"grad_norm": 2.0995168685913086,
|
| 42 |
+
"learning_rate": 4.995289152254744e-05,
|
| 43 |
+
"loss": 0.3836,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.19292604501607716,
|
| 48 |
+
"grad_norm": 2.24106764793396,
|
| 49 |
+
"learning_rate": 4.991627205825621e-05,
|
| 50 |
+
"loss": 0.3745,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.22508038585209003,
|
| 55 |
+
"grad_norm": 2.550299644470215,
|
| 56 |
+
"learning_rate": 4.986921618977664e-05,
|
| 57 |
+
"loss": 0.3658,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2572347266881029,
|
| 62 |
+
"grad_norm": 1.3360856771469116,
|
| 63 |
+
"learning_rate": 4.981174362688158e-05,
|
| 64 |
+
"loss": 0.346,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.28938906752411575,
|
| 69 |
+
"grad_norm": 1.1294679641723633,
|
| 70 |
+
"learning_rate": 4.974387844246987e-05,
|
| 71 |
+
"loss": 0.3624,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3215434083601286,
|
| 76 |
+
"grad_norm": 0.6543893218040466,
|
| 77 |
+
"learning_rate": 4.9665649062483115e-05,
|
| 78 |
+
"loss": 0.3588,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3215434083601286,
|
| 83 |
+
"eval_loss": 0.3202289044857025,
|
| 84 |
+
"eval_runtime": 2.9115,
|
| 85 |
+
"eval_samples_per_second": 44.993,
|
| 86 |
+
"eval_steps_per_second": 5.839,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.3536977491961415,
|
| 91 |
+
"grad_norm": 0.378452867269516,
|
| 92 |
+
"learning_rate": 4.957708825399927e-05,
|
| 93 |
+
"loss": 0.341,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.3858520900321543,
|
| 98 |
+
"grad_norm": 0.8828644156455994,
|
| 99 |
+
"learning_rate": 4.9478233111507856e-05,
|
| 100 |
+
"loss": 0.3741,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.4180064308681672,
|
| 105 |
+
"grad_norm": 0.3250252604484558,
|
| 106 |
+
"learning_rate": 4.936912504137257e-05,
|
| 107 |
+
"loss": 0.3254,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.45016077170418006,
|
| 112 |
+
"grad_norm": 0.7310301661491394,
|
| 113 |
+
"learning_rate": 4.924980974448791e-05,
|
| 114 |
+
"loss": 0.3496,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.48231511254019294,
|
| 119 |
+
"grad_norm": 1.3139760494232178,
|
| 120 |
+
"learning_rate": 4.912033719713687e-05,
|
| 121 |
+
"loss": 0.3569,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5144694533762058,
|
| 126 |
+
"grad_norm": 1.1433072090148926,
|
| 127 |
+
"learning_rate": 4.8980761630058014e-05,
|
| 128 |
+
"loss": 0.3066,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.5466237942122186,
|
| 133 |
+
"grad_norm": 0.12614063918590546,
|
| 134 |
+
"learning_rate": 4.883114150573037e-05,
|
| 135 |
+
"loss": 0.356,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5787781350482315,
|
| 140 |
+
"grad_norm": 1.8395532369613647,
|
| 141 |
+
"learning_rate": 4.8671539493885934e-05,
|
| 142 |
+
"loss": 0.3955,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6109324758842444,
|
| 147 |
+
"grad_norm": 0.9796155691146851,
|
| 148 |
+
"learning_rate": 4.850202244525987e-05,
|
| 149 |
+
"loss": 0.3876,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.6430868167202572,
|
| 154 |
+
"grad_norm": 0.8637738227844238,
|
| 155 |
+
"learning_rate": 4.8322661363589507e-05,
|
| 156 |
+
"loss": 0.321,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.6430868167202572,
|
| 161 |
+
"eval_loss": 0.32409238815307617,
|
| 162 |
+
"eval_runtime": 2.9231,
|
| 163 |
+
"eval_samples_per_second": 44.816,
|
| 164 |
+
"eval_steps_per_second": 5.816,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.6752411575562701,
|
| 169 |
+
"grad_norm": 0.38207629323005676,
|
| 170 |
+
"learning_rate": 4.813353137587377e-05,
|
| 171 |
+
"loss": 0.39,
|
| 172 |
+
"step": 210
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.707395498392283,
|
| 176 |
+
"grad_norm": 0.8289644718170166,
|
| 177 |
+
"learning_rate": 4.793471170090555e-05,
|
| 178 |
+
"loss": 0.3429,
|
| 179 |
+
"step": 220
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.7395498392282959,
|
| 183 |
+
"grad_norm": 0.26011592149734497,
|
| 184 |
+
"learning_rate": 4.772628561609022e-05,
|
| 185 |
+
"loss": 0.3208,
|
| 186 |
+
"step": 230
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.7717041800643086,
|
| 190 |
+
"grad_norm": 0.571058988571167,
|
| 191 |
+
"learning_rate": 4.7508340422564134e-05,
|
| 192 |
+
"loss": 0.344,
|
| 193 |
+
"step": 240
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.8038585209003215,
|
| 197 |
+
"grad_norm": 0.8589864373207092,
|
| 198 |
+
"learning_rate": 4.728096740862778e-05,
|
| 199 |
+
"loss": 0.2976,
|
| 200 |
+
"step": 250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.8360128617363344,
|
| 204 |
+
"grad_norm": 0.08967006206512451,
|
| 205 |
+
"learning_rate": 4.704426181150884e-05,
|
| 206 |
+
"loss": 0.3684,
|
| 207 |
+
"step": 260
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.8681672025723473,
|
| 211 |
+
"grad_norm": 0.5221372246742249,
|
| 212 |
+
"learning_rate": 4.6798322777471216e-05,
|
| 213 |
+
"loss": 0.3398,
|
| 214 |
+
"step": 270
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.9003215434083601,
|
| 218 |
+
"grad_norm": 1.0666356086730957,
|
| 219 |
+
"learning_rate": 4.654325332028676e-05,
|
| 220 |
+
"loss": 0.3236,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.932475884244373,
|
| 225 |
+
"grad_norm": 0.281319797039032,
|
| 226 |
+
"learning_rate": 4.6279160278086994e-05,
|
| 227 |
+
"loss": 0.2567,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.9646302250803859,
|
| 232 |
+
"grad_norm": 0.15490597486495972,
|
| 233 |
+
"learning_rate": 4.6006154268613014e-05,
|
| 234 |
+
"loss": 0.3268,
|
| 235 |
+
"step": 300
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.9646302250803859,
|
| 239 |
+
"eval_loss": 0.3192877471446991,
|
| 240 |
+
"eval_runtime": 2.9293,
|
| 241 |
+
"eval_samples_per_second": 44.72,
|
| 242 |
+
"eval_steps_per_second": 5.803,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.9967845659163987,
|
| 247 |
+
"grad_norm": 0.10922815650701523,
|
| 248 |
+
"learning_rate": 4.572434964288226e-05,
|
| 249 |
+
"loss": 0.3136,
|
| 250 |
+
"step": 310
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.0289389067524115,
|
| 254 |
+
"grad_norm": 0.5204551219940186,
|
| 255 |
+
"learning_rate": 4.543386443729157e-05,
|
| 256 |
+
"loss": 0.3386,
|
| 257 |
+
"step": 320
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.0610932475884245,
|
| 261 |
+
"grad_norm": 0.6060867309570312,
|
| 262 |
+
"learning_rate": 4.513482032417656e-05,
|
| 263 |
+
"loss": 0.3385,
|
| 264 |
+
"step": 330
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.0932475884244373,
|
| 268 |
+
"grad_norm": 0.8849338889122009,
|
| 269 |
+
"learning_rate": 4.48273425608481e-05,
|
| 270 |
+
"loss": 0.3345,
|
| 271 |
+
"step": 340
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.1254019292604502,
|
| 275 |
+
"grad_norm": 0.22567600011825562,
|
| 276 |
+
"learning_rate": 4.451155993712711e-05,
|
| 277 |
+
"loss": 0.3515,
|
| 278 |
+
"step": 350
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.157556270096463,
|
| 282 |
+
"grad_norm": 0.1096111610531807,
|
| 283 |
+
"learning_rate": 4.4187604721399877e-05,
|
| 284 |
+
"loss": 0.3363,
|
| 285 |
+
"step": 360
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.189710610932476,
|
| 289 |
+
"grad_norm": 0.1326136738061905,
|
| 290 |
+
"learning_rate": 4.3855612605216174e-05,
|
| 291 |
+
"loss": 0.3453,
|
| 292 |
+
"step": 370
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.2218649517684887,
|
| 296 |
+
"grad_norm": 0.10588031262159348,
|
| 297 |
+
"learning_rate": 4.351572264645366e-05,
|
| 298 |
+
"loss": 0.3297,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.2540192926045015,
|
| 303 |
+
"grad_norm": 0.1992698311805725,
|
| 304 |
+
"learning_rate": 4.3168077211072263e-05,
|
| 305 |
+
"loss": 0.3453,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.2861736334405145,
|
| 310 |
+
"grad_norm": 0.40842464566230774,
|
| 311 |
+
"learning_rate": 4.281282191348289e-05,
|
| 312 |
+
"loss": 0.34,
|
| 313 |
+
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.2861736334405145,
|
| 317 |
+
"eval_loss": 0.32504987716674805,
|
| 318 |
+
"eval_runtime": 2.9329,
|
| 319 |
+
"eval_samples_per_second": 44.666,
|
| 320 |
+
"eval_steps_per_second": 5.796,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.3183279742765273,
|
| 325 |
+
"grad_norm": 0.34837374091148376,
|
| 326 |
+
"learning_rate": 4.245010555555554e-05,
|
| 327 |
+
"loss": 0.3324,
|
| 328 |
+
"step": 410
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.3504823151125402,
|
| 332 |
+
"grad_norm": 0.16926288604736328,
|
| 333 |
+
"learning_rate": 4.2080080064292304e-05,
|
| 334 |
+
"loss": 0.3564,
|
| 335 |
+
"step": 420
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.382636655948553,
|
| 339 |
+
"grad_norm": 0.2140832394361496,
|
| 340 |
+
"learning_rate": 4.1702900428191374e-05,
|
| 341 |
+
"loss": 0.3105,
|
| 342 |
+
"step": 430
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.414790996784566,
|
| 346 |
+
"grad_norm": 1.07697594165802,
|
| 347 |
+
"learning_rate": 4.131872463232872e-05,
|
| 348 |
+
"loss": 0.2817,
|
| 349 |
+
"step": 440
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.4469453376205788,
|
| 353 |
+
"grad_norm": 0.19250230491161346,
|
| 354 |
+
"learning_rate": 4.092771359218461e-05,
|
| 355 |
+
"loss": 0.3865,
|
| 356 |
+
"step": 450
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.4790996784565915,
|
| 360 |
+
"grad_norm": 1.0127387046813965,
|
| 361 |
+
"learning_rate": 4.053003108624276e-05,
|
| 362 |
+
"loss": 0.3358,
|
| 363 |
+
"step": 460
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.5112540192926045,
|
| 367 |
+
"grad_norm": 0.3083811402320862,
|
| 368 |
+
"learning_rate": 4.0125843687390166e-05,
|
| 369 |
+
"loss": 0.3586,
|
| 370 |
+
"step": 470
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.5434083601286175,
|
| 374 |
+
"grad_norm": 0.6321075558662415,
|
| 375 |
+
"learning_rate": 3.9715320693146655e-05,
|
| 376 |
+
"loss": 0.3285,
|
| 377 |
+
"step": 480
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.5755627009646302,
|
| 381 |
+
"grad_norm": 0.1519564539194107,
|
| 382 |
+
"learning_rate": 3.9298634054753026e-05,
|
| 383 |
+
"loss": 0.3437,
|
| 384 |
+
"step": 490
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.607717041800643,
|
| 388 |
+
"grad_norm": 0.1895354837179184,
|
| 389 |
+
"learning_rate": 3.887595830514775e-05,
|
| 390 |
+
"loss": 0.3221,
|
| 391 |
+
"step": 500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.607717041800643,
|
| 395 |
+
"eval_loss": 0.31748995184898376,
|
| 396 |
+
"eval_runtime": 2.9296,
|
| 397 |
+
"eval_samples_per_second": 44.716,
|
| 398 |
+
"eval_steps_per_second": 5.803,
|
| 399 |
+
"step": 500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.639871382636656,
|
| 403 |
+
"grad_norm": 0.10975853353738785,
|
| 404 |
+
"learning_rate": 3.844747048586228e-05,
|
| 405 |
+
"loss": 0.3011,
|
| 406 |
+
"step": 510
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.6720257234726688,
|
| 410 |
+
"grad_norm": 0.6922447681427002,
|
| 411 |
+
"learning_rate": 3.801335007286564e-05,
|
| 412 |
+
"loss": 0.3461,
|
| 413 |
+
"step": 520
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.7041800643086815,
|
| 417 |
+
"grad_norm": 0.40238264203071594,
|
| 418 |
+
"learning_rate": 3.757377890138927e-05,
|
| 419 |
+
"loss": 0.3477,
|
| 420 |
+
"step": 530
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.7363344051446945,
|
| 424 |
+
"grad_norm": 0.5762842297554016,
|
| 425 |
+
"learning_rate": 3.712894108976372e-05,
|
| 426 |
+
"loss": 0.3507,
|
| 427 |
+
"step": 540
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.7684887459807075,
|
| 431 |
+
"grad_norm": 0.5789851546287537,
|
| 432 |
+
"learning_rate": 3.667902296229905e-05,
|
| 433 |
+
"loss": 0.3327,
|
| 434 |
+
"step": 550
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.8006430868167203,
|
| 438 |
+
"grad_norm": 1.1416003704071045,
|
| 439 |
+
"learning_rate": 3.622421297124122e-05,
|
| 440 |
+
"loss": 0.3312,
|
| 441 |
+
"step": 560
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.832797427652733,
|
| 445 |
+
"grad_norm": 0.2402690201997757,
|
| 446 |
+
"learning_rate": 3.576470161783712e-05,
|
| 447 |
+
"loss": 0.3659,
|
| 448 |
+
"step": 570
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.864951768488746,
|
| 452 |
+
"grad_norm": 0.17154522240161896,
|
| 453 |
+
"learning_rate": 3.5300681372541476e-05,
|
| 454 |
+
"loss": 0.3347,
|
| 455 |
+
"step": 580
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.897106109324759,
|
| 459 |
+
"grad_norm": 0.14049768447875977,
|
| 460 |
+
"learning_rate": 3.483234659439889e-05,
|
| 461 |
+
"loss": 0.3146,
|
| 462 |
+
"step": 590
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.9292604501607717,
|
| 466 |
+
"grad_norm": 0.23624245822429657,
|
| 467 |
+
"learning_rate": 3.435989344963471e-05,
|
| 468 |
+
"loss": 0.3193,
|
| 469 |
+
"step": 600
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.9292604501607717,
|
| 473 |
+
"eval_loss": 0.3193986415863037,
|
| 474 |
+
"eval_runtime": 2.9308,
|
| 475 |
+
"eval_samples_per_second": 44.698,
|
| 476 |
+
"eval_steps_per_second": 5.801,
|
| 477 |
+
"step": 600
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.9614147909967845,
|
| 481 |
+
"grad_norm": 0.11554815620183945,
|
| 482 |
+
"learning_rate": 3.3883519829489154e-05,
|
| 483 |
+
"loss": 0.3494,
|
| 484 |
+
"step": 610
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.9935691318327975,
|
| 488 |
+
"grad_norm": 0.15566588938236237,
|
| 489 |
+
"learning_rate": 3.3403425267328715e-05,
|
| 490 |
+
"loss": 0.2765,
|
| 491 |
+
"step": 620
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.0257234726688105,
|
| 495 |
+
"grad_norm": 0.10102688521146774,
|
| 496 |
+
"learning_rate": 3.2919810855069864e-05,
|
| 497 |
+
"loss": 0.327,
|
| 498 |
+
"step": 630
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.057877813504823,
|
| 502 |
+
"grad_norm": 0.26385530829429626,
|
| 503 |
+
"learning_rate": 3.243287915894987e-05,
|
| 504 |
+
"loss": 0.362,
|
| 505 |
+
"step": 640
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.090032154340836,
|
| 509 |
+
"grad_norm": 0.14168129861354828,
|
| 510 |
+
"learning_rate": 3.1942834134680124e-05,
|
| 511 |
+
"loss": 0.3393,
|
| 512 |
+
"step": 650
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.122186495176849,
|
| 516 |
+
"grad_norm": 0.10720091313123703,
|
| 517 |
+
"learning_rate": 3.144988104201745e-05,
|
| 518 |
+
"loss": 0.3322,
|
| 519 |
+
"step": 660
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.154340836012862,
|
| 523 |
+
"grad_norm": 0.12918303906917572,
|
| 524 |
+
"learning_rate": 3.095422635878923e-05,
|
| 525 |
+
"loss": 0.3191,
|
| 526 |
+
"step": 670
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.1864951768488745,
|
| 530 |
+
"grad_norm": 0.13608509302139282,
|
| 531 |
+
"learning_rate": 3.045607769440829e-05,
|
| 532 |
+
"loss": 0.3311,
|
| 533 |
+
"step": 680
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.2186495176848875,
|
| 537 |
+
"grad_norm": 0.2435235232114792,
|
| 538 |
+
"learning_rate": 2.9955643702913865e-05,
|
| 539 |
+
"loss": 0.3412,
|
| 540 |
+
"step": 690
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.2508038585209005,
|
| 544 |
+
"grad_norm": 0.4761883616447449,
|
| 545 |
+
"learning_rate": 2.9453133995574955e-05,
|
| 546 |
+
"loss": 0.339,
|
| 547 |
+
"step": 700
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 2.2508038585209005,
|
| 551 |
+
"eval_loss": 0.32114845514297485,
|
| 552 |
+
"eval_runtime": 2.9341,
|
| 553 |
+
"eval_samples_per_second": 44.647,
|
| 554 |
+
"eval_steps_per_second": 5.794,
|
| 555 |
+
"step": 700
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.282958199356913,
|
| 559 |
+
"grad_norm": 0.47587987780570984,
|
| 560 |
+
"learning_rate": 2.8948759053092754e-05,
|
| 561 |
+
"loss": 0.3128,
|
| 562 |
+
"step": 710
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.315112540192926,
|
| 566 |
+
"grad_norm": 0.11377859860658646,
|
| 567 |
+
"learning_rate": 2.844273013743896e-05,
|
| 568 |
+
"loss": 0.3448,
|
| 569 |
+
"step": 720
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.347266881028939,
|
| 573 |
+
"grad_norm": 0.7121096253395081,
|
| 574 |
+
"learning_rate": 2.7935259203366777e-05,
|
| 575 |
+
"loss": 0.3295,
|
| 576 |
+
"step": 730
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.379421221864952,
|
| 580 |
+
"grad_norm": 0.6000668406486511,
|
| 581 |
+
"learning_rate": 2.7426558809631748e-05,
|
| 582 |
+
"loss": 0.3249,
|
| 583 |
+
"step": 740
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.4115755627009645,
|
| 587 |
+
"grad_norm": 0.14565663039684296,
|
| 588 |
+
"learning_rate": 2.691684202995966e-05,
|
| 589 |
+
"loss": 0.3213,
|
| 590 |
+
"step": 750
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.4437299035369775,
|
| 594 |
+
"grad_norm": 0.12155289202928543,
|
| 595 |
+
"learning_rate": 2.6406322363798657e-05,
|
| 596 |
+
"loss": 0.3157,
|
| 597 |
+
"step": 760
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.4758842443729905,
|
| 601 |
+
"grad_norm": 1.0030161142349243,
|
| 602 |
+
"learning_rate": 2.589521364689308e-05,
|
| 603 |
+
"loss": 0.3537,
|
| 604 |
+
"step": 770
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.508038585209003,
|
| 608 |
+
"grad_norm": 0.19715431332588196,
|
| 609 |
+
"learning_rate": 2.5383729961716483e-05,
|
| 610 |
+
"loss": 0.3344,
|
| 611 |
+
"step": 780
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.540192926045016,
|
| 615 |
+
"grad_norm": 0.15441320836544037,
|
| 616 |
+
"learning_rate": 2.487208554780125e-05,
|
| 617 |
+
"loss": 0.3398,
|
| 618 |
+
"step": 790
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.572347266881029,
|
| 622 |
+
"grad_norm": 0.22851267457008362,
|
| 623 |
+
"learning_rate": 2.4360494712002423e-05,
|
| 624 |
+
"loss": 0.3347,
|
| 625 |
+
"step": 800
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.572347266881029,
|
| 629 |
+
"eval_loss": 0.3262169659137726,
|
| 630 |
+
"eval_runtime": 2.9319,
|
| 631 |
+
"eval_samples_per_second": 44.681,
|
| 632 |
+
"eval_steps_per_second": 5.798,
|
| 633 |
+
"step": 800
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.572347266881029,
|
| 637 |
+
"step": 800,
|
| 638 |
+
"total_flos": 1.4161342881595392e+17,
|
| 639 |
+
"train_loss": 0.5724774128198624,
|
| 640 |
+
"train_runtime": 490.2786,
|
| 641 |
+
"train_samples_per_second": 25.302,
|
| 642 |
+
"train_steps_per_second": 3.172
|
| 643 |
+
}
|
| 644 |
+
],
|
| 645 |
+
"logging_steps": 10,
|
| 646 |
+
"max_steps": 1555,
|
| 647 |
+
"num_input_tokens_seen": 0,
|
| 648 |
+
"num_train_epochs": 5,
|
| 649 |
+
"save_steps": 100,
|
| 650 |
+
"total_flos": 1.4161342881595392e+17,
|
| 651 |
+
"train_batch_size": 4,
|
| 652 |
+
"trial_name": null,
|
| 653 |
+
"trial_params": null
|
| 654 |
+
}
|
llama2_13b_peft/play_dialog_same_or_different/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd8f472354811e14472287f3112efe50d2e4c9ca31cc439047b7e79f5de56f64
|
| 3 |
+
size 5240
|
llama2_13b_peft/play_dialog_same_or_different/training_eval_loss.png
ADDED
|
llama2_13b_peft/play_dialog_same_or_different/training_loss.png
ADDED
|
llama2_13b_peft/question_selection/README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: /data1/model/llama2/meta-llama/Llama2-13b
|
| 9 |
+
model-index:
|
| 10 |
+
- name: question_selection_no_sys
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# question_selection_no_sys
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the question_selection_no_sys dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0145
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0005
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 3
|
| 46 |
+
- total_train_batch_size: 24
|
| 47 |
+
- total_eval_batch_size: 24
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_steps: 20
|
| 51 |
+
- num_epochs: 10.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 0.013 | 2.22 | 100 | 0.0138 |
|
| 58 |
+
| 0.0034 | 4.44 | 200 | 0.0183 |
|
| 59 |
+
| 0.0001 | 6.67 | 300 | 0.0147 |
|
| 60 |
+
| 0.0 | 8.89 | 400 | 0.0143 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.9.0
|
| 66 |
+
- Transformers 4.38.2
|
| 67 |
+
- Pytorch 2.2.1
|
| 68 |
+
- Datasets 2.18.0
|
| 69 |
+
- Tokenizers 0.15.2
|
llama2_13b_peft/question_selection/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.0,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 8,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"q_proj",
|
| 23 |
+
"v_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"up_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"use_dora": false,
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
llama2_13b_peft/question_selection/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14b62eee50bb68fb7f84fecf1df8e492a6fa0ce84af109e4a47f551691f19426
|
| 3 |
+
size 125248064
|
llama2_13b_peft/question_selection/all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 0.014549500308930874,
|
| 4 |
+
"eval_runtime": 4.8285,
|
| 5 |
+
"eval_samples_per_second": 39.349,
|
| 6 |
+
"eval_steps_per_second": 1.657,
|
| 7 |
+
"train_loss": 0.025018121934683425,
|
| 8 |
+
"train_runtime": 909.2296,
|
| 9 |
+
"train_samples_per_second": 11.834,
|
| 10 |
+
"train_steps_per_second": 0.495
|
| 11 |
+
}
|
llama2_13b_peft/question_selection/eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 0.014549500308930874,
|
| 4 |
+
"eval_runtime": 4.8285,
|
| 5 |
+
"eval_samples_per_second": 39.349,
|
| 6 |
+
"eval_steps_per_second": 1.657
|
| 7 |
+
}
|
llama2_13b_peft/question_selection/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
llama2_13b_peft/question_selection/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
llama2_13b_peft/question_selection/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false
|
| 45 |
+
}
|
llama2_13b_peft/question_selection/train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.025018121934683425,
|
| 4 |
+
"train_runtime": 909.2296,
|
| 5 |
+
"train_samples_per_second": 11.834,
|
| 6 |
+
"train_steps_per_second": 0.495
|
| 7 |
+
}
|
llama2_13b_peft/question_selection/trainer_log.jsonl
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 450, "loss": 0.7467, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025, "epoch": 0.22, "percentage": 2.22, "elapsed_time": "0:00:20", "remaining_time": "0:14:55"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 450, "loss": 0.0676, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005, "epoch": 0.44, "percentage": 4.44, "elapsed_time": "0:00:42", "remaining_time": "0:15:05"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 450, "loss": 0.0669, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004993330709158879, "epoch": 0.67, "percentage": 6.67, "elapsed_time": "0:01:00", "remaining_time": "0:14:05"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 450, "loss": 0.0401, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004973358420187776, "epoch": 0.89, "percentage": 8.89, "elapsed_time": "0:01:20", "remaining_time": "0:13:44"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 450, "loss": 0.0267, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004940189693889818, "epoch": 1.11, "percentage": 11.11, "elapsed_time": "0:01:40", "remaining_time": "0:13:26"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 450, "loss": 0.0172, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004894001499771015, "epoch": 1.33, "percentage": 13.33, "elapsed_time": "0:02:00", "remaining_time": "0:13:02"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 450, "loss": 0.0141, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00048350402718313703, "epoch": 1.56, "percentage": 15.56, "elapsed_time": "0:02:18", "remaining_time": "0:12:29"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 450, "loss": 0.0225, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004763620593732867, "epoch": 1.78, "percentage": 17.78, "elapsed_time": "0:02:37", "remaining_time": "0:12:06"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 450, "loss": 0.0182, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00046801235203595195, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:02:57", "remaining_time": "0:11:49"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 450, "loss": 0.013, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004584994544724695, "epoch": 2.22, "percentage": 22.22, "elapsed_time": "0:03:17", "remaining_time": "0:11:31"}
|
| 11 |
+
{"current_steps": 100, "total_steps": 450, "loss": null, "eval_loss": 0.013783249072730541, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.22, "percentage": 22.22, "elapsed_time": "0:03:17", "remaining_time": "0:11:31"}
|
| 12 |
+
{"current_steps": 110, "total_steps": 450, "loss": 0.0078, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00044787412210731353, "epoch": 2.44, "percentage": 24.44, "elapsed_time": "0:03:42", "remaining_time": "0:11:28"}
|
| 13 |
+
{"current_steps": 120, "total_steps": 450, "loss": 0.0104, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00043619304568594545, "epoch": 2.67, "percentage": 26.67, "elapsed_time": "0:04:01", "remaining_time": "0:11:05"}
|
| 14 |
+
{"current_steps": 130, "total_steps": 450, "loss": 0.0191, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004235185488051585, "epoch": 2.89, "percentage": 28.89, "elapsed_time": "0:04:20", "remaining_time": "0:10:41"}
|
| 15 |
+
{"current_steps": 140, "total_steps": 450, "loss": 0.0065, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004099182553897228, "epoch": 3.11, "percentage": 31.11, "elapsed_time": "0:04:38", "remaining_time": "0:10:16"}
|
| 16 |
+
{"current_steps": 150, "total_steps": 450, "loss": 0.0034, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00039546472888948826, "epoch": 3.33, "percentage": 33.33, "elapsed_time": "0:04:57", "remaining_time": "0:09:54"}
|
| 17 |
+
{"current_steps": 160, "total_steps": 450, "loss": 0.007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003802350851219826, "epoch": 3.56, "percentage": 35.56, "elapsed_time": "0:05:20", "remaining_time": "0:09:40"}
|
| 18 |
+
{"current_steps": 170, "total_steps": 450, "loss": 0.0058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00036431058082615964, "epoch": 3.78, "percentage": 37.78, "elapsed_time": "0:05:38", "remaining_time": "0:09:18"}
|
| 19 |
+
{"current_steps": 180, "total_steps": 450, "loss": 0.0039, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00034777618012253895, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "0:05:57", "remaining_time": "0:08:56"}
|
| 20 |
+
{"current_steps": 190, "total_steps": 450, "loss": 0.0035, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00033072010119286155, "epoch": 4.22, "percentage": 42.22, "elapsed_time": "0:06:16", "remaining_time": "0:08:35"}
|
| 21 |
+
{"current_steps": 200, "total_steps": 450, "loss": 0.0034, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003132333455979202, "epoch": 4.44, "percentage": 44.44, "elapsed_time": "0:06:37", "remaining_time": "0:08:17"}
|
| 22 |
+
{"current_steps": 200, "total_steps": 450, "loss": null, "eval_loss": 0.01827273517847061, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.44, "percentage": 44.44, "elapsed_time": "0:06:37", "remaining_time": "0:08:17"}
|
| 23 |
+
{"current_steps": 210, "total_steps": 450, "loss": 0.0043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002954092127448591, "epoch": 4.67, "percentage": 46.67, "elapsed_time": "0:07:02", "remaining_time": "0:08:03"}
|
| 24 |
+
{"current_steps": 220, "total_steps": 450, "loss": 0.0033, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00027734280209446867, "epoch": 4.89, "percentage": 48.89, "elapsed_time": "0:07:22", "remaining_time": "0:07:42"}
|
| 25 |
+
{"current_steps": 230, "total_steps": 450, "loss": 0.0051, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025913050576441477, "epoch": 5.11, "percentage": 51.11, "elapsed_time": "0:07:40", "remaining_time": "0:07:20"}
|
| 26 |
+
{"current_steps": 240, "total_steps": 450, "loss": 0.0011, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00024086949423558527, "epoch": 5.33, "percentage": 53.33, "elapsed_time": "0:07:59", "remaining_time": "0:06:59"}
|
| 27 |
+
{"current_steps": 250, "total_steps": 450, "loss": 0.0032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00022265719790553147, "epoch": 5.56, "percentage": 55.56, "elapsed_time": "0:08:20", "remaining_time": "0:06:40"}
|
| 28 |
+
{"current_steps": 260, "total_steps": 450, "loss": 0.0016, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002045907872551409, "epoch": 5.78, "percentage": 57.78, "elapsed_time": "0:08:41", "remaining_time": "0:06:20"}
|
| 29 |
+
{"current_steps": 270, "total_steps": 450, "loss": 0.0008, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001867666544020798, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "0:09:00", "remaining_time": "0:06:00"}
|
| 30 |
+
{"current_steps": 280, "total_steps": 450, "loss": 0.0008, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016927989880713852, "epoch": 6.22, "percentage": 62.22, "elapsed_time": "0:09:22", "remaining_time": "0:05:41"}
|
| 31 |
+
{"current_steps": 290, "total_steps": 450, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015222381987746103, "epoch": 6.44, "percentage": 64.44, "elapsed_time": "0:09:41", "remaining_time": "0:05:20"}
|
| 32 |
+
{"current_steps": 300, "total_steps": 450, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013568941917384037, "epoch": 6.67, "percentage": 66.67, "elapsed_time": "0:09:58", "remaining_time": "0:04:59"}
|
| 33 |
+
{"current_steps": 300, "total_steps": 450, "loss": null, "eval_loss": 0.01472838968038559, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 6.67, "percentage": 66.67, "elapsed_time": "0:09:58", "remaining_time": "0:04:59"}
|
| 34 |
+
{"current_steps": 310, "total_steps": 450, "loss": 0.0008, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011976491487801746, "epoch": 6.89, "percentage": 68.89, "elapsed_time": "0:10:22", "remaining_time": "0:04:41"}
|
| 35 |
+
{"current_steps": 320, "total_steps": 450, "loss": 0.0002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010453527111051184, "epoch": 7.11, "percentage": 71.11, "elapsed_time": "0:10:42", "remaining_time": "0:04:20"}
|
| 36 |
+
{"current_steps": 330, "total_steps": 450, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.008174461027724e-05, "epoch": 7.33, "percentage": 73.33, "elapsed_time": "0:11:02", "remaining_time": "0:04:00"}
|
| 37 |
+
{"current_steps": 340, "total_steps": 450, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.648145119484151e-05, "epoch": 7.56, "percentage": 75.56, "elapsed_time": "0:11:22", "remaining_time": "0:03:40"}
|
| 38 |
+
{"current_steps": 350, "total_steps": 450, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.380695431405453e-05, "epoch": 7.78, "percentage": 77.78, "elapsed_time": "0:11:40", "remaining_time": "0:03:20"}
|
| 39 |
+
{"current_steps": 360, "total_steps": 450, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.21258778926865e-05, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "0:12:01", "remaining_time": "0:03:00"}
|
| 40 |
+
{"current_steps": 370, "total_steps": 450, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.150054552753055e-05, "epoch": 8.22, "percentage": 82.22, "elapsed_time": "0:12:19", "remaining_time": "0:02:39"}
|
| 41 |
+
{"current_steps": 380, "total_steps": 450, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.198764796404807e-05, "epoch": 8.44, "percentage": 84.44, "elapsed_time": "0:12:39", "remaining_time": "0:02:19"}
|
| 42 |
+
{"current_steps": 390, "total_steps": 450, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3637940626713344e-05, "epoch": 8.67, "percentage": 86.67, "elapsed_time": "0:13:00", "remaining_time": "0:02:00"}
|
| 43 |
+
{"current_steps": 400, "total_steps": 450, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.649597281686302e-05, "epoch": 8.89, "percentage": 88.89, "elapsed_time": "0:13:19", "remaining_time": "0:01:39"}
|
| 44 |
+
{"current_steps": 400, "total_steps": 450, "loss": null, "eval_loss": 0.014345706440508366, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 8.89, "percentage": 88.89, "elapsed_time": "0:13:19", "remaining_time": "0:01:39"}
|
| 45 |
+
{"current_steps": 410, "total_steps": 450, "loss": 0.0001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0599850022898538e-05, "epoch": 9.11, "percentage": 91.11, "elapsed_time": "0:13:44", "remaining_time": "0:01:20"}
|
| 46 |
+
{"current_steps": 420, "total_steps": 450, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.981030611018234e-06, "epoch": 9.33, "percentage": 93.33, "elapsed_time": "0:14:03", "remaining_time": "0:01:00"}
|
| 47 |
+
{"current_steps": 430, "total_steps": 450, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.664157981222437e-06, "epoch": 9.56, "percentage": 95.56, "elapsed_time": "0:14:23", "remaining_time": "0:00:40"}
|
| 48 |
+
{"current_steps": 440, "total_steps": 450, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.66929084112089e-07, "epoch": 9.78, "percentage": 97.78, "elapsed_time": "0:14:42", "remaining_time": "0:00:20"}
|
| 49 |
+
{"current_steps": 450, "total_steps": 450, "loss": 0.0, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:15:03", "remaining_time": "0:00:00"}
|
| 50 |
+
{"current_steps": 450, "total_steps": 450, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:15:03", "remaining_time": "0:00:00"}
|
| 51 |
+
{"current_steps": 8, "total_steps": 8, "loss": null, "eval_loss": 0.014549500308930874, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:15:08", "remaining_time": "0:00:00"}
|
llama2_13b_peft/question_selection/trainer_state.json
ADDED
|
@@ -0,0 +1,377 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 450,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.22,
|
| 13 |
+
"grad_norm": 0.2616782486438751,
|
| 14 |
+
"learning_rate": 0.00025,
|
| 15 |
+
"loss": 0.7467,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.44,
|
| 20 |
+
"grad_norm": 0.4230063855648041,
|
| 21 |
+
"learning_rate": 0.0005,
|
| 22 |
+
"loss": 0.0676,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.67,
|
| 27 |
+
"grad_norm": 0.4279615581035614,
|
| 28 |
+
"learning_rate": 0.0004993330709158879,
|
| 29 |
+
"loss": 0.0669,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.89,
|
| 34 |
+
"grad_norm": 0.26194414496421814,
|
| 35 |
+
"learning_rate": 0.0004973358420187776,
|
| 36 |
+
"loss": 0.0401,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.11,
|
| 41 |
+
"grad_norm": 0.18304042518138885,
|
| 42 |
+
"learning_rate": 0.0004940189693889818,
|
| 43 |
+
"loss": 0.0267,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.33,
|
| 48 |
+
"grad_norm": 0.15659470856189728,
|
| 49 |
+
"learning_rate": 0.0004894001499771015,
|
| 50 |
+
"loss": 0.0172,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.56,
|
| 55 |
+
"grad_norm": 0.8856974840164185,
|
| 56 |
+
"learning_rate": 0.00048350402718313703,
|
| 57 |
+
"loss": 0.0141,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.78,
|
| 62 |
+
"grad_norm": 0.2954822778701782,
|
| 63 |
+
"learning_rate": 0.0004763620593732867,
|
| 64 |
+
"loss": 0.0225,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.0,
|
| 69 |
+
"grad_norm": 0.36144667863845825,
|
| 70 |
+
"learning_rate": 0.00046801235203595195,
|
| 71 |
+
"loss": 0.0182,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.22,
|
| 76 |
+
"grad_norm": 0.20678772032260895,
|
| 77 |
+
"learning_rate": 0.0004584994544724695,
|
| 78 |
+
"loss": 0.013,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.22,
|
| 83 |
+
"eval_loss": 0.013783249072730541,
|
| 84 |
+
"eval_runtime": 4.8183,
|
| 85 |
+
"eval_samples_per_second": 39.433,
|
| 86 |
+
"eval_steps_per_second": 1.66,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.44,
|
| 91 |
+
"grad_norm": 0.3987113833427429,
|
| 92 |
+
"learning_rate": 0.00044787412210731353,
|
| 93 |
+
"loss": 0.0078,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 2.67,
|
| 98 |
+
"grad_norm": 0.23118920624256134,
|
| 99 |
+
"learning_rate": 0.00043619304568594545,
|
| 100 |
+
"loss": 0.0104,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.89,
|
| 105 |
+
"grad_norm": 0.1873694211244583,
|
| 106 |
+
"learning_rate": 0.0004235185488051585,
|
| 107 |
+
"loss": 0.0191,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.11,
|
| 112 |
+
"grad_norm": 0.03233395144343376,
|
| 113 |
+
"learning_rate": 0.0004099182553897228,
|
| 114 |
+
"loss": 0.0065,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 3.33,
|
| 119 |
+
"grad_norm": 0.5932971239089966,
|
| 120 |
+
"learning_rate": 0.00039546472888948826,
|
| 121 |
+
"loss": 0.0034,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.56,
|
| 126 |
+
"grad_norm": 0.13725461065769196,
|
| 127 |
+
"learning_rate": 0.0003802350851219826,
|
| 128 |
+
"loss": 0.007,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.78,
|
| 133 |
+
"grad_norm": 0.22745588421821594,
|
| 134 |
+
"learning_rate": 0.00036431058082615964,
|
| 135 |
+
"loss": 0.0058,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 4.0,
|
| 140 |
+
"grad_norm": 0.0794651210308075,
|
| 141 |
+
"learning_rate": 0.00034777618012253895,
|
| 142 |
+
"loss": 0.0039,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 4.22,
|
| 147 |
+
"grad_norm": 0.06090324744582176,
|
| 148 |
+
"learning_rate": 0.00033072010119286155,
|
| 149 |
+
"loss": 0.0035,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 4.44,
|
| 154 |
+
"grad_norm": 0.17350110411643982,
|
| 155 |
+
"learning_rate": 0.0003132333455979202,
|
| 156 |
+
"loss": 0.0034,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 4.44,
|
| 161 |
+
"eval_loss": 0.01827273517847061,
|
| 162 |
+
"eval_runtime": 4.8208,
|
| 163 |
+
"eval_samples_per_second": 39.413,
|
| 164 |
+
"eval_steps_per_second": 1.659,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 4.67,
|
| 169 |
+
"grad_norm": 0.0679766833782196,
|
| 170 |
+
"learning_rate": 0.0002954092127448591,
|
| 171 |
+
"loss": 0.0043,
|
| 172 |
+
"step": 210
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 4.89,
|
| 176 |
+
"grad_norm": 0.2287779450416565,
|
| 177 |
+
"learning_rate": 0.00027734280209446867,
|
| 178 |
+
"loss": 0.0033,
|
| 179 |
+
"step": 220
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 5.11,
|
| 183 |
+
"grad_norm": 0.022623347118496895,
|
| 184 |
+
"learning_rate": 0.00025913050576441477,
|
| 185 |
+
"loss": 0.0051,
|
| 186 |
+
"step": 230
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 5.33,
|
| 190 |
+
"grad_norm": 0.023388344794511795,
|
| 191 |
+
"learning_rate": 0.00024086949423558527,
|
| 192 |
+
"loss": 0.0011,
|
| 193 |
+
"step": 240
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 5.56,
|
| 197 |
+
"grad_norm": 0.06873177736997604,
|
| 198 |
+
"learning_rate": 0.00022265719790553147,
|
| 199 |
+
"loss": 0.0032,
|
| 200 |
+
"step": 250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 5.78,
|
| 204 |
+
"grad_norm": 0.00556823518127203,
|
| 205 |
+
"learning_rate": 0.0002045907872551409,
|
| 206 |
+
"loss": 0.0016,
|
| 207 |
+
"step": 260
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 6.0,
|
| 211 |
+
"grad_norm": 0.00377739779651165,
|
| 212 |
+
"learning_rate": 0.0001867666544020798,
|
| 213 |
+
"loss": 0.0008,
|
| 214 |
+
"step": 270
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 6.22,
|
| 218 |
+
"grad_norm": 0.017272206023335457,
|
| 219 |
+
"learning_rate": 0.00016927989880713852,
|
| 220 |
+
"loss": 0.0008,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 6.44,
|
| 225 |
+
"grad_norm": 0.028082353994250298,
|
| 226 |
+
"learning_rate": 0.00015222381987746103,
|
| 227 |
+
"loss": 0.0002,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 6.67,
|
| 232 |
+
"grad_norm": 0.0010064858943223953,
|
| 233 |
+
"learning_rate": 0.00013568941917384037,
|
| 234 |
+
"loss": 0.0001,
|
| 235 |
+
"step": 300
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 6.67,
|
| 239 |
+
"eval_loss": 0.01472838968038559,
|
| 240 |
+
"eval_runtime": 4.8243,
|
| 241 |
+
"eval_samples_per_second": 39.384,
|
| 242 |
+
"eval_steps_per_second": 1.658,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 6.89,
|
| 247 |
+
"grad_norm": 0.0007610166212543845,
|
| 248 |
+
"learning_rate": 0.00011976491487801746,
|
| 249 |
+
"loss": 0.0008,
|
| 250 |
+
"step": 310
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 7.11,
|
| 254 |
+
"grad_norm": 0.04695134982466698,
|
| 255 |
+
"learning_rate": 0.00010453527111051184,
|
| 256 |
+
"loss": 0.0002,
|
| 257 |
+
"step": 320
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 7.33,
|
| 261 |
+
"grad_norm": 0.0033624598290771246,
|
| 262 |
+
"learning_rate": 9.008174461027724e-05,
|
| 263 |
+
"loss": 0.0,
|
| 264 |
+
"step": 330
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 7.56,
|
| 268 |
+
"grad_norm": 0.003984487149864435,
|
| 269 |
+
"learning_rate": 7.648145119484151e-05,
|
| 270 |
+
"loss": 0.0001,
|
| 271 |
+
"step": 340
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 7.78,
|
| 275 |
+
"grad_norm": 0.002355258446186781,
|
| 276 |
+
"learning_rate": 6.380695431405453e-05,
|
| 277 |
+
"loss": 0.0,
|
| 278 |
+
"step": 350
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 8.0,
|
| 282 |
+
"grad_norm": 0.00041891244472935796,
|
| 283 |
+
"learning_rate": 5.21258778926865e-05,
|
| 284 |
+
"loss": 0.0,
|
| 285 |
+
"step": 360
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 8.22,
|
| 289 |
+
"grad_norm": 0.0004031055432278663,
|
| 290 |
+
"learning_rate": 4.150054552753055e-05,
|
| 291 |
+
"loss": 0.0,
|
| 292 |
+
"step": 370
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 8.44,
|
| 296 |
+
"grad_norm": 0.00040033855475485325,
|
| 297 |
+
"learning_rate": 3.198764796404807e-05,
|
| 298 |
+
"loss": 0.0,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 8.67,
|
| 303 |
+
"grad_norm": 0.0015161971095949411,
|
| 304 |
+
"learning_rate": 2.3637940626713344e-05,
|
| 305 |
+
"loss": 0.0,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 8.89,
|
| 310 |
+
"grad_norm": 0.0011603726306930184,
|
| 311 |
+
"learning_rate": 1.649597281686302e-05,
|
| 312 |
+
"loss": 0.0,
|
| 313 |
+
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 8.89,
|
| 317 |
+
"eval_loss": 0.014345706440508366,
|
| 318 |
+
"eval_runtime": 4.8186,
|
| 319 |
+
"eval_samples_per_second": 39.43,
|
| 320 |
+
"eval_steps_per_second": 1.66,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 9.11,
|
| 325 |
+
"grad_norm": 0.0003027151105925441,
|
| 326 |
+
"learning_rate": 1.0599850022898538e-05,
|
| 327 |
+
"loss": 0.0001,
|
| 328 |
+
"step": 410
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 9.33,
|
| 332 |
+
"grad_norm": 0.0009049432119354606,
|
| 333 |
+
"learning_rate": 5.981030611018234e-06,
|
| 334 |
+
"loss": 0.0,
|
| 335 |
+
"step": 420
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 9.56,
|
| 339 |
+
"grad_norm": 0.0018125231144949794,
|
| 340 |
+
"learning_rate": 2.664157981222437e-06,
|
| 341 |
+
"loss": 0.0,
|
| 342 |
+
"step": 430
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 9.78,
|
| 346 |
+
"grad_norm": 0.003249464090913534,
|
| 347 |
+
"learning_rate": 6.66929084112089e-07,
|
| 348 |
+
"loss": 0.0,
|
| 349 |
+
"step": 440
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 10.0,
|
| 353 |
+
"grad_norm": 0.0004782461328431964,
|
| 354 |
+
"learning_rate": 0.0,
|
| 355 |
+
"loss": 0.0,
|
| 356 |
+
"step": 450
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 10.0,
|
| 360 |
+
"step": 450,
|
| 361 |
+
"total_flos": 4.3483361730730394e+17,
|
| 362 |
+
"train_loss": 0.025018121934683425,
|
| 363 |
+
"train_runtime": 909.2296,
|
| 364 |
+
"train_samples_per_second": 11.834,
|
| 365 |
+
"train_steps_per_second": 0.495
|
| 366 |
+
}
|
| 367 |
+
],
|
| 368 |
+
"logging_steps": 10,
|
| 369 |
+
"max_steps": 450,
|
| 370 |
+
"num_input_tokens_seen": 0,
|
| 371 |
+
"num_train_epochs": 10,
|
| 372 |
+
"save_steps": 500,
|
| 373 |
+
"total_flos": 4.3483361730730394e+17,
|
| 374 |
+
"train_batch_size": 8,
|
| 375 |
+
"trial_name": null,
|
| 376 |
+
"trial_params": null
|
| 377 |
+
}
|
llama2_13b_peft/question_selection/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1534a1067a92ba562ea5440d758f3eb4b29d90267fe1882cd21507d9bbcec9e5
|
| 3 |
+
size 5112
|
llama2_13b_peft/question_selection/training_eval_loss.png
ADDED
|
llama2_13b_peft/question_selection/training_loss.png
ADDED
|
llama2_13b_peft/reasoning_about_colored_objects/README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: /data1/model/llama2/meta-llama/Llama2-13b
|
| 9 |
+
model-index:
|
| 10 |
+
- name: reasoning_about_colored_objects_no_sys
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# reasoning_about_colored_objects_no_sys
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the reasoning_about_colored_objects_no_sys dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0522
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_steps: 20
|
| 47 |
+
- num_epochs: 5.0
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 0.2126 | 0.2632 | 100 | 0.1725 |
|
| 54 |
+
| 0.1793 | 0.5263 | 200 | 0.1547 |
|
| 55 |
+
| 0.1496 | 0.7895 | 300 | 0.1156 |
|
| 56 |
+
| 0.2432 | 1.0526 | 400 | 0.0812 |
|
| 57 |
+
| 0.1287 | 1.3158 | 500 | 0.0522 |
|
| 58 |
+
| 0.1829 | 1.5789 | 600 | 0.1413 |
|
| 59 |
+
| 0.0235 | 1.8421 | 700 | 0.0713 |
|
| 60 |
+
| 0.1101 | 2.1053 | 800 | 0.0611 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.10.0
|
| 66 |
+
- Transformers 4.40.0
|
| 67 |
+
- Pytorch 2.2.1
|
| 68 |
+
- Datasets 2.18.0
|
| 69 |
+
- Tokenizers 0.19.1
|
llama2_13b_peft/reasoning_about_colored_objects/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
llama2_13b_peft/reasoning_about_colored_objects/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c19495b1207cd22a199f60666c7f5a7f69fecf07adfa400406e1ca671ecae0c4
|
| 3 |
+
size 125248064
|
llama2_13b_peft/reasoning_about_colored_objects/all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.1052631578947367,
|
| 3 |
+
"eval_loss": 0.05217451602220535,
|
| 4 |
+
"eval_runtime": 1.5829,
|
| 5 |
+
"eval_samples_per_second": 50.54,
|
| 6 |
+
"eval_steps_per_second": 12.635,
|
| 7 |
+
"total_flos": 2.241573610389504e+16,
|
| 8 |
+
"train_loss": 0.32420646863698493,
|
| 9 |
+
"train_runtime": 246.1313,
|
| 10 |
+
"train_samples_per_second": 30.878,
|
| 11 |
+
"train_steps_per_second": 7.719
|
| 12 |
+
}
|
llama2_13b_peft/reasoning_about_colored_objects/eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.1052631578947367,
|
| 3 |
+
"eval_loss": 0.05217451602220535,
|
| 4 |
+
"eval_runtime": 1.5829,
|
| 5 |
+
"eval_samples_per_second": 50.54,
|
| 6 |
+
"eval_steps_per_second": 12.635
|
| 7 |
+
}
|
llama2_13b_peft/reasoning_about_colored_objects/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
llama2_13b_peft/reasoning_about_colored_objects/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
llama2_13b_peft/reasoning_about_colored_objects/tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false
|
| 45 |
+
}
|