Upload 16 files
Browse files- README.md +61 -3
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- all_results.json +12 -0
- eval_results.json +7 -0
- merges.txt +0 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- train_results.json +8 -0
- trainer_log.jsonl +113 -0
- trainer_state.json +826 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,61 @@
|
|
| 1 |
-
---
|
| 2 |
-
license:
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- lora
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: Qwen2/Qwen2-7B-Instruct
|
| 9 |
+
model-index:
|
| 10 |
+
- name: sft_0622_policy2
|
| 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 |
+
# sft_0622_policy2
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-lora-06072000](https://huggingface.co//root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-lora-06072000) on the sft_data_3491 dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.8861
|
| 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: 0.0001
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 5.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.11.1
|
| 58 |
+
- Transformers 4.41.2
|
| 59 |
+
- Pytorch 2.1.2
|
| 60 |
+
- Datasets 2.19.2
|
| 61 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-lora-06072000",
|
| 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 |
+
"gate_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13569dac5b2628e6527a51321413e5afa127454efeb57c4f8bbfc1c7e38ad4db
|
| 3 |
+
size 80792096
|
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 0.8860704898834229,
|
| 4 |
+
"eval_runtime": 0.6946,
|
| 5 |
+
"eval_samples_per_second": 21.597,
|
| 6 |
+
"eval_steps_per_second": 21.597,
|
| 7 |
+
"total_flos": 8.831352737326694e+16,
|
| 8 |
+
"train_loss": 0.6794352424144745,
|
| 9 |
+
"train_runtime": 806.654,
|
| 10 |
+
"train_samples_per_second": 8.926,
|
| 11 |
+
"train_steps_per_second": 0.279
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 0.8860704898834229,
|
| 4 |
+
"eval_runtime": 0.6946,
|
| 5 |
+
"eval_samples_per_second": 21.597,
|
| 6 |
+
"eval_steps_per_second": 21.597
|
| 7 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|im_end|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|im_end|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 131072,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"padding_side": "right",
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 43 |
+
"unk_token": null
|
| 44 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 8.831352737326694e+16,
|
| 4 |
+
"train_loss": 0.6794352424144745,
|
| 5 |
+
"train_runtime": 806.654,
|
| 6 |
+
"train_samples_per_second": 8.926,
|
| 7 |
+
"train_steps_per_second": 0.279
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 2, "total_steps": 225, "loss": 0.9284, "learning_rate": 8.695652173913044e-06, "epoch": 0.044444444444444446, "percentage": 0.89, "elapsed_time": "0:00:07", "remaining_time": "0:13:41", "throughput": "0.00", "total_tokens": 0}
|
| 2 |
+
{"current_steps": 4, "total_steps": 225, "loss": 0.9365, "learning_rate": 1.739130434782609e-05, "epoch": 0.08888888888888889, "percentage": 1.78, "elapsed_time": "0:00:15", "remaining_time": "0:14:03", "throughput": "0.00", "total_tokens": 0}
|
| 3 |
+
{"current_steps": 6, "total_steps": 225, "loss": 0.9367, "learning_rate": 2.608695652173913e-05, "epoch": 0.13333333333333333, "percentage": 2.67, "elapsed_time": "0:00:22", "remaining_time": "0:13:31", "throughput": "0.00", "total_tokens": 0}
|
| 4 |
+
{"current_steps": 8, "total_steps": 225, "loss": 0.8894, "learning_rate": 3.478260869565218e-05, "epoch": 0.17777777777777778, "percentage": 3.56, "elapsed_time": "0:00:33", "remaining_time": "0:15:15", "throughput": "0.00", "total_tokens": 0}
|
| 5 |
+
{"current_steps": 10, "total_steps": 225, "loss": 0.9455, "learning_rate": 4.347826086956522e-05, "epoch": 0.2222222222222222, "percentage": 4.44, "elapsed_time": "0:00:42", "remaining_time": "0:15:21", "throughput": "0.00", "total_tokens": 0}
|
| 6 |
+
{"current_steps": 12, "total_steps": 225, "loss": 1.0121, "learning_rate": 5.217391304347826e-05, "epoch": 0.26666666666666666, "percentage": 5.33, "elapsed_time": "0:00:48", "remaining_time": "0:14:21", "throughput": "0.00", "total_tokens": 0}
|
| 7 |
+
{"current_steps": 14, "total_steps": 225, "loss": 0.8756, "learning_rate": 6.086956521739131e-05, "epoch": 0.3111111111111111, "percentage": 6.22, "elapsed_time": "0:00:55", "remaining_time": "0:13:58", "throughput": "0.00", "total_tokens": 0}
|
| 8 |
+
{"current_steps": 16, "total_steps": 225, "loss": 0.9091, "learning_rate": 6.956521739130436e-05, "epoch": 0.35555555555555557, "percentage": 7.11, "elapsed_time": "0:01:02", "remaining_time": "0:13:31", "throughput": "0.00", "total_tokens": 0}
|
| 9 |
+
{"current_steps": 18, "total_steps": 225, "loss": 0.9091, "learning_rate": 7.82608695652174e-05, "epoch": 0.4, "percentage": 8.0, "elapsed_time": "0:01:09", "remaining_time": "0:13:22", "throughput": "0.00", "total_tokens": 0}
|
| 10 |
+
{"current_steps": 20, "total_steps": 225, "loss": 0.8018, "learning_rate": 8.695652173913044e-05, "epoch": 0.4444444444444444, "percentage": 8.89, "elapsed_time": "0:01:17", "remaining_time": "0:13:12", "throughput": "0.00", "total_tokens": 0}
|
| 11 |
+
{"current_steps": 22, "total_steps": 225, "loss": 0.796, "learning_rate": 9.565217391304348e-05, "epoch": 0.4888888888888889, "percentage": 9.78, "elapsed_time": "0:01:24", "remaining_time": "0:12:58", "throughput": "0.00", "total_tokens": 0}
|
| 12 |
+
{"current_steps": 24, "total_steps": 225, "loss": 0.8837, "learning_rate": 9.999395316300748e-05, "epoch": 0.5333333333333333, "percentage": 10.67, "elapsed_time": "0:01:31", "remaining_time": "0:12:43", "throughput": "0.00", "total_tokens": 0}
|
| 13 |
+
{"current_steps": 26, "total_steps": 225, "loss": 0.8367, "learning_rate": 9.994558724213054e-05, "epoch": 0.5777777777777777, "percentage": 11.56, "elapsed_time": "0:01:37", "remaining_time": "0:12:28", "throughput": "0.00", "total_tokens": 0}
|
| 14 |
+
{"current_steps": 28, "total_steps": 225, "loss": 0.8764, "learning_rate": 9.984890219128146e-05, "epoch": 0.6222222222222222, "percentage": 12.44, "elapsed_time": "0:01:45", "remaining_time": "0:12:25", "throughput": "0.00", "total_tokens": 0}
|
| 15 |
+
{"current_steps": 30, "total_steps": 225, "loss": 0.8687, "learning_rate": 9.970399154700263e-05, "epoch": 0.6666666666666666, "percentage": 13.33, "elapsed_time": "0:01:52", "remaining_time": "0:12:08", "throughput": "0.00", "total_tokens": 0}
|
| 16 |
+
{"current_steps": 32, "total_steps": 225, "loss": 0.8371, "learning_rate": 9.951099550098349e-05, "epoch": 0.7111111111111111, "percentage": 14.22, "elapsed_time": "0:01:58", "remaining_time": "0:11:53", "throughput": "0.00", "total_tokens": 0}
|
| 17 |
+
{"current_steps": 34, "total_steps": 225, "loss": 0.8085, "learning_rate": 9.927010076443407e-05, "epoch": 0.7555555555555555, "percentage": 15.11, "elapsed_time": "0:02:05", "remaining_time": "0:11:45", "throughput": "0.00", "total_tokens": 0}
|
| 18 |
+
{"current_steps": 36, "total_steps": 225, "loss": 0.8812, "learning_rate": 9.898154038745408e-05, "epoch": 0.8, "percentage": 16.0, "elapsed_time": "0:02:12", "remaining_time": "0:11:33", "throughput": "0.00", "total_tokens": 0}
|
| 19 |
+
{"current_steps": 38, "total_steps": 225, "loss": 0.7953, "learning_rate": 9.864559353357187e-05, "epoch": 0.8444444444444444, "percentage": 16.89, "elapsed_time": "0:02:20", "remaining_time": "0:11:29", "throughput": "0.00", "total_tokens": 0}
|
| 20 |
+
{"current_steps": 40, "total_steps": 225, "loss": 0.7484, "learning_rate": 9.826258520967178e-05, "epoch": 0.8888888888888888, "percentage": 17.78, "elapsed_time": "0:02:27", "remaining_time": "0:11:22", "throughput": "0.00", "total_tokens": 0}
|
| 21 |
+
{"current_steps": 42, "total_steps": 225, "loss": 0.7931, "learning_rate": 9.783288595157098e-05, "epoch": 0.9333333333333333, "percentage": 18.67, "elapsed_time": "0:02:35", "remaining_time": "0:11:16", "throughput": "0.00", "total_tokens": 0}
|
| 22 |
+
{"current_steps": 44, "total_steps": 225, "loss": 0.8413, "learning_rate": 9.735691146555002e-05, "epoch": 0.9777777777777777, "percentage": 19.56, "elapsed_time": "0:02:41", "remaining_time": "0:11:04", "throughput": "0.00", "total_tokens": 0}
|
| 23 |
+
{"current_steps": 46, "total_steps": 225, "loss": 0.8391, "learning_rate": 9.683512222618377e-05, "epoch": 1.0222222222222221, "percentage": 20.44, "elapsed_time": "0:02:48", "remaining_time": "0:10:57", "throughput": "0.00", "total_tokens": 0}
|
| 24 |
+
{"current_steps": 48, "total_steps": 225, "loss": 0.7997, "learning_rate": 9.626802303086208e-05, "epoch": 1.0666666666666667, "percentage": 21.33, "elapsed_time": "0:02:55", "remaining_time": "0:10:48", "throughput": "0.00", "total_tokens": 0}
|
| 25 |
+
{"current_steps": 50, "total_steps": 225, "loss": 0.9146, "learning_rate": 9.565616251143094e-05, "epoch": 1.1111111111111112, "percentage": 22.22, "elapsed_time": "0:03:03", "remaining_time": "0:10:43", "throughput": "0.00", "total_tokens": 0}
|
| 26 |
+
{"current_steps": 52, "total_steps": 225, "loss": 0.7813, "learning_rate": 9.500013260342651e-05, "epoch": 1.1555555555555554, "percentage": 23.11, "elapsed_time": "0:03:11", "remaining_time": "0:10:36", "throughput": "0.00", "total_tokens": 0}
|
| 27 |
+
{"current_steps": 54, "total_steps": 225, "loss": 0.7282, "learning_rate": 9.430056797341574e-05, "epoch": 1.2, "percentage": 24.0, "elapsed_time": "0:03:17", "remaining_time": "0:10:25", "throughput": "0.00", "total_tokens": 0}
|
| 28 |
+
{"current_steps": 56, "total_steps": 225, "loss": 0.7598, "learning_rate": 9.355814540499752e-05, "epoch": 1.2444444444444445, "percentage": 24.89, "elapsed_time": "0:03:24", "remaining_time": "0:10:18", "throughput": "0.00", "total_tokens": 0}
|
| 29 |
+
{"current_steps": 58, "total_steps": 225, "loss": 0.7959, "learning_rate": 9.27735831440582e-05, "epoch": 1.2888888888888888, "percentage": 25.78, "elapsed_time": "0:03:32", "remaining_time": "0:10:10", "throughput": "0.00", "total_tokens": 0}
|
| 30 |
+
{"current_steps": 60, "total_steps": 225, "loss": 0.7853, "learning_rate": 9.194764020391506e-05, "epoch": 1.3333333333333333, "percentage": 26.67, "elapsed_time": "0:03:38", "remaining_time": "0:10:00", "throughput": "0.00", "total_tokens": 0}
|
| 31 |
+
{"current_steps": 62, "total_steps": 225, "loss": 0.7553, "learning_rate": 9.108111563102004e-05, "epoch": 1.3777777777777778, "percentage": 27.56, "elapsed_time": "0:03:46", "remaining_time": "0:09:55", "throughput": "0.00", "total_tokens": 0}
|
| 32 |
+
{"current_steps": 64, "total_steps": 225, "loss": 0.7809, "learning_rate": 9.017484773193378e-05, "epoch": 1.4222222222222223, "percentage": 28.44, "elapsed_time": "0:03:53", "remaining_time": "0:09:46", "throughput": "0.00", "total_tokens": 0}
|
| 33 |
+
{"current_steps": 66, "total_steps": 225, "loss": 0.7628, "learning_rate": 8.92297132623183e-05, "epoch": 1.4666666666666668, "percentage": 29.33, "elapsed_time": "0:03:59", "remaining_time": "0:09:36", "throughput": "0.00", "total_tokens": 0}
|
| 34 |
+
{"current_steps": 68, "total_steps": 225, "loss": 0.7763, "learning_rate": 8.824662657873239e-05, "epoch": 1.511111111111111, "percentage": 30.22, "elapsed_time": "0:04:05", "remaining_time": "0:09:27", "throughput": "0.00", "total_tokens": 0}
|
| 35 |
+
{"current_steps": 70, "total_steps": 225, "loss": 0.737, "learning_rate": 8.722653875405075e-05, "epoch": 1.5555555555555556, "percentage": 31.11, "elapsed_time": "0:04:13", "remaining_time": "0:09:21", "throughput": "0.00", "total_tokens": 0}
|
| 36 |
+
{"current_steps": 72, "total_steps": 225, "loss": 0.7879, "learning_rate": 8.617043665736249e-05, "epoch": 1.6, "percentage": 32.0, "elapsed_time": "0:04:20", "remaining_time": "0:09:13", "throughput": "0.00", "total_tokens": 0}
|
| 37 |
+
{"current_steps": 74, "total_steps": 225, "loss": 0.7707, "learning_rate": 8.507934199923884e-05, "epoch": 1.6444444444444444, "percentage": 32.89, "elapsed_time": "0:04:27", "remaining_time": "0:09:05", "throughput": "0.00", "total_tokens": 0}
|
| 38 |
+
{"current_steps": 76, "total_steps": 225, "loss": 0.727, "learning_rate": 8.39543103432943e-05, "epoch": 1.6888888888888889, "percentage": 33.78, "elapsed_time": "0:04:35", "remaining_time": "0:08:59", "throughput": "0.00", "total_tokens": 0}
|
| 39 |
+
{"current_steps": 78, "total_steps": 225, "loss": 0.7193, "learning_rate": 8.2796430084997e-05, "epoch": 1.7333333333333334, "percentage": 34.67, "elapsed_time": "0:04:42", "remaining_time": "0:08:52", "throughput": "0.00", "total_tokens": 0}
|
| 40 |
+
{"current_steps": 80, "total_steps": 225, "loss": 0.7573, "learning_rate": 8.160682139871633e-05, "epoch": 1.7777777777777777, "percentage": 35.56, "elapsed_time": "0:04:49", "remaining_time": "0:08:45", "throughput": "0.00", "total_tokens": 0}
|
| 41 |
+
{"current_steps": 82, "total_steps": 225, "loss": 0.7711, "learning_rate": 8.03866351540266e-05, "epoch": 1.8222222222222222, "percentage": 36.44, "elapsed_time": "0:04:57", "remaining_time": "0:08:38", "throughput": "0.00", "total_tokens": 0}
|
| 42 |
+
{"current_steps": 84, "total_steps": 225, "loss": 0.7741, "learning_rate": 7.913705180231505e-05, "epoch": 1.8666666666666667, "percentage": 37.33, "elapsed_time": "0:05:04", "remaining_time": "0:08:31", "throughput": "0.00", "total_tokens": 0}
|
| 43 |
+
{"current_steps": 86, "total_steps": 225, "loss": 0.812, "learning_rate": 7.785928023477142e-05, "epoch": 1.911111111111111, "percentage": 38.22, "elapsed_time": "0:05:10", "remaining_time": "0:08:21", "throughput": "0.00", "total_tokens": 0}
|
| 44 |
+
{"current_steps": 88, "total_steps": 225, "loss": 0.7561, "learning_rate": 7.655455661286376e-05, "epoch": 1.9555555555555557, "percentage": 39.11, "elapsed_time": "0:05:17", "remaining_time": "0:08:13", "throughput": "0.00", "total_tokens": 0}
|
| 45 |
+
{"current_steps": 90, "total_steps": 225, "loss": 0.7797, "learning_rate": 7.5224143172432e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:05:25", "remaining_time": "0:08:07", "throughput": "0.00", "total_tokens": 0}
|
| 46 |
+
{"current_steps": 92, "total_steps": 225, "loss": 0.7651, "learning_rate": 7.386932700255636e-05, "epoch": 2.0444444444444443, "percentage": 40.89, "elapsed_time": "0:05:32", "remaining_time": "0:08:00", "throughput": "0.00", "total_tokens": 0}
|
| 47 |
+
{"current_steps": 94, "total_steps": 225, "loss": 0.741, "learning_rate": 7.24914188003818e-05, "epoch": 2.088888888888889, "percentage": 41.78, "elapsed_time": "0:05:39", "remaining_time": "0:07:53", "throughput": "0.00", "total_tokens": 0}
|
| 48 |
+
{"current_steps": 96, "total_steps": 225, "loss": 0.695, "learning_rate": 7.109175160310312e-05, "epoch": 2.1333333333333333, "percentage": 42.67, "elapsed_time": "0:05:46", "remaining_time": "0:07:45", "throughput": "0.00", "total_tokens": 0}
|
| 49 |
+
{"current_steps": 98, "total_steps": 225, "loss": 0.7259, "learning_rate": 6.967167949833763e-05, "epoch": 2.1777777777777776, "percentage": 43.56, "elapsed_time": "0:05:52", "remaining_time": "0:07:36", "throughput": "0.00", "total_tokens": 0}
|
| 50 |
+
{"current_steps": 100, "total_steps": 225, "loss": 0.7574, "learning_rate": 6.823257631413276e-05, "epoch": 2.2222222222222223, "percentage": 44.44, "elapsed_time": "0:06:00", "remaining_time": "0:07:30", "throughput": "0.00", "total_tokens": 0}
|
| 51 |
+
{"current_steps": 102, "total_steps": 225, "loss": 0.6457, "learning_rate": 6.677583428987625e-05, "epoch": 2.2666666666666666, "percentage": 45.33, "elapsed_time": "0:06:07", "remaining_time": "0:07:23", "throughput": "0.00", "total_tokens": 0}
|
| 52 |
+
{"current_steps": 104, "total_steps": 225, "loss": 0.6498, "learning_rate": 6.530286272939437e-05, "epoch": 2.311111111111111, "percentage": 46.22, "elapsed_time": "0:06:14", "remaining_time": "0:07:15", "throughput": "0.00", "total_tokens": 0}
|
| 53 |
+
{"current_steps": 106, "total_steps": 225, "loss": 0.6389, "learning_rate": 6.381508663754153e-05, "epoch": 2.3555555555555556, "percentage": 47.11, "elapsed_time": "0:06:21", "remaining_time": "0:07:08", "throughput": "0.00", "total_tokens": 0}
|
| 54 |
+
{"current_steps": 108, "total_steps": 225, "loss": 0.7215, "learning_rate": 6.231394534160008e-05, "epoch": 2.4, "percentage": 48.0, "elapsed_time": "0:06:28", "remaining_time": "0:07:00", "throughput": "0.00", "total_tokens": 0}
|
| 55 |
+
{"current_steps": 110, "total_steps": 225, "loss": 0.7096, "learning_rate": 6.0800891098824186e-05, "epoch": 2.4444444444444446, "percentage": 48.89, "elapsed_time": "0:06:34", "remaining_time": "0:06:52", "throughput": "0.00", "total_tokens": 0}
|
| 56 |
+
{"current_steps": 112, "total_steps": 225, "loss": 0.6736, "learning_rate": 5.9277387691474676e-05, "epoch": 2.488888888888889, "percentage": 49.78, "elapsed_time": "0:06:42", "remaining_time": "0:06:46", "throughput": "0.00", "total_tokens": 0}
|
| 57 |
+
{"current_steps": 114, "total_steps": 225, "loss": 0.6875, "learning_rate": 5.774490901070424e-05, "epoch": 2.533333333333333, "percentage": 50.67, "elapsed_time": "0:06:49", "remaining_time": "0:06:39", "throughput": "0.00", "total_tokens": 0}
|
| 58 |
+
{"current_steps": 116, "total_steps": 225, "loss": 0.6023, "learning_rate": 5.620493763066297e-05, "epoch": 2.5777777777777775, "percentage": 51.56, "elapsed_time": "0:06:56", "remaining_time": "0:06:31", "throughput": "0.00", "total_tokens": 0}
|
| 59 |
+
{"current_steps": 118, "total_steps": 225, "loss": 0.6356, "learning_rate": 5.465896337420359e-05, "epoch": 2.6222222222222222, "percentage": 52.44, "elapsed_time": "0:07:03", "remaining_time": "0:06:24", "throughput": "0.00", "total_tokens": 0}
|
| 60 |
+
{"current_steps": 120, "total_steps": 225, "loss": 0.6939, "learning_rate": 5.3108481871574036e-05, "epoch": 2.6666666666666665, "percentage": 53.33, "elapsed_time": "0:07:10", "remaining_time": "0:06:16", "throughput": "0.00", "total_tokens": 0}
|
| 61 |
+
{"current_steps": 122, "total_steps": 225, "loss": 0.6981, "learning_rate": 5.155499311349185e-05, "epoch": 2.7111111111111112, "percentage": 54.22, "elapsed_time": "0:07:17", "remaining_time": "0:06:09", "throughput": "0.00", "total_tokens": 0}
|
| 62 |
+
{"current_steps": 124, "total_steps": 225, "loss": 0.6733, "learning_rate": 5e-05, "epoch": 2.7555555555555555, "percentage": 55.11, "elapsed_time": "0:07:23", "remaining_time": "0:06:01", "throughput": "0.00", "total_tokens": 0}
|
| 63 |
+
{"current_steps": 126, "total_steps": 225, "loss": 0.6851, "learning_rate": 4.844500688650816e-05, "epoch": 2.8, "percentage": 56.0, "elapsed_time": "0:07:30", "remaining_time": "0:05:53", "throughput": "0.00", "total_tokens": 0}
|
| 64 |
+
{"current_steps": 128, "total_steps": 225, "loss": 0.654, "learning_rate": 4.6891518128425976e-05, "epoch": 2.8444444444444446, "percentage": 56.89, "elapsed_time": "0:07:37", "remaining_time": "0:05:46", "throughput": "0.00", "total_tokens": 0}
|
| 65 |
+
{"current_steps": 130, "total_steps": 225, "loss": 0.6303, "learning_rate": 4.534103662579642e-05, "epoch": 2.888888888888889, "percentage": 57.78, "elapsed_time": "0:07:45", "remaining_time": "0:05:40", "throughput": "0.00", "total_tokens": 0}
|
| 66 |
+
{"current_steps": 132, "total_steps": 225, "loss": 0.5819, "learning_rate": 4.3795062369337034e-05, "epoch": 2.9333333333333336, "percentage": 58.67, "elapsed_time": "0:07:52", "remaining_time": "0:05:32", "throughput": "0.00", "total_tokens": 0}
|
| 67 |
+
{"current_steps": 134, "total_steps": 225, "loss": 0.6726, "learning_rate": 4.2255090989295764e-05, "epoch": 2.977777777777778, "percentage": 59.56, "elapsed_time": "0:07:59", "remaining_time": "0:05:25", "throughput": "0.00", "total_tokens": 0}
|
| 68 |
+
{"current_steps": 136, "total_steps": 225, "loss": 0.6621, "learning_rate": 4.0722612308525335e-05, "epoch": 3.022222222222222, "percentage": 60.44, "elapsed_time": "0:08:08", "remaining_time": "0:05:19", "throughput": "0.00", "total_tokens": 0}
|
| 69 |
+
{"current_steps": 138, "total_steps": 225, "loss": 0.5295, "learning_rate": 3.919910890117584e-05, "epoch": 3.066666666666667, "percentage": 61.33, "elapsed_time": "0:08:15", "remaining_time": "0:05:12", "throughput": "0.00", "total_tokens": 0}
|
| 70 |
+
{"current_steps": 140, "total_steps": 225, "loss": 0.5466, "learning_rate": 3.7686054658399935e-05, "epoch": 3.111111111111111, "percentage": 62.22, "elapsed_time": "0:08:22", "remaining_time": "0:05:05", "throughput": "0.00", "total_tokens": 0}
|
| 71 |
+
{"current_steps": 142, "total_steps": 225, "loss": 0.5419, "learning_rate": 3.618491336245849e-05, "epoch": 3.1555555555555554, "percentage": 63.11, "elapsed_time": "0:08:29", "remaining_time": "0:04:57", "throughput": "0.00", "total_tokens": 0}
|
| 72 |
+
{"current_steps": 144, "total_steps": 225, "loss": 0.6171, "learning_rate": 3.469713727060564e-05, "epoch": 3.2, "percentage": 64.0, "elapsed_time": "0:08:35", "remaining_time": "0:04:50", "throughput": "0.00", "total_tokens": 0}
|
| 73 |
+
{"current_steps": 146, "total_steps": 225, "loss": 0.5628, "learning_rate": 3.3224165710123756e-05, "epoch": 3.2444444444444445, "percentage": 64.89, "elapsed_time": "0:08:42", "remaining_time": "0:04:42", "throughput": "0.00", "total_tokens": 0}
|
| 74 |
+
{"current_steps": 148, "total_steps": 225, "loss": 0.5923, "learning_rate": 3.176742368586725e-05, "epoch": 3.2888888888888888, "percentage": 65.78, "elapsed_time": "0:08:49", "remaining_time": "0:04:35", "throughput": "0.00", "total_tokens": 0}
|
| 75 |
+
{"current_steps": 150, "total_steps": 225, "loss": 0.5308, "learning_rate": 3.032832050166239e-05, "epoch": 3.3333333333333335, "percentage": 66.67, "elapsed_time": "0:08:56", "remaining_time": "0:04:28", "throughput": "0.00", "total_tokens": 0}
|
| 76 |
+
{"current_steps": 152, "total_steps": 225, "loss": 0.6444, "learning_rate": 2.890824839689689e-05, "epoch": 3.3777777777777778, "percentage": 67.56, "elapsed_time": "0:09:03", "remaining_time": "0:04:20", "throughput": "0.00", "total_tokens": 0}
|
| 77 |
+
{"current_steps": 154, "total_steps": 225, "loss": 0.6573, "learning_rate": 2.750858119961821e-05, "epoch": 3.422222222222222, "percentage": 68.44, "elapsed_time": "0:09:09", "remaining_time": "0:04:13", "throughput": "0.00", "total_tokens": 0}
|
| 78 |
+
{"current_steps": 156, "total_steps": 225, "loss": 0.582, "learning_rate": 2.613067299744364e-05, "epoch": 3.466666666666667, "percentage": 69.33, "elapsed_time": "0:09:17", "remaining_time": "0:04:06", "throughput": "0.00", "total_tokens": 0}
|
| 79 |
+
{"current_steps": 158, "total_steps": 225, "loss": 0.6335, "learning_rate": 2.4775856827568016e-05, "epoch": 3.511111111111111, "percentage": 70.22, "elapsed_time": "0:09:24", "remaining_time": "0:03:59", "throughput": "0.00", "total_tokens": 0}
|
| 80 |
+
{"current_steps": 160, "total_steps": 225, "loss": 0.508, "learning_rate": 2.3445443387136244e-05, "epoch": 3.5555555555555554, "percentage": 71.11, "elapsed_time": "0:09:31", "remaining_time": "0:03:52", "throughput": "0.00", "total_tokens": 0}
|
| 81 |
+
{"current_steps": 162, "total_steps": 225, "loss": 0.5991, "learning_rate": 2.2140719765228584e-05, "epoch": 3.6, "percentage": 72.0, "elapsed_time": "0:09:38", "remaining_time": "0:03:45", "throughput": "0.00", "total_tokens": 0}
|
| 82 |
+
{"current_steps": 164, "total_steps": 225, "loss": 0.5808, "learning_rate": 2.0862948197684955e-05, "epoch": 3.6444444444444444, "percentage": 72.89, "elapsed_time": "0:09:46", "remaining_time": "0:03:38", "throughput": "0.00", "total_tokens": 0}
|
| 83 |
+
{"current_steps": 166, "total_steps": 225, "loss": 0.5703, "learning_rate": 1.961336484597343e-05, "epoch": 3.688888888888889, "percentage": 73.78, "elapsed_time": "0:09:53", "remaining_time": "0:03:30", "throughput": "0.00", "total_tokens": 0}
|
| 84 |
+
{"current_steps": 168, "total_steps": 225, "loss": 0.5002, "learning_rate": 1.8393178601283683e-05, "epoch": 3.7333333333333334, "percentage": 74.67, "elapsed_time": "0:09:59", "remaining_time": "0:03:23", "throughput": "0.00", "total_tokens": 0}
|
| 85 |
+
{"current_steps": 170, "total_steps": 225, "loss": 0.5269, "learning_rate": 1.7203569915003005e-05, "epoch": 3.7777777777777777, "percentage": 75.56, "elapsed_time": "0:10:06", "remaining_time": "0:03:16", "throughput": "0.00", "total_tokens": 0}
|
| 86 |
+
{"current_steps": 172, "total_steps": 225, "loss": 0.4902, "learning_rate": 1.6045689656705716e-05, "epoch": 3.822222222222222, "percentage": 76.44, "elapsed_time": "0:10:14", "remaining_time": "0:03:09", "throughput": "0.00", "total_tokens": 0}
|
| 87 |
+
{"current_steps": 174, "total_steps": 225, "loss": 0.6185, "learning_rate": 1.4920658000761174e-05, "epoch": 3.8666666666666667, "percentage": 77.33, "elapsed_time": "0:10:21", "remaining_time": "0:03:02", "throughput": "0.00", "total_tokens": 0}
|
| 88 |
+
{"current_steps": 176, "total_steps": 225, "loss": 0.537, "learning_rate": 1.3829563342637513e-05, "epoch": 3.911111111111111, "percentage": 78.22, "elapsed_time": "0:10:28", "remaining_time": "0:02:55", "throughput": "0.00", "total_tokens": 0}
|
| 89 |
+
{"current_steps": 178, "total_steps": 225, "loss": 0.5637, "learning_rate": 1.2773461245949247e-05, "epoch": 3.9555555555555557, "percentage": 79.11, "elapsed_time": "0:10:36", "remaining_time": "0:02:47", "throughput": "0.00", "total_tokens": 0}
|
| 90 |
+
{"current_steps": 180, "total_steps": 225, "loss": 0.5124, "learning_rate": 1.1753373421267621e-05, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:10:42", "remaining_time": "0:02:40", "throughput": "0.00", "total_tokens": 0}
|
| 91 |
+
{"current_steps": 182, "total_steps": 225, "loss": 0.5488, "learning_rate": 1.0770286737681701e-05, "epoch": 4.044444444444444, "percentage": 80.89, "elapsed_time": "0:10:51", "remaining_time": "0:02:33", "throughput": "0.00", "total_tokens": 0}
|
| 92 |
+
{"current_steps": 184, "total_steps": 225, "loss": 0.4998, "learning_rate": 9.825152268066213e-06, "epoch": 4.088888888888889, "percentage": 81.78, "elapsed_time": "0:11:01", "remaining_time": "0:02:27", "throughput": "0.00", "total_tokens": 0}
|
| 93 |
+
{"current_steps": 186, "total_steps": 225, "loss": 0.4892, "learning_rate": 8.91888436897997e-06, "epoch": 4.133333333333334, "percentage": 82.67, "elapsed_time": "0:11:09", "remaining_time": "0:02:20", "throughput": "0.00", "total_tokens": 0}
|
| 94 |
+
{"current_steps": 188, "total_steps": 225, "loss": 0.5365, "learning_rate": 8.052359796084951e-06, "epoch": 4.177777777777778, "percentage": 83.56, "elapsed_time": "0:11:16", "remaining_time": "0:02:13", "throughput": "0.00", "total_tokens": 0}
|
| 95 |
+
{"current_steps": 190, "total_steps": 225, "loss": 0.4963, "learning_rate": 7.226416855941814e-06, "epoch": 4.222222222222222, "percentage": 84.44, "elapsed_time": "0:11:22", "remaining_time": "0:02:05", "throughput": "0.00", "total_tokens": 0}
|
| 96 |
+
{"current_steps": 192, "total_steps": 225, "loss": 0.5367, "learning_rate": 6.441854595002477e-06, "epoch": 4.266666666666667, "percentage": 85.33, "elapsed_time": "0:11:28", "remaining_time": "0:01:58", "throughput": "0.00", "total_tokens": 0}
|
| 97 |
+
{"current_steps": 194, "total_steps": 225, "loss": 0.5051, "learning_rate": 5.699432026584267e-06, "epoch": 4.311111111111111, "percentage": 86.22, "elapsed_time": "0:11:35", "remaining_time": "0:01:51", "throughput": "0.00", "total_tokens": 0}
|
| 98 |
+
{"current_steps": 196, "total_steps": 225, "loss": 0.5326, "learning_rate": 4.999867396573499e-06, "epoch": 4.355555555555555, "percentage": 87.11, "elapsed_time": "0:11:42", "remaining_time": "0:01:43", "throughput": "0.00", "total_tokens": 0}
|
| 99 |
+
{"current_steps": 198, "total_steps": 225, "loss": 0.4549, "learning_rate": 4.343837488569058e-06, "epoch": 4.4, "percentage": 88.0, "elapsed_time": "0:11:51", "remaining_time": "0:01:37", "throughput": "0.00", "total_tokens": 0}
|
| 100 |
+
{"current_steps": 200, "total_steps": 225, "loss": 0.4968, "learning_rate": 3.731976969137929e-06, "epoch": 4.444444444444445, "percentage": 88.89, "elapsed_time": "0:11:57", "remaining_time": "0:01:29", "throughput": "0.00", "total_tokens": 0}
|
| 101 |
+
{"current_steps": 202, "total_steps": 225, "loss": 0.4623, "learning_rate": 3.1648777738162494e-06, "epoch": 4.488888888888889, "percentage": 89.78, "elapsed_time": "0:12:05", "remaining_time": "0:01:22", "throughput": "0.00", "total_tokens": 0}
|
| 102 |
+
{"current_steps": 204, "total_steps": 225, "loss": 0.4445, "learning_rate": 2.6430885344499946e-06, "epoch": 4.533333333333333, "percentage": 90.67, "elapsed_time": "0:12:13", "remaining_time": "0:01:15", "throughput": "0.00", "total_tokens": 0}
|
| 103 |
+
{"current_steps": 206, "total_steps": 225, "loss": 0.4678, "learning_rate": 2.1671140484290142e-06, "epoch": 4.5777777777777775, "percentage": 91.56, "elapsed_time": "0:12:20", "remaining_time": "0:01:08", "throughput": "0.00", "total_tokens": 0}
|
| 104 |
+
{"current_steps": 208, "total_steps": 225, "loss": 0.5377, "learning_rate": 1.7374147903282178e-06, "epoch": 4.622222222222222, "percentage": 92.44, "elapsed_time": "0:12:27", "remaining_time": "0:01:01", "throughput": "0.00", "total_tokens": 0}
|
| 105 |
+
{"current_steps": 210, "total_steps": 225, "loss": 0.5819, "learning_rate": 1.3544064664281265e-06, "epoch": 4.666666666666667, "percentage": 93.33, "elapsed_time": "0:12:33", "remaining_time": "0:00:53", "throughput": "0.00", "total_tokens": 0}
|
| 106 |
+
{"current_steps": 212, "total_steps": 225, "loss": 0.494, "learning_rate": 1.0184596125459135e-06, "epoch": 4.711111111111111, "percentage": 94.22, "elapsed_time": "0:12:41", "remaining_time": "0:00:46", "throughput": "0.00", "total_tokens": 0}
|
| 107 |
+
{"current_steps": 214, "total_steps": 225, "loss": 0.4983, "learning_rate": 7.29899235565934e-07, "epoch": 4.7555555555555555, "percentage": 95.11, "elapsed_time": "0:12:48", "remaining_time": "0:00:39", "throughput": "0.00", "total_tokens": 0}
|
| 108 |
+
{"current_steps": 216, "total_steps": 225, "loss": 0.5186, "learning_rate": 4.890044990165321e-07, "epoch": 4.8, "percentage": 96.0, "elapsed_time": "0:12:54", "remaining_time": "0:00:32", "throughput": "0.00", "total_tokens": 0}
|
| 109 |
+
{"current_steps": 218, "total_steps": 225, "loss": 0.5044, "learning_rate": 2.9600845299737056e-07, "epoch": 4.844444444444444, "percentage": 96.89, "elapsed_time": "0:13:01", "remaining_time": "0:00:25", "throughput": "0.00", "total_tokens": 0}
|
| 110 |
+
{"current_steps": 220, "total_steps": 225, "loss": 0.5062, "learning_rate": 1.5109780871853663e-07, "epoch": 4.888888888888889, "percentage": 97.78, "elapsed_time": "0:13:08", "remaining_time": "0:00:17", "throughput": "0.00", "total_tokens": 0}
|
| 111 |
+
{"current_steps": 222, "total_steps": 225, "loss": 0.5391, "learning_rate": 5.4412757869459763e-08, "epoch": 4.933333333333334, "percentage": 98.67, "elapsed_time": "0:13:15", "remaining_time": "0:00:10", "throughput": "0.00", "total_tokens": 0}
|
| 112 |
+
{"current_steps": 224, "total_steps": 225, "loss": 0.5243, "learning_rate": 6.04683699252373e-09, "epoch": 4.977777777777778, "percentage": 99.56, "elapsed_time": "0:13:23", "remaining_time": "0:00:03", "throughput": "0.00", "total_tokens": 0}
|
| 113 |
+
{"current_steps": 225, "total_steps": 225, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:13:26", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,826 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 225,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.044444444444444446,
|
| 13 |
+
"grad_norm": 0.17873810231685638,
|
| 14 |
+
"learning_rate": 8.695652173913044e-06,
|
| 15 |
+
"loss": 0.9284,
|
| 16 |
+
"step": 2
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08888888888888889,
|
| 20 |
+
"grad_norm": 0.1875726729631424,
|
| 21 |
+
"learning_rate": 1.739130434782609e-05,
|
| 22 |
+
"loss": 0.9365,
|
| 23 |
+
"step": 4
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.13333333333333333,
|
| 27 |
+
"grad_norm": 0.2115127593278885,
|
| 28 |
+
"learning_rate": 2.608695652173913e-05,
|
| 29 |
+
"loss": 0.9367,
|
| 30 |
+
"step": 6
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.17777777777777778,
|
| 34 |
+
"grad_norm": 0.2282930463552475,
|
| 35 |
+
"learning_rate": 3.478260869565218e-05,
|
| 36 |
+
"loss": 0.8894,
|
| 37 |
+
"step": 8
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2222222222222222,
|
| 41 |
+
"grad_norm": 0.2383526861667633,
|
| 42 |
+
"learning_rate": 4.347826086956522e-05,
|
| 43 |
+
"loss": 0.9455,
|
| 44 |
+
"step": 10
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.26666666666666666,
|
| 48 |
+
"grad_norm": 0.23653796315193176,
|
| 49 |
+
"learning_rate": 5.217391304347826e-05,
|
| 50 |
+
"loss": 1.0121,
|
| 51 |
+
"step": 12
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3111111111111111,
|
| 55 |
+
"grad_norm": 0.253218412399292,
|
| 56 |
+
"learning_rate": 6.086956521739131e-05,
|
| 57 |
+
"loss": 0.8756,
|
| 58 |
+
"step": 14
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.35555555555555557,
|
| 62 |
+
"grad_norm": 0.24895112216472626,
|
| 63 |
+
"learning_rate": 6.956521739130436e-05,
|
| 64 |
+
"loss": 0.9091,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.4,
|
| 69 |
+
"grad_norm": 0.2350614368915558,
|
| 70 |
+
"learning_rate": 7.82608695652174e-05,
|
| 71 |
+
"loss": 0.9091,
|
| 72 |
+
"step": 18
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4444444444444444,
|
| 76 |
+
"grad_norm": 0.27106258273124695,
|
| 77 |
+
"learning_rate": 8.695652173913044e-05,
|
| 78 |
+
"loss": 0.8018,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4888888888888889,
|
| 83 |
+
"grad_norm": 0.3147624731063843,
|
| 84 |
+
"learning_rate": 9.565217391304348e-05,
|
| 85 |
+
"loss": 0.796,
|
| 86 |
+
"step": 22
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5333333333333333,
|
| 90 |
+
"grad_norm": 0.3592516779899597,
|
| 91 |
+
"learning_rate": 9.999395316300748e-05,
|
| 92 |
+
"loss": 0.8837,
|
| 93 |
+
"step": 24
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5777777777777777,
|
| 97 |
+
"grad_norm": 0.27557510137557983,
|
| 98 |
+
"learning_rate": 9.994558724213054e-05,
|
| 99 |
+
"loss": 0.8367,
|
| 100 |
+
"step": 26
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6222222222222222,
|
| 104 |
+
"grad_norm": 0.2757929861545563,
|
| 105 |
+
"learning_rate": 9.984890219128146e-05,
|
| 106 |
+
"loss": 0.8764,
|
| 107 |
+
"step": 28
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6666666666666666,
|
| 111 |
+
"grad_norm": 0.30082619190216064,
|
| 112 |
+
"learning_rate": 9.970399154700263e-05,
|
| 113 |
+
"loss": 0.8687,
|
| 114 |
+
"step": 30
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.7111111111111111,
|
| 118 |
+
"grad_norm": 0.26034796237945557,
|
| 119 |
+
"learning_rate": 9.951099550098349e-05,
|
| 120 |
+
"loss": 0.8371,
|
| 121 |
+
"step": 32
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.7555555555555555,
|
| 125 |
+
"grad_norm": 0.22807522118091583,
|
| 126 |
+
"learning_rate": 9.927010076443407e-05,
|
| 127 |
+
"loss": 0.8085,
|
| 128 |
+
"step": 34
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.8,
|
| 132 |
+
"grad_norm": 0.22343170642852783,
|
| 133 |
+
"learning_rate": 9.898154038745408e-05,
|
| 134 |
+
"loss": 0.8812,
|
| 135 |
+
"step": 36
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.8444444444444444,
|
| 139 |
+
"grad_norm": 0.18960116803646088,
|
| 140 |
+
"learning_rate": 9.864559353357187e-05,
|
| 141 |
+
"loss": 0.7953,
|
| 142 |
+
"step": 38
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8888888888888888,
|
| 146 |
+
"grad_norm": 0.21037450432777405,
|
| 147 |
+
"learning_rate": 9.826258520967178e-05,
|
| 148 |
+
"loss": 0.7484,
|
| 149 |
+
"step": 40
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.9333333333333333,
|
| 153 |
+
"grad_norm": 0.2212020456790924,
|
| 154 |
+
"learning_rate": 9.783288595157098e-05,
|
| 155 |
+
"loss": 0.7931,
|
| 156 |
+
"step": 42
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.9777777777777777,
|
| 160 |
+
"grad_norm": 0.23480449616909027,
|
| 161 |
+
"learning_rate": 9.735691146555002e-05,
|
| 162 |
+
"loss": 0.8413,
|
| 163 |
+
"step": 44
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.0222222222222221,
|
| 167 |
+
"grad_norm": 0.22327324748039246,
|
| 168 |
+
"learning_rate": 9.683512222618377e-05,
|
| 169 |
+
"loss": 0.8391,
|
| 170 |
+
"step": 46
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.0666666666666667,
|
| 174 |
+
"grad_norm": 0.24856683611869812,
|
| 175 |
+
"learning_rate": 9.626802303086208e-05,
|
| 176 |
+
"loss": 0.7997,
|
| 177 |
+
"step": 48
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.1111111111111112,
|
| 181 |
+
"grad_norm": 0.2144002616405487,
|
| 182 |
+
"learning_rate": 9.565616251143094e-05,
|
| 183 |
+
"loss": 0.9146,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.1555555555555554,
|
| 188 |
+
"grad_norm": 0.24486525356769562,
|
| 189 |
+
"learning_rate": 9.500013260342651e-05,
|
| 190 |
+
"loss": 0.7813,
|
| 191 |
+
"step": 52
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.2,
|
| 195 |
+
"grad_norm": 0.23040799796581268,
|
| 196 |
+
"learning_rate": 9.430056797341574e-05,
|
| 197 |
+
"loss": 0.7282,
|
| 198 |
+
"step": 54
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.2444444444444445,
|
| 202 |
+
"grad_norm": 0.24283307790756226,
|
| 203 |
+
"learning_rate": 9.355814540499752e-05,
|
| 204 |
+
"loss": 0.7598,
|
| 205 |
+
"step": 56
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.2888888888888888,
|
| 209 |
+
"grad_norm": 0.25237399339675903,
|
| 210 |
+
"learning_rate": 9.27735831440582e-05,
|
| 211 |
+
"loss": 0.7959,
|
| 212 |
+
"step": 58
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.3333333333333333,
|
| 216 |
+
"grad_norm": 0.2991330325603485,
|
| 217 |
+
"learning_rate": 9.194764020391506e-05,
|
| 218 |
+
"loss": 0.7853,
|
| 219 |
+
"step": 60
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.3777777777777778,
|
| 223 |
+
"grad_norm": 0.27033334970474243,
|
| 224 |
+
"learning_rate": 9.108111563102004e-05,
|
| 225 |
+
"loss": 0.7553,
|
| 226 |
+
"step": 62
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.4222222222222223,
|
| 230 |
+
"grad_norm": 0.32717347145080566,
|
| 231 |
+
"learning_rate": 9.017484773193378e-05,
|
| 232 |
+
"loss": 0.7809,
|
| 233 |
+
"step": 64
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.4666666666666668,
|
| 237 |
+
"grad_norm": 0.29897943139076233,
|
| 238 |
+
"learning_rate": 8.92297132623183e-05,
|
| 239 |
+
"loss": 0.7628,
|
| 240 |
+
"step": 66
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.511111111111111,
|
| 244 |
+
"grad_norm": 0.30663371086120605,
|
| 245 |
+
"learning_rate": 8.824662657873239e-05,
|
| 246 |
+
"loss": 0.7763,
|
| 247 |
+
"step": 68
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.5555555555555556,
|
| 251 |
+
"grad_norm": 0.28747016191482544,
|
| 252 |
+
"learning_rate": 8.722653875405075e-05,
|
| 253 |
+
"loss": 0.737,
|
| 254 |
+
"step": 70
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.6,
|
| 258 |
+
"grad_norm": 0.30916616320610046,
|
| 259 |
+
"learning_rate": 8.617043665736249e-05,
|
| 260 |
+
"loss": 0.7879,
|
| 261 |
+
"step": 72
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.6444444444444444,
|
| 265 |
+
"grad_norm": 0.35312747955322266,
|
| 266 |
+
"learning_rate": 8.507934199923884e-05,
|
| 267 |
+
"loss": 0.7707,
|
| 268 |
+
"step": 74
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.6888888888888889,
|
| 272 |
+
"grad_norm": 0.36939722299575806,
|
| 273 |
+
"learning_rate": 8.39543103432943e-05,
|
| 274 |
+
"loss": 0.727,
|
| 275 |
+
"step": 76
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.7333333333333334,
|
| 279 |
+
"grad_norm": 0.3665863871574402,
|
| 280 |
+
"learning_rate": 8.2796430084997e-05,
|
| 281 |
+
"loss": 0.7193,
|
| 282 |
+
"step": 78
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.7777777777777777,
|
| 286 |
+
"grad_norm": 0.34428849816322327,
|
| 287 |
+
"learning_rate": 8.160682139871633e-05,
|
| 288 |
+
"loss": 0.7573,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.8222222222222222,
|
| 293 |
+
"grad_norm": 0.3433472216129303,
|
| 294 |
+
"learning_rate": 8.03866351540266e-05,
|
| 295 |
+
"loss": 0.7711,
|
| 296 |
+
"step": 82
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.8666666666666667,
|
| 300 |
+
"grad_norm": 0.3693158030509949,
|
| 301 |
+
"learning_rate": 7.913705180231505e-05,
|
| 302 |
+
"loss": 0.7741,
|
| 303 |
+
"step": 84
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.911111111111111,
|
| 307 |
+
"grad_norm": 0.4667452573776245,
|
| 308 |
+
"learning_rate": 7.785928023477142e-05,
|
| 309 |
+
"loss": 0.812,
|
| 310 |
+
"step": 86
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.9555555555555557,
|
| 314 |
+
"grad_norm": 0.36592212319374084,
|
| 315 |
+
"learning_rate": 7.655455661286376e-05,
|
| 316 |
+
"loss": 0.7561,
|
| 317 |
+
"step": 88
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.0,
|
| 321 |
+
"grad_norm": 0.4149788022041321,
|
| 322 |
+
"learning_rate": 7.5224143172432e-05,
|
| 323 |
+
"loss": 0.7797,
|
| 324 |
+
"step": 90
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.0444444444444443,
|
| 328 |
+
"grad_norm": 0.39174893498420715,
|
| 329 |
+
"learning_rate": 7.386932700255636e-05,
|
| 330 |
+
"loss": 0.7651,
|
| 331 |
+
"step": 92
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.088888888888889,
|
| 335 |
+
"grad_norm": 0.4016912877559662,
|
| 336 |
+
"learning_rate": 7.24914188003818e-05,
|
| 337 |
+
"loss": 0.741,
|
| 338 |
+
"step": 94
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.1333333333333333,
|
| 342 |
+
"grad_norm": 0.46315836906433105,
|
| 343 |
+
"learning_rate": 7.109175160310312e-05,
|
| 344 |
+
"loss": 0.695,
|
| 345 |
+
"step": 96
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.1777777777777776,
|
| 349 |
+
"grad_norm": 0.48870378732681274,
|
| 350 |
+
"learning_rate": 6.967167949833763e-05,
|
| 351 |
+
"loss": 0.7259,
|
| 352 |
+
"step": 98
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.2222222222222223,
|
| 356 |
+
"grad_norm": 0.43603938817977905,
|
| 357 |
+
"learning_rate": 6.823257631413276e-05,
|
| 358 |
+
"loss": 0.7574,
|
| 359 |
+
"step": 100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.2666666666666666,
|
| 363 |
+
"grad_norm": 0.46362167596817017,
|
| 364 |
+
"learning_rate": 6.677583428987625e-05,
|
| 365 |
+
"loss": 0.6457,
|
| 366 |
+
"step": 102
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.311111111111111,
|
| 370 |
+
"grad_norm": 0.5170242786407471,
|
| 371 |
+
"learning_rate": 6.530286272939437e-05,
|
| 372 |
+
"loss": 0.6498,
|
| 373 |
+
"step": 104
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.3555555555555556,
|
| 377 |
+
"grad_norm": 0.4572562575340271,
|
| 378 |
+
"learning_rate": 6.381508663754153e-05,
|
| 379 |
+
"loss": 0.6389,
|
| 380 |
+
"step": 106
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.4,
|
| 384 |
+
"grad_norm": 0.5652968287467957,
|
| 385 |
+
"learning_rate": 6.231394534160008e-05,
|
| 386 |
+
"loss": 0.7215,
|
| 387 |
+
"step": 108
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.4444444444444446,
|
| 391 |
+
"grad_norm": 0.5415116548538208,
|
| 392 |
+
"learning_rate": 6.0800891098824186e-05,
|
| 393 |
+
"loss": 0.7096,
|
| 394 |
+
"step": 110
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.488888888888889,
|
| 398 |
+
"grad_norm": 0.493282675743103,
|
| 399 |
+
"learning_rate": 5.9277387691474676e-05,
|
| 400 |
+
"loss": 0.6736,
|
| 401 |
+
"step": 112
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.533333333333333,
|
| 405 |
+
"grad_norm": 0.6388583183288574,
|
| 406 |
+
"learning_rate": 5.774490901070424e-05,
|
| 407 |
+
"loss": 0.6875,
|
| 408 |
+
"step": 114
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.5777777777777775,
|
| 412 |
+
"grad_norm": 0.4991196393966675,
|
| 413 |
+
"learning_rate": 5.620493763066297e-05,
|
| 414 |
+
"loss": 0.6023,
|
| 415 |
+
"step": 116
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.6222222222222222,
|
| 419 |
+
"grad_norm": 0.5749160051345825,
|
| 420 |
+
"learning_rate": 5.465896337420359e-05,
|
| 421 |
+
"loss": 0.6356,
|
| 422 |
+
"step": 118
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.6666666666666665,
|
| 426 |
+
"grad_norm": 0.6559845209121704,
|
| 427 |
+
"learning_rate": 5.3108481871574036e-05,
|
| 428 |
+
"loss": 0.6939,
|
| 429 |
+
"step": 120
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.7111111111111112,
|
| 433 |
+
"grad_norm": 0.6793063879013062,
|
| 434 |
+
"learning_rate": 5.155499311349185e-05,
|
| 435 |
+
"loss": 0.6981,
|
| 436 |
+
"step": 122
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.7555555555555555,
|
| 440 |
+
"grad_norm": 0.6073561310768127,
|
| 441 |
+
"learning_rate": 5e-05,
|
| 442 |
+
"loss": 0.6733,
|
| 443 |
+
"step": 124
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.8,
|
| 447 |
+
"grad_norm": 0.6620696187019348,
|
| 448 |
+
"learning_rate": 4.844500688650816e-05,
|
| 449 |
+
"loss": 0.6851,
|
| 450 |
+
"step": 126
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.8444444444444446,
|
| 454 |
+
"grad_norm": 0.626446545124054,
|
| 455 |
+
"learning_rate": 4.6891518128425976e-05,
|
| 456 |
+
"loss": 0.654,
|
| 457 |
+
"step": 128
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.888888888888889,
|
| 461 |
+
"grad_norm": 0.6012407541275024,
|
| 462 |
+
"learning_rate": 4.534103662579642e-05,
|
| 463 |
+
"loss": 0.6303,
|
| 464 |
+
"step": 130
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.9333333333333336,
|
| 468 |
+
"grad_norm": 0.6335547566413879,
|
| 469 |
+
"learning_rate": 4.3795062369337034e-05,
|
| 470 |
+
"loss": 0.5819,
|
| 471 |
+
"step": 132
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.977777777777778,
|
| 475 |
+
"grad_norm": 0.6275166273117065,
|
| 476 |
+
"learning_rate": 4.2255090989295764e-05,
|
| 477 |
+
"loss": 0.6726,
|
| 478 |
+
"step": 134
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 3.022222222222222,
|
| 482 |
+
"grad_norm": 0.545259416103363,
|
| 483 |
+
"learning_rate": 4.0722612308525335e-05,
|
| 484 |
+
"loss": 0.6621,
|
| 485 |
+
"step": 136
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 3.066666666666667,
|
| 489 |
+
"grad_norm": 0.6598561406135559,
|
| 490 |
+
"learning_rate": 3.919910890117584e-05,
|
| 491 |
+
"loss": 0.5295,
|
| 492 |
+
"step": 138
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 3.111111111111111,
|
| 496 |
+
"grad_norm": 0.6240947842597961,
|
| 497 |
+
"learning_rate": 3.7686054658399935e-05,
|
| 498 |
+
"loss": 0.5466,
|
| 499 |
+
"step": 140
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 3.1555555555555554,
|
| 503 |
+
"grad_norm": 0.682789146900177,
|
| 504 |
+
"learning_rate": 3.618491336245849e-05,
|
| 505 |
+
"loss": 0.5419,
|
| 506 |
+
"step": 142
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 3.2,
|
| 510 |
+
"grad_norm": 0.7448738217353821,
|
| 511 |
+
"learning_rate": 3.469713727060564e-05,
|
| 512 |
+
"loss": 0.6171,
|
| 513 |
+
"step": 144
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 3.2444444444444445,
|
| 517 |
+
"grad_norm": 0.7555476427078247,
|
| 518 |
+
"learning_rate": 3.3224165710123756e-05,
|
| 519 |
+
"loss": 0.5628,
|
| 520 |
+
"step": 146
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 3.2888888888888888,
|
| 524 |
+
"grad_norm": 0.7862750887870789,
|
| 525 |
+
"learning_rate": 3.176742368586725e-05,
|
| 526 |
+
"loss": 0.5923,
|
| 527 |
+
"step": 148
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 3.3333333333333335,
|
| 531 |
+
"grad_norm": 0.7729607224464417,
|
| 532 |
+
"learning_rate": 3.032832050166239e-05,
|
| 533 |
+
"loss": 0.5308,
|
| 534 |
+
"step": 150
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 3.3777777777777778,
|
| 538 |
+
"grad_norm": 0.7676399350166321,
|
| 539 |
+
"learning_rate": 2.890824839689689e-05,
|
| 540 |
+
"loss": 0.6444,
|
| 541 |
+
"step": 152
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 3.422222222222222,
|
| 545 |
+
"grad_norm": 0.8251731991767883,
|
| 546 |
+
"learning_rate": 2.750858119961821e-05,
|
| 547 |
+
"loss": 0.6573,
|
| 548 |
+
"step": 154
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.466666666666667,
|
| 552 |
+
"grad_norm": 0.8169701099395752,
|
| 553 |
+
"learning_rate": 2.613067299744364e-05,
|
| 554 |
+
"loss": 0.582,
|
| 555 |
+
"step": 156
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.511111111111111,
|
| 559 |
+
"grad_norm": 0.7788083553314209,
|
| 560 |
+
"learning_rate": 2.4775856827568016e-05,
|
| 561 |
+
"loss": 0.6335,
|
| 562 |
+
"step": 158
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 3.5555555555555554,
|
| 566 |
+
"grad_norm": 0.8565711379051208,
|
| 567 |
+
"learning_rate": 2.3445443387136244e-05,
|
| 568 |
+
"loss": 0.508,
|
| 569 |
+
"step": 160
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.6,
|
| 573 |
+
"grad_norm": 0.8271569609642029,
|
| 574 |
+
"learning_rate": 2.2140719765228584e-05,
|
| 575 |
+
"loss": 0.5991,
|
| 576 |
+
"step": 162
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.6444444444444444,
|
| 580 |
+
"grad_norm": 0.812567412853241,
|
| 581 |
+
"learning_rate": 2.0862948197684955e-05,
|
| 582 |
+
"loss": 0.5808,
|
| 583 |
+
"step": 164
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 3.688888888888889,
|
| 587 |
+
"grad_norm": 0.7940819263458252,
|
| 588 |
+
"learning_rate": 1.961336484597343e-05,
|
| 589 |
+
"loss": 0.5703,
|
| 590 |
+
"step": 166
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.7333333333333334,
|
| 594 |
+
"grad_norm": 0.9031268358230591,
|
| 595 |
+
"learning_rate": 1.8393178601283683e-05,
|
| 596 |
+
"loss": 0.5002,
|
| 597 |
+
"step": 168
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.7777777777777777,
|
| 601 |
+
"grad_norm": 0.8260697722434998,
|
| 602 |
+
"learning_rate": 1.7203569915003005e-05,
|
| 603 |
+
"loss": 0.5269,
|
| 604 |
+
"step": 170
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.822222222222222,
|
| 608 |
+
"grad_norm": 0.9412121772766113,
|
| 609 |
+
"learning_rate": 1.6045689656705716e-05,
|
| 610 |
+
"loss": 0.4902,
|
| 611 |
+
"step": 172
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.8666666666666667,
|
| 615 |
+
"grad_norm": 0.9131683707237244,
|
| 616 |
+
"learning_rate": 1.4920658000761174e-05,
|
| 617 |
+
"loss": 0.6185,
|
| 618 |
+
"step": 174
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 3.911111111111111,
|
| 622 |
+
"grad_norm": 0.7923269271850586,
|
| 623 |
+
"learning_rate": 1.3829563342637513e-05,
|
| 624 |
+
"loss": 0.537,
|
| 625 |
+
"step": 176
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 3.9555555555555557,
|
| 629 |
+
"grad_norm": 0.8013989329338074,
|
| 630 |
+
"learning_rate": 1.2773461245949247e-05,
|
| 631 |
+
"loss": 0.5637,
|
| 632 |
+
"step": 178
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 4.0,
|
| 636 |
+
"grad_norm": 0.7401474118232727,
|
| 637 |
+
"learning_rate": 1.1753373421267621e-05,
|
| 638 |
+
"loss": 0.5124,
|
| 639 |
+
"step": 180
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 4.044444444444444,
|
| 643 |
+
"grad_norm": 0.8890312910079956,
|
| 644 |
+
"learning_rate": 1.0770286737681701e-05,
|
| 645 |
+
"loss": 0.5488,
|
| 646 |
+
"step": 182
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 4.088888888888889,
|
| 650 |
+
"grad_norm": 0.858996570110321,
|
| 651 |
+
"learning_rate": 9.825152268066213e-06,
|
| 652 |
+
"loss": 0.4998,
|
| 653 |
+
"step": 184
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 4.133333333333334,
|
| 657 |
+
"grad_norm": 0.755382239818573,
|
| 658 |
+
"learning_rate": 8.91888436897997e-06,
|
| 659 |
+
"loss": 0.4892,
|
| 660 |
+
"step": 186
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 4.177777777777778,
|
| 664 |
+
"grad_norm": 0.8359836935997009,
|
| 665 |
+
"learning_rate": 8.052359796084951e-06,
|
| 666 |
+
"loss": 0.5365,
|
| 667 |
+
"step": 188
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 4.222222222222222,
|
| 671 |
+
"grad_norm": 0.8235160112380981,
|
| 672 |
+
"learning_rate": 7.226416855941814e-06,
|
| 673 |
+
"loss": 0.4963,
|
| 674 |
+
"step": 190
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 4.266666666666667,
|
| 678 |
+
"grad_norm": 0.9951562881469727,
|
| 679 |
+
"learning_rate": 6.441854595002477e-06,
|
| 680 |
+
"loss": 0.5367,
|
| 681 |
+
"step": 192
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 4.311111111111111,
|
| 685 |
+
"grad_norm": 0.907408595085144,
|
| 686 |
+
"learning_rate": 5.699432026584267e-06,
|
| 687 |
+
"loss": 0.5051,
|
| 688 |
+
"step": 194
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 4.355555555555555,
|
| 692 |
+
"grad_norm": 0.9453915357589722,
|
| 693 |
+
"learning_rate": 4.999867396573499e-06,
|
| 694 |
+
"loss": 0.5326,
|
| 695 |
+
"step": 196
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 4.4,
|
| 699 |
+
"grad_norm": 0.8306211829185486,
|
| 700 |
+
"learning_rate": 4.343837488569058e-06,
|
| 701 |
+
"loss": 0.4549,
|
| 702 |
+
"step": 198
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 4.444444444444445,
|
| 706 |
+
"grad_norm": 0.9665538668632507,
|
| 707 |
+
"learning_rate": 3.731976969137929e-06,
|
| 708 |
+
"loss": 0.4968,
|
| 709 |
+
"step": 200
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 4.488888888888889,
|
| 713 |
+
"grad_norm": 0.9233301281929016,
|
| 714 |
+
"learning_rate": 3.1648777738162494e-06,
|
| 715 |
+
"loss": 0.4623,
|
| 716 |
+
"step": 202
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 4.533333333333333,
|
| 720 |
+
"grad_norm": 0.8156710267066956,
|
| 721 |
+
"learning_rate": 2.6430885344499946e-06,
|
| 722 |
+
"loss": 0.4445,
|
| 723 |
+
"step": 204
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 4.5777777777777775,
|
| 727 |
+
"grad_norm": 0.8379063010215759,
|
| 728 |
+
"learning_rate": 2.1671140484290142e-06,
|
| 729 |
+
"loss": 0.4678,
|
| 730 |
+
"step": 206
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 4.622222222222222,
|
| 734 |
+
"grad_norm": 0.8422232866287231,
|
| 735 |
+
"learning_rate": 1.7374147903282178e-06,
|
| 736 |
+
"loss": 0.5377,
|
| 737 |
+
"step": 208
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 4.666666666666667,
|
| 741 |
+
"grad_norm": 0.9653432965278625,
|
| 742 |
+
"learning_rate": 1.3544064664281265e-06,
|
| 743 |
+
"loss": 0.5819,
|
| 744 |
+
"step": 210
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 4.711111111111111,
|
| 748 |
+
"grad_norm": 0.8152110576629639,
|
| 749 |
+
"learning_rate": 1.0184596125459135e-06,
|
| 750 |
+
"loss": 0.494,
|
| 751 |
+
"step": 212
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 4.7555555555555555,
|
| 755 |
+
"grad_norm": 0.9850694537162781,
|
| 756 |
+
"learning_rate": 7.29899235565934e-07,
|
| 757 |
+
"loss": 0.4983,
|
| 758 |
+
"step": 214
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 4.8,
|
| 762 |
+
"grad_norm": 0.9584403038024902,
|
| 763 |
+
"learning_rate": 4.890044990165321e-07,
|
| 764 |
+
"loss": 0.5186,
|
| 765 |
+
"step": 216
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 4.844444444444444,
|
| 769 |
+
"grad_norm": 0.948579728603363,
|
| 770 |
+
"learning_rate": 2.9600845299737056e-07,
|
| 771 |
+
"loss": 0.5044,
|
| 772 |
+
"step": 218
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 4.888888888888889,
|
| 776 |
+
"grad_norm": 0.8661581873893738,
|
| 777 |
+
"learning_rate": 1.5109780871853663e-07,
|
| 778 |
+
"loss": 0.5062,
|
| 779 |
+
"step": 220
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 4.933333333333334,
|
| 783 |
+
"grad_norm": 0.9714407324790955,
|
| 784 |
+
"learning_rate": 5.4412757869459763e-08,
|
| 785 |
+
"loss": 0.5391,
|
| 786 |
+
"step": 222
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 4.977777777777778,
|
| 790 |
+
"grad_norm": 0.7409553527832031,
|
| 791 |
+
"learning_rate": 6.04683699252373e-09,
|
| 792 |
+
"loss": 0.5243,
|
| 793 |
+
"step": 224
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 5.0,
|
| 797 |
+
"step": 225,
|
| 798 |
+
"total_flos": 8.831352737326694e+16,
|
| 799 |
+
"train_loss": 0.6794352424144745,
|
| 800 |
+
"train_runtime": 806.654,
|
| 801 |
+
"train_samples_per_second": 8.926,
|
| 802 |
+
"train_steps_per_second": 0.279
|
| 803 |
+
}
|
| 804 |
+
],
|
| 805 |
+
"logging_steps": 2,
|
| 806 |
+
"max_steps": 225,
|
| 807 |
+
"num_input_tokens_seen": 0,
|
| 808 |
+
"num_train_epochs": 5,
|
| 809 |
+
"save_steps": 500,
|
| 810 |
+
"stateful_callbacks": {
|
| 811 |
+
"TrainerControl": {
|
| 812 |
+
"args": {
|
| 813 |
+
"should_epoch_stop": false,
|
| 814 |
+
"should_evaluate": false,
|
| 815 |
+
"should_log": false,
|
| 816 |
+
"should_save": false,
|
| 817 |
+
"should_training_stop": false
|
| 818 |
+
},
|
| 819 |
+
"attributes": {}
|
| 820 |
+
}
|
| 821 |
+
},
|
| 822 |
+
"total_flos": 8.831352737326694e+16,
|
| 823 |
+
"train_batch_size": 4,
|
| 824 |
+
"trial_name": null,
|
| 825 |
+
"trial_params": null
|
| 826 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0580a4ecca43c5ffc70f6e5bf2d0953ab337d8cc242e410e069987c4f1b5fc2
|
| 3 |
+
size 5304
|
training_loss.png
ADDED
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|