End of training
Browse files- README.md +110 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- all_results.json +18 -0
- eval_results.json +7 -0
- metrics.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +51 -0
- train_results.json +7 -0
- trainer_state.json +690 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 7 |
+
datasets:
|
| 8 |
+
- mbe
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: Mistral-7B-v0.1_mbe_no
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# Mistral-7B-v0.1_mbe_no
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the mbe dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.7827
|
| 24 |
+
- Accuracy: 0.5493
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 3e-05
|
| 44 |
+
- train_batch_size: 4
|
| 45 |
+
- eval_batch_size: 4
|
| 46 |
+
- seed: 42
|
| 47 |
+
- gradient_accumulation_steps: 4
|
| 48 |
+
- total_train_batch_size: 16
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: constant
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 52 |
+
- num_epochs: 3.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 58 |
+
| 1.5293 | 0.07 | 10 | 0.6504 | 0.3520 |
|
| 59 |
+
| 0.6652 | 0.13 | 20 | 0.6469 | 0.3783 |
|
| 60 |
+
| 0.6523 | 0.2 | 30 | 0.6430 | 0.3651 |
|
| 61 |
+
| 0.613 | 0.27 | 40 | 0.6341 | 0.4079 |
|
| 62 |
+
| 0.6586 | 0.33 | 50 | 0.6206 | 0.3882 |
|
| 63 |
+
| 0.586 | 0.4 | 60 | 0.6269 | 0.4178 |
|
| 64 |
+
| 0.594 | 0.47 | 70 | 0.6046 | 0.4276 |
|
| 65 |
+
| 0.6063 | 0.53 | 80 | 0.6135 | 0.4178 |
|
| 66 |
+
| 0.5988 | 0.6 | 90 | 0.6097 | 0.4276 |
|
| 67 |
+
| 0.6217 | 0.67 | 100 | 0.6098 | 0.4539 |
|
| 68 |
+
| 0.5817 | 0.73 | 110 | 0.6022 | 0.4539 |
|
| 69 |
+
| 0.6219 | 0.8 | 120 | 0.5926 | 0.4572 |
|
| 70 |
+
| 0.559 | 0.87 | 130 | 0.5816 | 0.4605 |
|
| 71 |
+
| 0.5514 | 0.93 | 140 | 0.5783 | 0.4737 |
|
| 72 |
+
| 0.59 | 1.0 | 150 | 0.5622 | 0.4868 |
|
| 73 |
+
| 0.46 | 1.07 | 160 | 0.5868 | 0.4803 |
|
| 74 |
+
| 0.4484 | 1.14 | 170 | 0.5667 | 0.4868 |
|
| 75 |
+
| 0.4162 | 1.2 | 180 | 0.5820 | 0.4803 |
|
| 76 |
+
| 0.4716 | 1.27 | 190 | 0.5904 | 0.4638 |
|
| 77 |
+
| 0.4486 | 1.34 | 200 | 0.5777 | 0.5099 |
|
| 78 |
+
| 0.4264 | 1.4 | 210 | 0.6482 | 0.4967 |
|
| 79 |
+
| 0.4236 | 1.47 | 220 | 0.5741 | 0.5033 |
|
| 80 |
+
| 0.4141 | 1.54 | 230 | 0.5608 | 0.5164 |
|
| 81 |
+
| 0.4308 | 1.6 | 240 | 0.5539 | 0.5099 |
|
| 82 |
+
| 0.4505 | 1.67 | 250 | 0.5495 | 0.5033 |
|
| 83 |
+
| 0.3958 | 1.74 | 260 | 0.5594 | 0.5099 |
|
| 84 |
+
| 0.4432 | 1.8 | 270 | 0.5492 | 0.5164 |
|
| 85 |
+
| 0.4067 | 1.87 | 280 | 0.6024 | 0.5066 |
|
| 86 |
+
| 0.3988 | 1.94 | 290 | 0.5607 | 0.5099 |
|
| 87 |
+
| 0.3992 | 2.0 | 300 | 0.5670 | 0.5164 |
|
| 88 |
+
| 0.2304 | 2.07 | 310 | 0.8200 | 0.5362 |
|
| 89 |
+
| 0.1696 | 2.14 | 320 | 0.9087 | 0.5296 |
|
| 90 |
+
| 0.2255 | 2.2 | 330 | 0.7566 | 0.5362 |
|
| 91 |
+
| 0.1923 | 2.27 | 340 | 0.7020 | 0.5197 |
|
| 92 |
+
| 0.281 | 2.34 | 350 | 0.6653 | 0.5033 |
|
| 93 |
+
| 0.2311 | 2.4 | 360 | 0.6412 | 0.5132 |
|
| 94 |
+
| 0.1523 | 2.47 | 370 | 0.8846 | 0.5230 |
|
| 95 |
+
| 0.2451 | 2.54 | 380 | 0.9252 | 0.5164 |
|
| 96 |
+
| 0.2022 | 2.6 | 390 | 0.7422 | 0.5197 |
|
| 97 |
+
| 0.217 | 2.67 | 400 | 0.7558 | 0.5329 |
|
| 98 |
+
| 0.165 | 2.74 | 410 | 0.7846 | 0.5428 |
|
| 99 |
+
| 0.2025 | 2.8 | 420 | 0.7254 | 0.5230 |
|
| 100 |
+
| 0.2201 | 2.87 | 430 | 0.6531 | 0.5296 |
|
| 101 |
+
| 0.2037 | 2.94 | 440 | 0.7827 | 0.5493 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- PEFT 0.7.1
|
| 107 |
+
- Transformers 4.37.2
|
| 108 |
+
- Pytorch 2.1.2+cu121
|
| 109 |
+
- Datasets 2.17.1
|
| 110 |
+
- Tokenizers 0.15.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
| 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": 0.1,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 64,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"gate_proj",
|
| 23 |
+
"k_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"q_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"down_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM"
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87e2c9555bace0e632ac55bd4001d73139fb9ed91755fda1410bed2f02808894
|
| 3 |
+
size 335605144
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.98,
|
| 3 |
+
"eval_accuracy": 0.8141509433962264,
|
| 4 |
+
"eval_f1_macro": 0.7097996478763092,
|
| 5 |
+
"eval_f1_micro": 0.8141509433962264,
|
| 6 |
+
"eval_loss": 1.1632015705108643,
|
| 7 |
+
"eval_precision_macro": 0.7222302630120379,
|
| 8 |
+
"eval_precision_micro": 0.8141509433962264,
|
| 9 |
+
"eval_recall_macro": 0.7125706602249756,
|
| 10 |
+
"eval_recall_micro": 0.8141509433962264,
|
| 11 |
+
"eval_runtime": 19.7133,
|
| 12 |
+
"eval_samples_per_second": 25.009,
|
| 13 |
+
"eval_steps_per_second": 1.573,
|
| 14 |
+
"train_loss": 0.43748926956381573,
|
| 15 |
+
"train_runtime": 1886.9121,
|
| 16 |
+
"train_samples_per_second": 3.809,
|
| 17 |
+
"train_steps_per_second": 0.237
|
| 18 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 1.1632015705108643,
|
| 4 |
+
"eval_runtime": 19.7133,
|
| 5 |
+
"eval_samples_per_second": 25.009,
|
| 6 |
+
"eval_steps_per_second": 1.573
|
| 7 |
+
}
|
metrics.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"run_name": "./output", "train_runtime": 10306.9039, "train_samples_per_second": 9.463, "train_steps_per_second": 0.148, "train_loss": 1.1488912840840697, "epoch": 2.0, "eval_loss": 1.1632015705108643, "eval_runtime": 19.7133, "eval_samples_per_second": 25.009, "eval_steps_per_second": 1.573}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "[PAD]",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"additional_special_tokens": [],
|
| 39 |
+
"bos_token": "<s>",
|
| 40 |
+
"clean_up_tokenization_spaces": false,
|
| 41 |
+
"eos_token": "</s>",
|
| 42 |
+
"legacy": true,
|
| 43 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 44 |
+
"pad_token": "[PAD]",
|
| 45 |
+
"padding_side": "left",
|
| 46 |
+
"sp_model_kwargs": {},
|
| 47 |
+
"spaces_between_special_tokens": false,
|
| 48 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 49 |
+
"unk_token": "<unk>",
|
| 50 |
+
"use_default_system_prompt": false
|
| 51 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.98,
|
| 3 |
+
"train_loss": 0.43748926956381573,
|
| 4 |
+
"train_runtime": 1886.9121,
|
| 5 |
+
"train_samples_per_second": 3.809,
|
| 6 |
+
"train_steps_per_second": 0.237
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,690 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.984974958263773,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 447,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07,
|
| 13 |
+
"learning_rate": 3e-05,
|
| 14 |
+
"loss": 1.5293,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"eval_accuracy": 0.3519736842105263,
|
| 20 |
+
"eval_loss": 0.6503910422325134,
|
| 21 |
+
"eval_runtime": 16.3619,
|
| 22 |
+
"eval_samples_per_second": 18.58,
|
| 23 |
+
"eval_steps_per_second": 4.645,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.13,
|
| 28 |
+
"learning_rate": 3e-05,
|
| 29 |
+
"loss": 0.6652,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.13,
|
| 34 |
+
"eval_accuracy": 0.3782894736842105,
|
| 35 |
+
"eval_loss": 0.6469289660453796,
|
| 36 |
+
"eval_runtime": 16.3596,
|
| 37 |
+
"eval_samples_per_second": 18.582,
|
| 38 |
+
"eval_steps_per_second": 4.646,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.2,
|
| 43 |
+
"learning_rate": 3e-05,
|
| 44 |
+
"loss": 0.6523,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2,
|
| 49 |
+
"eval_accuracy": 0.3651315789473684,
|
| 50 |
+
"eval_loss": 0.6429744362831116,
|
| 51 |
+
"eval_runtime": 16.3534,
|
| 52 |
+
"eval_samples_per_second": 18.589,
|
| 53 |
+
"eval_steps_per_second": 4.647,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.27,
|
| 58 |
+
"learning_rate": 3e-05,
|
| 59 |
+
"loss": 0.613,
|
| 60 |
+
"step": 40
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.27,
|
| 64 |
+
"eval_accuracy": 0.40789473684210525,
|
| 65 |
+
"eval_loss": 0.6341487765312195,
|
| 66 |
+
"eval_runtime": 16.4446,
|
| 67 |
+
"eval_samples_per_second": 18.486,
|
| 68 |
+
"eval_steps_per_second": 4.622,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.33,
|
| 73 |
+
"learning_rate": 3e-05,
|
| 74 |
+
"loss": 0.6586,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.33,
|
| 79 |
+
"eval_accuracy": 0.3881578947368421,
|
| 80 |
+
"eval_loss": 0.6206462979316711,
|
| 81 |
+
"eval_runtime": 16.366,
|
| 82 |
+
"eval_samples_per_second": 18.575,
|
| 83 |
+
"eval_steps_per_second": 4.644,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.4,
|
| 88 |
+
"learning_rate": 3e-05,
|
| 89 |
+
"loss": 0.586,
|
| 90 |
+
"step": 60
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.4,
|
| 94 |
+
"eval_accuracy": 0.41776315789473684,
|
| 95 |
+
"eval_loss": 0.6268599033355713,
|
| 96 |
+
"eval_runtime": 16.3556,
|
| 97 |
+
"eval_samples_per_second": 18.587,
|
| 98 |
+
"eval_steps_per_second": 4.647,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.47,
|
| 103 |
+
"learning_rate": 3e-05,
|
| 104 |
+
"loss": 0.594,
|
| 105 |
+
"step": 70
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.47,
|
| 109 |
+
"eval_accuracy": 0.4276315789473684,
|
| 110 |
+
"eval_loss": 0.6045505404472351,
|
| 111 |
+
"eval_runtime": 16.3658,
|
| 112 |
+
"eval_samples_per_second": 18.575,
|
| 113 |
+
"eval_steps_per_second": 4.644,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.53,
|
| 118 |
+
"learning_rate": 3e-05,
|
| 119 |
+
"loss": 0.6063,
|
| 120 |
+
"step": 80
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.53,
|
| 124 |
+
"eval_accuracy": 0.41776315789473684,
|
| 125 |
+
"eval_loss": 0.6135305762290955,
|
| 126 |
+
"eval_runtime": 16.3648,
|
| 127 |
+
"eval_samples_per_second": 18.576,
|
| 128 |
+
"eval_steps_per_second": 4.644,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6,
|
| 133 |
+
"learning_rate": 3e-05,
|
| 134 |
+
"loss": 0.5988,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6,
|
| 139 |
+
"eval_accuracy": 0.4276315789473684,
|
| 140 |
+
"eval_loss": 0.6097424626350403,
|
| 141 |
+
"eval_runtime": 16.3755,
|
| 142 |
+
"eval_samples_per_second": 18.564,
|
| 143 |
+
"eval_steps_per_second": 4.641,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.67,
|
| 148 |
+
"learning_rate": 3e-05,
|
| 149 |
+
"loss": 0.6217,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.67,
|
| 154 |
+
"eval_accuracy": 0.45394736842105265,
|
| 155 |
+
"eval_loss": 0.6098220348358154,
|
| 156 |
+
"eval_runtime": 16.3674,
|
| 157 |
+
"eval_samples_per_second": 18.574,
|
| 158 |
+
"eval_steps_per_second": 4.643,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.73,
|
| 163 |
+
"learning_rate": 3e-05,
|
| 164 |
+
"loss": 0.5817,
|
| 165 |
+
"step": 110
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.73,
|
| 169 |
+
"eval_accuracy": 0.45394736842105265,
|
| 170 |
+
"eval_loss": 0.6021943092346191,
|
| 171 |
+
"eval_runtime": 16.3678,
|
| 172 |
+
"eval_samples_per_second": 18.573,
|
| 173 |
+
"eval_steps_per_second": 4.643,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.8,
|
| 178 |
+
"learning_rate": 3e-05,
|
| 179 |
+
"loss": 0.6219,
|
| 180 |
+
"step": 120
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.8,
|
| 184 |
+
"eval_accuracy": 0.45723684210526316,
|
| 185 |
+
"eval_loss": 0.5926041007041931,
|
| 186 |
+
"eval_runtime": 16.3627,
|
| 187 |
+
"eval_samples_per_second": 18.579,
|
| 188 |
+
"eval_steps_per_second": 4.645,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.87,
|
| 193 |
+
"learning_rate": 3e-05,
|
| 194 |
+
"loss": 0.559,
|
| 195 |
+
"step": 130
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.87,
|
| 199 |
+
"eval_accuracy": 0.4605263157894737,
|
| 200 |
+
"eval_loss": 0.5816267728805542,
|
| 201 |
+
"eval_runtime": 16.3673,
|
| 202 |
+
"eval_samples_per_second": 18.574,
|
| 203 |
+
"eval_steps_per_second": 4.643,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.93,
|
| 208 |
+
"learning_rate": 3e-05,
|
| 209 |
+
"loss": 0.5514,
|
| 210 |
+
"step": 140
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.93,
|
| 214 |
+
"eval_accuracy": 0.47368421052631576,
|
| 215 |
+
"eval_loss": 0.5783373713493347,
|
| 216 |
+
"eval_runtime": 16.368,
|
| 217 |
+
"eval_samples_per_second": 18.573,
|
| 218 |
+
"eval_steps_per_second": 4.643,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0,
|
| 223 |
+
"learning_rate": 3e-05,
|
| 224 |
+
"loss": 0.59,
|
| 225 |
+
"step": 150
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.0,
|
| 229 |
+
"eval_accuracy": 0.4868421052631579,
|
| 230 |
+
"eval_loss": 0.5621668100357056,
|
| 231 |
+
"eval_runtime": 16.3648,
|
| 232 |
+
"eval_samples_per_second": 18.576,
|
| 233 |
+
"eval_steps_per_second": 4.644,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.07,
|
| 238 |
+
"learning_rate": 3e-05,
|
| 239 |
+
"loss": 0.46,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.07,
|
| 244 |
+
"eval_accuracy": 0.48026315789473684,
|
| 245 |
+
"eval_loss": 0.5867581367492676,
|
| 246 |
+
"eval_runtime": 16.3579,
|
| 247 |
+
"eval_samples_per_second": 18.584,
|
| 248 |
+
"eval_steps_per_second": 4.646,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.14,
|
| 253 |
+
"learning_rate": 3e-05,
|
| 254 |
+
"loss": 0.4484,
|
| 255 |
+
"step": 170
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.14,
|
| 259 |
+
"eval_accuracy": 0.4868421052631579,
|
| 260 |
+
"eval_loss": 0.5666611194610596,
|
| 261 |
+
"eval_runtime": 16.3613,
|
| 262 |
+
"eval_samples_per_second": 18.58,
|
| 263 |
+
"eval_steps_per_second": 4.645,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.2,
|
| 268 |
+
"learning_rate": 3e-05,
|
| 269 |
+
"loss": 0.4162,
|
| 270 |
+
"step": 180
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.2,
|
| 274 |
+
"eval_accuracy": 0.48026315789473684,
|
| 275 |
+
"eval_loss": 0.5819750428199768,
|
| 276 |
+
"eval_runtime": 16.3725,
|
| 277 |
+
"eval_samples_per_second": 18.568,
|
| 278 |
+
"eval_steps_per_second": 4.642,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.27,
|
| 283 |
+
"learning_rate": 3e-05,
|
| 284 |
+
"loss": 0.4716,
|
| 285 |
+
"step": 190
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.27,
|
| 289 |
+
"eval_accuracy": 0.46381578947368424,
|
| 290 |
+
"eval_loss": 0.590432345867157,
|
| 291 |
+
"eval_runtime": 16.361,
|
| 292 |
+
"eval_samples_per_second": 18.581,
|
| 293 |
+
"eval_steps_per_second": 4.645,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.34,
|
| 298 |
+
"learning_rate": 3e-05,
|
| 299 |
+
"loss": 0.4486,
|
| 300 |
+
"step": 200
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.34,
|
| 304 |
+
"eval_accuracy": 0.5098684210526315,
|
| 305 |
+
"eval_loss": 0.5777420997619629,
|
| 306 |
+
"eval_runtime": 16.354,
|
| 307 |
+
"eval_samples_per_second": 18.589,
|
| 308 |
+
"eval_steps_per_second": 4.647,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.4,
|
| 313 |
+
"learning_rate": 3e-05,
|
| 314 |
+
"loss": 0.4264,
|
| 315 |
+
"step": 210
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.4,
|
| 319 |
+
"eval_accuracy": 0.4967105263157895,
|
| 320 |
+
"eval_loss": 0.6482496857643127,
|
| 321 |
+
"eval_runtime": 16.3696,
|
| 322 |
+
"eval_samples_per_second": 18.571,
|
| 323 |
+
"eval_steps_per_second": 4.643,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.47,
|
| 328 |
+
"learning_rate": 3e-05,
|
| 329 |
+
"loss": 0.4236,
|
| 330 |
+
"step": 220
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.47,
|
| 334 |
+
"eval_accuracy": 0.5032894736842105,
|
| 335 |
+
"eval_loss": 0.5741015076637268,
|
| 336 |
+
"eval_runtime": 16.3648,
|
| 337 |
+
"eval_samples_per_second": 18.576,
|
| 338 |
+
"eval_steps_per_second": 4.644,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.54,
|
| 343 |
+
"learning_rate": 3e-05,
|
| 344 |
+
"loss": 0.4141,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.54,
|
| 349 |
+
"eval_accuracy": 0.5164473684210527,
|
| 350 |
+
"eval_loss": 0.5607666373252869,
|
| 351 |
+
"eval_runtime": 16.3604,
|
| 352 |
+
"eval_samples_per_second": 18.581,
|
| 353 |
+
"eval_steps_per_second": 4.645,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.6,
|
| 358 |
+
"learning_rate": 3e-05,
|
| 359 |
+
"loss": 0.4308,
|
| 360 |
+
"step": 240
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.6,
|
| 364 |
+
"eval_accuracy": 0.5098684210526315,
|
| 365 |
+
"eval_loss": 0.5539161562919617,
|
| 366 |
+
"eval_runtime": 16.3597,
|
| 367 |
+
"eval_samples_per_second": 18.582,
|
| 368 |
+
"eval_steps_per_second": 4.646,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.67,
|
| 373 |
+
"learning_rate": 3e-05,
|
| 374 |
+
"loss": 0.4505,
|
| 375 |
+
"step": 250
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.67,
|
| 379 |
+
"eval_accuracy": 0.5032894736842105,
|
| 380 |
+
"eval_loss": 0.5494562387466431,
|
| 381 |
+
"eval_runtime": 16.3671,
|
| 382 |
+
"eval_samples_per_second": 18.574,
|
| 383 |
+
"eval_steps_per_second": 4.643,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.74,
|
| 388 |
+
"learning_rate": 3e-05,
|
| 389 |
+
"loss": 0.3958,
|
| 390 |
+
"step": 260
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.74,
|
| 394 |
+
"eval_accuracy": 0.5098684210526315,
|
| 395 |
+
"eval_loss": 0.5593812465667725,
|
| 396 |
+
"eval_runtime": 16.3598,
|
| 397 |
+
"eval_samples_per_second": 18.582,
|
| 398 |
+
"eval_steps_per_second": 4.646,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.8,
|
| 403 |
+
"learning_rate": 3e-05,
|
| 404 |
+
"loss": 0.4432,
|
| 405 |
+
"step": 270
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.8,
|
| 409 |
+
"eval_accuracy": 0.5164473684210527,
|
| 410 |
+
"eval_loss": 0.5492013096809387,
|
| 411 |
+
"eval_runtime": 16.3635,
|
| 412 |
+
"eval_samples_per_second": 18.578,
|
| 413 |
+
"eval_steps_per_second": 4.644,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.87,
|
| 418 |
+
"learning_rate": 3e-05,
|
| 419 |
+
"loss": 0.4067,
|
| 420 |
+
"step": 280
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.87,
|
| 424 |
+
"eval_accuracy": 0.506578947368421,
|
| 425 |
+
"eval_loss": 0.6023809313774109,
|
| 426 |
+
"eval_runtime": 16.3658,
|
| 427 |
+
"eval_samples_per_second": 18.575,
|
| 428 |
+
"eval_steps_per_second": 4.644,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.94,
|
| 433 |
+
"learning_rate": 3e-05,
|
| 434 |
+
"loss": 0.3988,
|
| 435 |
+
"step": 290
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.94,
|
| 439 |
+
"eval_accuracy": 0.5098684210526315,
|
| 440 |
+
"eval_loss": 0.5606762766838074,
|
| 441 |
+
"eval_runtime": 16.3642,
|
| 442 |
+
"eval_samples_per_second": 18.577,
|
| 443 |
+
"eval_steps_per_second": 4.644,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.0,
|
| 448 |
+
"learning_rate": 3e-05,
|
| 449 |
+
"loss": 0.3992,
|
| 450 |
+
"step": 300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.0,
|
| 454 |
+
"eval_accuracy": 0.5164473684210527,
|
| 455 |
+
"eval_loss": 0.5669550895690918,
|
| 456 |
+
"eval_runtime": 16.3688,
|
| 457 |
+
"eval_samples_per_second": 18.572,
|
| 458 |
+
"eval_steps_per_second": 4.643,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.07,
|
| 463 |
+
"learning_rate": 3e-05,
|
| 464 |
+
"loss": 0.2304,
|
| 465 |
+
"step": 310
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.07,
|
| 469 |
+
"eval_accuracy": 0.5361842105263158,
|
| 470 |
+
"eval_loss": 0.8199814558029175,
|
| 471 |
+
"eval_runtime": 16.3644,
|
| 472 |
+
"eval_samples_per_second": 18.577,
|
| 473 |
+
"eval_steps_per_second": 4.644,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.14,
|
| 478 |
+
"learning_rate": 3e-05,
|
| 479 |
+
"loss": 0.1696,
|
| 480 |
+
"step": 320
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.14,
|
| 484 |
+
"eval_accuracy": 0.5296052631578947,
|
| 485 |
+
"eval_loss": 0.9087279438972473,
|
| 486 |
+
"eval_runtime": 16.362,
|
| 487 |
+
"eval_samples_per_second": 18.58,
|
| 488 |
+
"eval_steps_per_second": 4.645,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.2,
|
| 493 |
+
"learning_rate": 3e-05,
|
| 494 |
+
"loss": 0.2255,
|
| 495 |
+
"step": 330
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.2,
|
| 499 |
+
"eval_accuracy": 0.5361842105263158,
|
| 500 |
+
"eval_loss": 0.7565640211105347,
|
| 501 |
+
"eval_runtime": 16.3681,
|
| 502 |
+
"eval_samples_per_second": 18.573,
|
| 503 |
+
"eval_steps_per_second": 4.643,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 2.27,
|
| 508 |
+
"learning_rate": 3e-05,
|
| 509 |
+
"loss": 0.1923,
|
| 510 |
+
"step": 340
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.27,
|
| 514 |
+
"eval_accuracy": 0.5197368421052632,
|
| 515 |
+
"eval_loss": 0.701989471912384,
|
| 516 |
+
"eval_runtime": 16.3692,
|
| 517 |
+
"eval_samples_per_second": 18.571,
|
| 518 |
+
"eval_steps_per_second": 4.643,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.34,
|
| 523 |
+
"learning_rate": 3e-05,
|
| 524 |
+
"loss": 0.281,
|
| 525 |
+
"step": 350
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.34,
|
| 529 |
+
"eval_accuracy": 0.5032894736842105,
|
| 530 |
+
"eval_loss": 0.6653422117233276,
|
| 531 |
+
"eval_runtime": 16.3703,
|
| 532 |
+
"eval_samples_per_second": 18.57,
|
| 533 |
+
"eval_steps_per_second": 4.643,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.4,
|
| 538 |
+
"learning_rate": 3e-05,
|
| 539 |
+
"loss": 0.2311,
|
| 540 |
+
"step": 360
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.4,
|
| 544 |
+
"eval_accuracy": 0.5131578947368421,
|
| 545 |
+
"eval_loss": 0.6411683559417725,
|
| 546 |
+
"eval_runtime": 16.3702,
|
| 547 |
+
"eval_samples_per_second": 18.57,
|
| 548 |
+
"eval_steps_per_second": 4.643,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.47,
|
| 553 |
+
"learning_rate": 3e-05,
|
| 554 |
+
"loss": 0.1523,
|
| 555 |
+
"step": 370
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.47,
|
| 559 |
+
"eval_accuracy": 0.5230263157894737,
|
| 560 |
+
"eval_loss": 0.8846220970153809,
|
| 561 |
+
"eval_runtime": 16.3728,
|
| 562 |
+
"eval_samples_per_second": 18.567,
|
| 563 |
+
"eval_steps_per_second": 4.642,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.54,
|
| 568 |
+
"learning_rate": 3e-05,
|
| 569 |
+
"loss": 0.2451,
|
| 570 |
+
"step": 380
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.54,
|
| 574 |
+
"eval_accuracy": 0.5164473684210527,
|
| 575 |
+
"eval_loss": 0.9251819252967834,
|
| 576 |
+
"eval_runtime": 16.379,
|
| 577 |
+
"eval_samples_per_second": 18.56,
|
| 578 |
+
"eval_steps_per_second": 4.64,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.6,
|
| 583 |
+
"learning_rate": 3e-05,
|
| 584 |
+
"loss": 0.2022,
|
| 585 |
+
"step": 390
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.6,
|
| 589 |
+
"eval_accuracy": 0.5197368421052632,
|
| 590 |
+
"eval_loss": 0.7422206401824951,
|
| 591 |
+
"eval_runtime": 16.3727,
|
| 592 |
+
"eval_samples_per_second": 18.567,
|
| 593 |
+
"eval_steps_per_second": 4.642,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.67,
|
| 598 |
+
"learning_rate": 3e-05,
|
| 599 |
+
"loss": 0.217,
|
| 600 |
+
"step": 400
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 2.67,
|
| 604 |
+
"eval_accuracy": 0.5328947368421053,
|
| 605 |
+
"eval_loss": 0.7557851076126099,
|
| 606 |
+
"eval_runtime": 16.3638,
|
| 607 |
+
"eval_samples_per_second": 18.578,
|
| 608 |
+
"eval_steps_per_second": 4.644,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.74,
|
| 613 |
+
"learning_rate": 3e-05,
|
| 614 |
+
"loss": 0.165,
|
| 615 |
+
"step": 410
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.74,
|
| 619 |
+
"eval_accuracy": 0.5427631578947368,
|
| 620 |
+
"eval_loss": 0.7846018075942993,
|
| 621 |
+
"eval_runtime": 16.3674,
|
| 622 |
+
"eval_samples_per_second": 18.574,
|
| 623 |
+
"eval_steps_per_second": 4.643,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.8,
|
| 628 |
+
"learning_rate": 3e-05,
|
| 629 |
+
"loss": 0.2025,
|
| 630 |
+
"step": 420
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.8,
|
| 634 |
+
"eval_accuracy": 0.5230263157894737,
|
| 635 |
+
"eval_loss": 0.725389301776886,
|
| 636 |
+
"eval_runtime": 16.3775,
|
| 637 |
+
"eval_samples_per_second": 18.562,
|
| 638 |
+
"eval_steps_per_second": 4.641,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.87,
|
| 643 |
+
"learning_rate": 3e-05,
|
| 644 |
+
"loss": 0.2201,
|
| 645 |
+
"step": 430
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 2.87,
|
| 649 |
+
"eval_accuracy": 0.5296052631578947,
|
| 650 |
+
"eval_loss": 0.6530900001525879,
|
| 651 |
+
"eval_runtime": 16.3694,
|
| 652 |
+
"eval_samples_per_second": 18.571,
|
| 653 |
+
"eval_steps_per_second": 4.643,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.94,
|
| 658 |
+
"learning_rate": 3e-05,
|
| 659 |
+
"loss": 0.2037,
|
| 660 |
+
"step": 440
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.94,
|
| 664 |
+
"eval_accuracy": 0.5493421052631579,
|
| 665 |
+
"eval_loss": 0.7827179431915283,
|
| 666 |
+
"eval_runtime": 16.3682,
|
| 667 |
+
"eval_samples_per_second": 18.573,
|
| 668 |
+
"eval_steps_per_second": 4.643,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.98,
|
| 673 |
+
"step": 447,
|
| 674 |
+
"total_flos": 1.09848374069035e+17,
|
| 675 |
+
"train_loss": 0.43748926956381573,
|
| 676 |
+
"train_runtime": 1886.9121,
|
| 677 |
+
"train_samples_per_second": 3.809,
|
| 678 |
+
"train_steps_per_second": 0.237
|
| 679 |
+
}
|
| 680 |
+
],
|
| 681 |
+
"logging_steps": 10,
|
| 682 |
+
"max_steps": 447,
|
| 683 |
+
"num_input_tokens_seen": 0,
|
| 684 |
+
"num_train_epochs": 3,
|
| 685 |
+
"save_steps": 250,
|
| 686 |
+
"total_flos": 1.09848374069035e+17,
|
| 687 |
+
"train_batch_size": 4,
|
| 688 |
+
"trial_name": null,
|
| 689 |
+
"trial_params": null
|
| 690 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:103e5da4968375ab36f9593bf410c45d9e405b7af46f4c859ad873d05c786bf3
|
| 3 |
+
size 6712
|