Commit
•
96712f3
1
Parent(s):
8ff07a9
End of training
Browse files- README.md +195 -0
- all_results.json +13 -0
- config.json +71 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- train_results.json +8 -0
- trainer_state.json +1944 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/convnextv2-tiny-1k-224
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: convnextv2-tiny-1k-224-finetuned-fullwear
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Image Classification
|
| 15 |
+
type: image-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: imagefolder
|
| 18 |
+
type: imagefolder
|
| 19 |
+
config: default
|
| 20 |
+
split: train
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.8402777777777778
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# convnextv2-tiny-1k-224-finetuned-fullwear
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [facebook/convnextv2-tiny-1k-224](https://huggingface.co/facebook/convnextv2-tiny-1k-224) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.5203
|
| 36 |
+
- Accuracy: 0.8403
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 5e-05
|
| 56 |
+
- train_batch_size: 32
|
| 57 |
+
- eval_batch_size: 32
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 128
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
+
- num_epochs: 120
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:--------:|:----:|:---------------:|:--------:|
|
| 70 |
+
| 2.4871 | 0.9756 | 10 | 2.4771 | 0.0694 |
|
| 71 |
+
| 2.4464 | 1.9512 | 20 | 2.4333 | 0.1528 |
|
| 72 |
+
| 2.3911 | 2.9268 | 30 | 2.3670 | 0.2778 |
|
| 73 |
+
| 2.3204 | 4.0 | 41 | 2.2617 | 0.3681 |
|
| 74 |
+
| 2.206 | 4.9756 | 51 | 2.1445 | 0.3958 |
|
| 75 |
+
| 2.0869 | 5.9512 | 61 | 2.0146 | 0.4444 |
|
| 76 |
+
| 1.9756 | 6.9268 | 71 | 1.8763 | 0.5139 |
|
| 77 |
+
| 1.8124 | 8.0 | 82 | 1.7422 | 0.5486 |
|
| 78 |
+
| 1.6624 | 8.9756 | 92 | 1.6629 | 0.5903 |
|
| 79 |
+
| 1.587 | 9.9512 | 102 | 1.5474 | 0.6111 |
|
| 80 |
+
| 1.4746 | 10.9268 | 112 | 1.4577 | 0.625 |
|
| 81 |
+
| 1.359 | 12.0 | 123 | 1.3055 | 0.6736 |
|
| 82 |
+
| 1.2412 | 12.9756 | 133 | 1.2241 | 0.6736 |
|
| 83 |
+
| 1.1374 | 13.9512 | 143 | 1.2003 | 0.6736 |
|
| 84 |
+
| 1.0194 | 14.9268 | 153 | 1.0233 | 0.7569 |
|
| 85 |
+
| 0.9705 | 16.0 | 164 | 0.9492 | 0.7847 |
|
| 86 |
+
| 0.8949 | 16.9756 | 174 | 0.9246 | 0.75 |
|
| 87 |
+
| 0.7959 | 17.9512 | 184 | 0.8148 | 0.7639 |
|
| 88 |
+
| 0.7491 | 18.9268 | 194 | 0.7858 | 0.7569 |
|
| 89 |
+
| 0.6783 | 20.0 | 205 | 0.8010 | 0.7569 |
|
| 90 |
+
| 0.6257 | 20.9756 | 215 | 0.7295 | 0.7847 |
|
| 91 |
+
| 0.5999 | 21.9512 | 225 | 0.6219 | 0.8333 |
|
| 92 |
+
| 0.5701 | 22.9268 | 235 | 0.5932 | 0.8403 |
|
| 93 |
+
| 0.4926 | 24.0 | 246 | 0.5970 | 0.8056 |
|
| 94 |
+
| 0.4692 | 24.9756 | 256 | 0.6298 | 0.8194 |
|
| 95 |
+
| 0.4393 | 25.9512 | 266 | 0.5857 | 0.8056 |
|
| 96 |
+
| 0.419 | 26.9268 | 276 | 0.5203 | 0.8542 |
|
| 97 |
+
| 0.3454 | 28.0 | 287 | 0.6084 | 0.8264 |
|
| 98 |
+
| 0.36 | 28.9756 | 297 | 0.5928 | 0.8264 |
|
| 99 |
+
| 0.3265 | 29.9512 | 307 | 0.5303 | 0.8403 |
|
| 100 |
+
| 0.3278 | 30.9268 | 317 | 0.6049 | 0.8194 |
|
| 101 |
+
| 0.2766 | 32.0 | 328 | 0.5656 | 0.8264 |
|
| 102 |
+
| 0.2805 | 32.9756 | 338 | 0.5003 | 0.8681 |
|
| 103 |
+
| 0.2505 | 33.9512 | 348 | 0.5412 | 0.8403 |
|
| 104 |
+
| 0.2464 | 34.9268 | 358 | 0.5410 | 0.8333 |
|
| 105 |
+
| 0.2166 | 36.0 | 369 | 0.5000 | 0.8472 |
|
| 106 |
+
| 0.2 | 36.9756 | 379 | 0.5053 | 0.8056 |
|
| 107 |
+
| 0.1914 | 37.9512 | 389 | 0.5161 | 0.8403 |
|
| 108 |
+
| 0.186 | 38.9268 | 399 | 0.4242 | 0.8681 |
|
| 109 |
+
| 0.1592 | 40.0 | 410 | 0.5059 | 0.8472 |
|
| 110 |
+
| 0.1598 | 40.9756 | 420 | 0.5143 | 0.8264 |
|
| 111 |
+
| 0.1565 | 41.9512 | 430 | 0.4703 | 0.8542 |
|
| 112 |
+
| 0.1598 | 42.9268 | 440 | 0.4384 | 0.8542 |
|
| 113 |
+
| 0.139 | 44.0 | 451 | 0.4850 | 0.8403 |
|
| 114 |
+
| 0.1137 | 44.9756 | 461 | 0.4405 | 0.8542 |
|
| 115 |
+
| 0.1158 | 45.9512 | 471 | 0.5250 | 0.8333 |
|
| 116 |
+
| 0.1192 | 46.9268 | 481 | 0.5843 | 0.8194 |
|
| 117 |
+
| 0.1271 | 48.0 | 492 | 0.4498 | 0.8611 |
|
| 118 |
+
| 0.0914 | 48.9756 | 502 | 0.5167 | 0.8264 |
|
| 119 |
+
| 0.1079 | 49.9512 | 512 | 0.4648 | 0.8681 |
|
| 120 |
+
| 0.091 | 50.9268 | 522 | 0.5321 | 0.8194 |
|
| 121 |
+
| 0.1053 | 52.0 | 533 | 0.4402 | 0.8611 |
|
| 122 |
+
| 0.0842 | 52.9756 | 543 | 0.4776 | 0.8542 |
|
| 123 |
+
| 0.0961 | 53.9512 | 553 | 0.4762 | 0.8681 |
|
| 124 |
+
| 0.0896 | 54.9268 | 563 | 0.4477 | 0.8681 |
|
| 125 |
+
| 0.0876 | 56.0 | 574 | 0.4951 | 0.8472 |
|
| 126 |
+
| 0.0855 | 56.9756 | 584 | 0.5653 | 0.8125 |
|
| 127 |
+
| 0.073 | 57.9512 | 594 | 0.5315 | 0.8472 |
|
| 128 |
+
| 0.0804 | 58.9268 | 604 | 0.5064 | 0.8681 |
|
| 129 |
+
| 0.0765 | 60.0 | 615 | 0.6316 | 0.8264 |
|
| 130 |
+
| 0.0782 | 60.9756 | 625 | 0.5733 | 0.8056 |
|
| 131 |
+
| 0.069 | 61.9512 | 635 | 0.6994 | 0.8056 |
|
| 132 |
+
| 0.0809 | 62.9268 | 645 | 0.4898 | 0.8611 |
|
| 133 |
+
| 0.0829 | 64.0 | 656 | 0.6042 | 0.8194 |
|
| 134 |
+
| 0.0735 | 64.9756 | 666 | 0.4758 | 0.8611 |
|
| 135 |
+
| 0.0763 | 65.9512 | 676 | 0.4921 | 0.8542 |
|
| 136 |
+
| 0.0565 | 66.9268 | 686 | 0.4700 | 0.8681 |
|
| 137 |
+
| 0.062 | 68.0 | 697 | 0.4944 | 0.8819 |
|
| 138 |
+
| 0.0644 | 68.9756 | 707 | 0.4733 | 0.8681 |
|
| 139 |
+
| 0.0659 | 69.9512 | 717 | 0.4703 | 0.8819 |
|
| 140 |
+
| 0.0625 | 70.9268 | 727 | 0.5075 | 0.8542 |
|
| 141 |
+
| 0.042 | 72.0 | 738 | 0.5464 | 0.8264 |
|
| 142 |
+
| 0.056 | 72.9756 | 748 | 0.5186 | 0.8333 |
|
| 143 |
+
| 0.0858 | 73.9512 | 758 | 0.5403 | 0.8264 |
|
| 144 |
+
| 0.0616 | 74.9268 | 768 | 0.5104 | 0.8472 |
|
| 145 |
+
| 0.0777 | 76.0 | 779 | 0.5516 | 0.8403 |
|
| 146 |
+
| 0.0668 | 76.9756 | 789 | 0.4918 | 0.8611 |
|
| 147 |
+
| 0.0585 | 77.9512 | 799 | 0.5692 | 0.8403 |
|
| 148 |
+
| 0.0562 | 78.9268 | 809 | 0.5734 | 0.8403 |
|
| 149 |
+
| 0.0653 | 80.0 | 820 | 0.5403 | 0.8264 |
|
| 150 |
+
| 0.0434 | 80.9756 | 830 | 0.5108 | 0.8333 |
|
| 151 |
+
| 0.0483 | 81.9512 | 840 | 0.5699 | 0.8125 |
|
| 152 |
+
| 0.0329 | 82.9268 | 850 | 0.6028 | 0.8056 |
|
| 153 |
+
| 0.0431 | 84.0 | 861 | 0.5230 | 0.8333 |
|
| 154 |
+
| 0.042 | 84.9756 | 871 | 0.5875 | 0.8194 |
|
| 155 |
+
| 0.0449 | 85.9512 | 881 | 0.5180 | 0.8611 |
|
| 156 |
+
| 0.0512 | 86.9268 | 891 | 0.5425 | 0.8194 |
|
| 157 |
+
| 0.0545 | 88.0 | 902 | 0.5690 | 0.8264 |
|
| 158 |
+
| 0.0496 | 88.9756 | 912 | 0.5619 | 0.8611 |
|
| 159 |
+
| 0.0449 | 89.9512 | 922 | 0.5626 | 0.8333 |
|
| 160 |
+
| 0.0405 | 90.9268 | 932 | 0.5267 | 0.8403 |
|
| 161 |
+
| 0.0344 | 92.0 | 943 | 0.5617 | 0.8403 |
|
| 162 |
+
| 0.0421 | 92.9756 | 953 | 0.5400 | 0.8611 |
|
| 163 |
+
| 0.0341 | 93.9512 | 963 | 0.5729 | 0.8333 |
|
| 164 |
+
| 0.0492 | 94.9268 | 973 | 0.5855 | 0.8056 |
|
| 165 |
+
| 0.0374 | 96.0 | 984 | 0.6113 | 0.8125 |
|
| 166 |
+
| 0.0375 | 96.9756 | 994 | 0.5511 | 0.8403 |
|
| 167 |
+
| 0.0373 | 97.9512 | 1004 | 0.4942 | 0.8542 |
|
| 168 |
+
| 0.0447 | 98.9268 | 1014 | 0.5031 | 0.8542 |
|
| 169 |
+
| 0.0519 | 100.0 | 1025 | 0.5349 | 0.8542 |
|
| 170 |
+
| 0.0387 | 100.9756 | 1035 | 0.5511 | 0.8542 |
|
| 171 |
+
| 0.0256 | 101.9512 | 1045 | 0.5319 | 0.8403 |
|
| 172 |
+
| 0.043 | 102.9268 | 1055 | 0.5605 | 0.8264 |
|
| 173 |
+
| 0.029 | 104.0 | 1066 | 0.5776 | 0.8403 |
|
| 174 |
+
| 0.0379 | 104.9756 | 1076 | 0.5697 | 0.8472 |
|
| 175 |
+
| 0.0445 | 105.9512 | 1086 | 0.5133 | 0.8681 |
|
| 176 |
+
| 0.0267 | 106.9268 | 1096 | 0.5076 | 0.8681 |
|
| 177 |
+
| 0.044 | 108.0 | 1107 | 0.5260 | 0.8403 |
|
| 178 |
+
| 0.0263 | 108.9756 | 1117 | 0.5101 | 0.8542 |
|
| 179 |
+
| 0.0247 | 109.9512 | 1127 | 0.4972 | 0.8542 |
|
| 180 |
+
| 0.0441 | 110.9268 | 1137 | 0.5094 | 0.8472 |
|
| 181 |
+
| 0.0263 | 112.0 | 1148 | 0.5259 | 0.8333 |
|
| 182 |
+
| 0.0247 | 112.9756 | 1158 | 0.5323 | 0.8403 |
|
| 183 |
+
| 0.0356 | 113.9512 | 1168 | 0.5275 | 0.8403 |
|
| 184 |
+
| 0.0297 | 114.9268 | 1178 | 0.5240 | 0.8333 |
|
| 185 |
+
| 0.044 | 116.0 | 1189 | 0.5201 | 0.8472 |
|
| 186 |
+
| 0.031 | 116.9756 | 1199 | 0.5203 | 0.8403 |
|
| 187 |
+
| 0.0369 | 117.0732 | 1200 | 0.5203 | 0.8403 |
|
| 188 |
+
|
| 189 |
+
|
| 190 |
+
### Framework versions
|
| 191 |
+
|
| 192 |
+
- Transformers 4.44.0
|
| 193 |
+
- Pytorch 2.4.0
|
| 194 |
+
- Datasets 2.21.0
|
| 195 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 117.07317073170732,
|
| 3 |
+
"eval_accuracy": 0.8402777777777778,
|
| 4 |
+
"eval_loss": 0.5202847123146057,
|
| 5 |
+
"eval_runtime": 3.1405,
|
| 6 |
+
"eval_samples_per_second": 45.852,
|
| 7 |
+
"eval_steps_per_second": 1.592,
|
| 8 |
+
"total_flos": 3.819974210196996e+18,
|
| 9 |
+
"train_loss": 0.3624983422954877,
|
| 10 |
+
"train_runtime": 4158.3882,
|
| 11 |
+
"train_samples_per_second": 37.399,
|
| 12 |
+
"train_steps_per_second": 0.289
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/convnextv2-tiny-1k-224",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ConvNextV2ForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"depths": [
|
| 7 |
+
3,
|
| 8 |
+
3,
|
| 9 |
+
9,
|
| 10 |
+
3
|
| 11 |
+
],
|
| 12 |
+
"drop_path_rate": 0.0,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_sizes": [
|
| 15 |
+
96,
|
| 16 |
+
192,
|
| 17 |
+
384,
|
| 18 |
+
768
|
| 19 |
+
],
|
| 20 |
+
"id2label": {
|
| 21 |
+
"0": "Co_ords",
|
| 22 |
+
"1": "Kaftan",
|
| 23 |
+
"2": "anarkali",
|
| 24 |
+
"3": "cloaks_abaya",
|
| 25 |
+
"4": "dress",
|
| 26 |
+
"5": "dungaree",
|
| 27 |
+
"6": "ethnic",
|
| 28 |
+
"7": "gown",
|
| 29 |
+
"8": "jumpsuit",
|
| 30 |
+
"9": "robe",
|
| 31 |
+
"10": "salwar_suit",
|
| 32 |
+
"11": "saree"
|
| 33 |
+
},
|
| 34 |
+
"image_size": 224,
|
| 35 |
+
"initializer_range": 0.02,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"Co_ords": 0,
|
| 38 |
+
"Kaftan": 1,
|
| 39 |
+
"anarkali": 2,
|
| 40 |
+
"cloaks_abaya": 3,
|
| 41 |
+
"dress": 4,
|
| 42 |
+
"dungaree": 5,
|
| 43 |
+
"ethnic": 6,
|
| 44 |
+
"gown": 7,
|
| 45 |
+
"jumpsuit": 8,
|
| 46 |
+
"robe": 9,
|
| 47 |
+
"salwar_suit": 10,
|
| 48 |
+
"saree": 11
|
| 49 |
+
},
|
| 50 |
+
"layer_norm_eps": 1e-12,
|
| 51 |
+
"model_type": "convnextv2",
|
| 52 |
+
"num_channels": 3,
|
| 53 |
+
"num_stages": 4,
|
| 54 |
+
"out_features": [
|
| 55 |
+
"stage4"
|
| 56 |
+
],
|
| 57 |
+
"out_indices": [
|
| 58 |
+
4
|
| 59 |
+
],
|
| 60 |
+
"patch_size": 4,
|
| 61 |
+
"problem_type": "single_label_classification",
|
| 62 |
+
"stage_names": [
|
| 63 |
+
"stem",
|
| 64 |
+
"stage1",
|
| 65 |
+
"stage2",
|
| 66 |
+
"stage3",
|
| 67 |
+
"stage4"
|
| 68 |
+
],
|
| 69 |
+
"torch_dtype": "float32",
|
| 70 |
+
"transformers_version": "4.44.0"
|
| 71 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 117.07317073170732,
|
| 3 |
+
"eval_accuracy": 0.8402777777777778,
|
| 4 |
+
"eval_loss": 0.5202847123146057,
|
| 5 |
+
"eval_runtime": 3.1405,
|
| 6 |
+
"eval_samples_per_second": 45.852,
|
| 7 |
+
"eval_steps_per_second": 1.592
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8800c431490f289e457718c9f52dffebdccfedd69f45c4922365a8a84a3b5788
|
| 3 |
+
size 111526592
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_pct": 0.875,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.229,
|
| 14 |
+
0.224,
|
| 15 |
+
0.225
|
| 16 |
+
],
|
| 17 |
+
"resample": 3,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"shortest_edge": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 117.07317073170732,
|
| 3 |
+
"total_flos": 3.819974210196996e+18,
|
| 4 |
+
"train_loss": 0.3624983422954877,
|
| 5 |
+
"train_runtime": 4158.3882,
|
| 6 |
+
"train_samples_per_second": 37.399,
|
| 7 |
+
"train_steps_per_second": 0.289
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1944 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 117.07317073170732,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.975609756097561,
|
| 13 |
+
"grad_norm": 3.532809257507324,
|
| 14 |
+
"learning_rate": 4.166666666666667e-06,
|
| 15 |
+
"loss": 2.4871,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.975609756097561,
|
| 20 |
+
"eval_accuracy": 0.06944444444444445,
|
| 21 |
+
"eval_loss": 2.4770686626434326,
|
| 22 |
+
"eval_runtime": 3.5274,
|
| 23 |
+
"eval_samples_per_second": 40.824,
|
| 24 |
+
"eval_steps_per_second": 1.417,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.951219512195122,
|
| 29 |
+
"grad_norm": 5.7173171043396,
|
| 30 |
+
"learning_rate": 8.333333333333334e-06,
|
| 31 |
+
"loss": 2.4464,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.951219512195122,
|
| 36 |
+
"eval_accuracy": 0.1527777777777778,
|
| 37 |
+
"eval_loss": 2.4332642555236816,
|
| 38 |
+
"eval_runtime": 2.9731,
|
| 39 |
+
"eval_samples_per_second": 48.435,
|
| 40 |
+
"eval_steps_per_second": 1.682,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.926829268292683,
|
| 45 |
+
"grad_norm": 6.289983749389648,
|
| 46 |
+
"learning_rate": 1.25e-05,
|
| 47 |
+
"loss": 2.3911,
|
| 48 |
+
"step": 30
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.926829268292683,
|
| 52 |
+
"eval_accuracy": 0.2777777777777778,
|
| 53 |
+
"eval_loss": 2.3669984340667725,
|
| 54 |
+
"eval_runtime": 2.9436,
|
| 55 |
+
"eval_samples_per_second": 48.919,
|
| 56 |
+
"eval_steps_per_second": 1.699,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.902439024390244,
|
| 61 |
+
"grad_norm": 12.364039421081543,
|
| 62 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 63 |
+
"loss": 2.3204,
|
| 64 |
+
"step": 40
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.0,
|
| 68 |
+
"eval_accuracy": 0.3680555555555556,
|
| 69 |
+
"eval_loss": 2.261659860610962,
|
| 70 |
+
"eval_runtime": 2.9933,
|
| 71 |
+
"eval_samples_per_second": 48.107,
|
| 72 |
+
"eval_steps_per_second": 1.67,
|
| 73 |
+
"step": 41
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.878048780487805,
|
| 77 |
+
"grad_norm": 14.902889251708984,
|
| 78 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 79 |
+
"loss": 2.206,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.975609756097561,
|
| 84 |
+
"eval_accuracy": 0.3958333333333333,
|
| 85 |
+
"eval_loss": 2.144454002380371,
|
| 86 |
+
"eval_runtime": 3.011,
|
| 87 |
+
"eval_samples_per_second": 47.824,
|
| 88 |
+
"eval_steps_per_second": 1.661,
|
| 89 |
+
"step": 51
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.853658536585366,
|
| 93 |
+
"grad_norm": 17.006898880004883,
|
| 94 |
+
"learning_rate": 2.5e-05,
|
| 95 |
+
"loss": 2.0869,
|
| 96 |
+
"step": 60
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.951219512195122,
|
| 100 |
+
"eval_accuracy": 0.4444444444444444,
|
| 101 |
+
"eval_loss": 2.0146427154541016,
|
| 102 |
+
"eval_runtime": 3.0417,
|
| 103 |
+
"eval_samples_per_second": 47.342,
|
| 104 |
+
"eval_steps_per_second": 1.644,
|
| 105 |
+
"step": 61
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.829268292682927,
|
| 109 |
+
"grad_norm": 42.38038635253906,
|
| 110 |
+
"learning_rate": 2.916666666666667e-05,
|
| 111 |
+
"loss": 1.9756,
|
| 112 |
+
"step": 70
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 6.926829268292683,
|
| 116 |
+
"eval_accuracy": 0.5138888888888888,
|
| 117 |
+
"eval_loss": 1.8763340711593628,
|
| 118 |
+
"eval_runtime": 3.096,
|
| 119 |
+
"eval_samples_per_second": 46.512,
|
| 120 |
+
"eval_steps_per_second": 1.615,
|
| 121 |
+
"step": 71
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 7.804878048780488,
|
| 125 |
+
"grad_norm": 26.403841018676758,
|
| 126 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 127 |
+
"loss": 1.8124,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"eval_accuracy": 0.5486111111111112,
|
| 133 |
+
"eval_loss": 1.7422140836715698,
|
| 134 |
+
"eval_runtime": 3.1203,
|
| 135 |
+
"eval_samples_per_second": 46.15,
|
| 136 |
+
"eval_steps_per_second": 1.602,
|
| 137 |
+
"step": 82
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 8.78048780487805,
|
| 141 |
+
"grad_norm": 38.676876068115234,
|
| 142 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 143 |
+
"loss": 1.6624,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 8.975609756097562,
|
| 148 |
+
"eval_accuracy": 0.5902777777777778,
|
| 149 |
+
"eval_loss": 1.6628881692886353,
|
| 150 |
+
"eval_runtime": 3.1378,
|
| 151 |
+
"eval_samples_per_second": 45.893,
|
| 152 |
+
"eval_steps_per_second": 1.593,
|
| 153 |
+
"step": 92
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 9.75609756097561,
|
| 157 |
+
"grad_norm": 25.14325523376465,
|
| 158 |
+
"learning_rate": 4.166666666666667e-05,
|
| 159 |
+
"loss": 1.587,
|
| 160 |
+
"step": 100
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 9.951219512195122,
|
| 164 |
+
"eval_accuracy": 0.6111111111111112,
|
| 165 |
+
"eval_loss": 1.547376036643982,
|
| 166 |
+
"eval_runtime": 3.0786,
|
| 167 |
+
"eval_samples_per_second": 46.774,
|
| 168 |
+
"eval_steps_per_second": 1.624,
|
| 169 |
+
"step": 102
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 10.731707317073171,
|
| 173 |
+
"grad_norm": 59.02862548828125,
|
| 174 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 175 |
+
"loss": 1.4746,
|
| 176 |
+
"step": 110
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 10.926829268292684,
|
| 180 |
+
"eval_accuracy": 0.625,
|
| 181 |
+
"eval_loss": 1.4577171802520752,
|
| 182 |
+
"eval_runtime": 3.0847,
|
| 183 |
+
"eval_samples_per_second": 46.683,
|
| 184 |
+
"eval_steps_per_second": 1.621,
|
| 185 |
+
"step": 112
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 11.707317073170731,
|
| 189 |
+
"grad_norm": 39.518768310546875,
|
| 190 |
+
"learning_rate": 5e-05,
|
| 191 |
+
"loss": 1.359,
|
| 192 |
+
"step": 120
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 12.0,
|
| 196 |
+
"eval_accuracy": 0.6736111111111112,
|
| 197 |
+
"eval_loss": 1.30553138256073,
|
| 198 |
+
"eval_runtime": 3.1033,
|
| 199 |
+
"eval_samples_per_second": 46.403,
|
| 200 |
+
"eval_steps_per_second": 1.611,
|
| 201 |
+
"step": 123
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 12.682926829268293,
|
| 205 |
+
"grad_norm": 41.855445861816406,
|
| 206 |
+
"learning_rate": 4.9537037037037035e-05,
|
| 207 |
+
"loss": 1.2412,
|
| 208 |
+
"step": 130
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 12.975609756097562,
|
| 212 |
+
"eval_accuracy": 0.6736111111111112,
|
| 213 |
+
"eval_loss": 1.2240564823150635,
|
| 214 |
+
"eval_runtime": 3.1092,
|
| 215 |
+
"eval_samples_per_second": 46.314,
|
| 216 |
+
"eval_steps_per_second": 1.608,
|
| 217 |
+
"step": 133
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 13.658536585365853,
|
| 221 |
+
"grad_norm": 14.434544563293457,
|
| 222 |
+
"learning_rate": 4.9074074074074075e-05,
|
| 223 |
+
"loss": 1.1374,
|
| 224 |
+
"step": 140
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 13.951219512195122,
|
| 228 |
+
"eval_accuracy": 0.6736111111111112,
|
| 229 |
+
"eval_loss": 1.2003458738327026,
|
| 230 |
+
"eval_runtime": 3.1022,
|
| 231 |
+
"eval_samples_per_second": 46.419,
|
| 232 |
+
"eval_steps_per_second": 1.612,
|
| 233 |
+
"step": 143
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 14.634146341463415,
|
| 237 |
+
"grad_norm": 51.862064361572266,
|
| 238 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 239 |
+
"loss": 1.0194,
|
| 240 |
+
"step": 150
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 14.926829268292684,
|
| 244 |
+
"eval_accuracy": 0.7569444444444444,
|
| 245 |
+
"eval_loss": 1.0233235359191895,
|
| 246 |
+
"eval_runtime": 3.1109,
|
| 247 |
+
"eval_samples_per_second": 46.288,
|
| 248 |
+
"eval_steps_per_second": 1.607,
|
| 249 |
+
"step": 153
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 15.609756097560975,
|
| 253 |
+
"grad_norm": 59.053375244140625,
|
| 254 |
+
"learning_rate": 4.814814814814815e-05,
|
| 255 |
+
"loss": 0.9705,
|
| 256 |
+
"step": 160
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 16.0,
|
| 260 |
+
"eval_accuracy": 0.7847222222222222,
|
| 261 |
+
"eval_loss": 0.9492360353469849,
|
| 262 |
+
"eval_runtime": 3.0962,
|
| 263 |
+
"eval_samples_per_second": 46.509,
|
| 264 |
+
"eval_steps_per_second": 1.615,
|
| 265 |
+
"step": 164
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 16.585365853658537,
|
| 269 |
+
"grad_norm": 23.618066787719727,
|
| 270 |
+
"learning_rate": 4.768518518518519e-05,
|
| 271 |
+
"loss": 0.8949,
|
| 272 |
+
"step": 170
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 16.975609756097562,
|
| 276 |
+
"eval_accuracy": 0.75,
|
| 277 |
+
"eval_loss": 0.9246302843093872,
|
| 278 |
+
"eval_runtime": 3.3666,
|
| 279 |
+
"eval_samples_per_second": 42.773,
|
| 280 |
+
"eval_steps_per_second": 1.485,
|
| 281 |
+
"step": 174
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 17.5609756097561,
|
| 285 |
+
"grad_norm": 37.61671447753906,
|
| 286 |
+
"learning_rate": 4.722222222222222e-05,
|
| 287 |
+
"loss": 0.7959,
|
| 288 |
+
"step": 180
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 17.951219512195124,
|
| 292 |
+
"eval_accuracy": 0.7638888888888888,
|
| 293 |
+
"eval_loss": 0.8147740960121155,
|
| 294 |
+
"eval_runtime": 3.1586,
|
| 295 |
+
"eval_samples_per_second": 45.589,
|
| 296 |
+
"eval_steps_per_second": 1.583,
|
| 297 |
+
"step": 184
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 18.536585365853657,
|
| 301 |
+
"grad_norm": 22.54252052307129,
|
| 302 |
+
"learning_rate": 4.675925925925926e-05,
|
| 303 |
+
"loss": 0.7491,
|
| 304 |
+
"step": 190
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 18.926829268292682,
|
| 308 |
+
"eval_accuracy": 0.7569444444444444,
|
| 309 |
+
"eval_loss": 0.785780668258667,
|
| 310 |
+
"eval_runtime": 3.1126,
|
| 311 |
+
"eval_samples_per_second": 46.264,
|
| 312 |
+
"eval_steps_per_second": 1.606,
|
| 313 |
+
"step": 194
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 19.51219512195122,
|
| 317 |
+
"grad_norm": 73.11436462402344,
|
| 318 |
+
"learning_rate": 4.62962962962963e-05,
|
| 319 |
+
"loss": 0.6783,
|
| 320 |
+
"step": 200
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 20.0,
|
| 324 |
+
"eval_accuracy": 0.7569444444444444,
|
| 325 |
+
"eval_loss": 0.8010105490684509,
|
| 326 |
+
"eval_runtime": 3.0934,
|
| 327 |
+
"eval_samples_per_second": 46.55,
|
| 328 |
+
"eval_steps_per_second": 1.616,
|
| 329 |
+
"step": 205
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 20.48780487804878,
|
| 333 |
+
"grad_norm": 25.613719940185547,
|
| 334 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 335 |
+
"loss": 0.6257,
|
| 336 |
+
"step": 210
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 20.975609756097562,
|
| 340 |
+
"eval_accuracy": 0.7847222222222222,
|
| 341 |
+
"eval_loss": 0.7294739484786987,
|
| 342 |
+
"eval_runtime": 3.0855,
|
| 343 |
+
"eval_samples_per_second": 46.67,
|
| 344 |
+
"eval_steps_per_second": 1.62,
|
| 345 |
+
"step": 215
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 21.463414634146343,
|
| 349 |
+
"grad_norm": 21.02585220336914,
|
| 350 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 351 |
+
"loss": 0.5999,
|
| 352 |
+
"step": 220
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 21.951219512195124,
|
| 356 |
+
"eval_accuracy": 0.8333333333333334,
|
| 357 |
+
"eval_loss": 0.6218506097793579,
|
| 358 |
+
"eval_runtime": 3.0821,
|
| 359 |
+
"eval_samples_per_second": 46.722,
|
| 360 |
+
"eval_steps_per_second": 1.622,
|
| 361 |
+
"step": 225
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 22.4390243902439,
|
| 365 |
+
"grad_norm": 24.335525512695312,
|
| 366 |
+
"learning_rate": 4.490740740740741e-05,
|
| 367 |
+
"loss": 0.5701,
|
| 368 |
+
"step": 230
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 22.926829268292682,
|
| 372 |
+
"eval_accuracy": 0.8402777777777778,
|
| 373 |
+
"eval_loss": 0.5932477116584778,
|
| 374 |
+
"eval_runtime": 3.1062,
|
| 375 |
+
"eval_samples_per_second": 46.359,
|
| 376 |
+
"eval_steps_per_second": 1.61,
|
| 377 |
+
"step": 235
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 23.414634146341463,
|
| 381 |
+
"grad_norm": 25.651668548583984,
|
| 382 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 383 |
+
"loss": 0.4926,
|
| 384 |
+
"step": 240
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 24.0,
|
| 388 |
+
"eval_accuracy": 0.8055555555555556,
|
| 389 |
+
"eval_loss": 0.5970398783683777,
|
| 390 |
+
"eval_runtime": 3.1225,
|
| 391 |
+
"eval_samples_per_second": 46.116,
|
| 392 |
+
"eval_steps_per_second": 1.601,
|
| 393 |
+
"step": 246
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 24.390243902439025,
|
| 397 |
+
"grad_norm": 46.76804733276367,
|
| 398 |
+
"learning_rate": 4.3981481481481486e-05,
|
| 399 |
+
"loss": 0.4692,
|
| 400 |
+
"step": 250
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 24.975609756097562,
|
| 404 |
+
"eval_accuracy": 0.8194444444444444,
|
| 405 |
+
"eval_loss": 0.6297520995140076,
|
| 406 |
+
"eval_runtime": 3.3496,
|
| 407 |
+
"eval_samples_per_second": 42.99,
|
| 408 |
+
"eval_steps_per_second": 1.493,
|
| 409 |
+
"step": 256
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 25.365853658536587,
|
| 413 |
+
"grad_norm": 28.9127140045166,
|
| 414 |
+
"learning_rate": 4.351851851851852e-05,
|
| 415 |
+
"loss": 0.4393,
|
| 416 |
+
"step": 260
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 25.951219512195124,
|
| 420 |
+
"eval_accuracy": 0.8055555555555556,
|
| 421 |
+
"eval_loss": 0.5856587886810303,
|
| 422 |
+
"eval_runtime": 3.1545,
|
| 423 |
+
"eval_samples_per_second": 45.648,
|
| 424 |
+
"eval_steps_per_second": 1.585,
|
| 425 |
+
"step": 266
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 26.341463414634145,
|
| 429 |
+
"grad_norm": 18.964569091796875,
|
| 430 |
+
"learning_rate": 4.305555555555556e-05,
|
| 431 |
+
"loss": 0.419,
|
| 432 |
+
"step": 270
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 26.926829268292682,
|
| 436 |
+
"eval_accuracy": 0.8541666666666666,
|
| 437 |
+
"eval_loss": 0.5202641487121582,
|
| 438 |
+
"eval_runtime": 3.0877,
|
| 439 |
+
"eval_samples_per_second": 46.637,
|
| 440 |
+
"eval_steps_per_second": 1.619,
|
| 441 |
+
"step": 276
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 27.317073170731707,
|
| 445 |
+
"grad_norm": 27.72169303894043,
|
| 446 |
+
"learning_rate": 4.259259259259259e-05,
|
| 447 |
+
"loss": 0.3454,
|
| 448 |
+
"step": 280
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 28.0,
|
| 452 |
+
"eval_accuracy": 0.8263888888888888,
|
| 453 |
+
"eval_loss": 0.6083860397338867,
|
| 454 |
+
"eval_runtime": 3.1332,
|
| 455 |
+
"eval_samples_per_second": 45.959,
|
| 456 |
+
"eval_steps_per_second": 1.596,
|
| 457 |
+
"step": 287
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 28.29268292682927,
|
| 461 |
+
"grad_norm": 34.03929138183594,
|
| 462 |
+
"learning_rate": 4.212962962962963e-05,
|
| 463 |
+
"loss": 0.36,
|
| 464 |
+
"step": 290
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 28.975609756097562,
|
| 468 |
+
"eval_accuracy": 0.8263888888888888,
|
| 469 |
+
"eval_loss": 0.5927634835243225,
|
| 470 |
+
"eval_runtime": 3.105,
|
| 471 |
+
"eval_samples_per_second": 46.377,
|
| 472 |
+
"eval_steps_per_second": 1.61,
|
| 473 |
+
"step": 297
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 29.26829268292683,
|
| 477 |
+
"grad_norm": 12.895988464355469,
|
| 478 |
+
"learning_rate": 4.166666666666667e-05,
|
| 479 |
+
"loss": 0.3265,
|
| 480 |
+
"step": 300
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 29.951219512195124,
|
| 484 |
+
"eval_accuracy": 0.8402777777777778,
|
| 485 |
+
"eval_loss": 0.5302631855010986,
|
| 486 |
+
"eval_runtime": 3.1155,
|
| 487 |
+
"eval_samples_per_second": 46.22,
|
| 488 |
+
"eval_steps_per_second": 1.605,
|
| 489 |
+
"step": 307
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 30.24390243902439,
|
| 493 |
+
"grad_norm": 25.50472640991211,
|
| 494 |
+
"learning_rate": 4.1203703703703705e-05,
|
| 495 |
+
"loss": 0.3278,
|
| 496 |
+
"step": 310
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 30.926829268292682,
|
| 500 |
+
"eval_accuracy": 0.8194444444444444,
|
| 501 |
+
"eval_loss": 0.6049231886863708,
|
| 502 |
+
"eval_runtime": 3.093,
|
| 503 |
+
"eval_samples_per_second": 46.557,
|
| 504 |
+
"eval_steps_per_second": 1.617,
|
| 505 |
+
"step": 317
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 31.21951219512195,
|
| 509 |
+
"grad_norm": 24.565650939941406,
|
| 510 |
+
"learning_rate": 4.074074074074074e-05,
|
| 511 |
+
"loss": 0.2766,
|
| 512 |
+
"step": 320
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 32.0,
|
| 516 |
+
"eval_accuracy": 0.8263888888888888,
|
| 517 |
+
"eval_loss": 0.5656167268753052,
|
| 518 |
+
"eval_runtime": 3.1109,
|
| 519 |
+
"eval_samples_per_second": 46.289,
|
| 520 |
+
"eval_steps_per_second": 1.607,
|
| 521 |
+
"step": 328
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 32.19512195121951,
|
| 525 |
+
"grad_norm": 55.43843460083008,
|
| 526 |
+
"learning_rate": 4.027777777777778e-05,
|
| 527 |
+
"loss": 0.2805,
|
| 528 |
+
"step": 330
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 32.97560975609756,
|
| 532 |
+
"eval_accuracy": 0.8680555555555556,
|
| 533 |
+
"eval_loss": 0.500336229801178,
|
| 534 |
+
"eval_runtime": 3.0516,
|
| 535 |
+
"eval_samples_per_second": 47.188,
|
| 536 |
+
"eval_steps_per_second": 1.638,
|
| 537 |
+
"step": 338
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 33.170731707317074,
|
| 541 |
+
"grad_norm": 21.027912139892578,
|
| 542 |
+
"learning_rate": 3.981481481481482e-05,
|
| 543 |
+
"loss": 0.2505,
|
| 544 |
+
"step": 340
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 33.951219512195124,
|
| 548 |
+
"eval_accuracy": 0.8402777777777778,
|
| 549 |
+
"eval_loss": 0.5412003397941589,
|
| 550 |
+
"eval_runtime": 2.9972,
|
| 551 |
+
"eval_samples_per_second": 48.044,
|
| 552 |
+
"eval_steps_per_second": 1.668,
|
| 553 |
+
"step": 348
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 34.146341463414636,
|
| 557 |
+
"grad_norm": 15.519696235656738,
|
| 558 |
+
"learning_rate": 3.935185185185186e-05,
|
| 559 |
+
"loss": 0.2464,
|
| 560 |
+
"step": 350
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 34.926829268292686,
|
| 564 |
+
"eval_accuracy": 0.8333333333333334,
|
| 565 |
+
"eval_loss": 0.5409752130508423,
|
| 566 |
+
"eval_runtime": 3.024,
|
| 567 |
+
"eval_samples_per_second": 47.62,
|
| 568 |
+
"eval_steps_per_second": 1.653,
|
| 569 |
+
"step": 358
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 35.1219512195122,
|
| 573 |
+
"grad_norm": 24.68006134033203,
|
| 574 |
+
"learning_rate": 3.888888888888889e-05,
|
| 575 |
+
"loss": 0.2166,
|
| 576 |
+
"step": 360
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 36.0,
|
| 580 |
+
"eval_accuracy": 0.8472222222222222,
|
| 581 |
+
"eval_loss": 0.499971866607666,
|
| 582 |
+
"eval_runtime": 2.9993,
|
| 583 |
+
"eval_samples_per_second": 48.011,
|
| 584 |
+
"eval_steps_per_second": 1.667,
|
| 585 |
+
"step": 369
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 36.09756097560975,
|
| 589 |
+
"grad_norm": 16.784454345703125,
|
| 590 |
+
"learning_rate": 3.8425925925925924e-05,
|
| 591 |
+
"loss": 0.2,
|
| 592 |
+
"step": 370
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 36.97560975609756,
|
| 596 |
+
"eval_accuracy": 0.8055555555555556,
|
| 597 |
+
"eval_loss": 0.5053013563156128,
|
| 598 |
+
"eval_runtime": 2.9731,
|
| 599 |
+
"eval_samples_per_second": 48.435,
|
| 600 |
+
"eval_steps_per_second": 1.682,
|
| 601 |
+
"step": 379
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 37.073170731707314,
|
| 605 |
+
"grad_norm": 16.091339111328125,
|
| 606 |
+
"learning_rate": 3.7962962962962964e-05,
|
| 607 |
+
"loss": 0.1914,
|
| 608 |
+
"step": 380
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 37.951219512195124,
|
| 612 |
+
"eval_accuracy": 0.8402777777777778,
|
| 613 |
+
"eval_loss": 0.5161268711090088,
|
| 614 |
+
"eval_runtime": 3.0408,
|
| 615 |
+
"eval_samples_per_second": 47.356,
|
| 616 |
+
"eval_steps_per_second": 1.644,
|
| 617 |
+
"step": 389
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 38.048780487804876,
|
| 621 |
+
"grad_norm": 19.708166122436523,
|
| 622 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 623 |
+
"loss": 0.186,
|
| 624 |
+
"step": 390
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 38.926829268292686,
|
| 628 |
+
"eval_accuracy": 0.8680555555555556,
|
| 629 |
+
"eval_loss": 0.42421483993530273,
|
| 630 |
+
"eval_runtime": 3.0128,
|
| 631 |
+
"eval_samples_per_second": 47.796,
|
| 632 |
+
"eval_steps_per_second": 1.66,
|
| 633 |
+
"step": 399
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 39.02439024390244,
|
| 637 |
+
"grad_norm": 18.210954666137695,
|
| 638 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 639 |
+
"loss": 0.1767,
|
| 640 |
+
"step": 400
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 40.0,
|
| 644 |
+
"grad_norm": 12.815789222717285,
|
| 645 |
+
"learning_rate": 3.6574074074074076e-05,
|
| 646 |
+
"loss": 0.1592,
|
| 647 |
+
"step": 410
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 40.0,
|
| 651 |
+
"eval_accuracy": 0.8472222222222222,
|
| 652 |
+
"eval_loss": 0.5058771967887878,
|
| 653 |
+
"eval_runtime": 3.0381,
|
| 654 |
+
"eval_samples_per_second": 47.399,
|
| 655 |
+
"eval_steps_per_second": 1.646,
|
| 656 |
+
"step": 410
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 40.97560975609756,
|
| 660 |
+
"grad_norm": 17.878015518188477,
|
| 661 |
+
"learning_rate": 3.611111111111111e-05,
|
| 662 |
+
"loss": 0.1598,
|
| 663 |
+
"step": 420
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 40.97560975609756,
|
| 667 |
+
"eval_accuracy": 0.8263888888888888,
|
| 668 |
+
"eval_loss": 0.5143249034881592,
|
| 669 |
+
"eval_runtime": 3.2074,
|
| 670 |
+
"eval_samples_per_second": 44.896,
|
| 671 |
+
"eval_steps_per_second": 1.559,
|
| 672 |
+
"step": 420
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 41.951219512195124,
|
| 676 |
+
"grad_norm": 18.464937210083008,
|
| 677 |
+
"learning_rate": 3.564814814814815e-05,
|
| 678 |
+
"loss": 0.1565,
|
| 679 |
+
"step": 430
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 41.951219512195124,
|
| 683 |
+
"eval_accuracy": 0.8541666666666666,
|
| 684 |
+
"eval_loss": 0.47032684087753296,
|
| 685 |
+
"eval_runtime": 3.4622,
|
| 686 |
+
"eval_samples_per_second": 41.592,
|
| 687 |
+
"eval_steps_per_second": 1.444,
|
| 688 |
+
"step": 430
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 42.926829268292686,
|
| 692 |
+
"grad_norm": 21.608076095581055,
|
| 693 |
+
"learning_rate": 3.518518518518519e-05,
|
| 694 |
+
"loss": 0.1598,
|
| 695 |
+
"step": 440
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 42.926829268292686,
|
| 699 |
+
"eval_accuracy": 0.8541666666666666,
|
| 700 |
+
"eval_loss": 0.4383782148361206,
|
| 701 |
+
"eval_runtime": 3.2144,
|
| 702 |
+
"eval_samples_per_second": 44.798,
|
| 703 |
+
"eval_steps_per_second": 1.555,
|
| 704 |
+
"step": 440
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 43.90243902439025,
|
| 708 |
+
"grad_norm": 16.986896514892578,
|
| 709 |
+
"learning_rate": 3.472222222222222e-05,
|
| 710 |
+
"loss": 0.139,
|
| 711 |
+
"step": 450
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 44.0,
|
| 715 |
+
"eval_accuracy": 0.8402777777777778,
|
| 716 |
+
"eval_loss": 0.48497942090034485,
|
| 717 |
+
"eval_runtime": 3.1916,
|
| 718 |
+
"eval_samples_per_second": 45.118,
|
| 719 |
+
"eval_steps_per_second": 1.567,
|
| 720 |
+
"step": 451
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 44.8780487804878,
|
| 724 |
+
"grad_norm": 10.322036743164062,
|
| 725 |
+
"learning_rate": 3.425925925925926e-05,
|
| 726 |
+
"loss": 0.1137,
|
| 727 |
+
"step": 460
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 44.97560975609756,
|
| 731 |
+
"eval_accuracy": 0.8541666666666666,
|
| 732 |
+
"eval_loss": 0.4405103623867035,
|
| 733 |
+
"eval_runtime": 3.1456,
|
| 734 |
+
"eval_samples_per_second": 45.778,
|
| 735 |
+
"eval_steps_per_second": 1.59,
|
| 736 |
+
"step": 461
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 45.853658536585364,
|
| 740 |
+
"grad_norm": 24.03445053100586,
|
| 741 |
+
"learning_rate": 3.3796296296296295e-05,
|
| 742 |
+
"loss": 0.1158,
|
| 743 |
+
"step": 470
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 45.951219512195124,
|
| 747 |
+
"eval_accuracy": 0.8333333333333334,
|
| 748 |
+
"eval_loss": 0.5250218510627747,
|
| 749 |
+
"eval_runtime": 3.2289,
|
| 750 |
+
"eval_samples_per_second": 44.597,
|
| 751 |
+
"eval_steps_per_second": 1.549,
|
| 752 |
+
"step": 471
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 46.829268292682926,
|
| 756 |
+
"grad_norm": 19.822120666503906,
|
| 757 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 758 |
+
"loss": 0.1192,
|
| 759 |
+
"step": 480
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 46.926829268292686,
|
| 763 |
+
"eval_accuracy": 0.8194444444444444,
|
| 764 |
+
"eval_loss": 0.5843467116355896,
|
| 765 |
+
"eval_runtime": 3.1862,
|
| 766 |
+
"eval_samples_per_second": 45.195,
|
| 767 |
+
"eval_steps_per_second": 1.569,
|
| 768 |
+
"step": 481
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 47.80487804878049,
|
| 772 |
+
"grad_norm": 14.12452220916748,
|
| 773 |
+
"learning_rate": 3.2870370370370375e-05,
|
| 774 |
+
"loss": 0.1271,
|
| 775 |
+
"step": 490
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 48.0,
|
| 779 |
+
"eval_accuracy": 0.8611111111111112,
|
| 780 |
+
"eval_loss": 0.44981643557548523,
|
| 781 |
+
"eval_runtime": 3.0999,
|
| 782 |
+
"eval_samples_per_second": 46.453,
|
| 783 |
+
"eval_steps_per_second": 1.613,
|
| 784 |
+
"step": 492
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 48.78048780487805,
|
| 788 |
+
"grad_norm": 12.838052749633789,
|
| 789 |
+
"learning_rate": 3.240740740740741e-05,
|
| 790 |
+
"loss": 0.0914,
|
| 791 |
+
"step": 500
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 48.97560975609756,
|
| 795 |
+
"eval_accuracy": 0.8263888888888888,
|
| 796 |
+
"eval_loss": 0.5166668891906738,
|
| 797 |
+
"eval_runtime": 3.2195,
|
| 798 |
+
"eval_samples_per_second": 44.728,
|
| 799 |
+
"eval_steps_per_second": 1.553,
|
| 800 |
+
"step": 502
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 49.75609756097561,
|
| 804 |
+
"grad_norm": 20.458118438720703,
|
| 805 |
+
"learning_rate": 3.194444444444444e-05,
|
| 806 |
+
"loss": 0.1079,
|
| 807 |
+
"step": 510
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 49.951219512195124,
|
| 811 |
+
"eval_accuracy": 0.8680555555555556,
|
| 812 |
+
"eval_loss": 0.46484246850013733,
|
| 813 |
+
"eval_runtime": 3.1773,
|
| 814 |
+
"eval_samples_per_second": 45.322,
|
| 815 |
+
"eval_steps_per_second": 1.574,
|
| 816 |
+
"step": 512
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 50.73170731707317,
|
| 820 |
+
"grad_norm": 20.558439254760742,
|
| 821 |
+
"learning_rate": 3.148148148148148e-05,
|
| 822 |
+
"loss": 0.091,
|
| 823 |
+
"step": 520
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 50.926829268292686,
|
| 827 |
+
"eval_accuracy": 0.8194444444444444,
|
| 828 |
+
"eval_loss": 0.5321457386016846,
|
| 829 |
+
"eval_runtime": 3.1291,
|
| 830 |
+
"eval_samples_per_second": 46.02,
|
| 831 |
+
"eval_steps_per_second": 1.598,
|
| 832 |
+
"step": 522
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 51.707317073170735,
|
| 836 |
+
"grad_norm": 11.692161560058594,
|
| 837 |
+
"learning_rate": 3.101851851851852e-05,
|
| 838 |
+
"loss": 0.1053,
|
| 839 |
+
"step": 530
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 52.0,
|
| 843 |
+
"eval_accuracy": 0.8611111111111112,
|
| 844 |
+
"eval_loss": 0.4402025043964386,
|
| 845 |
+
"eval_runtime": 3.1245,
|
| 846 |
+
"eval_samples_per_second": 46.087,
|
| 847 |
+
"eval_steps_per_second": 1.6,
|
| 848 |
+
"step": 533
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 52.68292682926829,
|
| 852 |
+
"grad_norm": 8.12877082824707,
|
| 853 |
+
"learning_rate": 3.055555555555556e-05,
|
| 854 |
+
"loss": 0.0842,
|
| 855 |
+
"step": 540
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 52.97560975609756,
|
| 859 |
+
"eval_accuracy": 0.8541666666666666,
|
| 860 |
+
"eval_loss": 0.477556437253952,
|
| 861 |
+
"eval_runtime": 3.1029,
|
| 862 |
+
"eval_samples_per_second": 46.408,
|
| 863 |
+
"eval_steps_per_second": 1.611,
|
| 864 |
+
"step": 543
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 53.65853658536585,
|
| 868 |
+
"grad_norm": 21.6231746673584,
|
| 869 |
+
"learning_rate": 3.0092592592592593e-05,
|
| 870 |
+
"loss": 0.0961,
|
| 871 |
+
"step": 550
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 53.951219512195124,
|
| 875 |
+
"eval_accuracy": 0.8680555555555556,
|
| 876 |
+
"eval_loss": 0.4761970341205597,
|
| 877 |
+
"eval_runtime": 3.0897,
|
| 878 |
+
"eval_samples_per_second": 46.607,
|
| 879 |
+
"eval_steps_per_second": 1.618,
|
| 880 |
+
"step": 553
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 54.63414634146341,
|
| 884 |
+
"grad_norm": 22.6603946685791,
|
| 885 |
+
"learning_rate": 2.962962962962963e-05,
|
| 886 |
+
"loss": 0.0896,
|
| 887 |
+
"step": 560
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 54.926829268292686,
|
| 891 |
+
"eval_accuracy": 0.8680555555555556,
|
| 892 |
+
"eval_loss": 0.4477081894874573,
|
| 893 |
+
"eval_runtime": 3.1158,
|
| 894 |
+
"eval_samples_per_second": 46.216,
|
| 895 |
+
"eval_steps_per_second": 1.605,
|
| 896 |
+
"step": 563
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 55.609756097560975,
|
| 900 |
+
"grad_norm": 20.613056182861328,
|
| 901 |
+
"learning_rate": 2.916666666666667e-05,
|
| 902 |
+
"loss": 0.0876,
|
| 903 |
+
"step": 570
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 56.0,
|
| 907 |
+
"eval_accuracy": 0.8472222222222222,
|
| 908 |
+
"eval_loss": 0.49506622552871704,
|
| 909 |
+
"eval_runtime": 3.1109,
|
| 910 |
+
"eval_samples_per_second": 46.289,
|
| 911 |
+
"eval_steps_per_second": 1.607,
|
| 912 |
+
"step": 574
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 56.58536585365854,
|
| 916 |
+
"grad_norm": 15.108587265014648,
|
| 917 |
+
"learning_rate": 2.8703703703703706e-05,
|
| 918 |
+
"loss": 0.0855,
|
| 919 |
+
"step": 580
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 56.97560975609756,
|
| 923 |
+
"eval_accuracy": 0.8125,
|
| 924 |
+
"eval_loss": 0.565302312374115,
|
| 925 |
+
"eval_runtime": 3.3057,
|
| 926 |
+
"eval_samples_per_second": 43.562,
|
| 927 |
+
"eval_steps_per_second": 1.513,
|
| 928 |
+
"step": 584
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 57.5609756097561,
|
| 932 |
+
"grad_norm": 14.336268424987793,
|
| 933 |
+
"learning_rate": 2.824074074074074e-05,
|
| 934 |
+
"loss": 0.073,
|
| 935 |
+
"step": 590
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 57.951219512195124,
|
| 939 |
+
"eval_accuracy": 0.8472222222222222,
|
| 940 |
+
"eval_loss": 0.5314738750457764,
|
| 941 |
+
"eval_runtime": 3.1166,
|
| 942 |
+
"eval_samples_per_second": 46.205,
|
| 943 |
+
"eval_steps_per_second": 1.604,
|
| 944 |
+
"step": 594
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 58.53658536585366,
|
| 948 |
+
"grad_norm": 31.659631729125977,
|
| 949 |
+
"learning_rate": 2.777777777777778e-05,
|
| 950 |
+
"loss": 0.0804,
|
| 951 |
+
"step": 600
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 58.926829268292686,
|
| 955 |
+
"eval_accuracy": 0.8680555555555556,
|
| 956 |
+
"eval_loss": 0.5064035058021545,
|
| 957 |
+
"eval_runtime": 3.1077,
|
| 958 |
+
"eval_samples_per_second": 46.336,
|
| 959 |
+
"eval_steps_per_second": 1.609,
|
| 960 |
+
"step": 604
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 59.51219512195122,
|
| 964 |
+
"grad_norm": 6.317721366882324,
|
| 965 |
+
"learning_rate": 2.7314814814814816e-05,
|
| 966 |
+
"loss": 0.0765,
|
| 967 |
+
"step": 610
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 60.0,
|
| 971 |
+
"eval_accuracy": 0.8263888888888888,
|
| 972 |
+
"eval_loss": 0.63160640001297,
|
| 973 |
+
"eval_runtime": 3.0861,
|
| 974 |
+
"eval_samples_per_second": 46.661,
|
| 975 |
+
"eval_steps_per_second": 1.62,
|
| 976 |
+
"step": 615
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 60.48780487804878,
|
| 980 |
+
"grad_norm": 41.102962493896484,
|
| 981 |
+
"learning_rate": 2.6851851851851855e-05,
|
| 982 |
+
"loss": 0.0782,
|
| 983 |
+
"step": 620
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 60.97560975609756,
|
| 987 |
+
"eval_accuracy": 0.8055555555555556,
|
| 988 |
+
"eval_loss": 0.5733475089073181,
|
| 989 |
+
"eval_runtime": 3.1325,
|
| 990 |
+
"eval_samples_per_second": 45.97,
|
| 991 |
+
"eval_steps_per_second": 1.596,
|
| 992 |
+
"step": 625
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 61.46341463414634,
|
| 996 |
+
"grad_norm": 6.797872066497803,
|
| 997 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 998 |
+
"loss": 0.069,
|
| 999 |
+
"step": 630
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 61.951219512195124,
|
| 1003 |
+
"eval_accuracy": 0.8055555555555556,
|
| 1004 |
+
"eval_loss": 0.6994370222091675,
|
| 1005 |
+
"eval_runtime": 3.1742,
|
| 1006 |
+
"eval_samples_per_second": 45.365,
|
| 1007 |
+
"eval_steps_per_second": 1.575,
|
| 1008 |
+
"step": 635
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 62.4390243902439,
|
| 1012 |
+
"grad_norm": 9.439558029174805,
|
| 1013 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 1014 |
+
"loss": 0.0809,
|
| 1015 |
+
"step": 640
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 62.926829268292686,
|
| 1019 |
+
"eval_accuracy": 0.8611111111111112,
|
| 1020 |
+
"eval_loss": 0.48975637555122375,
|
| 1021 |
+
"eval_runtime": 3.1035,
|
| 1022 |
+
"eval_samples_per_second": 46.4,
|
| 1023 |
+
"eval_steps_per_second": 1.611,
|
| 1024 |
+
"step": 645
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 63.41463414634146,
|
| 1028 |
+
"grad_norm": 23.557085037231445,
|
| 1029 |
+
"learning_rate": 2.5462962962962965e-05,
|
| 1030 |
+
"loss": 0.0829,
|
| 1031 |
+
"step": 650
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 64.0,
|
| 1035 |
+
"eval_accuracy": 0.8194444444444444,
|
| 1036 |
+
"eval_loss": 0.6042267680168152,
|
| 1037 |
+
"eval_runtime": 3.0922,
|
| 1038 |
+
"eval_samples_per_second": 46.569,
|
| 1039 |
+
"eval_steps_per_second": 1.617,
|
| 1040 |
+
"step": 656
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 64.39024390243902,
|
| 1044 |
+
"grad_norm": 5.313930511474609,
|
| 1045 |
+
"learning_rate": 2.5e-05,
|
| 1046 |
+
"loss": 0.0735,
|
| 1047 |
+
"step": 660
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 64.97560975609755,
|
| 1051 |
+
"eval_accuracy": 0.8611111111111112,
|
| 1052 |
+
"eval_loss": 0.4758368730545044,
|
| 1053 |
+
"eval_runtime": 3.1221,
|
| 1054 |
+
"eval_samples_per_second": 46.122,
|
| 1055 |
+
"eval_steps_per_second": 1.601,
|
| 1056 |
+
"step": 666
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 65.36585365853658,
|
| 1060 |
+
"grad_norm": 21.385704040527344,
|
| 1061 |
+
"learning_rate": 2.4537037037037038e-05,
|
| 1062 |
+
"loss": 0.0763,
|
| 1063 |
+
"step": 670
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 65.95121951219512,
|
| 1067 |
+
"eval_accuracy": 0.8541666666666666,
|
| 1068 |
+
"eval_loss": 0.4920533001422882,
|
| 1069 |
+
"eval_runtime": 3.0958,
|
| 1070 |
+
"eval_samples_per_second": 46.514,
|
| 1071 |
+
"eval_steps_per_second": 1.615,
|
| 1072 |
+
"step": 676
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 66.34146341463415,
|
| 1076 |
+
"grad_norm": 5.922763347625732,
|
| 1077 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 1078 |
+
"loss": 0.0565,
|
| 1079 |
+
"step": 680
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 66.92682926829268,
|
| 1083 |
+
"eval_accuracy": 0.8680555555555556,
|
| 1084 |
+
"eval_loss": 0.47003433108329773,
|
| 1085 |
+
"eval_runtime": 3.0115,
|
| 1086 |
+
"eval_samples_per_second": 47.816,
|
| 1087 |
+
"eval_steps_per_second": 1.66,
|
| 1088 |
+
"step": 686
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 67.3170731707317,
|
| 1092 |
+
"grad_norm": 8.859350204467773,
|
| 1093 |
+
"learning_rate": 2.361111111111111e-05,
|
| 1094 |
+
"loss": 0.062,
|
| 1095 |
+
"step": 690
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 68.0,
|
| 1099 |
+
"eval_accuracy": 0.8819444444444444,
|
| 1100 |
+
"eval_loss": 0.49443933367729187,
|
| 1101 |
+
"eval_runtime": 3.0558,
|
| 1102 |
+
"eval_samples_per_second": 47.123,
|
| 1103 |
+
"eval_steps_per_second": 1.636,
|
| 1104 |
+
"step": 697
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 68.29268292682927,
|
| 1108 |
+
"grad_norm": 11.291411399841309,
|
| 1109 |
+
"learning_rate": 2.314814814814815e-05,
|
| 1110 |
+
"loss": 0.0644,
|
| 1111 |
+
"step": 700
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 68.97560975609755,
|
| 1115 |
+
"eval_accuracy": 0.8680555555555556,
|
| 1116 |
+
"eval_loss": 0.47334182262420654,
|
| 1117 |
+
"eval_runtime": 3.1099,
|
| 1118 |
+
"eval_samples_per_second": 46.303,
|
| 1119 |
+
"eval_steps_per_second": 1.608,
|
| 1120 |
+
"step": 707
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 69.26829268292683,
|
| 1124 |
+
"grad_norm": 4.428774356842041,
|
| 1125 |
+
"learning_rate": 2.2685185185185187e-05,
|
| 1126 |
+
"loss": 0.0659,
|
| 1127 |
+
"step": 710
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 69.95121951219512,
|
| 1131 |
+
"eval_accuracy": 0.8819444444444444,
|
| 1132 |
+
"eval_loss": 0.4702872037887573,
|
| 1133 |
+
"eval_runtime": 3.1595,
|
| 1134 |
+
"eval_samples_per_second": 45.577,
|
| 1135 |
+
"eval_steps_per_second": 1.583,
|
| 1136 |
+
"step": 717
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 70.2439024390244,
|
| 1140 |
+
"grad_norm": 20.887792587280273,
|
| 1141 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 1142 |
+
"loss": 0.0625,
|
| 1143 |
+
"step": 720
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 70.92682926829268,
|
| 1147 |
+
"eval_accuracy": 0.8541666666666666,
|
| 1148 |
+
"eval_loss": 0.5075345635414124,
|
| 1149 |
+
"eval_runtime": 3.1136,
|
| 1150 |
+
"eval_samples_per_second": 46.248,
|
| 1151 |
+
"eval_steps_per_second": 1.606,
|
| 1152 |
+
"step": 727
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 71.21951219512195,
|
| 1156 |
+
"grad_norm": 7.4120917320251465,
|
| 1157 |
+
"learning_rate": 2.175925925925926e-05,
|
| 1158 |
+
"loss": 0.042,
|
| 1159 |
+
"step": 730
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 72.0,
|
| 1163 |
+
"eval_accuracy": 0.8263888888888888,
|
| 1164 |
+
"eval_loss": 0.5463792085647583,
|
| 1165 |
+
"eval_runtime": 3.1979,
|
| 1166 |
+
"eval_samples_per_second": 45.029,
|
| 1167 |
+
"eval_steps_per_second": 1.564,
|
| 1168 |
+
"step": 738
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 72.1951219512195,
|
| 1172 |
+
"grad_norm": 4.7453532218933105,
|
| 1173 |
+
"learning_rate": 2.1296296296296296e-05,
|
| 1174 |
+
"loss": 0.056,
|
| 1175 |
+
"step": 740
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 72.97560975609755,
|
| 1179 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1180 |
+
"eval_loss": 0.5185548067092896,
|
| 1181 |
+
"eval_runtime": 3.2157,
|
| 1182 |
+
"eval_samples_per_second": 44.78,
|
| 1183 |
+
"eval_steps_per_second": 1.555,
|
| 1184 |
+
"step": 748
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 73.17073170731707,
|
| 1188 |
+
"grad_norm": 40.11507034301758,
|
| 1189 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 1190 |
+
"loss": 0.0858,
|
| 1191 |
+
"step": 750
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 73.95121951219512,
|
| 1195 |
+
"eval_accuracy": 0.8263888888888888,
|
| 1196 |
+
"eval_loss": 0.5403424501419067,
|
| 1197 |
+
"eval_runtime": 3.1711,
|
| 1198 |
+
"eval_samples_per_second": 45.41,
|
| 1199 |
+
"eval_steps_per_second": 1.577,
|
| 1200 |
+
"step": 758
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 74.14634146341463,
|
| 1204 |
+
"grad_norm": 21.469833374023438,
|
| 1205 |
+
"learning_rate": 2.037037037037037e-05,
|
| 1206 |
+
"loss": 0.0616,
|
| 1207 |
+
"step": 760
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 74.92682926829268,
|
| 1211 |
+
"eval_accuracy": 0.8472222222222222,
|
| 1212 |
+
"eval_loss": 0.5104292631149292,
|
| 1213 |
+
"eval_runtime": 3.1108,
|
| 1214 |
+
"eval_samples_per_second": 46.29,
|
| 1215 |
+
"eval_steps_per_second": 1.607,
|
| 1216 |
+
"step": 768
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 75.1219512195122,
|
| 1220 |
+
"grad_norm": 17.34604263305664,
|
| 1221 |
+
"learning_rate": 1.990740740740741e-05,
|
| 1222 |
+
"loss": 0.0777,
|
| 1223 |
+
"step": 770
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 76.0,
|
| 1227 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1228 |
+
"eval_loss": 0.5515955686569214,
|
| 1229 |
+
"eval_runtime": 3.0985,
|
| 1230 |
+
"eval_samples_per_second": 46.474,
|
| 1231 |
+
"eval_steps_per_second": 1.614,
|
| 1232 |
+
"step": 779
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 76.09756097560975,
|
| 1236 |
+
"grad_norm": 25.844533920288086,
|
| 1237 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 1238 |
+
"loss": 0.0668,
|
| 1239 |
+
"step": 780
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 76.97560975609755,
|
| 1243 |
+
"eval_accuracy": 0.8611111111111112,
|
| 1244 |
+
"eval_loss": 0.49184906482696533,
|
| 1245 |
+
"eval_runtime": 3.1523,
|
| 1246 |
+
"eval_samples_per_second": 45.68,
|
| 1247 |
+
"eval_steps_per_second": 1.586,
|
| 1248 |
+
"step": 789
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 77.07317073170732,
|
| 1252 |
+
"grad_norm": 3.816899299621582,
|
| 1253 |
+
"learning_rate": 1.8981481481481482e-05,
|
| 1254 |
+
"loss": 0.0585,
|
| 1255 |
+
"step": 790
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 77.95121951219512,
|
| 1259 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1260 |
+
"eval_loss": 0.5692147612571716,
|
| 1261 |
+
"eval_runtime": 3.1238,
|
| 1262 |
+
"eval_samples_per_second": 46.098,
|
| 1263 |
+
"eval_steps_per_second": 1.601,
|
| 1264 |
+
"step": 799
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 78.04878048780488,
|
| 1268 |
+
"grad_norm": 1.5959941148757935,
|
| 1269 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 1270 |
+
"loss": 0.0562,
|
| 1271 |
+
"step": 800
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 78.92682926829268,
|
| 1275 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1276 |
+
"eval_loss": 0.5733731389045715,
|
| 1277 |
+
"eval_runtime": 3.161,
|
| 1278 |
+
"eval_samples_per_second": 45.556,
|
| 1279 |
+
"eval_steps_per_second": 1.582,
|
| 1280 |
+
"step": 809
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 79.02439024390245,
|
| 1284 |
+
"grad_norm": 8.219141960144043,
|
| 1285 |
+
"learning_rate": 1.8055555555555555e-05,
|
| 1286 |
+
"loss": 0.067,
|
| 1287 |
+
"step": 810
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 80.0,
|
| 1291 |
+
"grad_norm": 15.953410148620605,
|
| 1292 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 1293 |
+
"loss": 0.0653,
|
| 1294 |
+
"step": 820
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 80.0,
|
| 1298 |
+
"eval_accuracy": 0.8263888888888888,
|
| 1299 |
+
"eval_loss": 0.5403192639350891,
|
| 1300 |
+
"eval_runtime": 3.2805,
|
| 1301 |
+
"eval_samples_per_second": 43.896,
|
| 1302 |
+
"eval_steps_per_second": 1.524,
|
| 1303 |
+
"step": 820
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 80.97560975609755,
|
| 1307 |
+
"grad_norm": 6.4320783615112305,
|
| 1308 |
+
"learning_rate": 1.712962962962963e-05,
|
| 1309 |
+
"loss": 0.0434,
|
| 1310 |
+
"step": 830
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 80.97560975609755,
|
| 1314 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1315 |
+
"eval_loss": 0.5107588171958923,
|
| 1316 |
+
"eval_runtime": 3.1353,
|
| 1317 |
+
"eval_samples_per_second": 45.929,
|
| 1318 |
+
"eval_steps_per_second": 1.595,
|
| 1319 |
+
"step": 830
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 81.95121951219512,
|
| 1323 |
+
"grad_norm": 4.175785064697266,
|
| 1324 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 1325 |
+
"loss": 0.0483,
|
| 1326 |
+
"step": 840
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 81.95121951219512,
|
| 1330 |
+
"eval_accuracy": 0.8125,
|
| 1331 |
+
"eval_loss": 0.5699278712272644,
|
| 1332 |
+
"eval_runtime": 3.084,
|
| 1333 |
+
"eval_samples_per_second": 46.693,
|
| 1334 |
+
"eval_steps_per_second": 1.621,
|
| 1335 |
+
"step": 840
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 82.92682926829268,
|
| 1339 |
+
"grad_norm": 7.429763317108154,
|
| 1340 |
+
"learning_rate": 1.6203703703703704e-05,
|
| 1341 |
+
"loss": 0.0329,
|
| 1342 |
+
"step": 850
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 82.92682926829268,
|
| 1346 |
+
"eval_accuracy": 0.8055555555555556,
|
| 1347 |
+
"eval_loss": 0.6027733087539673,
|
| 1348 |
+
"eval_runtime": 3.1234,
|
| 1349 |
+
"eval_samples_per_second": 46.104,
|
| 1350 |
+
"eval_steps_per_second": 1.601,
|
| 1351 |
+
"step": 850
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 83.90243902439025,
|
| 1355 |
+
"grad_norm": 5.646729946136475,
|
| 1356 |
+
"learning_rate": 1.574074074074074e-05,
|
| 1357 |
+
"loss": 0.0431,
|
| 1358 |
+
"step": 860
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 84.0,
|
| 1362 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1363 |
+
"eval_loss": 0.5230019092559814,
|
| 1364 |
+
"eval_runtime": 3.1681,
|
| 1365 |
+
"eval_samples_per_second": 45.453,
|
| 1366 |
+
"eval_steps_per_second": 1.578,
|
| 1367 |
+
"step": 861
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 84.8780487804878,
|
| 1371 |
+
"grad_norm": 4.747640132904053,
|
| 1372 |
+
"learning_rate": 1.527777777777778e-05,
|
| 1373 |
+
"loss": 0.042,
|
| 1374 |
+
"step": 870
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 84.97560975609755,
|
| 1378 |
+
"eval_accuracy": 0.8194444444444444,
|
| 1379 |
+
"eval_loss": 0.5875388979911804,
|
| 1380 |
+
"eval_runtime": 3.1311,
|
| 1381 |
+
"eval_samples_per_second": 45.99,
|
| 1382 |
+
"eval_steps_per_second": 1.597,
|
| 1383 |
+
"step": 871
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 85.85365853658537,
|
| 1387 |
+
"grad_norm": 7.094844341278076,
|
| 1388 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 1389 |
+
"loss": 0.0449,
|
| 1390 |
+
"step": 880
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 85.95121951219512,
|
| 1394 |
+
"eval_accuracy": 0.8611111111111112,
|
| 1395 |
+
"eval_loss": 0.5179998278617859,
|
| 1396 |
+
"eval_runtime": 3.1291,
|
| 1397 |
+
"eval_samples_per_second": 46.02,
|
| 1398 |
+
"eval_steps_per_second": 1.598,
|
| 1399 |
+
"step": 881
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 86.82926829268293,
|
| 1403 |
+
"grad_norm": 9.338136672973633,
|
| 1404 |
+
"learning_rate": 1.4351851851851853e-05,
|
| 1405 |
+
"loss": 0.0512,
|
| 1406 |
+
"step": 890
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 86.92682926829268,
|
| 1410 |
+
"eval_accuracy": 0.8194444444444444,
|
| 1411 |
+
"eval_loss": 0.5425156354904175,
|
| 1412 |
+
"eval_runtime": 3.1587,
|
| 1413 |
+
"eval_samples_per_second": 45.588,
|
| 1414 |
+
"eval_steps_per_second": 1.583,
|
| 1415 |
+
"step": 891
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 87.8048780487805,
|
| 1419 |
+
"grad_norm": 20.005054473876953,
|
| 1420 |
+
"learning_rate": 1.388888888888889e-05,
|
| 1421 |
+
"loss": 0.0545,
|
| 1422 |
+
"step": 900
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 88.0,
|
| 1426 |
+
"eval_accuracy": 0.8263888888888888,
|
| 1427 |
+
"eval_loss": 0.5689591765403748,
|
| 1428 |
+
"eval_runtime": 3.1184,
|
| 1429 |
+
"eval_samples_per_second": 46.177,
|
| 1430 |
+
"eval_steps_per_second": 1.603,
|
| 1431 |
+
"step": 902
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 88.78048780487805,
|
| 1435 |
+
"grad_norm": 6.419548034667969,
|
| 1436 |
+
"learning_rate": 1.3425925925925928e-05,
|
| 1437 |
+
"loss": 0.0496,
|
| 1438 |
+
"step": 910
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 88.97560975609755,
|
| 1442 |
+
"eval_accuracy": 0.8611111111111112,
|
| 1443 |
+
"eval_loss": 0.5619076490402222,
|
| 1444 |
+
"eval_runtime": 3.1196,
|
| 1445 |
+
"eval_samples_per_second": 46.16,
|
| 1446 |
+
"eval_steps_per_second": 1.603,
|
| 1447 |
+
"step": 912
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 89.7560975609756,
|
| 1451 |
+
"grad_norm": 4.659784317016602,
|
| 1452 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 1453 |
+
"loss": 0.0449,
|
| 1454 |
+
"step": 920
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 89.95121951219512,
|
| 1458 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1459 |
+
"eval_loss": 0.5625645518302917,
|
| 1460 |
+
"eval_runtime": 3.1196,
|
| 1461 |
+
"eval_samples_per_second": 46.16,
|
| 1462 |
+
"eval_steps_per_second": 1.603,
|
| 1463 |
+
"step": 922
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 90.73170731707317,
|
| 1467 |
+
"grad_norm": 10.376348495483398,
|
| 1468 |
+
"learning_rate": 1.25e-05,
|
| 1469 |
+
"loss": 0.0405,
|
| 1470 |
+
"step": 930
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 90.92682926829268,
|
| 1474 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1475 |
+
"eval_loss": 0.526747465133667,
|
| 1476 |
+
"eval_runtime": 3.1368,
|
| 1477 |
+
"eval_samples_per_second": 45.906,
|
| 1478 |
+
"eval_steps_per_second": 1.594,
|
| 1479 |
+
"step": 932
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 91.70731707317073,
|
| 1483 |
+
"grad_norm": 1.9461939334869385,
|
| 1484 |
+
"learning_rate": 1.2037037037037037e-05,
|
| 1485 |
+
"loss": 0.0344,
|
| 1486 |
+
"step": 940
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 92.0,
|
| 1490 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1491 |
+
"eval_loss": 0.5616637468338013,
|
| 1492 |
+
"eval_runtime": 3.1356,
|
| 1493 |
+
"eval_samples_per_second": 45.925,
|
| 1494 |
+
"eval_steps_per_second": 1.595,
|
| 1495 |
+
"step": 943
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 92.6829268292683,
|
| 1499 |
+
"grad_norm": 6.943029880523682,
|
| 1500 |
+
"learning_rate": 1.1574074074074075e-05,
|
| 1501 |
+
"loss": 0.0421,
|
| 1502 |
+
"step": 950
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 92.97560975609755,
|
| 1506 |
+
"eval_accuracy": 0.8611111111111112,
|
| 1507 |
+
"eval_loss": 0.5399531126022339,
|
| 1508 |
+
"eval_runtime": 3.1511,
|
| 1509 |
+
"eval_samples_per_second": 45.698,
|
| 1510 |
+
"eval_steps_per_second": 1.587,
|
| 1511 |
+
"step": 953
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 93.65853658536585,
|
| 1515 |
+
"grad_norm": 3.614881753921509,
|
| 1516 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 1517 |
+
"loss": 0.0341,
|
| 1518 |
+
"step": 960
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 93.95121951219512,
|
| 1522 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1523 |
+
"eval_loss": 0.5728729963302612,
|
| 1524 |
+
"eval_runtime": 3.1618,
|
| 1525 |
+
"eval_samples_per_second": 45.544,
|
| 1526 |
+
"eval_steps_per_second": 1.581,
|
| 1527 |
+
"step": 963
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 94.63414634146342,
|
| 1531 |
+
"grad_norm": 24.69358253479004,
|
| 1532 |
+
"learning_rate": 1.0648148148148148e-05,
|
| 1533 |
+
"loss": 0.0492,
|
| 1534 |
+
"step": 970
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 94.92682926829268,
|
| 1538 |
+
"eval_accuracy": 0.8055555555555556,
|
| 1539 |
+
"eval_loss": 0.5855351686477661,
|
| 1540 |
+
"eval_runtime": 3.1608,
|
| 1541 |
+
"eval_samples_per_second": 45.559,
|
| 1542 |
+
"eval_steps_per_second": 1.582,
|
| 1543 |
+
"step": 973
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 95.60975609756098,
|
| 1547 |
+
"grad_norm": 7.931139945983887,
|
| 1548 |
+
"learning_rate": 1.0185185185185185e-05,
|
| 1549 |
+
"loss": 0.0374,
|
| 1550 |
+
"step": 980
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 96.0,
|
| 1554 |
+
"eval_accuracy": 0.8125,
|
| 1555 |
+
"eval_loss": 0.6113177537918091,
|
| 1556 |
+
"eval_runtime": 2.99,
|
| 1557 |
+
"eval_samples_per_second": 48.161,
|
| 1558 |
+
"eval_steps_per_second": 1.672,
|
| 1559 |
+
"step": 984
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 96.58536585365853,
|
| 1563 |
+
"grad_norm": 7.854911804199219,
|
| 1564 |
+
"learning_rate": 9.722222222222223e-06,
|
| 1565 |
+
"loss": 0.0375,
|
| 1566 |
+
"step": 990
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 96.97560975609755,
|
| 1570 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1571 |
+
"eval_loss": 0.5511393547058105,
|
| 1572 |
+
"eval_runtime": 3.0799,
|
| 1573 |
+
"eval_samples_per_second": 46.755,
|
| 1574 |
+
"eval_steps_per_second": 1.623,
|
| 1575 |
+
"step": 994
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 97.5609756097561,
|
| 1579 |
+
"grad_norm": 19.6168270111084,
|
| 1580 |
+
"learning_rate": 9.259259259259259e-06,
|
| 1581 |
+
"loss": 0.0373,
|
| 1582 |
+
"step": 1000
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 97.95121951219512,
|
| 1586 |
+
"eval_accuracy": 0.8541666666666666,
|
| 1587 |
+
"eval_loss": 0.49421417713165283,
|
| 1588 |
+
"eval_runtime": 3.1042,
|
| 1589 |
+
"eval_samples_per_second": 46.388,
|
| 1590 |
+
"eval_steps_per_second": 1.611,
|
| 1591 |
+
"step": 1004
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 98.53658536585365,
|
| 1595 |
+
"grad_norm": 11.319071769714355,
|
| 1596 |
+
"learning_rate": 8.796296296296297e-06,
|
| 1597 |
+
"loss": 0.0447,
|
| 1598 |
+
"step": 1010
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 98.92682926829268,
|
| 1602 |
+
"eval_accuracy": 0.8541666666666666,
|
| 1603 |
+
"eval_loss": 0.5030938982963562,
|
| 1604 |
+
"eval_runtime": 3.0891,
|
| 1605 |
+
"eval_samples_per_second": 46.615,
|
| 1606 |
+
"eval_steps_per_second": 1.619,
|
| 1607 |
+
"step": 1014
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 99.51219512195122,
|
| 1611 |
+
"grad_norm": 12.67363452911377,
|
| 1612 |
+
"learning_rate": 8.333333333333334e-06,
|
| 1613 |
+
"loss": 0.0519,
|
| 1614 |
+
"step": 1020
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 100.0,
|
| 1618 |
+
"eval_accuracy": 0.8541666666666666,
|
| 1619 |
+
"eval_loss": 0.5348986983299255,
|
| 1620 |
+
"eval_runtime": 3.0853,
|
| 1621 |
+
"eval_samples_per_second": 46.673,
|
| 1622 |
+
"eval_steps_per_second": 1.621,
|
| 1623 |
+
"step": 1025
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 100.48780487804878,
|
| 1627 |
+
"grad_norm": 17.858867645263672,
|
| 1628 |
+
"learning_rate": 7.87037037037037e-06,
|
| 1629 |
+
"loss": 0.0387,
|
| 1630 |
+
"step": 1030
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 100.97560975609755,
|
| 1634 |
+
"eval_accuracy": 0.8541666666666666,
|
| 1635 |
+
"eval_loss": 0.5510598421096802,
|
| 1636 |
+
"eval_runtime": 3.1136,
|
| 1637 |
+
"eval_samples_per_second": 46.249,
|
| 1638 |
+
"eval_steps_per_second": 1.606,
|
| 1639 |
+
"step": 1035
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 101.46341463414635,
|
| 1643 |
+
"grad_norm": 2.6209030151367188,
|
| 1644 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 1645 |
+
"loss": 0.0256,
|
| 1646 |
+
"step": 1040
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 101.95121951219512,
|
| 1650 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1651 |
+
"eval_loss": 0.5319210290908813,
|
| 1652 |
+
"eval_runtime": 3.0318,
|
| 1653 |
+
"eval_samples_per_second": 47.496,
|
| 1654 |
+
"eval_steps_per_second": 1.649,
|
| 1655 |
+
"step": 1045
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 102.4390243902439,
|
| 1659 |
+
"grad_norm": 8.14228630065918,
|
| 1660 |
+
"learning_rate": 6.944444444444445e-06,
|
| 1661 |
+
"loss": 0.043,
|
| 1662 |
+
"step": 1050
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 102.92682926829268,
|
| 1666 |
+
"eval_accuracy": 0.8263888888888888,
|
| 1667 |
+
"eval_loss": 0.5605261325836182,
|
| 1668 |
+
"eval_runtime": 3.0596,
|
| 1669 |
+
"eval_samples_per_second": 47.064,
|
| 1670 |
+
"eval_steps_per_second": 1.634,
|
| 1671 |
+
"step": 1055
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 103.41463414634147,
|
| 1675 |
+
"grad_norm": 8.247823715209961,
|
| 1676 |
+
"learning_rate": 6.481481481481481e-06,
|
| 1677 |
+
"loss": 0.029,
|
| 1678 |
+
"step": 1060
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 104.0,
|
| 1682 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1683 |
+
"eval_loss": 0.5775593519210815,
|
| 1684 |
+
"eval_runtime": 3.3388,
|
| 1685 |
+
"eval_samples_per_second": 43.13,
|
| 1686 |
+
"eval_steps_per_second": 1.498,
|
| 1687 |
+
"step": 1066
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 104.39024390243902,
|
| 1691 |
+
"grad_norm": 7.826836585998535,
|
| 1692 |
+
"learning_rate": 6.0185185185185185e-06,
|
| 1693 |
+
"loss": 0.0379,
|
| 1694 |
+
"step": 1070
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 104.97560975609755,
|
| 1698 |
+
"eval_accuracy": 0.8472222222222222,
|
| 1699 |
+
"eval_loss": 0.5697184801101685,
|
| 1700 |
+
"eval_runtime": 3.1172,
|
| 1701 |
+
"eval_samples_per_second": 46.196,
|
| 1702 |
+
"eval_steps_per_second": 1.604,
|
| 1703 |
+
"step": 1076
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 105.36585365853658,
|
| 1707 |
+
"grad_norm": 7.729676246643066,
|
| 1708 |
+
"learning_rate": 5.555555555555556e-06,
|
| 1709 |
+
"loss": 0.0445,
|
| 1710 |
+
"step": 1080
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 105.95121951219512,
|
| 1714 |
+
"eval_accuracy": 0.8680555555555556,
|
| 1715 |
+
"eval_loss": 0.5132907629013062,
|
| 1716 |
+
"eval_runtime": 3.1003,
|
| 1717 |
+
"eval_samples_per_second": 46.447,
|
| 1718 |
+
"eval_steps_per_second": 1.613,
|
| 1719 |
+
"step": 1086
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 106.34146341463415,
|
| 1723 |
+
"grad_norm": 18.125850677490234,
|
| 1724 |
+
"learning_rate": 5.092592592592592e-06,
|
| 1725 |
+
"loss": 0.0267,
|
| 1726 |
+
"step": 1090
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 106.92682926829268,
|
| 1730 |
+
"eval_accuracy": 0.8680555555555556,
|
| 1731 |
+
"eval_loss": 0.5075670480728149,
|
| 1732 |
+
"eval_runtime": 2.9664,
|
| 1733 |
+
"eval_samples_per_second": 48.543,
|
| 1734 |
+
"eval_steps_per_second": 1.686,
|
| 1735 |
+
"step": 1096
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 107.3170731707317,
|
| 1739 |
+
"grad_norm": 11.351465225219727,
|
| 1740 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 1741 |
+
"loss": 0.044,
|
| 1742 |
+
"step": 1100
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 108.0,
|
| 1746 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1747 |
+
"eval_loss": 0.5260215401649475,
|
| 1748 |
+
"eval_runtime": 3.1083,
|
| 1749 |
+
"eval_samples_per_second": 46.328,
|
| 1750 |
+
"eval_steps_per_second": 1.609,
|
| 1751 |
+
"step": 1107
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 108.29268292682927,
|
| 1755 |
+
"grad_norm": 2.0481507778167725,
|
| 1756 |
+
"learning_rate": 4.166666666666667e-06,
|
| 1757 |
+
"loss": 0.0263,
|
| 1758 |
+
"step": 1110
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 108.97560975609755,
|
| 1762 |
+
"eval_accuracy": 0.8541666666666666,
|
| 1763 |
+
"eval_loss": 0.5101317167282104,
|
| 1764 |
+
"eval_runtime": 3.0889,
|
| 1765 |
+
"eval_samples_per_second": 46.619,
|
| 1766 |
+
"eval_steps_per_second": 1.619,
|
| 1767 |
+
"step": 1117
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 109.26829268292683,
|
| 1771 |
+
"grad_norm": 4.980681419372559,
|
| 1772 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 1773 |
+
"loss": 0.0247,
|
| 1774 |
+
"step": 1120
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 109.95121951219512,
|
| 1778 |
+
"eval_accuracy": 0.8541666666666666,
|
| 1779 |
+
"eval_loss": 0.49724239110946655,
|
| 1780 |
+
"eval_runtime": 3.1321,
|
| 1781 |
+
"eval_samples_per_second": 45.975,
|
| 1782 |
+
"eval_steps_per_second": 1.596,
|
| 1783 |
+
"step": 1127
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 110.2439024390244,
|
| 1787 |
+
"grad_norm": 11.607294082641602,
|
| 1788 |
+
"learning_rate": 3.2407407407407406e-06,
|
| 1789 |
+
"loss": 0.0441,
|
| 1790 |
+
"step": 1130
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 110.92682926829268,
|
| 1794 |
+
"eval_accuracy": 0.8472222222222222,
|
| 1795 |
+
"eval_loss": 0.5093557834625244,
|
| 1796 |
+
"eval_runtime": 3.2177,
|
| 1797 |
+
"eval_samples_per_second": 44.753,
|
| 1798 |
+
"eval_steps_per_second": 1.554,
|
| 1799 |
+
"step": 1137
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 111.21951219512195,
|
| 1803 |
+
"grad_norm": 0.6021797060966492,
|
| 1804 |
+
"learning_rate": 2.777777777777778e-06,
|
| 1805 |
+
"loss": 0.0263,
|
| 1806 |
+
"step": 1140
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 112.0,
|
| 1810 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1811 |
+
"eval_loss": 0.525884747505188,
|
| 1812 |
+
"eval_runtime": 3.1645,
|
| 1813 |
+
"eval_samples_per_second": 45.505,
|
| 1814 |
+
"eval_steps_per_second": 1.58,
|
| 1815 |
+
"step": 1148
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 112.1951219512195,
|
| 1819 |
+
"grad_norm": 8.183242797851562,
|
| 1820 |
+
"learning_rate": 2.3148148148148148e-06,
|
| 1821 |
+
"loss": 0.0247,
|
| 1822 |
+
"step": 1150
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 112.97560975609755,
|
| 1826 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1827 |
+
"eval_loss": 0.5323313474655151,
|
| 1828 |
+
"eval_runtime": 3.0594,
|
| 1829 |
+
"eval_samples_per_second": 47.067,
|
| 1830 |
+
"eval_steps_per_second": 1.634,
|
| 1831 |
+
"step": 1158
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 113.17073170731707,
|
| 1835 |
+
"grad_norm": 18.887975692749023,
|
| 1836 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 1837 |
+
"loss": 0.0356,
|
| 1838 |
+
"step": 1160
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 113.95121951219512,
|
| 1842 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1843 |
+
"eval_loss": 0.5275124907493591,
|
| 1844 |
+
"eval_runtime": 3.1264,
|
| 1845 |
+
"eval_samples_per_second": 46.059,
|
| 1846 |
+
"eval_steps_per_second": 1.599,
|
| 1847 |
+
"step": 1168
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 114.14634146341463,
|
| 1851 |
+
"grad_norm": 9.692997932434082,
|
| 1852 |
+
"learning_rate": 1.388888888888889e-06,
|
| 1853 |
+
"loss": 0.0297,
|
| 1854 |
+
"step": 1170
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 114.92682926829268,
|
| 1858 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1859 |
+
"eval_loss": 0.5239912867546082,
|
| 1860 |
+
"eval_runtime": 3.0878,
|
| 1861 |
+
"eval_samples_per_second": 46.636,
|
| 1862 |
+
"eval_steps_per_second": 1.619,
|
| 1863 |
+
"step": 1178
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 115.1219512195122,
|
| 1867 |
+
"grad_norm": 7.508498191833496,
|
| 1868 |
+
"learning_rate": 9.259259259259259e-07,
|
| 1869 |
+
"loss": 0.044,
|
| 1870 |
+
"step": 1180
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 116.0,
|
| 1874 |
+
"eval_accuracy": 0.8472222222222222,
|
| 1875 |
+
"eval_loss": 0.520145833492279,
|
| 1876 |
+
"eval_runtime": 3.0984,
|
| 1877 |
+
"eval_samples_per_second": 46.475,
|
| 1878 |
+
"eval_steps_per_second": 1.614,
|
| 1879 |
+
"step": 1189
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 116.09756097560975,
|
| 1883 |
+
"grad_norm": 2.9772377014160156,
|
| 1884 |
+
"learning_rate": 4.6296296296296297e-07,
|
| 1885 |
+
"loss": 0.031,
|
| 1886 |
+
"step": 1190
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 116.97560975609755,
|
| 1890 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1891 |
+
"eval_loss": 0.5203036069869995,
|
| 1892 |
+
"eval_runtime": 3.066,
|
| 1893 |
+
"eval_samples_per_second": 46.966,
|
| 1894 |
+
"eval_steps_per_second": 1.631,
|
| 1895 |
+
"step": 1199
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 117.07317073170732,
|
| 1899 |
+
"grad_norm": 3.435035467147827,
|
| 1900 |
+
"learning_rate": 0.0,
|
| 1901 |
+
"loss": 0.0369,
|
| 1902 |
+
"step": 1200
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 117.07317073170732,
|
| 1906 |
+
"eval_accuracy": 0.8402777777777778,
|
| 1907 |
+
"eval_loss": 0.5202847123146057,
|
| 1908 |
+
"eval_runtime": 3.0873,
|
| 1909 |
+
"eval_samples_per_second": 46.642,
|
| 1910 |
+
"eval_steps_per_second": 1.62,
|
| 1911 |
+
"step": 1200
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 117.07317073170732,
|
| 1915 |
+
"step": 1200,
|
| 1916 |
+
"total_flos": 3.819974210196996e+18,
|
| 1917 |
+
"train_loss": 0.3624983422954877,
|
| 1918 |
+
"train_runtime": 4158.3882,
|
| 1919 |
+
"train_samples_per_second": 37.399,
|
| 1920 |
+
"train_steps_per_second": 0.289
|
| 1921 |
+
}
|
| 1922 |
+
],
|
| 1923 |
+
"logging_steps": 10,
|
| 1924 |
+
"max_steps": 1200,
|
| 1925 |
+
"num_input_tokens_seen": 0,
|
| 1926 |
+
"num_train_epochs": 120,
|
| 1927 |
+
"save_steps": 500,
|
| 1928 |
+
"stateful_callbacks": {
|
| 1929 |
+
"TrainerControl": {
|
| 1930 |
+
"args": {
|
| 1931 |
+
"should_epoch_stop": false,
|
| 1932 |
+
"should_evaluate": false,
|
| 1933 |
+
"should_log": false,
|
| 1934 |
+
"should_save": false,
|
| 1935 |
+
"should_training_stop": false
|
| 1936 |
+
},
|
| 1937 |
+
"attributes": {}
|
| 1938 |
+
}
|
| 1939 |
+
},
|
| 1940 |
+
"total_flos": 3.819974210196996e+18,
|
| 1941 |
+
"train_batch_size": 32,
|
| 1942 |
+
"trial_name": null,
|
| 1943 |
+
"trial_params": null
|
| 1944 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2df9544a19a4652671b3b26f754625fdaf4703202fcdfb2d53d46014e546b32e
|
| 3 |
+
size 5240
|