Commit
•
2759634
1
Parent(s):
2f0bae4
End of training
Browse files- README.md +211 -0
- all_results.json +13 -0
- config.json +63 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- train_results.json +8 -0
- trainer_state.json +1878 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,211 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-bottomwear
|
| 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: 0.875
|
| 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-bottomwear
|
| 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: 0.3252
|
| 36 |
+
- Accuracy: 0.875
|
| 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: 150
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:--------:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 0.8889 | 6 | 2.0789 | 0.0938 |
|
| 71 |
+
| 2.1005 | 1.9259 | 13 | 2.0276 | 0.125 |
|
| 72 |
+
| 2.0321 | 2.9630 | 20 | 1.9456 | 0.2812 |
|
| 73 |
+
| 2.0321 | 4.0 | 27 | 1.8393 | 0.4583 |
|
| 74 |
+
| 1.9151 | 4.8889 | 33 | 1.7343 | 0.5833 |
|
| 75 |
+
| 1.7396 | 5.9259 | 40 | 1.5972 | 0.6042 |
|
| 76 |
+
| 1.7396 | 6.9630 | 47 | 1.4546 | 0.6771 |
|
| 77 |
+
| 1.5392 | 8.0 | 54 | 1.2943 | 0.7396 |
|
| 78 |
+
| 1.3096 | 8.8889 | 60 | 1.1409 | 0.7396 |
|
| 79 |
+
| 1.3096 | 9.9259 | 67 | 0.9841 | 0.8229 |
|
| 80 |
+
| 1.1062 | 10.9630 | 74 | 0.8512 | 0.8229 |
|
| 81 |
+
| 0.896 | 12.0 | 81 | 0.7128 | 0.8542 |
|
| 82 |
+
| 0.896 | 12.8889 | 87 | 0.6366 | 0.8333 |
|
| 83 |
+
| 0.712 | 13.9259 | 94 | 0.5419 | 0.8646 |
|
| 84 |
+
| 0.6231 | 14.9630 | 101 | 0.5082 | 0.8646 |
|
| 85 |
+
| 0.6231 | 16.0 | 108 | 0.4674 | 0.875 |
|
| 86 |
+
| 0.4962 | 16.8889 | 114 | 0.4480 | 0.8542 |
|
| 87 |
+
| 0.4322 | 17.9259 | 121 | 0.4138 | 0.875 |
|
| 88 |
+
| 0.4322 | 18.9630 | 128 | 0.3947 | 0.8646 |
|
| 89 |
+
| 0.3937 | 20.0 | 135 | 0.3827 | 0.8646 |
|
| 90 |
+
| 0.3377 | 20.8889 | 141 | 0.3626 | 0.8646 |
|
| 91 |
+
| 0.3377 | 21.9259 | 148 | 0.3579 | 0.8646 |
|
| 92 |
+
| 0.3099 | 22.9630 | 155 | 0.3558 | 0.8646 |
|
| 93 |
+
| 0.2895 | 24.0 | 162 | 0.3243 | 0.8646 |
|
| 94 |
+
| 0.2895 | 24.8889 | 168 | 0.3473 | 0.875 |
|
| 95 |
+
| 0.2732 | 25.9259 | 175 | 0.3461 | 0.8646 |
|
| 96 |
+
| 0.2447 | 26.9630 | 182 | 0.3450 | 0.8958 |
|
| 97 |
+
| 0.2447 | 28.0 | 189 | 0.3603 | 0.8958 |
|
| 98 |
+
| 0.2009 | 28.8889 | 195 | 0.3214 | 0.8854 |
|
| 99 |
+
| 0.2064 | 29.9259 | 202 | 0.3043 | 0.875 |
|
| 100 |
+
| 0.2064 | 30.9630 | 209 | 0.2917 | 0.8958 |
|
| 101 |
+
| 0.2139 | 32.0 | 216 | 0.2860 | 0.8958 |
|
| 102 |
+
| 0.1732 | 32.8889 | 222 | 0.3314 | 0.8333 |
|
| 103 |
+
| 0.1732 | 33.9259 | 229 | 0.3391 | 0.875 |
|
| 104 |
+
| 0.2009 | 34.9630 | 236 | 0.3118 | 0.8958 |
|
| 105 |
+
| 0.1683 | 36.0 | 243 | 0.3162 | 0.875 |
|
| 106 |
+
| 0.1683 | 36.8889 | 249 | 0.3011 | 0.8646 |
|
| 107 |
+
| 0.16 | 37.9259 | 256 | 0.2981 | 0.8854 |
|
| 108 |
+
| 0.1448 | 38.9630 | 263 | 0.3417 | 0.9062 |
|
| 109 |
+
| 0.1272 | 40.0 | 270 | 0.3558 | 0.8646 |
|
| 110 |
+
| 0.1272 | 40.8889 | 276 | 0.3948 | 0.8542 |
|
| 111 |
+
| 0.1578 | 41.9259 | 283 | 0.3668 | 0.8646 |
|
| 112 |
+
| 0.1604 | 42.9630 | 290 | 0.3342 | 0.8958 |
|
| 113 |
+
| 0.1604 | 44.0 | 297 | 0.3141 | 0.9167 |
|
| 114 |
+
| 0.1251 | 44.8889 | 303 | 0.3266 | 0.8854 |
|
| 115 |
+
| 0.1449 | 45.9259 | 310 | 0.3438 | 0.8854 |
|
| 116 |
+
| 0.1449 | 46.9630 | 317 | 0.3383 | 0.875 |
|
| 117 |
+
| 0.1134 | 48.0 | 324 | 0.3341 | 0.8958 |
|
| 118 |
+
| 0.1558 | 48.8889 | 330 | 0.2855 | 0.8958 |
|
| 119 |
+
| 0.1558 | 49.9259 | 337 | 0.2843 | 0.8958 |
|
| 120 |
+
| 0.1433 | 50.9630 | 344 | 0.2879 | 0.8438 |
|
| 121 |
+
| 0.1207 | 52.0 | 351 | 0.2887 | 0.8854 |
|
| 122 |
+
| 0.1207 | 52.8889 | 357 | 0.3173 | 0.8958 |
|
| 123 |
+
| 0.1006 | 53.9259 | 364 | 0.2926 | 0.8854 |
|
| 124 |
+
| 0.1053 | 54.9630 | 371 | 0.2791 | 0.9062 |
|
| 125 |
+
| 0.1053 | 56.0 | 378 | 0.3276 | 0.875 |
|
| 126 |
+
| 0.106 | 56.8889 | 384 | 0.3224 | 0.875 |
|
| 127 |
+
| 0.1058 | 57.9259 | 391 | 0.3385 | 0.8854 |
|
| 128 |
+
| 0.1058 | 58.9630 | 398 | 0.3494 | 0.8958 |
|
| 129 |
+
| 0.0962 | 60.0 | 405 | 0.2798 | 0.8854 |
|
| 130 |
+
| 0.0883 | 60.8889 | 411 | 0.2934 | 0.8854 |
|
| 131 |
+
| 0.0883 | 61.9259 | 418 | 0.2956 | 0.875 |
|
| 132 |
+
| 0.084 | 62.9630 | 425 | 0.2918 | 0.8958 |
|
| 133 |
+
| 0.0808 | 64.0 | 432 | 0.3416 | 0.8854 |
|
| 134 |
+
| 0.0808 | 64.8889 | 438 | 0.3502 | 0.8854 |
|
| 135 |
+
| 0.0804 | 65.9259 | 445 | 0.2985 | 0.8958 |
|
| 136 |
+
| 0.0854 | 66.9630 | 452 | 0.2792 | 0.9062 |
|
| 137 |
+
| 0.0854 | 68.0 | 459 | 0.3644 | 0.8958 |
|
| 138 |
+
| 0.0887 | 68.8889 | 465 | 0.2684 | 0.9062 |
|
| 139 |
+
| 0.0671 | 69.9259 | 472 | 0.2802 | 0.8958 |
|
| 140 |
+
| 0.0671 | 70.9630 | 479 | 0.2901 | 0.9062 |
|
| 141 |
+
| 0.0704 | 72.0 | 486 | 0.3098 | 0.8854 |
|
| 142 |
+
| 0.0802 | 72.8889 | 492 | 0.2960 | 0.8854 |
|
| 143 |
+
| 0.0802 | 73.9259 | 499 | 0.2757 | 0.875 |
|
| 144 |
+
| 0.09 | 74.9630 | 506 | 0.3104 | 0.8646 |
|
| 145 |
+
| 0.0772 | 76.0 | 513 | 0.3120 | 0.8958 |
|
| 146 |
+
| 0.0772 | 76.8889 | 519 | 0.2803 | 0.9167 |
|
| 147 |
+
| 0.0725 | 77.9259 | 526 | 0.2825 | 0.8958 |
|
| 148 |
+
| 0.0684 | 78.9630 | 533 | 0.3255 | 0.875 |
|
| 149 |
+
| 0.0732 | 80.0 | 540 | 0.3091 | 0.9062 |
|
| 150 |
+
| 0.0732 | 80.8889 | 546 | 0.2876 | 0.9167 |
|
| 151 |
+
| 0.0743 | 81.9259 | 553 | 0.3035 | 0.8646 |
|
| 152 |
+
| 0.0807 | 82.9630 | 560 | 0.2751 | 0.9271 |
|
| 153 |
+
| 0.0807 | 84.0 | 567 | 0.2657 | 0.9167 |
|
| 154 |
+
| 0.0799 | 84.8889 | 573 | 0.2810 | 0.9062 |
|
| 155 |
+
| 0.0632 | 85.9259 | 580 | 0.3037 | 0.9062 |
|
| 156 |
+
| 0.0632 | 86.9630 | 587 | 0.3357 | 0.9062 |
|
| 157 |
+
| 0.0579 | 88.0 | 594 | 0.3171 | 0.8646 |
|
| 158 |
+
| 0.0593 | 88.8889 | 600 | 0.3223 | 0.8854 |
|
| 159 |
+
| 0.0593 | 89.9259 | 607 | 0.2977 | 0.8958 |
|
| 160 |
+
| 0.0418 | 90.9630 | 614 | 0.3380 | 0.9062 |
|
| 161 |
+
| 0.0647 | 92.0 | 621 | 0.2863 | 0.875 |
|
| 162 |
+
| 0.0647 | 92.8889 | 627 | 0.2899 | 0.9167 |
|
| 163 |
+
| 0.0649 | 93.9259 | 634 | 0.2853 | 0.8958 |
|
| 164 |
+
| 0.0538 | 94.9630 | 641 | 0.2452 | 0.8854 |
|
| 165 |
+
| 0.0538 | 96.0 | 648 | 0.2569 | 0.8958 |
|
| 166 |
+
| 0.0483 | 96.8889 | 654 | 0.2687 | 0.9062 |
|
| 167 |
+
| 0.0597 | 97.9259 | 661 | 0.3083 | 0.875 |
|
| 168 |
+
| 0.0597 | 98.9630 | 668 | 0.2929 | 0.8646 |
|
| 169 |
+
| 0.0544 | 100.0 | 675 | 0.3253 | 0.875 |
|
| 170 |
+
| 0.0585 | 100.8889 | 681 | 0.3394 | 0.8646 |
|
| 171 |
+
| 0.0585 | 101.9259 | 688 | 0.3748 | 0.8542 |
|
| 172 |
+
| 0.0563 | 102.9630 | 695 | 0.3890 | 0.8646 |
|
| 173 |
+
| 0.059 | 104.0 | 702 | 0.3460 | 0.8854 |
|
| 174 |
+
| 0.059 | 104.8889 | 708 | 0.3308 | 0.875 |
|
| 175 |
+
| 0.0601 | 105.9259 | 715 | 0.3228 | 0.875 |
|
| 176 |
+
| 0.0512 | 106.9630 | 722 | 0.3190 | 0.8854 |
|
| 177 |
+
| 0.0512 | 108.0 | 729 | 0.3028 | 0.875 |
|
| 178 |
+
| 0.0346 | 108.8889 | 735 | 0.3066 | 0.9062 |
|
| 179 |
+
| 0.0434 | 109.9259 | 742 | 0.2952 | 0.9062 |
|
| 180 |
+
| 0.0434 | 110.9630 | 749 | 0.3054 | 0.9062 |
|
| 181 |
+
| 0.0466 | 112.0 | 756 | 0.3087 | 0.8958 |
|
| 182 |
+
| 0.0402 | 112.8889 | 762 | 0.3212 | 0.875 |
|
| 183 |
+
| 0.0402 | 113.9259 | 769 | 0.3235 | 0.8854 |
|
| 184 |
+
| 0.0491 | 114.9630 | 776 | 0.3135 | 0.9062 |
|
| 185 |
+
| 0.0495 | 116.0 | 783 | 0.2991 | 0.8958 |
|
| 186 |
+
| 0.0495 | 116.8889 | 789 | 0.3051 | 0.8854 |
|
| 187 |
+
| 0.0536 | 117.9259 | 796 | 0.3339 | 0.875 |
|
| 188 |
+
| 0.0419 | 118.9630 | 803 | 0.3371 | 0.8646 |
|
| 189 |
+
| 0.0333 | 120.0 | 810 | 0.3376 | 0.8646 |
|
| 190 |
+
| 0.0333 | 120.8889 | 816 | 0.3379 | 0.8646 |
|
| 191 |
+
| 0.0376 | 121.9259 | 823 | 0.3373 | 0.8542 |
|
| 192 |
+
| 0.0397 | 122.9630 | 830 | 0.3437 | 0.8646 |
|
| 193 |
+
| 0.0397 | 124.0 | 837 | 0.3585 | 0.8646 |
|
| 194 |
+
| 0.0299 | 124.8889 | 843 | 0.3514 | 0.8646 |
|
| 195 |
+
| 0.0468 | 125.9259 | 850 | 0.3397 | 0.8646 |
|
| 196 |
+
| 0.0468 | 126.9630 | 857 | 0.3316 | 0.8542 |
|
| 197 |
+
| 0.0351 | 128.0 | 864 | 0.3334 | 0.8646 |
|
| 198 |
+
| 0.0439 | 128.8889 | 870 | 0.3324 | 0.8646 |
|
| 199 |
+
| 0.0439 | 129.9259 | 877 | 0.3290 | 0.8646 |
|
| 200 |
+
| 0.0478 | 130.9630 | 884 | 0.3256 | 0.875 |
|
| 201 |
+
| 0.0434 | 132.0 | 891 | 0.3253 | 0.875 |
|
| 202 |
+
| 0.0434 | 132.8889 | 897 | 0.3251 | 0.875 |
|
| 203 |
+
| 0.0374 | 133.3333 | 900 | 0.3252 | 0.875 |
|
| 204 |
+
|
| 205 |
+
|
| 206 |
+
### Framework versions
|
| 207 |
+
|
| 208 |
+
- Transformers 4.44.0
|
| 209 |
+
- Pytorch 2.4.0
|
| 210 |
+
- Datasets 2.21.0
|
| 211 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 133.33333333333334,
|
| 3 |
+
"eval_accuracy": 0.875,
|
| 4 |
+
"eval_loss": 0.3251601457595825,
|
| 5 |
+
"eval_runtime": 1.9072,
|
| 6 |
+
"eval_samples_per_second": 50.336,
|
| 7 |
+
"eval_steps_per_second": 1.573,
|
| 8 |
+
"total_flos": 2.900008367869133e+18,
|
| 9 |
+
"train_loss": 0.254776107304626,
|
| 10 |
+
"train_runtime": 3168.008,
|
| 11 |
+
"train_samples_per_second": 40.909,
|
| 12 |
+
"train_steps_per_second": 0.284
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "Joggers",
|
| 22 |
+
"1": "capri",
|
| 23 |
+
"2": "jeans",
|
| 24 |
+
"3": "legging",
|
| 25 |
+
"4": "plazzo",
|
| 26 |
+
"5": "shorts",
|
| 27 |
+
"6": "skirt",
|
| 28 |
+
"7": "trouser"
|
| 29 |
+
},
|
| 30 |
+
"image_size": 224,
|
| 31 |
+
"initializer_range": 0.02,
|
| 32 |
+
"label2id": {
|
| 33 |
+
"Joggers": 0,
|
| 34 |
+
"capri": 1,
|
| 35 |
+
"jeans": 2,
|
| 36 |
+
"legging": 3,
|
| 37 |
+
"plazzo": 4,
|
| 38 |
+
"shorts": 5,
|
| 39 |
+
"skirt": 6,
|
| 40 |
+
"trouser": 7
|
| 41 |
+
},
|
| 42 |
+
"layer_norm_eps": 1e-12,
|
| 43 |
+
"model_type": "convnextv2",
|
| 44 |
+
"num_channels": 3,
|
| 45 |
+
"num_stages": 4,
|
| 46 |
+
"out_features": [
|
| 47 |
+
"stage4"
|
| 48 |
+
],
|
| 49 |
+
"out_indices": [
|
| 50 |
+
4
|
| 51 |
+
],
|
| 52 |
+
"patch_size": 4,
|
| 53 |
+
"problem_type": "single_label_classification",
|
| 54 |
+
"stage_names": [
|
| 55 |
+
"stem",
|
| 56 |
+
"stage1",
|
| 57 |
+
"stage2",
|
| 58 |
+
"stage3",
|
| 59 |
+
"stage4"
|
| 60 |
+
],
|
| 61 |
+
"torch_dtype": "float32",
|
| 62 |
+
"transformers_version": "4.44.0"
|
| 63 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 133.33333333333334,
|
| 3 |
+
"eval_accuracy": 0.875,
|
| 4 |
+
"eval_loss": 0.3251601457595825,
|
| 5 |
+
"eval_runtime": 1.9072,
|
| 6 |
+
"eval_samples_per_second": 50.336,
|
| 7 |
+
"eval_steps_per_second": 1.573
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8f099c1831a684faed07a84fae545a0dddb59175246b149de929085d23eaaca
|
| 3 |
+
size 111514288
|
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": 133.33333333333334,
|
| 3 |
+
"total_flos": 2.900008367869133e+18,
|
| 4 |
+
"train_loss": 0.254776107304626,
|
| 5 |
+
"train_runtime": 3168.008,
|
| 6 |
+
"train_samples_per_second": 40.909,
|
| 7 |
+
"train_steps_per_second": 0.284
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1878 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 133.33333333333334,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 900,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.8888888888888888,
|
| 13 |
+
"eval_accuracy": 0.09375,
|
| 14 |
+
"eval_loss": 2.078925609588623,
|
| 15 |
+
"eval_runtime": 2.1652,
|
| 16 |
+
"eval_samples_per_second": 44.337,
|
| 17 |
+
"eval_steps_per_second": 1.386,
|
| 18 |
+
"step": 6
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.4814814814814814,
|
| 22 |
+
"grad_norm": 4.666333198547363,
|
| 23 |
+
"learning_rate": 5.555555555555556e-06,
|
| 24 |
+
"loss": 2.1005,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.925925925925926,
|
| 29 |
+
"eval_accuracy": 0.125,
|
| 30 |
+
"eval_loss": 2.027583122253418,
|
| 31 |
+
"eval_runtime": 1.9426,
|
| 32 |
+
"eval_samples_per_second": 49.419,
|
| 33 |
+
"eval_steps_per_second": 1.544,
|
| 34 |
+
"step": 13
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.962962962962963,
|
| 38 |
+
"grad_norm": 6.9924726486206055,
|
| 39 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 40 |
+
"loss": 2.0321,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.962962962962963,
|
| 45 |
+
"eval_accuracy": 0.28125,
|
| 46 |
+
"eval_loss": 1.945550560951233,
|
| 47 |
+
"eval_runtime": 1.8821,
|
| 48 |
+
"eval_samples_per_second": 51.006,
|
| 49 |
+
"eval_steps_per_second": 1.594,
|
| 50 |
+
"step": 20
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"eval_accuracy": 0.4583333333333333,
|
| 55 |
+
"eval_loss": 1.8392573595046997,
|
| 56 |
+
"eval_runtime": 1.8452,
|
| 57 |
+
"eval_samples_per_second": 52.028,
|
| 58 |
+
"eval_steps_per_second": 1.626,
|
| 59 |
+
"step": 27
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.444444444444445,
|
| 63 |
+
"grad_norm": 6.883745193481445,
|
| 64 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 65 |
+
"loss": 1.9151,
|
| 66 |
+
"step": 30
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.888888888888889,
|
| 70 |
+
"eval_accuracy": 0.5833333333333334,
|
| 71 |
+
"eval_loss": 1.7343072891235352,
|
| 72 |
+
"eval_runtime": 1.8707,
|
| 73 |
+
"eval_samples_per_second": 51.318,
|
| 74 |
+
"eval_steps_per_second": 1.604,
|
| 75 |
+
"step": 33
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.925925925925926,
|
| 79 |
+
"grad_norm": 12.400025367736816,
|
| 80 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 81 |
+
"loss": 1.7396,
|
| 82 |
+
"step": 40
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 5.925925925925926,
|
| 86 |
+
"eval_accuracy": 0.6041666666666666,
|
| 87 |
+
"eval_loss": 1.5971508026123047,
|
| 88 |
+
"eval_runtime": 1.891,
|
| 89 |
+
"eval_samples_per_second": 50.767,
|
| 90 |
+
"eval_steps_per_second": 1.586,
|
| 91 |
+
"step": 40
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 6.962962962962963,
|
| 95 |
+
"eval_accuracy": 0.6770833333333334,
|
| 96 |
+
"eval_loss": 1.4546260833740234,
|
| 97 |
+
"eval_runtime": 1.8412,
|
| 98 |
+
"eval_samples_per_second": 52.14,
|
| 99 |
+
"eval_steps_per_second": 1.629,
|
| 100 |
+
"step": 47
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 7.407407407407407,
|
| 104 |
+
"grad_norm": 11.476837158203125,
|
| 105 |
+
"learning_rate": 2.777777777777778e-05,
|
| 106 |
+
"loss": 1.5392,
|
| 107 |
+
"step": 50
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"eval_accuracy": 0.7395833333333334,
|
| 112 |
+
"eval_loss": 1.2942534685134888,
|
| 113 |
+
"eval_runtime": 1.9365,
|
| 114 |
+
"eval_samples_per_second": 49.574,
|
| 115 |
+
"eval_steps_per_second": 1.549,
|
| 116 |
+
"step": 54
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 8.88888888888889,
|
| 120 |
+
"grad_norm": 14.580023765563965,
|
| 121 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 122 |
+
"loss": 1.3096,
|
| 123 |
+
"step": 60
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 8.88888888888889,
|
| 127 |
+
"eval_accuracy": 0.7395833333333334,
|
| 128 |
+
"eval_loss": 1.1409353017807007,
|
| 129 |
+
"eval_runtime": 1.8719,
|
| 130 |
+
"eval_samples_per_second": 51.286,
|
| 131 |
+
"eval_steps_per_second": 1.603,
|
| 132 |
+
"step": 60
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 9.925925925925926,
|
| 136 |
+
"eval_accuracy": 0.8229166666666666,
|
| 137 |
+
"eval_loss": 0.9840934872627258,
|
| 138 |
+
"eval_runtime": 1.8663,
|
| 139 |
+
"eval_samples_per_second": 51.44,
|
| 140 |
+
"eval_steps_per_second": 1.607,
|
| 141 |
+
"step": 67
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.37037037037037,
|
| 145 |
+
"grad_norm": 15.968297958374023,
|
| 146 |
+
"learning_rate": 3.888888888888889e-05,
|
| 147 |
+
"loss": 1.1062,
|
| 148 |
+
"step": 70
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 10.962962962962964,
|
| 152 |
+
"eval_accuracy": 0.8229166666666666,
|
| 153 |
+
"eval_loss": 0.851224958896637,
|
| 154 |
+
"eval_runtime": 1.9128,
|
| 155 |
+
"eval_samples_per_second": 50.189,
|
| 156 |
+
"eval_steps_per_second": 1.568,
|
| 157 |
+
"step": 74
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 11.851851851851851,
|
| 161 |
+
"grad_norm": 23.297271728515625,
|
| 162 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 163 |
+
"loss": 0.896,
|
| 164 |
+
"step": 80
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 12.0,
|
| 168 |
+
"eval_accuracy": 0.8541666666666666,
|
| 169 |
+
"eval_loss": 0.7128415703773499,
|
| 170 |
+
"eval_runtime": 1.8414,
|
| 171 |
+
"eval_samples_per_second": 52.136,
|
| 172 |
+
"eval_steps_per_second": 1.629,
|
| 173 |
+
"step": 81
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 12.88888888888889,
|
| 177 |
+
"eval_accuracy": 0.8333333333333334,
|
| 178 |
+
"eval_loss": 0.6365618109703064,
|
| 179 |
+
"eval_runtime": 1.8634,
|
| 180 |
+
"eval_samples_per_second": 51.518,
|
| 181 |
+
"eval_steps_per_second": 1.61,
|
| 182 |
+
"step": 87
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 13.333333333333334,
|
| 186 |
+
"grad_norm": 24.776830673217773,
|
| 187 |
+
"learning_rate": 5e-05,
|
| 188 |
+
"loss": 0.712,
|
| 189 |
+
"step": 90
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 13.925925925925926,
|
| 193 |
+
"eval_accuracy": 0.8645833333333334,
|
| 194 |
+
"eval_loss": 0.5419111847877502,
|
| 195 |
+
"eval_runtime": 1.874,
|
| 196 |
+
"eval_samples_per_second": 51.228,
|
| 197 |
+
"eval_steps_per_second": 1.601,
|
| 198 |
+
"step": 94
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 14.814814814814815,
|
| 202 |
+
"grad_norm": 26.37338638305664,
|
| 203 |
+
"learning_rate": 4.938271604938271e-05,
|
| 204 |
+
"loss": 0.6231,
|
| 205 |
+
"step": 100
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 14.962962962962964,
|
| 209 |
+
"eval_accuracy": 0.8645833333333334,
|
| 210 |
+
"eval_loss": 0.5082051753997803,
|
| 211 |
+
"eval_runtime": 1.8338,
|
| 212 |
+
"eval_samples_per_second": 52.35,
|
| 213 |
+
"eval_steps_per_second": 1.636,
|
| 214 |
+
"step": 101
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 16.0,
|
| 218 |
+
"eval_accuracy": 0.875,
|
| 219 |
+
"eval_loss": 0.4674176871776581,
|
| 220 |
+
"eval_runtime": 1.878,
|
| 221 |
+
"eval_samples_per_second": 51.118,
|
| 222 |
+
"eval_steps_per_second": 1.597,
|
| 223 |
+
"step": 108
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 16.296296296296298,
|
| 227 |
+
"grad_norm": 26.630212783813477,
|
| 228 |
+
"learning_rate": 4.876543209876544e-05,
|
| 229 |
+
"loss": 0.4962,
|
| 230 |
+
"step": 110
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 16.88888888888889,
|
| 234 |
+
"eval_accuracy": 0.8541666666666666,
|
| 235 |
+
"eval_loss": 0.4479581415653229,
|
| 236 |
+
"eval_runtime": 1.8306,
|
| 237 |
+
"eval_samples_per_second": 52.441,
|
| 238 |
+
"eval_steps_per_second": 1.639,
|
| 239 |
+
"step": 114
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 17.77777777777778,
|
| 243 |
+
"grad_norm": 23.847532272338867,
|
| 244 |
+
"learning_rate": 4.814814814814815e-05,
|
| 245 |
+
"loss": 0.4322,
|
| 246 |
+
"step": 120
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 17.925925925925927,
|
| 250 |
+
"eval_accuracy": 0.875,
|
| 251 |
+
"eval_loss": 0.41380929946899414,
|
| 252 |
+
"eval_runtime": 1.8812,
|
| 253 |
+
"eval_samples_per_second": 51.03,
|
| 254 |
+
"eval_steps_per_second": 1.595,
|
| 255 |
+
"step": 121
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 18.962962962962962,
|
| 259 |
+
"eval_accuracy": 0.8645833333333334,
|
| 260 |
+
"eval_loss": 0.39465710520744324,
|
| 261 |
+
"eval_runtime": 1.8978,
|
| 262 |
+
"eval_samples_per_second": 50.584,
|
| 263 |
+
"eval_steps_per_second": 1.581,
|
| 264 |
+
"step": 128
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 19.25925925925926,
|
| 268 |
+
"grad_norm": 23.30731201171875,
|
| 269 |
+
"learning_rate": 4.7530864197530866e-05,
|
| 270 |
+
"loss": 0.3937,
|
| 271 |
+
"step": 130
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 20.0,
|
| 275 |
+
"eval_accuracy": 0.8645833333333334,
|
| 276 |
+
"eval_loss": 0.3826509416103363,
|
| 277 |
+
"eval_runtime": 1.8444,
|
| 278 |
+
"eval_samples_per_second": 52.05,
|
| 279 |
+
"eval_steps_per_second": 1.627,
|
| 280 |
+
"step": 135
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 20.74074074074074,
|
| 284 |
+
"grad_norm": 22.551395416259766,
|
| 285 |
+
"learning_rate": 4.691358024691358e-05,
|
| 286 |
+
"loss": 0.3377,
|
| 287 |
+
"step": 140
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 20.88888888888889,
|
| 291 |
+
"eval_accuracy": 0.8645833333333334,
|
| 292 |
+
"eval_loss": 0.36256420612335205,
|
| 293 |
+
"eval_runtime": 1.8807,
|
| 294 |
+
"eval_samples_per_second": 51.044,
|
| 295 |
+
"eval_steps_per_second": 1.595,
|
| 296 |
+
"step": 141
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 21.925925925925927,
|
| 300 |
+
"eval_accuracy": 0.8645833333333334,
|
| 301 |
+
"eval_loss": 0.3579378128051758,
|
| 302 |
+
"eval_runtime": 1.8493,
|
| 303 |
+
"eval_samples_per_second": 51.911,
|
| 304 |
+
"eval_steps_per_second": 1.622,
|
| 305 |
+
"step": 148
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 22.22222222222222,
|
| 309 |
+
"grad_norm": 19.129470825195312,
|
| 310 |
+
"learning_rate": 4.62962962962963e-05,
|
| 311 |
+
"loss": 0.3099,
|
| 312 |
+
"step": 150
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 22.962962962962962,
|
| 316 |
+
"eval_accuracy": 0.8645833333333334,
|
| 317 |
+
"eval_loss": 0.35575783252716064,
|
| 318 |
+
"eval_runtime": 1.8947,
|
| 319 |
+
"eval_samples_per_second": 50.668,
|
| 320 |
+
"eval_steps_per_second": 1.583,
|
| 321 |
+
"step": 155
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 23.703703703703702,
|
| 325 |
+
"grad_norm": 34.541709899902344,
|
| 326 |
+
"learning_rate": 4.567901234567901e-05,
|
| 327 |
+
"loss": 0.2895,
|
| 328 |
+
"step": 160
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 24.0,
|
| 332 |
+
"eval_accuracy": 0.8645833333333334,
|
| 333 |
+
"eval_loss": 0.3242819011211395,
|
| 334 |
+
"eval_runtime": 1.9128,
|
| 335 |
+
"eval_samples_per_second": 50.188,
|
| 336 |
+
"eval_steps_per_second": 1.568,
|
| 337 |
+
"step": 162
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 24.88888888888889,
|
| 341 |
+
"eval_accuracy": 0.875,
|
| 342 |
+
"eval_loss": 0.34730610251426697,
|
| 343 |
+
"eval_runtime": 1.857,
|
| 344 |
+
"eval_samples_per_second": 51.697,
|
| 345 |
+
"eval_steps_per_second": 1.616,
|
| 346 |
+
"step": 168
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 25.185185185185187,
|
| 350 |
+
"grad_norm": 27.23337745666504,
|
| 351 |
+
"learning_rate": 4.506172839506173e-05,
|
| 352 |
+
"loss": 0.2732,
|
| 353 |
+
"step": 170
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 25.925925925925927,
|
| 357 |
+
"eval_accuracy": 0.8645833333333334,
|
| 358 |
+
"eval_loss": 0.34611785411834717,
|
| 359 |
+
"eval_runtime": 1.9339,
|
| 360 |
+
"eval_samples_per_second": 49.641,
|
| 361 |
+
"eval_steps_per_second": 1.551,
|
| 362 |
+
"step": 175
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 26.666666666666668,
|
| 366 |
+
"grad_norm": 26.6937255859375,
|
| 367 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 368 |
+
"loss": 0.2447,
|
| 369 |
+
"step": 180
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 26.962962962962962,
|
| 373 |
+
"eval_accuracy": 0.8958333333333334,
|
| 374 |
+
"eval_loss": 0.34497448801994324,
|
| 375 |
+
"eval_runtime": 1.9227,
|
| 376 |
+
"eval_samples_per_second": 49.929,
|
| 377 |
+
"eval_steps_per_second": 1.56,
|
| 378 |
+
"step": 182
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 28.0,
|
| 382 |
+
"eval_accuracy": 0.8958333333333334,
|
| 383 |
+
"eval_loss": 0.36034080386161804,
|
| 384 |
+
"eval_runtime": 1.8685,
|
| 385 |
+
"eval_samples_per_second": 51.378,
|
| 386 |
+
"eval_steps_per_second": 1.606,
|
| 387 |
+
"step": 189
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 28.14814814814815,
|
| 391 |
+
"grad_norm": 22.52947235107422,
|
| 392 |
+
"learning_rate": 4.3827160493827164e-05,
|
| 393 |
+
"loss": 0.2009,
|
| 394 |
+
"step": 190
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 28.88888888888889,
|
| 398 |
+
"eval_accuracy": 0.8854166666666666,
|
| 399 |
+
"eval_loss": 0.3214483857154846,
|
| 400 |
+
"eval_runtime": 1.8832,
|
| 401 |
+
"eval_samples_per_second": 50.977,
|
| 402 |
+
"eval_steps_per_second": 1.593,
|
| 403 |
+
"step": 195
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 29.62962962962963,
|
| 407 |
+
"grad_norm": 23.971797943115234,
|
| 408 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 409 |
+
"loss": 0.2064,
|
| 410 |
+
"step": 200
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 29.925925925925927,
|
| 414 |
+
"eval_accuracy": 0.875,
|
| 415 |
+
"eval_loss": 0.30430108308792114,
|
| 416 |
+
"eval_runtime": 1.8494,
|
| 417 |
+
"eval_samples_per_second": 51.909,
|
| 418 |
+
"eval_steps_per_second": 1.622,
|
| 419 |
+
"step": 202
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 30.962962962962962,
|
| 423 |
+
"eval_accuracy": 0.8958333333333334,
|
| 424 |
+
"eval_loss": 0.2916516661643982,
|
| 425 |
+
"eval_runtime": 1.8828,
|
| 426 |
+
"eval_samples_per_second": 50.987,
|
| 427 |
+
"eval_steps_per_second": 1.593,
|
| 428 |
+
"step": 209
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 31.11111111111111,
|
| 432 |
+
"grad_norm": 20.200942993164062,
|
| 433 |
+
"learning_rate": 4.259259259259259e-05,
|
| 434 |
+
"loss": 0.2139,
|
| 435 |
+
"step": 210
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 32.0,
|
| 439 |
+
"eval_accuracy": 0.8958333333333334,
|
| 440 |
+
"eval_loss": 0.28600063920021057,
|
| 441 |
+
"eval_runtime": 1.903,
|
| 442 |
+
"eval_samples_per_second": 50.448,
|
| 443 |
+
"eval_steps_per_second": 1.576,
|
| 444 |
+
"step": 216
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 32.592592592592595,
|
| 448 |
+
"grad_norm": 49.91157531738281,
|
| 449 |
+
"learning_rate": 4.197530864197531e-05,
|
| 450 |
+
"loss": 0.1732,
|
| 451 |
+
"step": 220
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 32.888888888888886,
|
| 455 |
+
"eval_accuracy": 0.8333333333333334,
|
| 456 |
+
"eval_loss": 0.3314121663570404,
|
| 457 |
+
"eval_runtime": 1.8588,
|
| 458 |
+
"eval_samples_per_second": 51.646,
|
| 459 |
+
"eval_steps_per_second": 1.614,
|
| 460 |
+
"step": 222
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 33.925925925925924,
|
| 464 |
+
"eval_accuracy": 0.875,
|
| 465 |
+
"eval_loss": 0.339076429605484,
|
| 466 |
+
"eval_runtime": 1.8736,
|
| 467 |
+
"eval_samples_per_second": 51.238,
|
| 468 |
+
"eval_steps_per_second": 1.601,
|
| 469 |
+
"step": 229
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 34.074074074074076,
|
| 473 |
+
"grad_norm": 15.412144660949707,
|
| 474 |
+
"learning_rate": 4.135802469135803e-05,
|
| 475 |
+
"loss": 0.2009,
|
| 476 |
+
"step": 230
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 34.96296296296296,
|
| 480 |
+
"eval_accuracy": 0.8958333333333334,
|
| 481 |
+
"eval_loss": 0.3118279278278351,
|
| 482 |
+
"eval_runtime": 1.8956,
|
| 483 |
+
"eval_samples_per_second": 50.645,
|
| 484 |
+
"eval_steps_per_second": 1.583,
|
| 485 |
+
"step": 236
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 35.55555555555556,
|
| 489 |
+
"grad_norm": 18.91287612915039,
|
| 490 |
+
"learning_rate": 4.074074074074074e-05,
|
| 491 |
+
"loss": 0.1683,
|
| 492 |
+
"step": 240
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 36.0,
|
| 496 |
+
"eval_accuracy": 0.875,
|
| 497 |
+
"eval_loss": 0.3162083327770233,
|
| 498 |
+
"eval_runtime": 1.8823,
|
| 499 |
+
"eval_samples_per_second": 51.002,
|
| 500 |
+
"eval_steps_per_second": 1.594,
|
| 501 |
+
"step": 243
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 36.888888888888886,
|
| 505 |
+
"eval_accuracy": 0.8645833333333334,
|
| 506 |
+
"eval_loss": 0.3011355996131897,
|
| 507 |
+
"eval_runtime": 1.8611,
|
| 508 |
+
"eval_samples_per_second": 51.582,
|
| 509 |
+
"eval_steps_per_second": 1.612,
|
| 510 |
+
"step": 249
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 37.03703703703704,
|
| 514 |
+
"grad_norm": 35.87955856323242,
|
| 515 |
+
"learning_rate": 4.012345679012346e-05,
|
| 516 |
+
"loss": 0.16,
|
| 517 |
+
"step": 250
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 37.925925925925924,
|
| 521 |
+
"eval_accuracy": 0.8854166666666666,
|
| 522 |
+
"eval_loss": 0.2981296479701996,
|
| 523 |
+
"eval_runtime": 1.9139,
|
| 524 |
+
"eval_samples_per_second": 50.159,
|
| 525 |
+
"eval_steps_per_second": 1.567,
|
| 526 |
+
"step": 256
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 38.51851851851852,
|
| 530 |
+
"grad_norm": 12.093141555786133,
|
| 531 |
+
"learning_rate": 3.950617283950617e-05,
|
| 532 |
+
"loss": 0.1448,
|
| 533 |
+
"step": 260
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 38.96296296296296,
|
| 537 |
+
"eval_accuracy": 0.90625,
|
| 538 |
+
"eval_loss": 0.34168219566345215,
|
| 539 |
+
"eval_runtime": 1.8741,
|
| 540 |
+
"eval_samples_per_second": 51.226,
|
| 541 |
+
"eval_steps_per_second": 1.601,
|
| 542 |
+
"step": 263
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 40.0,
|
| 546 |
+
"grad_norm": 36.96841049194336,
|
| 547 |
+
"learning_rate": 3.888888888888889e-05,
|
| 548 |
+
"loss": 0.1272,
|
| 549 |
+
"step": 270
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 40.0,
|
| 553 |
+
"eval_accuracy": 0.8645833333333334,
|
| 554 |
+
"eval_loss": 0.35579848289489746,
|
| 555 |
+
"eval_runtime": 1.8827,
|
| 556 |
+
"eval_samples_per_second": 50.992,
|
| 557 |
+
"eval_steps_per_second": 1.593,
|
| 558 |
+
"step": 270
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 40.888888888888886,
|
| 562 |
+
"eval_accuracy": 0.8541666666666666,
|
| 563 |
+
"eval_loss": 0.3948463499546051,
|
| 564 |
+
"eval_runtime": 1.8989,
|
| 565 |
+
"eval_samples_per_second": 50.557,
|
| 566 |
+
"eval_steps_per_second": 1.58,
|
| 567 |
+
"step": 276
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 41.48148148148148,
|
| 571 |
+
"grad_norm": 17.500049591064453,
|
| 572 |
+
"learning_rate": 3.82716049382716e-05,
|
| 573 |
+
"loss": 0.1578,
|
| 574 |
+
"step": 280
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 41.925925925925924,
|
| 578 |
+
"eval_accuracy": 0.8645833333333334,
|
| 579 |
+
"eval_loss": 0.36678051948547363,
|
| 580 |
+
"eval_runtime": 1.9696,
|
| 581 |
+
"eval_samples_per_second": 48.741,
|
| 582 |
+
"eval_steps_per_second": 1.523,
|
| 583 |
+
"step": 283
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 42.96296296296296,
|
| 587 |
+
"grad_norm": 19.923572540283203,
|
| 588 |
+
"learning_rate": 3.7654320987654326e-05,
|
| 589 |
+
"loss": 0.1604,
|
| 590 |
+
"step": 290
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 42.96296296296296,
|
| 594 |
+
"eval_accuracy": 0.8958333333333334,
|
| 595 |
+
"eval_loss": 0.33422672748565674,
|
| 596 |
+
"eval_runtime": 1.9103,
|
| 597 |
+
"eval_samples_per_second": 50.253,
|
| 598 |
+
"eval_steps_per_second": 1.57,
|
| 599 |
+
"step": 290
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 44.0,
|
| 603 |
+
"eval_accuracy": 0.9166666666666666,
|
| 604 |
+
"eval_loss": 0.314091295003891,
|
| 605 |
+
"eval_runtime": 1.8512,
|
| 606 |
+
"eval_samples_per_second": 51.858,
|
| 607 |
+
"eval_steps_per_second": 1.621,
|
| 608 |
+
"step": 297
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 44.44444444444444,
|
| 612 |
+
"grad_norm": 21.997079849243164,
|
| 613 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 614 |
+
"loss": 0.1251,
|
| 615 |
+
"step": 300
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 44.888888888888886,
|
| 619 |
+
"eval_accuracy": 0.8854166666666666,
|
| 620 |
+
"eval_loss": 0.3266027271747589,
|
| 621 |
+
"eval_runtime": 1.8596,
|
| 622 |
+
"eval_samples_per_second": 51.625,
|
| 623 |
+
"eval_steps_per_second": 1.613,
|
| 624 |
+
"step": 303
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 45.925925925925924,
|
| 628 |
+
"grad_norm": 27.58420753479004,
|
| 629 |
+
"learning_rate": 3.6419753086419754e-05,
|
| 630 |
+
"loss": 0.1449,
|
| 631 |
+
"step": 310
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 45.925925925925924,
|
| 635 |
+
"eval_accuracy": 0.8854166666666666,
|
| 636 |
+
"eval_loss": 0.34379109740257263,
|
| 637 |
+
"eval_runtime": 1.9283,
|
| 638 |
+
"eval_samples_per_second": 49.786,
|
| 639 |
+
"eval_steps_per_second": 1.556,
|
| 640 |
+
"step": 310
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 46.96296296296296,
|
| 644 |
+
"eval_accuracy": 0.875,
|
| 645 |
+
"eval_loss": 0.3382701873779297,
|
| 646 |
+
"eval_runtime": 1.8689,
|
| 647 |
+
"eval_samples_per_second": 51.368,
|
| 648 |
+
"eval_steps_per_second": 1.605,
|
| 649 |
+
"step": 317
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 47.407407407407405,
|
| 653 |
+
"grad_norm": 14.891225814819336,
|
| 654 |
+
"learning_rate": 3.580246913580247e-05,
|
| 655 |
+
"loss": 0.1134,
|
| 656 |
+
"step": 320
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 48.0,
|
| 660 |
+
"eval_accuracy": 0.8958333333333334,
|
| 661 |
+
"eval_loss": 0.33413389325141907,
|
| 662 |
+
"eval_runtime": 1.887,
|
| 663 |
+
"eval_samples_per_second": 50.875,
|
| 664 |
+
"eval_steps_per_second": 1.59,
|
| 665 |
+
"step": 324
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 48.888888888888886,
|
| 669 |
+
"grad_norm": 22.530115127563477,
|
| 670 |
+
"learning_rate": 3.518518518518519e-05,
|
| 671 |
+
"loss": 0.1558,
|
| 672 |
+
"step": 330
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 48.888888888888886,
|
| 676 |
+
"eval_accuracy": 0.8958333333333334,
|
| 677 |
+
"eval_loss": 0.2854965031147003,
|
| 678 |
+
"eval_runtime": 1.9011,
|
| 679 |
+
"eval_samples_per_second": 50.497,
|
| 680 |
+
"eval_steps_per_second": 1.578,
|
| 681 |
+
"step": 330
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 49.925925925925924,
|
| 685 |
+
"eval_accuracy": 0.8958333333333334,
|
| 686 |
+
"eval_loss": 0.2842860221862793,
|
| 687 |
+
"eval_runtime": 1.9386,
|
| 688 |
+
"eval_samples_per_second": 49.52,
|
| 689 |
+
"eval_steps_per_second": 1.547,
|
| 690 |
+
"step": 337
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 50.370370370370374,
|
| 694 |
+
"grad_norm": 45.90536880493164,
|
| 695 |
+
"learning_rate": 3.45679012345679e-05,
|
| 696 |
+
"loss": 0.1433,
|
| 697 |
+
"step": 340
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 50.96296296296296,
|
| 701 |
+
"eval_accuracy": 0.84375,
|
| 702 |
+
"eval_loss": 0.2878771126270294,
|
| 703 |
+
"eval_runtime": 1.8358,
|
| 704 |
+
"eval_samples_per_second": 52.292,
|
| 705 |
+
"eval_steps_per_second": 1.634,
|
| 706 |
+
"step": 344
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 51.851851851851855,
|
| 710 |
+
"grad_norm": 30.33245849609375,
|
| 711 |
+
"learning_rate": 3.395061728395062e-05,
|
| 712 |
+
"loss": 0.1207,
|
| 713 |
+
"step": 350
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 52.0,
|
| 717 |
+
"eval_accuracy": 0.8854166666666666,
|
| 718 |
+
"eval_loss": 0.28866705298423767,
|
| 719 |
+
"eval_runtime": 1.8609,
|
| 720 |
+
"eval_samples_per_second": 51.587,
|
| 721 |
+
"eval_steps_per_second": 1.612,
|
| 722 |
+
"step": 351
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 52.888888888888886,
|
| 726 |
+
"eval_accuracy": 0.8958333333333334,
|
| 727 |
+
"eval_loss": 0.3173443377017975,
|
| 728 |
+
"eval_runtime": 1.858,
|
| 729 |
+
"eval_samples_per_second": 51.668,
|
| 730 |
+
"eval_steps_per_second": 1.615,
|
| 731 |
+
"step": 357
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 53.333333333333336,
|
| 735 |
+
"grad_norm": 14.928536415100098,
|
| 736 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 737 |
+
"loss": 0.1006,
|
| 738 |
+
"step": 360
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 53.925925925925924,
|
| 742 |
+
"eval_accuracy": 0.8854166666666666,
|
| 743 |
+
"eval_loss": 0.2926301658153534,
|
| 744 |
+
"eval_runtime": 2.1238,
|
| 745 |
+
"eval_samples_per_second": 45.203,
|
| 746 |
+
"eval_steps_per_second": 1.413,
|
| 747 |
+
"step": 364
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 54.81481481481482,
|
| 751 |
+
"grad_norm": 16.707883834838867,
|
| 752 |
+
"learning_rate": 3.271604938271605e-05,
|
| 753 |
+
"loss": 0.1053,
|
| 754 |
+
"step": 370
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 54.96296296296296,
|
| 758 |
+
"eval_accuracy": 0.90625,
|
| 759 |
+
"eval_loss": 0.2791050672531128,
|
| 760 |
+
"eval_runtime": 1.8468,
|
| 761 |
+
"eval_samples_per_second": 51.982,
|
| 762 |
+
"eval_steps_per_second": 1.624,
|
| 763 |
+
"step": 371
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 56.0,
|
| 767 |
+
"eval_accuracy": 0.875,
|
| 768 |
+
"eval_loss": 0.3276265859603882,
|
| 769 |
+
"eval_runtime": 1.8761,
|
| 770 |
+
"eval_samples_per_second": 51.17,
|
| 771 |
+
"eval_steps_per_second": 1.599,
|
| 772 |
+
"step": 378
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 56.2962962962963,
|
| 776 |
+
"grad_norm": 19.896167755126953,
|
| 777 |
+
"learning_rate": 3.209876543209876e-05,
|
| 778 |
+
"loss": 0.106,
|
| 779 |
+
"step": 380
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 56.888888888888886,
|
| 783 |
+
"eval_accuracy": 0.875,
|
| 784 |
+
"eval_loss": 0.32238277792930603,
|
| 785 |
+
"eval_runtime": 1.9352,
|
| 786 |
+
"eval_samples_per_second": 49.608,
|
| 787 |
+
"eval_steps_per_second": 1.55,
|
| 788 |
+
"step": 384
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 57.77777777777778,
|
| 792 |
+
"grad_norm": 23.663541793823242,
|
| 793 |
+
"learning_rate": 3.148148148148148e-05,
|
| 794 |
+
"loss": 0.1058,
|
| 795 |
+
"step": 390
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 57.925925925925924,
|
| 799 |
+
"eval_accuracy": 0.8854166666666666,
|
| 800 |
+
"eval_loss": 0.33849918842315674,
|
| 801 |
+
"eval_runtime": 1.9952,
|
| 802 |
+
"eval_samples_per_second": 48.116,
|
| 803 |
+
"eval_steps_per_second": 1.504,
|
| 804 |
+
"step": 391
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 58.96296296296296,
|
| 808 |
+
"eval_accuracy": 0.8958333333333334,
|
| 809 |
+
"eval_loss": 0.34936726093292236,
|
| 810 |
+
"eval_runtime": 1.8826,
|
| 811 |
+
"eval_samples_per_second": 50.992,
|
| 812 |
+
"eval_steps_per_second": 1.594,
|
| 813 |
+
"step": 398
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 59.25925925925926,
|
| 817 |
+
"grad_norm": 6.200643539428711,
|
| 818 |
+
"learning_rate": 3.08641975308642e-05,
|
| 819 |
+
"loss": 0.0962,
|
| 820 |
+
"step": 400
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 60.0,
|
| 824 |
+
"eval_accuracy": 0.8854166666666666,
|
| 825 |
+
"eval_loss": 0.2797829508781433,
|
| 826 |
+
"eval_runtime": 1.8593,
|
| 827 |
+
"eval_samples_per_second": 51.633,
|
| 828 |
+
"eval_steps_per_second": 1.614,
|
| 829 |
+
"step": 405
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 60.74074074074074,
|
| 833 |
+
"grad_norm": 16.507617950439453,
|
| 834 |
+
"learning_rate": 3.0246913580246916e-05,
|
| 835 |
+
"loss": 0.0883,
|
| 836 |
+
"step": 410
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 60.888888888888886,
|
| 840 |
+
"eval_accuracy": 0.8854166666666666,
|
| 841 |
+
"eval_loss": 0.29343104362487793,
|
| 842 |
+
"eval_runtime": 1.8755,
|
| 843 |
+
"eval_samples_per_second": 51.187,
|
| 844 |
+
"eval_steps_per_second": 1.6,
|
| 845 |
+
"step": 411
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 61.925925925925924,
|
| 849 |
+
"eval_accuracy": 0.875,
|
| 850 |
+
"eval_loss": 0.2956160008907318,
|
| 851 |
+
"eval_runtime": 2.1241,
|
| 852 |
+
"eval_samples_per_second": 45.195,
|
| 853 |
+
"eval_steps_per_second": 1.412,
|
| 854 |
+
"step": 418
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 62.22222222222222,
|
| 858 |
+
"grad_norm": 19.266647338867188,
|
| 859 |
+
"learning_rate": 2.962962962962963e-05,
|
| 860 |
+
"loss": 0.084,
|
| 861 |
+
"step": 420
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 62.96296296296296,
|
| 865 |
+
"eval_accuracy": 0.8958333333333334,
|
| 866 |
+
"eval_loss": 0.291843980550766,
|
| 867 |
+
"eval_runtime": 1.864,
|
| 868 |
+
"eval_samples_per_second": 51.503,
|
| 869 |
+
"eval_steps_per_second": 1.609,
|
| 870 |
+
"step": 425
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 63.7037037037037,
|
| 874 |
+
"grad_norm": 27.770219802856445,
|
| 875 |
+
"learning_rate": 2.9012345679012347e-05,
|
| 876 |
+
"loss": 0.0808,
|
| 877 |
+
"step": 430
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 64.0,
|
| 881 |
+
"eval_accuracy": 0.8854166666666666,
|
| 882 |
+
"eval_loss": 0.3416362702846527,
|
| 883 |
+
"eval_runtime": 1.8651,
|
| 884 |
+
"eval_samples_per_second": 51.471,
|
| 885 |
+
"eval_steps_per_second": 1.608,
|
| 886 |
+
"step": 432
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 64.88888888888889,
|
| 890 |
+
"eval_accuracy": 0.8854166666666666,
|
| 891 |
+
"eval_loss": 0.35024556517601013,
|
| 892 |
+
"eval_runtime": 1.8463,
|
| 893 |
+
"eval_samples_per_second": 51.995,
|
| 894 |
+
"eval_steps_per_second": 1.625,
|
| 895 |
+
"step": 438
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 65.18518518518519,
|
| 899 |
+
"grad_norm": 14.995842933654785,
|
| 900 |
+
"learning_rate": 2.839506172839506e-05,
|
| 901 |
+
"loss": 0.0804,
|
| 902 |
+
"step": 440
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 65.92592592592592,
|
| 906 |
+
"eval_accuracy": 0.8958333333333334,
|
| 907 |
+
"eval_loss": 0.2984811067581177,
|
| 908 |
+
"eval_runtime": 2.0874,
|
| 909 |
+
"eval_samples_per_second": 45.989,
|
| 910 |
+
"eval_steps_per_second": 1.437,
|
| 911 |
+
"step": 445
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 66.66666666666667,
|
| 915 |
+
"grad_norm": 34.63008117675781,
|
| 916 |
+
"learning_rate": 2.777777777777778e-05,
|
| 917 |
+
"loss": 0.0854,
|
| 918 |
+
"step": 450
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 66.96296296296296,
|
| 922 |
+
"eval_accuracy": 0.90625,
|
| 923 |
+
"eval_loss": 0.2791596055030823,
|
| 924 |
+
"eval_runtime": 1.88,
|
| 925 |
+
"eval_samples_per_second": 51.064,
|
| 926 |
+
"eval_steps_per_second": 1.596,
|
| 927 |
+
"step": 452
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 68.0,
|
| 931 |
+
"eval_accuracy": 0.8958333333333334,
|
| 932 |
+
"eval_loss": 0.3643587827682495,
|
| 933 |
+
"eval_runtime": 1.8436,
|
| 934 |
+
"eval_samples_per_second": 52.072,
|
| 935 |
+
"eval_steps_per_second": 1.627,
|
| 936 |
+
"step": 459
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 68.14814814814815,
|
| 940 |
+
"grad_norm": 32.28718566894531,
|
| 941 |
+
"learning_rate": 2.7160493827160493e-05,
|
| 942 |
+
"loss": 0.0887,
|
| 943 |
+
"step": 460
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 68.88888888888889,
|
| 947 |
+
"eval_accuracy": 0.90625,
|
| 948 |
+
"eval_loss": 0.2684231400489807,
|
| 949 |
+
"eval_runtime": 1.8572,
|
| 950 |
+
"eval_samples_per_second": 51.691,
|
| 951 |
+
"eval_steps_per_second": 1.615,
|
| 952 |
+
"step": 465
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 69.62962962962963,
|
| 956 |
+
"grad_norm": 22.44804573059082,
|
| 957 |
+
"learning_rate": 2.654320987654321e-05,
|
| 958 |
+
"loss": 0.0671,
|
| 959 |
+
"step": 470
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 69.92592592592592,
|
| 963 |
+
"eval_accuracy": 0.8958333333333334,
|
| 964 |
+
"eval_loss": 0.28022265434265137,
|
| 965 |
+
"eval_runtime": 2.1506,
|
| 966 |
+
"eval_samples_per_second": 44.638,
|
| 967 |
+
"eval_steps_per_second": 1.395,
|
| 968 |
+
"step": 472
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 70.96296296296296,
|
| 972 |
+
"eval_accuracy": 0.90625,
|
| 973 |
+
"eval_loss": 0.2900524437427521,
|
| 974 |
+
"eval_runtime": 1.859,
|
| 975 |
+
"eval_samples_per_second": 51.641,
|
| 976 |
+
"eval_steps_per_second": 1.614,
|
| 977 |
+
"step": 479
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 71.11111111111111,
|
| 981 |
+
"grad_norm": 4.379269123077393,
|
| 982 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 983 |
+
"loss": 0.0704,
|
| 984 |
+
"step": 480
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 72.0,
|
| 988 |
+
"eval_accuracy": 0.8854166666666666,
|
| 989 |
+
"eval_loss": 0.3098466694355011,
|
| 990 |
+
"eval_runtime": 1.838,
|
| 991 |
+
"eval_samples_per_second": 52.23,
|
| 992 |
+
"eval_steps_per_second": 1.632,
|
| 993 |
+
"step": 486
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 72.5925925925926,
|
| 997 |
+
"grad_norm": 17.398576736450195,
|
| 998 |
+
"learning_rate": 2.5308641975308646e-05,
|
| 999 |
+
"loss": 0.0802,
|
| 1000 |
+
"step": 490
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 72.88888888888889,
|
| 1004 |
+
"eval_accuracy": 0.8854166666666666,
|
| 1005 |
+
"eval_loss": 0.2960352897644043,
|
| 1006 |
+
"eval_runtime": 1.867,
|
| 1007 |
+
"eval_samples_per_second": 51.421,
|
| 1008 |
+
"eval_steps_per_second": 1.607,
|
| 1009 |
+
"step": 492
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 73.92592592592592,
|
| 1013 |
+
"eval_accuracy": 0.875,
|
| 1014 |
+
"eval_loss": 0.2757139503955841,
|
| 1015 |
+
"eval_runtime": 2.0356,
|
| 1016 |
+
"eval_samples_per_second": 47.161,
|
| 1017 |
+
"eval_steps_per_second": 1.474,
|
| 1018 |
+
"step": 499
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 74.07407407407408,
|
| 1022 |
+
"grad_norm": 18.339569091796875,
|
| 1023 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 1024 |
+
"loss": 0.09,
|
| 1025 |
+
"step": 500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 74.96296296296296,
|
| 1029 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1030 |
+
"eval_loss": 0.31044331192970276,
|
| 1031 |
+
"eval_runtime": 1.8732,
|
| 1032 |
+
"eval_samples_per_second": 51.249,
|
| 1033 |
+
"eval_steps_per_second": 1.602,
|
| 1034 |
+
"step": 506
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 75.55555555555556,
|
| 1038 |
+
"grad_norm": 8.075996398925781,
|
| 1039 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 1040 |
+
"loss": 0.0772,
|
| 1041 |
+
"step": 510
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 76.0,
|
| 1045 |
+
"eval_accuracy": 0.8958333333333334,
|
| 1046 |
+
"eval_loss": 0.3120499849319458,
|
| 1047 |
+
"eval_runtime": 1.9108,
|
| 1048 |
+
"eval_samples_per_second": 50.239,
|
| 1049 |
+
"eval_steps_per_second": 1.57,
|
| 1050 |
+
"step": 513
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 76.88888888888889,
|
| 1054 |
+
"eval_accuracy": 0.9166666666666666,
|
| 1055 |
+
"eval_loss": 0.2803463637828827,
|
| 1056 |
+
"eval_runtime": 1.8689,
|
| 1057 |
+
"eval_samples_per_second": 51.368,
|
| 1058 |
+
"eval_steps_per_second": 1.605,
|
| 1059 |
+
"step": 519
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 77.03703703703704,
|
| 1063 |
+
"grad_norm": 3.0919692516326904,
|
| 1064 |
+
"learning_rate": 2.345679012345679e-05,
|
| 1065 |
+
"loss": 0.0725,
|
| 1066 |
+
"step": 520
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 77.92592592592592,
|
| 1070 |
+
"eval_accuracy": 0.8958333333333334,
|
| 1071 |
+
"eval_loss": 0.28252843022346497,
|
| 1072 |
+
"eval_runtime": 1.9144,
|
| 1073 |
+
"eval_samples_per_second": 50.146,
|
| 1074 |
+
"eval_steps_per_second": 1.567,
|
| 1075 |
+
"step": 526
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 78.51851851851852,
|
| 1079 |
+
"grad_norm": 14.103160858154297,
|
| 1080 |
+
"learning_rate": 2.2839506172839506e-05,
|
| 1081 |
+
"loss": 0.0684,
|
| 1082 |
+
"step": 530
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 78.96296296296296,
|
| 1086 |
+
"eval_accuracy": 0.875,
|
| 1087 |
+
"eval_loss": 0.325451523065567,
|
| 1088 |
+
"eval_runtime": 1.8932,
|
| 1089 |
+
"eval_samples_per_second": 50.708,
|
| 1090 |
+
"eval_steps_per_second": 1.585,
|
| 1091 |
+
"step": 533
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 80.0,
|
| 1095 |
+
"grad_norm": 25.228979110717773,
|
| 1096 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 1097 |
+
"loss": 0.0732,
|
| 1098 |
+
"step": 540
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 80.0,
|
| 1102 |
+
"eval_accuracy": 0.90625,
|
| 1103 |
+
"eval_loss": 0.3091324269771576,
|
| 1104 |
+
"eval_runtime": 1.8455,
|
| 1105 |
+
"eval_samples_per_second": 52.019,
|
| 1106 |
+
"eval_steps_per_second": 1.626,
|
| 1107 |
+
"step": 540
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 80.88888888888889,
|
| 1111 |
+
"eval_accuracy": 0.9166666666666666,
|
| 1112 |
+
"eval_loss": 0.2875919044017792,
|
| 1113 |
+
"eval_runtime": 1.8878,
|
| 1114 |
+
"eval_samples_per_second": 50.852,
|
| 1115 |
+
"eval_steps_per_second": 1.589,
|
| 1116 |
+
"step": 546
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 81.48148148148148,
|
| 1120 |
+
"grad_norm": 9.110090255737305,
|
| 1121 |
+
"learning_rate": 2.1604938271604937e-05,
|
| 1122 |
+
"loss": 0.0743,
|
| 1123 |
+
"step": 550
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 81.92592592592592,
|
| 1127 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1128 |
+
"eval_loss": 0.30346551537513733,
|
| 1129 |
+
"eval_runtime": 2.0498,
|
| 1130 |
+
"eval_samples_per_second": 46.834,
|
| 1131 |
+
"eval_steps_per_second": 1.464,
|
| 1132 |
+
"step": 553
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 82.96296296296296,
|
| 1136 |
+
"grad_norm": 23.57141876220703,
|
| 1137 |
+
"learning_rate": 2.0987654320987655e-05,
|
| 1138 |
+
"loss": 0.0807,
|
| 1139 |
+
"step": 560
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 82.96296296296296,
|
| 1143 |
+
"eval_accuracy": 0.9270833333333334,
|
| 1144 |
+
"eval_loss": 0.2750629186630249,
|
| 1145 |
+
"eval_runtime": 1.8436,
|
| 1146 |
+
"eval_samples_per_second": 52.073,
|
| 1147 |
+
"eval_steps_per_second": 1.627,
|
| 1148 |
+
"step": 560
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 84.0,
|
| 1152 |
+
"eval_accuracy": 0.9166666666666666,
|
| 1153 |
+
"eval_loss": 0.2656916677951813,
|
| 1154 |
+
"eval_runtime": 1.884,
|
| 1155 |
+
"eval_samples_per_second": 50.955,
|
| 1156 |
+
"eval_steps_per_second": 1.592,
|
| 1157 |
+
"step": 567
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 84.44444444444444,
|
| 1161 |
+
"grad_norm": 7.4042277336120605,
|
| 1162 |
+
"learning_rate": 2.037037037037037e-05,
|
| 1163 |
+
"loss": 0.0799,
|
| 1164 |
+
"step": 570
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 84.88888888888889,
|
| 1168 |
+
"eval_accuracy": 0.90625,
|
| 1169 |
+
"eval_loss": 0.2810324728488922,
|
| 1170 |
+
"eval_runtime": 1.8651,
|
| 1171 |
+
"eval_samples_per_second": 51.472,
|
| 1172 |
+
"eval_steps_per_second": 1.608,
|
| 1173 |
+
"step": 573
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 85.92592592592592,
|
| 1177 |
+
"grad_norm": 9.805841445922852,
|
| 1178 |
+
"learning_rate": 1.9753086419753087e-05,
|
| 1179 |
+
"loss": 0.0632,
|
| 1180 |
+
"step": 580
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 85.92592592592592,
|
| 1184 |
+
"eval_accuracy": 0.90625,
|
| 1185 |
+
"eval_loss": 0.303717702627182,
|
| 1186 |
+
"eval_runtime": 1.9401,
|
| 1187 |
+
"eval_samples_per_second": 49.481,
|
| 1188 |
+
"eval_steps_per_second": 1.546,
|
| 1189 |
+
"step": 580
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 86.96296296296296,
|
| 1193 |
+
"eval_accuracy": 0.90625,
|
| 1194 |
+
"eval_loss": 0.33565008640289307,
|
| 1195 |
+
"eval_runtime": 1.8817,
|
| 1196 |
+
"eval_samples_per_second": 51.018,
|
| 1197 |
+
"eval_steps_per_second": 1.594,
|
| 1198 |
+
"step": 587
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 87.4074074074074,
|
| 1202 |
+
"grad_norm": 27.298439025878906,
|
| 1203 |
+
"learning_rate": 1.91358024691358e-05,
|
| 1204 |
+
"loss": 0.0579,
|
| 1205 |
+
"step": 590
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 88.0,
|
| 1209 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1210 |
+
"eval_loss": 0.3170994818210602,
|
| 1211 |
+
"eval_runtime": 1.8439,
|
| 1212 |
+
"eval_samples_per_second": 52.063,
|
| 1213 |
+
"eval_steps_per_second": 1.627,
|
| 1214 |
+
"step": 594
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 88.88888888888889,
|
| 1218 |
+
"grad_norm": 12.730273246765137,
|
| 1219 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 1220 |
+
"loss": 0.0593,
|
| 1221 |
+
"step": 600
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 88.88888888888889,
|
| 1225 |
+
"eval_accuracy": 0.8854166666666666,
|
| 1226 |
+
"eval_loss": 0.32229921221733093,
|
| 1227 |
+
"eval_runtime": 1.8672,
|
| 1228 |
+
"eval_samples_per_second": 51.414,
|
| 1229 |
+
"eval_steps_per_second": 1.607,
|
| 1230 |
+
"step": 600
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 89.92592592592592,
|
| 1234 |
+
"eval_accuracy": 0.8958333333333334,
|
| 1235 |
+
"eval_loss": 0.29770705103874207,
|
| 1236 |
+
"eval_runtime": 1.9546,
|
| 1237 |
+
"eval_samples_per_second": 49.115,
|
| 1238 |
+
"eval_steps_per_second": 1.535,
|
| 1239 |
+
"step": 607
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 90.37037037037037,
|
| 1243 |
+
"grad_norm": 7.479738712310791,
|
| 1244 |
+
"learning_rate": 1.7901234567901236e-05,
|
| 1245 |
+
"loss": 0.0418,
|
| 1246 |
+
"step": 610
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 90.96296296296296,
|
| 1250 |
+
"eval_accuracy": 0.90625,
|
| 1251 |
+
"eval_loss": 0.3380300998687744,
|
| 1252 |
+
"eval_runtime": 1.8381,
|
| 1253 |
+
"eval_samples_per_second": 52.228,
|
| 1254 |
+
"eval_steps_per_second": 1.632,
|
| 1255 |
+
"step": 614
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 91.85185185185185,
|
| 1259 |
+
"grad_norm": 19.313344955444336,
|
| 1260 |
+
"learning_rate": 1.728395061728395e-05,
|
| 1261 |
+
"loss": 0.0647,
|
| 1262 |
+
"step": 620
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 92.0,
|
| 1266 |
+
"eval_accuracy": 0.875,
|
| 1267 |
+
"eval_loss": 0.28629523515701294,
|
| 1268 |
+
"eval_runtime": 1.9227,
|
| 1269 |
+
"eval_samples_per_second": 49.928,
|
| 1270 |
+
"eval_steps_per_second": 1.56,
|
| 1271 |
+
"step": 621
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 92.88888888888889,
|
| 1275 |
+
"eval_accuracy": 0.9166666666666666,
|
| 1276 |
+
"eval_loss": 0.2898975610733032,
|
| 1277 |
+
"eval_runtime": 1.8782,
|
| 1278 |
+
"eval_samples_per_second": 51.114,
|
| 1279 |
+
"eval_steps_per_second": 1.597,
|
| 1280 |
+
"step": 627
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 93.33333333333333,
|
| 1284 |
+
"grad_norm": 11.266192436218262,
|
| 1285 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 1286 |
+
"loss": 0.0649,
|
| 1287 |
+
"step": 630
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 93.92592592592592,
|
| 1291 |
+
"eval_accuracy": 0.8958333333333334,
|
| 1292 |
+
"eval_loss": 0.2853105962276459,
|
| 1293 |
+
"eval_runtime": 1.9709,
|
| 1294 |
+
"eval_samples_per_second": 48.708,
|
| 1295 |
+
"eval_steps_per_second": 1.522,
|
| 1296 |
+
"step": 634
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 94.81481481481481,
|
| 1300 |
+
"grad_norm": 9.165306091308594,
|
| 1301 |
+
"learning_rate": 1.604938271604938e-05,
|
| 1302 |
+
"loss": 0.0538,
|
| 1303 |
+
"step": 640
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 94.96296296296296,
|
| 1307 |
+
"eval_accuracy": 0.8854166666666666,
|
| 1308 |
+
"eval_loss": 0.24523399770259857,
|
| 1309 |
+
"eval_runtime": 1.9081,
|
| 1310 |
+
"eval_samples_per_second": 50.312,
|
| 1311 |
+
"eval_steps_per_second": 1.572,
|
| 1312 |
+
"step": 641
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 96.0,
|
| 1316 |
+
"eval_accuracy": 0.8958333333333334,
|
| 1317 |
+
"eval_loss": 0.2568932771682739,
|
| 1318 |
+
"eval_runtime": 1.8246,
|
| 1319 |
+
"eval_samples_per_second": 52.614,
|
| 1320 |
+
"eval_steps_per_second": 1.644,
|
| 1321 |
+
"step": 648
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 96.29629629629629,
|
| 1325 |
+
"grad_norm": 6.884490489959717,
|
| 1326 |
+
"learning_rate": 1.54320987654321e-05,
|
| 1327 |
+
"loss": 0.0483,
|
| 1328 |
+
"step": 650
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 96.88888888888889,
|
| 1332 |
+
"eval_accuracy": 0.90625,
|
| 1333 |
+
"eval_loss": 0.26870599389076233,
|
| 1334 |
+
"eval_runtime": 1.8508,
|
| 1335 |
+
"eval_samples_per_second": 51.87,
|
| 1336 |
+
"eval_steps_per_second": 1.621,
|
| 1337 |
+
"step": 654
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 97.77777777777777,
|
| 1341 |
+
"grad_norm": 10.973348617553711,
|
| 1342 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 1343 |
+
"loss": 0.0597,
|
| 1344 |
+
"step": 660
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 97.92592592592592,
|
| 1348 |
+
"eval_accuracy": 0.875,
|
| 1349 |
+
"eval_loss": 0.3083449900150299,
|
| 1350 |
+
"eval_runtime": 1.991,
|
| 1351 |
+
"eval_samples_per_second": 48.217,
|
| 1352 |
+
"eval_steps_per_second": 1.507,
|
| 1353 |
+
"step": 661
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 98.96296296296296,
|
| 1357 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1358 |
+
"eval_loss": 0.2929399311542511,
|
| 1359 |
+
"eval_runtime": 1.8639,
|
| 1360 |
+
"eval_samples_per_second": 51.505,
|
| 1361 |
+
"eval_steps_per_second": 1.61,
|
| 1362 |
+
"step": 668
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 99.25925925925925,
|
| 1366 |
+
"grad_norm": 7.356732368469238,
|
| 1367 |
+
"learning_rate": 1.419753086419753e-05,
|
| 1368 |
+
"loss": 0.0544,
|
| 1369 |
+
"step": 670
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 100.0,
|
| 1373 |
+
"eval_accuracy": 0.875,
|
| 1374 |
+
"eval_loss": 0.32528772950172424,
|
| 1375 |
+
"eval_runtime": 1.9688,
|
| 1376 |
+
"eval_samples_per_second": 48.76,
|
| 1377 |
+
"eval_steps_per_second": 1.524,
|
| 1378 |
+
"step": 675
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 100.74074074074075,
|
| 1382 |
+
"grad_norm": 5.596048831939697,
|
| 1383 |
+
"learning_rate": 1.3580246913580247e-05,
|
| 1384 |
+
"loss": 0.0585,
|
| 1385 |
+
"step": 680
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 100.88888888888889,
|
| 1389 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1390 |
+
"eval_loss": 0.33938369154930115,
|
| 1391 |
+
"eval_runtime": 1.8565,
|
| 1392 |
+
"eval_samples_per_second": 51.711,
|
| 1393 |
+
"eval_steps_per_second": 1.616,
|
| 1394 |
+
"step": 681
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 101.92592592592592,
|
| 1398 |
+
"eval_accuracy": 0.8541666666666666,
|
| 1399 |
+
"eval_loss": 0.37479040026664734,
|
| 1400 |
+
"eval_runtime": 2.0134,
|
| 1401 |
+
"eval_samples_per_second": 47.68,
|
| 1402 |
+
"eval_steps_per_second": 1.49,
|
| 1403 |
+
"step": 688
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 102.22222222222223,
|
| 1407 |
+
"grad_norm": 13.269804000854492,
|
| 1408 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 1409 |
+
"loss": 0.0563,
|
| 1410 |
+
"step": 690
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 102.96296296296296,
|
| 1414 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1415 |
+
"eval_loss": 0.38897252082824707,
|
| 1416 |
+
"eval_runtime": 1.8519,
|
| 1417 |
+
"eval_samples_per_second": 51.838,
|
| 1418 |
+
"eval_steps_per_second": 1.62,
|
| 1419 |
+
"step": 695
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 103.70370370370371,
|
| 1423 |
+
"grad_norm": 16.924348831176758,
|
| 1424 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 1425 |
+
"loss": 0.059,
|
| 1426 |
+
"step": 700
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 104.0,
|
| 1430 |
+
"eval_accuracy": 0.8854166666666666,
|
| 1431 |
+
"eval_loss": 0.3460318148136139,
|
| 1432 |
+
"eval_runtime": 1.8788,
|
| 1433 |
+
"eval_samples_per_second": 51.096,
|
| 1434 |
+
"eval_steps_per_second": 1.597,
|
| 1435 |
+
"step": 702
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 104.88888888888889,
|
| 1439 |
+
"eval_accuracy": 0.875,
|
| 1440 |
+
"eval_loss": 0.33083054423332214,
|
| 1441 |
+
"eval_runtime": 1.9045,
|
| 1442 |
+
"eval_samples_per_second": 50.406,
|
| 1443 |
+
"eval_steps_per_second": 1.575,
|
| 1444 |
+
"step": 708
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 105.18518518518519,
|
| 1448 |
+
"grad_norm": 34.068790435791016,
|
| 1449 |
+
"learning_rate": 1.1728395061728396e-05,
|
| 1450 |
+
"loss": 0.0601,
|
| 1451 |
+
"step": 710
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 105.92592592592592,
|
| 1455 |
+
"eval_accuracy": 0.875,
|
| 1456 |
+
"eval_loss": 0.3228204846382141,
|
| 1457 |
+
"eval_runtime": 1.8931,
|
| 1458 |
+
"eval_samples_per_second": 50.711,
|
| 1459 |
+
"eval_steps_per_second": 1.585,
|
| 1460 |
+
"step": 715
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 106.66666666666667,
|
| 1464 |
+
"grad_norm": 28.148273468017578,
|
| 1465 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 1466 |
+
"loss": 0.0512,
|
| 1467 |
+
"step": 720
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 106.96296296296296,
|
| 1471 |
+
"eval_accuracy": 0.8854166666666666,
|
| 1472 |
+
"eval_loss": 0.3189867436885834,
|
| 1473 |
+
"eval_runtime": 1.9115,
|
| 1474 |
+
"eval_samples_per_second": 50.224,
|
| 1475 |
+
"eval_steps_per_second": 1.569,
|
| 1476 |
+
"step": 722
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 108.0,
|
| 1480 |
+
"eval_accuracy": 0.875,
|
| 1481 |
+
"eval_loss": 0.30278849601745605,
|
| 1482 |
+
"eval_runtime": 1.8687,
|
| 1483 |
+
"eval_samples_per_second": 51.373,
|
| 1484 |
+
"eval_steps_per_second": 1.605,
|
| 1485 |
+
"step": 729
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 108.14814814814815,
|
| 1489 |
+
"grad_norm": 8.840377807617188,
|
| 1490 |
+
"learning_rate": 1.0493827160493827e-05,
|
| 1491 |
+
"loss": 0.0346,
|
| 1492 |
+
"step": 730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 108.88888888888889,
|
| 1496 |
+
"eval_accuracy": 0.90625,
|
| 1497 |
+
"eval_loss": 0.3065723478794098,
|
| 1498 |
+
"eval_runtime": 1.849,
|
| 1499 |
+
"eval_samples_per_second": 51.919,
|
| 1500 |
+
"eval_steps_per_second": 1.622,
|
| 1501 |
+
"step": 735
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 109.62962962962963,
|
| 1505 |
+
"grad_norm": 5.847916126251221,
|
| 1506 |
+
"learning_rate": 9.876543209876543e-06,
|
| 1507 |
+
"loss": 0.0434,
|
| 1508 |
+
"step": 740
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 109.92592592592592,
|
| 1512 |
+
"eval_accuracy": 0.90625,
|
| 1513 |
+
"eval_loss": 0.29524290561676025,
|
| 1514 |
+
"eval_runtime": 1.8637,
|
| 1515 |
+
"eval_samples_per_second": 51.511,
|
| 1516 |
+
"eval_steps_per_second": 1.61,
|
| 1517 |
+
"step": 742
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 110.96296296296296,
|
| 1521 |
+
"eval_accuracy": 0.90625,
|
| 1522 |
+
"eval_loss": 0.3053508698940277,
|
| 1523 |
+
"eval_runtime": 1.875,
|
| 1524 |
+
"eval_samples_per_second": 51.201,
|
| 1525 |
+
"eval_steps_per_second": 1.6,
|
| 1526 |
+
"step": 749
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 111.11111111111111,
|
| 1530 |
+
"grad_norm": 13.934989929199219,
|
| 1531 |
+
"learning_rate": 9.259259259259259e-06,
|
| 1532 |
+
"loss": 0.0466,
|
| 1533 |
+
"step": 750
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 112.0,
|
| 1537 |
+
"eval_accuracy": 0.8958333333333334,
|
| 1538 |
+
"eval_loss": 0.30871471762657166,
|
| 1539 |
+
"eval_runtime": 1.8837,
|
| 1540 |
+
"eval_samples_per_second": 50.965,
|
| 1541 |
+
"eval_steps_per_second": 1.593,
|
| 1542 |
+
"step": 756
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 112.5925925925926,
|
| 1546 |
+
"grad_norm": 4.37272834777832,
|
| 1547 |
+
"learning_rate": 8.641975308641975e-06,
|
| 1548 |
+
"loss": 0.0402,
|
| 1549 |
+
"step": 760
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 112.88888888888889,
|
| 1553 |
+
"eval_accuracy": 0.875,
|
| 1554 |
+
"eval_loss": 0.3211623728275299,
|
| 1555 |
+
"eval_runtime": 1.8685,
|
| 1556 |
+
"eval_samples_per_second": 51.377,
|
| 1557 |
+
"eval_steps_per_second": 1.606,
|
| 1558 |
+
"step": 762
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 113.92592592592592,
|
| 1562 |
+
"eval_accuracy": 0.8854166666666666,
|
| 1563 |
+
"eval_loss": 0.3235282897949219,
|
| 1564 |
+
"eval_runtime": 1.8591,
|
| 1565 |
+
"eval_samples_per_second": 51.637,
|
| 1566 |
+
"eval_steps_per_second": 1.614,
|
| 1567 |
+
"step": 769
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 114.07407407407408,
|
| 1571 |
+
"grad_norm": 17.743671417236328,
|
| 1572 |
+
"learning_rate": 8.02469135802469e-06,
|
| 1573 |
+
"loss": 0.0491,
|
| 1574 |
+
"step": 770
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 114.96296296296296,
|
| 1578 |
+
"eval_accuracy": 0.90625,
|
| 1579 |
+
"eval_loss": 0.3134639263153076,
|
| 1580 |
+
"eval_runtime": 1.8752,
|
| 1581 |
+
"eval_samples_per_second": 51.195,
|
| 1582 |
+
"eval_steps_per_second": 1.6,
|
| 1583 |
+
"step": 776
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 115.55555555555556,
|
| 1587 |
+
"grad_norm": 14.649134635925293,
|
| 1588 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 1589 |
+
"loss": 0.0495,
|
| 1590 |
+
"step": 780
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 116.0,
|
| 1594 |
+
"eval_accuracy": 0.8958333333333334,
|
| 1595 |
+
"eval_loss": 0.2991209924221039,
|
| 1596 |
+
"eval_runtime": 1.9038,
|
| 1597 |
+
"eval_samples_per_second": 50.426,
|
| 1598 |
+
"eval_steps_per_second": 1.576,
|
| 1599 |
+
"step": 783
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 116.88888888888889,
|
| 1603 |
+
"eval_accuracy": 0.8854166666666666,
|
| 1604 |
+
"eval_loss": 0.3050777018070221,
|
| 1605 |
+
"eval_runtime": 1.8271,
|
| 1606 |
+
"eval_samples_per_second": 52.541,
|
| 1607 |
+
"eval_steps_per_second": 1.642,
|
| 1608 |
+
"step": 789
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 117.03703703703704,
|
| 1612 |
+
"grad_norm": 14.181517601013184,
|
| 1613 |
+
"learning_rate": 6.790123456790123e-06,
|
| 1614 |
+
"loss": 0.0536,
|
| 1615 |
+
"step": 790
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 117.92592592592592,
|
| 1619 |
+
"eval_accuracy": 0.875,
|
| 1620 |
+
"eval_loss": 0.33390840888023376,
|
| 1621 |
+
"eval_runtime": 1.8859,
|
| 1622 |
+
"eval_samples_per_second": 50.904,
|
| 1623 |
+
"eval_steps_per_second": 1.591,
|
| 1624 |
+
"step": 796
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 118.51851851851852,
|
| 1628 |
+
"grad_norm": 13.237271308898926,
|
| 1629 |
+
"learning_rate": 6.172839506172839e-06,
|
| 1630 |
+
"loss": 0.0419,
|
| 1631 |
+
"step": 800
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 118.96296296296296,
|
| 1635 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1636 |
+
"eval_loss": 0.3370848596096039,
|
| 1637 |
+
"eval_runtime": 1.8605,
|
| 1638 |
+
"eval_samples_per_second": 51.6,
|
| 1639 |
+
"eval_steps_per_second": 1.612,
|
| 1640 |
+
"step": 803
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 120.0,
|
| 1644 |
+
"grad_norm": 5.592768669128418,
|
| 1645 |
+
"learning_rate": 5.555555555555556e-06,
|
| 1646 |
+
"loss": 0.0333,
|
| 1647 |
+
"step": 810
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 120.0,
|
| 1651 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1652 |
+
"eval_loss": 0.3375813066959381,
|
| 1653 |
+
"eval_runtime": 1.8801,
|
| 1654 |
+
"eval_samples_per_second": 51.06,
|
| 1655 |
+
"eval_steps_per_second": 1.596,
|
| 1656 |
+
"step": 810
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 120.88888888888889,
|
| 1660 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1661 |
+
"eval_loss": 0.33790695667266846,
|
| 1662 |
+
"eval_runtime": 1.8455,
|
| 1663 |
+
"eval_samples_per_second": 52.018,
|
| 1664 |
+
"eval_steps_per_second": 1.626,
|
| 1665 |
+
"step": 816
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 121.48148148148148,
|
| 1669 |
+
"grad_norm": 4.372032165527344,
|
| 1670 |
+
"learning_rate": 4.938271604938272e-06,
|
| 1671 |
+
"loss": 0.0376,
|
| 1672 |
+
"step": 820
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 121.92592592592592,
|
| 1676 |
+
"eval_accuracy": 0.8541666666666666,
|
| 1677 |
+
"eval_loss": 0.337320476770401,
|
| 1678 |
+
"eval_runtime": 1.8367,
|
| 1679 |
+
"eval_samples_per_second": 52.267,
|
| 1680 |
+
"eval_steps_per_second": 1.633,
|
| 1681 |
+
"step": 823
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 122.96296296296296,
|
| 1685 |
+
"grad_norm": 10.392346382141113,
|
| 1686 |
+
"learning_rate": 4.3209876543209875e-06,
|
| 1687 |
+
"loss": 0.0397,
|
| 1688 |
+
"step": 830
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 122.96296296296296,
|
| 1692 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1693 |
+
"eval_loss": 0.34366607666015625,
|
| 1694 |
+
"eval_runtime": 1.8522,
|
| 1695 |
+
"eval_samples_per_second": 51.831,
|
| 1696 |
+
"eval_steps_per_second": 1.62,
|
| 1697 |
+
"step": 830
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 124.0,
|
| 1701 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1702 |
+
"eval_loss": 0.35845816135406494,
|
| 1703 |
+
"eval_runtime": 1.8547,
|
| 1704 |
+
"eval_samples_per_second": 51.76,
|
| 1705 |
+
"eval_steps_per_second": 1.618,
|
| 1706 |
+
"step": 837
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 124.44444444444444,
|
| 1710 |
+
"grad_norm": 5.668208122253418,
|
| 1711 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 1712 |
+
"loss": 0.0299,
|
| 1713 |
+
"step": 840
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 124.88888888888889,
|
| 1717 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1718 |
+
"eval_loss": 0.3514343202114105,
|
| 1719 |
+
"eval_runtime": 1.8661,
|
| 1720 |
+
"eval_samples_per_second": 51.445,
|
| 1721 |
+
"eval_steps_per_second": 1.608,
|
| 1722 |
+
"step": 843
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 125.92592592592592,
|
| 1726 |
+
"grad_norm": 21.28321647644043,
|
| 1727 |
+
"learning_rate": 3.0864197530864196e-06,
|
| 1728 |
+
"loss": 0.0468,
|
| 1729 |
+
"step": 850
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 125.92592592592592,
|
| 1733 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1734 |
+
"eval_loss": 0.3397478759288788,
|
| 1735 |
+
"eval_runtime": 1.8626,
|
| 1736 |
+
"eval_samples_per_second": 51.54,
|
| 1737 |
+
"eval_steps_per_second": 1.611,
|
| 1738 |
+
"step": 850
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 126.96296296296296,
|
| 1742 |
+
"eval_accuracy": 0.8541666666666666,
|
| 1743 |
+
"eval_loss": 0.33162921667099,
|
| 1744 |
+
"eval_runtime": 1.9031,
|
| 1745 |
+
"eval_samples_per_second": 50.444,
|
| 1746 |
+
"eval_steps_per_second": 1.576,
|
| 1747 |
+
"step": 857
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 127.4074074074074,
|
| 1751 |
+
"grad_norm": 2.5001776218414307,
|
| 1752 |
+
"learning_rate": 2.469135802469136e-06,
|
| 1753 |
+
"loss": 0.0351,
|
| 1754 |
+
"step": 860
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 128.0,
|
| 1758 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1759 |
+
"eval_loss": 0.33344319462776184,
|
| 1760 |
+
"eval_runtime": 1.8441,
|
| 1761 |
+
"eval_samples_per_second": 52.058,
|
| 1762 |
+
"eval_steps_per_second": 1.627,
|
| 1763 |
+
"step": 864
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 128.88888888888889,
|
| 1767 |
+
"grad_norm": 9.004130363464355,
|
| 1768 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 1769 |
+
"loss": 0.0439,
|
| 1770 |
+
"step": 870
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 128.88888888888889,
|
| 1774 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1775 |
+
"eval_loss": 0.3323952555656433,
|
| 1776 |
+
"eval_runtime": 1.8475,
|
| 1777 |
+
"eval_samples_per_second": 51.963,
|
| 1778 |
+
"eval_steps_per_second": 1.624,
|
| 1779 |
+
"step": 870
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 129.92592592592592,
|
| 1783 |
+
"eval_accuracy": 0.8645833333333334,
|
| 1784 |
+
"eval_loss": 0.3289691209793091,
|
| 1785 |
+
"eval_runtime": 1.8689,
|
| 1786 |
+
"eval_samples_per_second": 51.368,
|
| 1787 |
+
"eval_steps_per_second": 1.605,
|
| 1788 |
+
"step": 877
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 130.37037037037038,
|
| 1792 |
+
"grad_norm": 12.271383285522461,
|
| 1793 |
+
"learning_rate": 1.234567901234568e-06,
|
| 1794 |
+
"loss": 0.0478,
|
| 1795 |
+
"step": 880
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 130.96296296296296,
|
| 1799 |
+
"eval_accuracy": 0.875,
|
| 1800 |
+
"eval_loss": 0.325620174407959,
|
| 1801 |
+
"eval_runtime": 1.8869,
|
| 1802 |
+
"eval_samples_per_second": 50.876,
|
| 1803 |
+
"eval_steps_per_second": 1.59,
|
| 1804 |
+
"step": 884
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 131.85185185185185,
|
| 1808 |
+
"grad_norm": 8.459063529968262,
|
| 1809 |
+
"learning_rate": 6.17283950617284e-07,
|
| 1810 |
+
"loss": 0.0434,
|
| 1811 |
+
"step": 890
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 132.0,
|
| 1815 |
+
"eval_accuracy": 0.875,
|
| 1816 |
+
"eval_loss": 0.32529863715171814,
|
| 1817 |
+
"eval_runtime": 1.8653,
|
| 1818 |
+
"eval_samples_per_second": 51.466,
|
| 1819 |
+
"eval_steps_per_second": 1.608,
|
| 1820 |
+
"step": 891
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 132.88888888888889,
|
| 1824 |
+
"eval_accuracy": 0.875,
|
| 1825 |
+
"eval_loss": 0.325122594833374,
|
| 1826 |
+
"eval_runtime": 1.835,
|
| 1827 |
+
"eval_samples_per_second": 52.315,
|
| 1828 |
+
"eval_steps_per_second": 1.635,
|
| 1829 |
+
"step": 897
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 133.33333333333334,
|
| 1833 |
+
"grad_norm": 9.571310997009277,
|
| 1834 |
+
"learning_rate": 0.0,
|
| 1835 |
+
"loss": 0.0374,
|
| 1836 |
+
"step": 900
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 133.33333333333334,
|
| 1840 |
+
"eval_accuracy": 0.875,
|
| 1841 |
+
"eval_loss": 0.3251601457595825,
|
| 1842 |
+
"eval_runtime": 1.8591,
|
| 1843 |
+
"eval_samples_per_second": 51.637,
|
| 1844 |
+
"eval_steps_per_second": 1.614,
|
| 1845 |
+
"step": 900
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 133.33333333333334,
|
| 1849 |
+
"step": 900,
|
| 1850 |
+
"total_flos": 2.900008367869133e+18,
|
| 1851 |
+
"train_loss": 0.254776107304626,
|
| 1852 |
+
"train_runtime": 3168.008,
|
| 1853 |
+
"train_samples_per_second": 40.909,
|
| 1854 |
+
"train_steps_per_second": 0.284
|
| 1855 |
+
}
|
| 1856 |
+
],
|
| 1857 |
+
"logging_steps": 10,
|
| 1858 |
+
"max_steps": 900,
|
| 1859 |
+
"num_input_tokens_seen": 0,
|
| 1860 |
+
"num_train_epochs": 150,
|
| 1861 |
+
"save_steps": 500,
|
| 1862 |
+
"stateful_callbacks": {
|
| 1863 |
+
"TrainerControl": {
|
| 1864 |
+
"args": {
|
| 1865 |
+
"should_epoch_stop": false,
|
| 1866 |
+
"should_evaluate": false,
|
| 1867 |
+
"should_log": false,
|
| 1868 |
+
"should_save": false,
|
| 1869 |
+
"should_training_stop": false
|
| 1870 |
+
},
|
| 1871 |
+
"attributes": {}
|
| 1872 |
+
}
|
| 1873 |
+
},
|
| 1874 |
+
"total_flos": 2.900008367869133e+18,
|
| 1875 |
+
"train_batch_size": 32,
|
| 1876 |
+
"trial_name": null,
|
| 1877 |
+
"trial_params": null
|
| 1878 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77b1f122645fc9b701412009c0189edbe21eafd935b30085f92eaec2b367eb00
|
| 3 |
+
size 5240
|