End of training
Browse files- README.md +190 -0
- all_results.json +13 -0
- config.json +77 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- train_results.json +8 -0
- trainer_state.json +2067 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,190 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-topwear
|
| 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: 0.8388888888888889
|
| 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-topwear
|
| 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: 0.6478
|
| 36 |
+
- Accuracy: 0.8389
|
| 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 |
+
| 2.7006 | 0.9412 | 12 | 2.6782 | 0.1167 |
|
| 71 |
+
| 2.6863 | 1.9608 | 25 | 2.6272 | 0.1611 |
|
| 72 |
+
| 2.6437 | 2.9804 | 38 | 2.5389 | 0.2889 |
|
| 73 |
+
| 2.4851 | 4.0 | 51 | 2.4116 | 0.4111 |
|
| 74 |
+
| 2.3732 | 4.9412 | 63 | 2.2707 | 0.4889 |
|
| 75 |
+
| 2.2546 | 5.9608 | 76 | 2.0710 | 0.5722 |
|
| 76 |
+
| 2.1023 | 6.9804 | 89 | 1.8371 | 0.6167 |
|
| 77 |
+
| 1.7115 | 8.0 | 102 | 1.6161 | 0.6111 |
|
| 78 |
+
| 1.5295 | 8.9412 | 114 | 1.4381 | 0.6278 |
|
| 79 |
+
| 1.3366 | 9.9608 | 127 | 1.2540 | 0.65 |
|
| 80 |
+
| 1.0556 | 10.9804 | 140 | 1.1632 | 0.6611 |
|
| 81 |
+
| 0.9657 | 12.0 | 153 | 1.0600 | 0.7 |
|
| 82 |
+
| 0.8703 | 12.9412 | 165 | 0.9983 | 0.7222 |
|
| 83 |
+
| 0.8007 | 13.9608 | 178 | 0.9474 | 0.7278 |
|
| 84 |
+
| 0.6398 | 14.9804 | 191 | 0.8634 | 0.75 |
|
| 85 |
+
| 0.6023 | 16.0 | 204 | 0.8527 | 0.7278 |
|
| 86 |
+
| 0.583 | 16.9412 | 216 | 0.7928 | 0.7667 |
|
| 87 |
+
| 0.5279 | 17.9608 | 229 | 0.7897 | 0.7833 |
|
| 88 |
+
| 0.4643 | 18.9804 | 242 | 0.7886 | 0.7667 |
|
| 89 |
+
| 0.4296 | 20.0 | 255 | 0.7329 | 0.7833 |
|
| 90 |
+
| 0.41 | 20.9412 | 267 | 0.7317 | 0.7611 |
|
| 91 |
+
| 0.3674 | 21.9608 | 280 | 0.7171 | 0.7667 |
|
| 92 |
+
| 0.3285 | 22.9804 | 293 | 0.7005 | 0.7833 |
|
| 93 |
+
| 0.2978 | 24.0 | 306 | 0.6576 | 0.7889 |
|
| 94 |
+
| 0.293 | 24.9412 | 318 | 0.6450 | 0.8 |
|
| 95 |
+
| 0.2724 | 25.9608 | 331 | 0.6765 | 0.7889 |
|
| 96 |
+
| 0.2494 | 26.9804 | 344 | 0.6826 | 0.8056 |
|
| 97 |
+
| 0.2504 | 28.0 | 357 | 0.6710 | 0.8056 |
|
| 98 |
+
| 0.2332 | 28.9412 | 369 | 0.6667 | 0.7778 |
|
| 99 |
+
| 0.2012 | 29.9608 | 382 | 0.7399 | 0.7944 |
|
| 100 |
+
| 0.1866 | 30.9804 | 395 | 0.7311 | 0.7833 |
|
| 101 |
+
| 0.2031 | 32.0 | 408 | 0.7077 | 0.7944 |
|
| 102 |
+
| 0.1969 | 32.9412 | 420 | 0.7769 | 0.7667 |
|
| 103 |
+
| 0.1968 | 33.9608 | 433 | 0.7666 | 0.7833 |
|
| 104 |
+
| 0.1712 | 34.9804 | 446 | 0.6796 | 0.8 |
|
| 105 |
+
| 0.1813 | 36.0 | 459 | 0.6654 | 0.8111 |
|
| 106 |
+
| 0.1678 | 36.9412 | 471 | 0.6851 | 0.7889 |
|
| 107 |
+
| 0.1461 | 37.9608 | 484 | 0.7054 | 0.7833 |
|
| 108 |
+
| 0.1244 | 38.9804 | 497 | 0.7013 | 0.8056 |
|
| 109 |
+
| 0.1329 | 40.0 | 510 | 0.6785 | 0.8 |
|
| 110 |
+
| 0.1186 | 40.9412 | 522 | 0.7500 | 0.7778 |
|
| 111 |
+
| 0.1397 | 41.9608 | 535 | 0.6819 | 0.8167 |
|
| 112 |
+
| 0.1324 | 42.9804 | 548 | 0.6257 | 0.8111 |
|
| 113 |
+
| 0.111 | 44.0 | 561 | 0.5939 | 0.8278 |
|
| 114 |
+
| 0.1228 | 44.9412 | 573 | 0.6379 | 0.8222 |
|
| 115 |
+
| 0.1085 | 45.9608 | 586 | 0.6789 | 0.8222 |
|
| 116 |
+
| 0.1234 | 46.9804 | 599 | 0.6241 | 0.8278 |
|
| 117 |
+
| 0.1129 | 48.0 | 612 | 0.7503 | 0.7889 |
|
| 118 |
+
| 0.1197 | 48.9412 | 624 | 0.6862 | 0.7944 |
|
| 119 |
+
| 0.0898 | 49.9608 | 637 | 0.6764 | 0.7889 |
|
| 120 |
+
| 0.1057 | 50.9804 | 650 | 0.6339 | 0.8167 |
|
| 121 |
+
| 0.0893 | 52.0 | 663 | 0.5828 | 0.85 |
|
| 122 |
+
| 0.0736 | 52.9412 | 675 | 0.6573 | 0.8111 |
|
| 123 |
+
| 0.0752 | 53.9608 | 688 | 0.6806 | 0.7944 |
|
| 124 |
+
| 0.1127 | 54.9804 | 701 | 0.6222 | 0.8111 |
|
| 125 |
+
| 0.1126 | 56.0 | 714 | 0.6305 | 0.8167 |
|
| 126 |
+
| 0.0874 | 56.9412 | 726 | 0.6593 | 0.8111 |
|
| 127 |
+
| 0.0806 | 57.9608 | 739 | 0.7006 | 0.8167 |
|
| 128 |
+
| 0.0978 | 58.9804 | 752 | 0.6680 | 0.8056 |
|
| 129 |
+
| 0.0875 | 60.0 | 765 | 0.6739 | 0.8167 |
|
| 130 |
+
| 0.0722 | 60.9412 | 777 | 0.6341 | 0.8333 |
|
| 131 |
+
| 0.0942 | 61.9608 | 790 | 0.6428 | 0.8 |
|
| 132 |
+
| 0.0957 | 62.9804 | 803 | 0.6758 | 0.8 |
|
| 133 |
+
| 0.0814 | 64.0 | 816 | 0.6104 | 0.8167 |
|
| 134 |
+
| 0.077 | 64.9412 | 828 | 0.6226 | 0.8111 |
|
| 135 |
+
| 0.1004 | 65.9608 | 841 | 0.6899 | 0.8056 |
|
| 136 |
+
| 0.0697 | 66.9804 | 854 | 0.7105 | 0.8167 |
|
| 137 |
+
| 0.0754 | 68.0 | 867 | 0.6751 | 0.8111 |
|
| 138 |
+
| 0.0842 | 68.9412 | 879 | 0.6912 | 0.7833 |
|
| 139 |
+
| 0.0684 | 69.9608 | 892 | 0.7235 | 0.8167 |
|
| 140 |
+
| 0.0684 | 70.9804 | 905 | 0.5840 | 0.8278 |
|
| 141 |
+
| 0.0705 | 72.0 | 918 | 0.6636 | 0.8222 |
|
| 142 |
+
| 0.0681 | 72.9412 | 930 | 0.6787 | 0.8 |
|
| 143 |
+
| 0.0906 | 73.9608 | 943 | 0.6243 | 0.8389 |
|
| 144 |
+
| 0.0453 | 74.9804 | 956 | 0.6787 | 0.8222 |
|
| 145 |
+
| 0.0874 | 76.0 | 969 | 0.6259 | 0.8278 |
|
| 146 |
+
| 0.051 | 76.9412 | 981 | 0.6590 | 0.8278 |
|
| 147 |
+
| 0.0858 | 77.9608 | 994 | 0.6307 | 0.8278 |
|
| 148 |
+
| 0.0601 | 78.9804 | 1007 | 0.6042 | 0.8444 |
|
| 149 |
+
| 0.0601 | 80.0 | 1020 | 0.5875 | 0.8389 |
|
| 150 |
+
| 0.067 | 80.9412 | 1032 | 0.6078 | 0.8389 |
|
| 151 |
+
| 0.0556 | 81.9608 | 1045 | 0.6007 | 0.8444 |
|
| 152 |
+
| 0.0661 | 82.9804 | 1058 | 0.6062 | 0.8333 |
|
| 153 |
+
| 0.0651 | 84.0 | 1071 | 0.6387 | 0.8111 |
|
| 154 |
+
| 0.0546 | 84.9412 | 1083 | 0.6861 | 0.8167 |
|
| 155 |
+
| 0.0827 | 85.9608 | 1096 | 0.6073 | 0.8389 |
|
| 156 |
+
| 0.052 | 86.9804 | 1109 | 0.5935 | 0.85 |
|
| 157 |
+
| 0.0524 | 88.0 | 1122 | 0.5899 | 0.8389 |
|
| 158 |
+
| 0.066 | 88.9412 | 1134 | 0.5954 | 0.8444 |
|
| 159 |
+
| 0.0617 | 89.9608 | 1147 | 0.6145 | 0.8444 |
|
| 160 |
+
| 0.0572 | 90.9804 | 1160 | 0.6176 | 0.8444 |
|
| 161 |
+
| 0.0719 | 92.0 | 1173 | 0.6406 | 0.8278 |
|
| 162 |
+
| 0.0734 | 92.9412 | 1185 | 0.6485 | 0.8333 |
|
| 163 |
+
| 0.0616 | 93.9608 | 1198 | 0.6198 | 0.8333 |
|
| 164 |
+
| 0.0557 | 94.9804 | 1211 | 0.6167 | 0.8389 |
|
| 165 |
+
| 0.0494 | 96.0 | 1224 | 0.6480 | 0.8444 |
|
| 166 |
+
| 0.0587 | 96.9412 | 1236 | 0.6076 | 0.85 |
|
| 167 |
+
| 0.052 | 97.9608 | 1249 | 0.6512 | 0.8389 |
|
| 168 |
+
| 0.0383 | 98.9804 | 1262 | 0.6782 | 0.8333 |
|
| 169 |
+
| 0.0499 | 100.0 | 1275 | 0.6542 | 0.8278 |
|
| 170 |
+
| 0.0511 | 100.9412 | 1287 | 0.6795 | 0.8389 |
|
| 171 |
+
| 0.0452 | 101.9608 | 1300 | 0.6740 | 0.8333 |
|
| 172 |
+
| 0.0475 | 102.9804 | 1313 | 0.6616 | 0.8389 |
|
| 173 |
+
| 0.0455 | 104.0 | 1326 | 0.6490 | 0.8278 |
|
| 174 |
+
| 0.0486 | 104.9412 | 1338 | 0.6331 | 0.8333 |
|
| 175 |
+
| 0.0585 | 105.9608 | 1351 | 0.6299 | 0.8333 |
|
| 176 |
+
| 0.0549 | 106.9804 | 1364 | 0.6398 | 0.8278 |
|
| 177 |
+
| 0.0436 | 108.0 | 1377 | 0.6338 | 0.8444 |
|
| 178 |
+
| 0.0429 | 108.9412 | 1389 | 0.6459 | 0.8389 |
|
| 179 |
+
| 0.0449 | 109.9608 | 1402 | 0.6470 | 0.8444 |
|
| 180 |
+
| 0.0559 | 110.9804 | 1415 | 0.6463 | 0.8389 |
|
| 181 |
+
| 0.0378 | 112.0 | 1428 | 0.6480 | 0.8389 |
|
| 182 |
+
| 0.0476 | 112.9412 | 1440 | 0.6478 | 0.8389 |
|
| 183 |
+
|
| 184 |
+
|
| 185 |
+
### Framework versions
|
| 186 |
+
|
| 187 |
+
- Transformers 4.44.0
|
| 188 |
+
- Pytorch 2.4.0
|
| 189 |
+
- Datasets 2.21.0
|
| 190 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 112.94117647058823,
|
| 3 |
+
"eval_accuracy": 0.8388888888888889,
|
| 4 |
+
"eval_loss": 0.6477780342102051,
|
| 5 |
+
"eval_runtime": 3.821,
|
| 6 |
+
"eval_samples_per_second": 47.108,
|
| 7 |
+
"eval_steps_per_second": 1.57,
|
| 8 |
+
"total_flos": 4.607069541812011e+18,
|
| 9 |
+
"train_loss": 0.33674598841203585,
|
| 10 |
+
"train_runtime": 5395.5485,
|
| 11 |
+
"train_samples_per_second": 36.03,
|
| 12 |
+
"train_steps_per_second": 0.267
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "blazer",
|
| 22 |
+
"1": "cardigan",
|
| 23 |
+
"2": "coat",
|
| 24 |
+
"3": "jacket",
|
| 25 |
+
"4": "kurta",
|
| 26 |
+
"5": "kurti",
|
| 27 |
+
"6": "poncho",
|
| 28 |
+
"7": "salwar",
|
| 29 |
+
"8": "shirt",
|
| 30 |
+
"9": "shrug",
|
| 31 |
+
"10": "summer_jacket",
|
| 32 |
+
"11": "sweatshirt_hoodie",
|
| 33 |
+
"12": "tshirt",
|
| 34 |
+
"13": "tunic",
|
| 35 |
+
"14": "waistcoat"
|
| 36 |
+
},
|
| 37 |
+
"image_size": 224,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"label2id": {
|
| 40 |
+
"blazer": 0,
|
| 41 |
+
"cardigan": 1,
|
| 42 |
+
"coat": 2,
|
| 43 |
+
"jacket": 3,
|
| 44 |
+
"kurta": 4,
|
| 45 |
+
"kurti": 5,
|
| 46 |
+
"poncho": 6,
|
| 47 |
+
"salwar": 7,
|
| 48 |
+
"shirt": 8,
|
| 49 |
+
"shrug": 9,
|
| 50 |
+
"summer_jacket": 10,
|
| 51 |
+
"sweatshirt_hoodie": 11,
|
| 52 |
+
"tshirt": 12,
|
| 53 |
+
"tunic": 13,
|
| 54 |
+
"waistcoat": 14
|
| 55 |
+
},
|
| 56 |
+
"layer_norm_eps": 1e-12,
|
| 57 |
+
"model_type": "convnextv2",
|
| 58 |
+
"num_channels": 3,
|
| 59 |
+
"num_stages": 4,
|
| 60 |
+
"out_features": [
|
| 61 |
+
"stage4"
|
| 62 |
+
],
|
| 63 |
+
"out_indices": [
|
| 64 |
+
4
|
| 65 |
+
],
|
| 66 |
+
"patch_size": 4,
|
| 67 |
+
"problem_type": "single_label_classification",
|
| 68 |
+
"stage_names": [
|
| 69 |
+
"stem",
|
| 70 |
+
"stage1",
|
| 71 |
+
"stage2",
|
| 72 |
+
"stage3",
|
| 73 |
+
"stage4"
|
| 74 |
+
],
|
| 75 |
+
"torch_dtype": "float32",
|
| 76 |
+
"transformers_version": "4.44.0"
|
| 77 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 112.94117647058823,
|
| 3 |
+
"eval_accuracy": 0.8388888888888889,
|
| 4 |
+
"eval_loss": 0.6477780342102051,
|
| 5 |
+
"eval_runtime": 3.821,
|
| 6 |
+
"eval_samples_per_second": 47.108,
|
| 7 |
+
"eval_steps_per_second": 1.57
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b61e70556d7d913a52ec1290e8b3a2f3f8d177e92b0011e44255a22d43f93167
|
| 3 |
+
size 111535820
|
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": 112.94117647058823,
|
| 3 |
+
"total_flos": 4.607069541812011e+18,
|
| 4 |
+
"train_loss": 0.33674598841203585,
|
| 5 |
+
"train_runtime": 5395.5485,
|
| 6 |
+
"train_samples_per_second": 36.03,
|
| 7 |
+
"train_steps_per_second": 0.267
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2067 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 112.94117647058823,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1440,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7843137254901961,
|
| 13 |
+
"grad_norm": 3.280456066131592,
|
| 14 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 15 |
+
"loss": 2.7006,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.9411764705882353,
|
| 20 |
+
"eval_accuracy": 0.11666666666666667,
|
| 21 |
+
"eval_loss": 2.678151845932007,
|
| 22 |
+
"eval_runtime": 4.6451,
|
| 23 |
+
"eval_samples_per_second": 38.751,
|
| 24 |
+
"eval_steps_per_second": 1.292,
|
| 25 |
+
"step": 12
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.5686274509803921,
|
| 29 |
+
"grad_norm": 7.857480049133301,
|
| 30 |
+
"learning_rate": 6.944444444444445e-06,
|
| 31 |
+
"loss": 2.6863,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.9607843137254903,
|
| 36 |
+
"eval_accuracy": 0.16111111111111112,
|
| 37 |
+
"eval_loss": 2.627171039581299,
|
| 38 |
+
"eval_runtime": 3.8353,
|
| 39 |
+
"eval_samples_per_second": 46.933,
|
| 40 |
+
"eval_steps_per_second": 1.564,
|
| 41 |
+
"step": 25
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.3529411764705883,
|
| 45 |
+
"grad_norm": 3.7707808017730713,
|
| 46 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 47 |
+
"loss": 2.6437,
|
| 48 |
+
"step": 30
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.980392156862745,
|
| 52 |
+
"eval_accuracy": 0.28888888888888886,
|
| 53 |
+
"eval_loss": 2.5389277935028076,
|
| 54 |
+
"eval_runtime": 3.8826,
|
| 55 |
+
"eval_samples_per_second": 46.36,
|
| 56 |
+
"eval_steps_per_second": 1.545,
|
| 57 |
+
"step": 38
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.1372549019607843,
|
| 61 |
+
"grad_norm": 5.107277870178223,
|
| 62 |
+
"learning_rate": 1.388888888888889e-05,
|
| 63 |
+
"loss": 2.5839,
|
| 64 |
+
"step": 40
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 3.9215686274509802,
|
| 68 |
+
"grad_norm": 6.703848361968994,
|
| 69 |
+
"learning_rate": 1.736111111111111e-05,
|
| 70 |
+
"loss": 2.4851,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 4.0,
|
| 75 |
+
"eval_accuracy": 0.4111111111111111,
|
| 76 |
+
"eval_loss": 2.411587953567505,
|
| 77 |
+
"eval_runtime": 3.8828,
|
| 78 |
+
"eval_samples_per_second": 46.359,
|
| 79 |
+
"eval_steps_per_second": 1.545,
|
| 80 |
+
"step": 51
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.705882352941177,
|
| 84 |
+
"grad_norm": 11.087530136108398,
|
| 85 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 86 |
+
"loss": 2.3732,
|
| 87 |
+
"step": 60
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 4.9411764705882355,
|
| 91 |
+
"eval_accuracy": 0.4888888888888889,
|
| 92 |
+
"eval_loss": 2.270714521408081,
|
| 93 |
+
"eval_runtime": 3.8466,
|
| 94 |
+
"eval_samples_per_second": 46.794,
|
| 95 |
+
"eval_steps_per_second": 1.56,
|
| 96 |
+
"step": 63
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.490196078431373,
|
| 100 |
+
"grad_norm": 7.360437393188477,
|
| 101 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 102 |
+
"loss": 2.2546,
|
| 103 |
+
"step": 70
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 5.96078431372549,
|
| 107 |
+
"eval_accuracy": 0.5722222222222222,
|
| 108 |
+
"eval_loss": 2.0710320472717285,
|
| 109 |
+
"eval_runtime": 3.9713,
|
| 110 |
+
"eval_samples_per_second": 45.326,
|
| 111 |
+
"eval_steps_per_second": 1.511,
|
| 112 |
+
"step": 76
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 6.2745098039215685,
|
| 116 |
+
"grad_norm": 6.191979885101318,
|
| 117 |
+
"learning_rate": 2.777777777777778e-05,
|
| 118 |
+
"loss": 2.1023,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 6.980392156862745,
|
| 123 |
+
"eval_accuracy": 0.6166666666666667,
|
| 124 |
+
"eval_loss": 1.8370894193649292,
|
| 125 |
+
"eval_runtime": 3.8628,
|
| 126 |
+
"eval_samples_per_second": 46.599,
|
| 127 |
+
"eval_steps_per_second": 1.553,
|
| 128 |
+
"step": 89
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.0588235294117645,
|
| 132 |
+
"grad_norm": 7.690328598022461,
|
| 133 |
+
"learning_rate": 3.125e-05,
|
| 134 |
+
"loss": 1.9156,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 7.8431372549019605,
|
| 139 |
+
"grad_norm": 7.919386863708496,
|
| 140 |
+
"learning_rate": 3.472222222222222e-05,
|
| 141 |
+
"loss": 1.7115,
|
| 142 |
+
"step": 100
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"eval_accuracy": 0.6111111111111112,
|
| 147 |
+
"eval_loss": 1.6161085367202759,
|
| 148 |
+
"eval_runtime": 3.8886,
|
| 149 |
+
"eval_samples_per_second": 46.29,
|
| 150 |
+
"eval_steps_per_second": 1.543,
|
| 151 |
+
"step": 102
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 8.627450980392156,
|
| 155 |
+
"grad_norm": 12.924628257751465,
|
| 156 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 157 |
+
"loss": 1.5295,
|
| 158 |
+
"step": 110
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 8.941176470588236,
|
| 162 |
+
"eval_accuracy": 0.6277777777777778,
|
| 163 |
+
"eval_loss": 1.4381340742111206,
|
| 164 |
+
"eval_runtime": 3.8538,
|
| 165 |
+
"eval_samples_per_second": 46.708,
|
| 166 |
+
"eval_steps_per_second": 1.557,
|
| 167 |
+
"step": 114
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 9.411764705882353,
|
| 171 |
+
"grad_norm": 14.41945743560791,
|
| 172 |
+
"learning_rate": 4.166666666666667e-05,
|
| 173 |
+
"loss": 1.3366,
|
| 174 |
+
"step": 120
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.96078431372549,
|
| 178 |
+
"eval_accuracy": 0.65,
|
| 179 |
+
"eval_loss": 1.2539671659469604,
|
| 180 |
+
"eval_runtime": 3.9661,
|
| 181 |
+
"eval_samples_per_second": 45.385,
|
| 182 |
+
"eval_steps_per_second": 1.513,
|
| 183 |
+
"step": 127
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 10.196078431372548,
|
| 187 |
+
"grad_norm": 17.627479553222656,
|
| 188 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 189 |
+
"loss": 1.2377,
|
| 190 |
+
"step": 130
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 10.980392156862745,
|
| 194 |
+
"grad_norm": 13.988055229187012,
|
| 195 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 196 |
+
"loss": 1.0556,
|
| 197 |
+
"step": 140
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 10.980392156862745,
|
| 201 |
+
"eval_accuracy": 0.6611111111111111,
|
| 202 |
+
"eval_loss": 1.1632429361343384,
|
| 203 |
+
"eval_runtime": 3.9305,
|
| 204 |
+
"eval_samples_per_second": 45.796,
|
| 205 |
+
"eval_steps_per_second": 1.527,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 11.764705882352942,
|
| 210 |
+
"grad_norm": 12.996641159057617,
|
| 211 |
+
"learning_rate": 4.976851851851852e-05,
|
| 212 |
+
"loss": 0.9657,
|
| 213 |
+
"step": 150
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 12.0,
|
| 217 |
+
"eval_accuracy": 0.7,
|
| 218 |
+
"eval_loss": 1.0600230693817139,
|
| 219 |
+
"eval_runtime": 3.9116,
|
| 220 |
+
"eval_samples_per_second": 46.016,
|
| 221 |
+
"eval_steps_per_second": 1.534,
|
| 222 |
+
"step": 153
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 12.549019607843137,
|
| 226 |
+
"grad_norm": 26.70894432067871,
|
| 227 |
+
"learning_rate": 4.938271604938271e-05,
|
| 228 |
+
"loss": 0.8703,
|
| 229 |
+
"step": 160
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 12.941176470588236,
|
| 233 |
+
"eval_accuracy": 0.7222222222222222,
|
| 234 |
+
"eval_loss": 0.9983330368995667,
|
| 235 |
+
"eval_runtime": 3.823,
|
| 236 |
+
"eval_samples_per_second": 47.084,
|
| 237 |
+
"eval_steps_per_second": 1.569,
|
| 238 |
+
"step": 165
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 13.333333333333334,
|
| 242 |
+
"grad_norm": 24.295700073242188,
|
| 243 |
+
"learning_rate": 4.899691358024692e-05,
|
| 244 |
+
"loss": 0.8007,
|
| 245 |
+
"step": 170
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 13.96078431372549,
|
| 249 |
+
"eval_accuracy": 0.7277777777777777,
|
| 250 |
+
"eval_loss": 0.9474301934242249,
|
| 251 |
+
"eval_runtime": 4.0708,
|
| 252 |
+
"eval_samples_per_second": 44.218,
|
| 253 |
+
"eval_steps_per_second": 1.474,
|
| 254 |
+
"step": 178
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 14.117647058823529,
|
| 258 |
+
"grad_norm": 19.43092918395996,
|
| 259 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 260 |
+
"loss": 0.7257,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 14.901960784313726,
|
| 265 |
+
"grad_norm": 22.165098190307617,
|
| 266 |
+
"learning_rate": 4.8225308641975306e-05,
|
| 267 |
+
"loss": 0.6398,
|
| 268 |
+
"step": 190
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 14.980392156862745,
|
| 272 |
+
"eval_accuracy": 0.75,
|
| 273 |
+
"eval_loss": 0.8633670210838318,
|
| 274 |
+
"eval_runtime": 4.1208,
|
| 275 |
+
"eval_samples_per_second": 43.681,
|
| 276 |
+
"eval_steps_per_second": 1.456,
|
| 277 |
+
"step": 191
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 15.686274509803921,
|
| 281 |
+
"grad_norm": 24.815359115600586,
|
| 282 |
+
"learning_rate": 4.783950617283951e-05,
|
| 283 |
+
"loss": 0.6023,
|
| 284 |
+
"step": 200
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 16.0,
|
| 288 |
+
"eval_accuracy": 0.7277777777777777,
|
| 289 |
+
"eval_loss": 0.8527319431304932,
|
| 290 |
+
"eval_runtime": 3.869,
|
| 291 |
+
"eval_samples_per_second": 46.524,
|
| 292 |
+
"eval_steps_per_second": 1.551,
|
| 293 |
+
"step": 204
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 16.470588235294116,
|
| 297 |
+
"grad_norm": 28.00403594970703,
|
| 298 |
+
"learning_rate": 4.745370370370371e-05,
|
| 299 |
+
"loss": 0.583,
|
| 300 |
+
"step": 210
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 16.941176470588236,
|
| 304 |
+
"eval_accuracy": 0.7666666666666667,
|
| 305 |
+
"eval_loss": 0.7927896976470947,
|
| 306 |
+
"eval_runtime": 3.8557,
|
| 307 |
+
"eval_samples_per_second": 46.684,
|
| 308 |
+
"eval_steps_per_second": 1.556,
|
| 309 |
+
"step": 216
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 17.254901960784313,
|
| 313 |
+
"grad_norm": 30.892383575439453,
|
| 314 |
+
"learning_rate": 4.70679012345679e-05,
|
| 315 |
+
"loss": 0.5279,
|
| 316 |
+
"step": 220
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 17.96078431372549,
|
| 320 |
+
"eval_accuracy": 0.7833333333333333,
|
| 321 |
+
"eval_loss": 0.7896744012832642,
|
| 322 |
+
"eval_runtime": 3.7921,
|
| 323 |
+
"eval_samples_per_second": 47.468,
|
| 324 |
+
"eval_steps_per_second": 1.582,
|
| 325 |
+
"step": 229
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 18.03921568627451,
|
| 329 |
+
"grad_norm": 19.16618537902832,
|
| 330 |
+
"learning_rate": 4.66820987654321e-05,
|
| 331 |
+
"loss": 0.5084,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 18.823529411764707,
|
| 336 |
+
"grad_norm": 13.686722755432129,
|
| 337 |
+
"learning_rate": 4.62962962962963e-05,
|
| 338 |
+
"loss": 0.4643,
|
| 339 |
+
"step": 240
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 18.980392156862745,
|
| 343 |
+
"eval_accuracy": 0.7666666666666667,
|
| 344 |
+
"eval_loss": 0.7885976433753967,
|
| 345 |
+
"eval_runtime": 3.8507,
|
| 346 |
+
"eval_samples_per_second": 46.745,
|
| 347 |
+
"eval_steps_per_second": 1.558,
|
| 348 |
+
"step": 242
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 19.607843137254903,
|
| 352 |
+
"grad_norm": 17.4645938873291,
|
| 353 |
+
"learning_rate": 4.591049382716049e-05,
|
| 354 |
+
"loss": 0.4296,
|
| 355 |
+
"step": 250
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 20.0,
|
| 359 |
+
"eval_accuracy": 0.7833333333333333,
|
| 360 |
+
"eval_loss": 0.7328829169273376,
|
| 361 |
+
"eval_runtime": 3.8093,
|
| 362 |
+
"eval_samples_per_second": 47.252,
|
| 363 |
+
"eval_steps_per_second": 1.575,
|
| 364 |
+
"step": 255
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 20.392156862745097,
|
| 368 |
+
"grad_norm": 16.678590774536133,
|
| 369 |
+
"learning_rate": 4.5524691358024696e-05,
|
| 370 |
+
"loss": 0.41,
|
| 371 |
+
"step": 260
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 20.941176470588236,
|
| 375 |
+
"eval_accuracy": 0.7611111111111111,
|
| 376 |
+
"eval_loss": 0.7316663861274719,
|
| 377 |
+
"eval_runtime": 3.8668,
|
| 378 |
+
"eval_samples_per_second": 46.55,
|
| 379 |
+
"eval_steps_per_second": 1.552,
|
| 380 |
+
"step": 267
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 21.176470588235293,
|
| 384 |
+
"grad_norm": 12.328489303588867,
|
| 385 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 386 |
+
"loss": 0.3663,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 21.96078431372549,
|
| 391 |
+
"grad_norm": 23.868070602416992,
|
| 392 |
+
"learning_rate": 4.4753086419753084e-05,
|
| 393 |
+
"loss": 0.3674,
|
| 394 |
+
"step": 280
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 21.96078431372549,
|
| 398 |
+
"eval_accuracy": 0.7666666666666667,
|
| 399 |
+
"eval_loss": 0.7170845866203308,
|
| 400 |
+
"eval_runtime": 3.956,
|
| 401 |
+
"eval_samples_per_second": 45.5,
|
| 402 |
+
"eval_steps_per_second": 1.517,
|
| 403 |
+
"step": 280
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 22.745098039215687,
|
| 407 |
+
"grad_norm": 21.286258697509766,
|
| 408 |
+
"learning_rate": 4.436728395061729e-05,
|
| 409 |
+
"loss": 0.3285,
|
| 410 |
+
"step": 290
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 22.980392156862745,
|
| 414 |
+
"eval_accuracy": 0.7833333333333333,
|
| 415 |
+
"eval_loss": 0.7005434036254883,
|
| 416 |
+
"eval_runtime": 3.9134,
|
| 417 |
+
"eval_samples_per_second": 45.996,
|
| 418 |
+
"eval_steps_per_second": 1.533,
|
| 419 |
+
"step": 293
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 23.529411764705884,
|
| 423 |
+
"grad_norm": 12.573646545410156,
|
| 424 |
+
"learning_rate": 4.3981481481481486e-05,
|
| 425 |
+
"loss": 0.2978,
|
| 426 |
+
"step": 300
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 24.0,
|
| 430 |
+
"eval_accuracy": 0.7888888888888889,
|
| 431 |
+
"eval_loss": 0.6576042771339417,
|
| 432 |
+
"eval_runtime": 3.8597,
|
| 433 |
+
"eval_samples_per_second": 46.636,
|
| 434 |
+
"eval_steps_per_second": 1.555,
|
| 435 |
+
"step": 306
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 24.313725490196077,
|
| 439 |
+
"grad_norm": 18.386383056640625,
|
| 440 |
+
"learning_rate": 4.359567901234568e-05,
|
| 441 |
+
"loss": 0.293,
|
| 442 |
+
"step": 310
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 24.941176470588236,
|
| 446 |
+
"eval_accuracy": 0.8,
|
| 447 |
+
"eval_loss": 0.644997239112854,
|
| 448 |
+
"eval_runtime": 4.0291,
|
| 449 |
+
"eval_samples_per_second": 44.675,
|
| 450 |
+
"eval_steps_per_second": 1.489,
|
| 451 |
+
"step": 318
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 25.098039215686274,
|
| 455 |
+
"grad_norm": 18.57107925415039,
|
| 456 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 457 |
+
"loss": 0.2665,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 25.88235294117647,
|
| 462 |
+
"grad_norm": 16.507802963256836,
|
| 463 |
+
"learning_rate": 4.282407407407408e-05,
|
| 464 |
+
"loss": 0.2724,
|
| 465 |
+
"step": 330
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 25.96078431372549,
|
| 469 |
+
"eval_accuracy": 0.7888888888888889,
|
| 470 |
+
"eval_loss": 0.6764713525772095,
|
| 471 |
+
"eval_runtime": 3.8073,
|
| 472 |
+
"eval_samples_per_second": 47.278,
|
| 473 |
+
"eval_steps_per_second": 1.576,
|
| 474 |
+
"step": 331
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 26.666666666666668,
|
| 478 |
+
"grad_norm": 18.386646270751953,
|
| 479 |
+
"learning_rate": 4.243827160493827e-05,
|
| 480 |
+
"loss": 0.2494,
|
| 481 |
+
"step": 340
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 26.980392156862745,
|
| 485 |
+
"eval_accuracy": 0.8055555555555556,
|
| 486 |
+
"eval_loss": 0.6826486587524414,
|
| 487 |
+
"eval_runtime": 3.9305,
|
| 488 |
+
"eval_samples_per_second": 45.796,
|
| 489 |
+
"eval_steps_per_second": 1.527,
|
| 490 |
+
"step": 344
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 27.45098039215686,
|
| 494 |
+
"grad_norm": 16.895566940307617,
|
| 495 |
+
"learning_rate": 4.205246913580247e-05,
|
| 496 |
+
"loss": 0.2504,
|
| 497 |
+
"step": 350
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 28.0,
|
| 501 |
+
"eval_accuracy": 0.8055555555555556,
|
| 502 |
+
"eval_loss": 0.6710352301597595,
|
| 503 |
+
"eval_runtime": 3.8264,
|
| 504 |
+
"eval_samples_per_second": 47.041,
|
| 505 |
+
"eval_steps_per_second": 1.568,
|
| 506 |
+
"step": 357
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 28.235294117647058,
|
| 510 |
+
"grad_norm": 14.318737983703613,
|
| 511 |
+
"learning_rate": 4.166666666666667e-05,
|
| 512 |
+
"loss": 0.2332,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 28.941176470588236,
|
| 517 |
+
"eval_accuracy": 0.7777777777777778,
|
| 518 |
+
"eval_loss": 0.666705846786499,
|
| 519 |
+
"eval_runtime": 3.9608,
|
| 520 |
+
"eval_samples_per_second": 45.445,
|
| 521 |
+
"eval_steps_per_second": 1.515,
|
| 522 |
+
"step": 369
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 29.019607843137255,
|
| 526 |
+
"grad_norm": 19.979778289794922,
|
| 527 |
+
"learning_rate": 4.128086419753087e-05,
|
| 528 |
+
"loss": 0.2071,
|
| 529 |
+
"step": 370
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 29.80392156862745,
|
| 533 |
+
"grad_norm": 14.415696144104004,
|
| 534 |
+
"learning_rate": 4.089506172839506e-05,
|
| 535 |
+
"loss": 0.2012,
|
| 536 |
+
"step": 380
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 29.96078431372549,
|
| 540 |
+
"eval_accuracy": 0.7944444444444444,
|
| 541 |
+
"eval_loss": 0.7399319410324097,
|
| 542 |
+
"eval_runtime": 3.8411,
|
| 543 |
+
"eval_samples_per_second": 46.861,
|
| 544 |
+
"eval_steps_per_second": 1.562,
|
| 545 |
+
"step": 382
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 30.58823529411765,
|
| 549 |
+
"grad_norm": 10.09865665435791,
|
| 550 |
+
"learning_rate": 4.0509259259259265e-05,
|
| 551 |
+
"loss": 0.1866,
|
| 552 |
+
"step": 390
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 30.980392156862745,
|
| 556 |
+
"eval_accuracy": 0.7833333333333333,
|
| 557 |
+
"eval_loss": 0.7311467528343201,
|
| 558 |
+
"eval_runtime": 4.2025,
|
| 559 |
+
"eval_samples_per_second": 42.831,
|
| 560 |
+
"eval_steps_per_second": 1.428,
|
| 561 |
+
"step": 395
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 31.372549019607842,
|
| 565 |
+
"grad_norm": 31.518268585205078,
|
| 566 |
+
"learning_rate": 4.012345679012346e-05,
|
| 567 |
+
"loss": 0.2031,
|
| 568 |
+
"step": 400
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 32.0,
|
| 572 |
+
"eval_accuracy": 0.7944444444444444,
|
| 573 |
+
"eval_loss": 0.7076573967933655,
|
| 574 |
+
"eval_runtime": 3.8553,
|
| 575 |
+
"eval_samples_per_second": 46.689,
|
| 576 |
+
"eval_steps_per_second": 1.556,
|
| 577 |
+
"step": 408
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 32.15686274509804,
|
| 581 |
+
"grad_norm": 18.065155029296875,
|
| 582 |
+
"learning_rate": 3.973765432098765e-05,
|
| 583 |
+
"loss": 0.1969,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 32.94117647058823,
|
| 588 |
+
"grad_norm": 19.082073211669922,
|
| 589 |
+
"learning_rate": 3.935185185185186e-05,
|
| 590 |
+
"loss": 0.1969,
|
| 591 |
+
"step": 420
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 32.94117647058823,
|
| 595 |
+
"eval_accuracy": 0.7666666666666667,
|
| 596 |
+
"eval_loss": 0.7769466638565063,
|
| 597 |
+
"eval_runtime": 3.9404,
|
| 598 |
+
"eval_samples_per_second": 45.681,
|
| 599 |
+
"eval_steps_per_second": 1.523,
|
| 600 |
+
"step": 420
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 33.72549019607843,
|
| 604 |
+
"grad_norm": 23.67195701599121,
|
| 605 |
+
"learning_rate": 3.8966049382716055e-05,
|
| 606 |
+
"loss": 0.1968,
|
| 607 |
+
"step": 430
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 33.96078431372549,
|
| 611 |
+
"eval_accuracy": 0.7833333333333333,
|
| 612 |
+
"eval_loss": 0.7666174173355103,
|
| 613 |
+
"eval_runtime": 3.7732,
|
| 614 |
+
"eval_samples_per_second": 47.705,
|
| 615 |
+
"eval_steps_per_second": 1.59,
|
| 616 |
+
"step": 433
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 34.509803921568626,
|
| 620 |
+
"grad_norm": 22.488903045654297,
|
| 621 |
+
"learning_rate": 3.8580246913580246e-05,
|
| 622 |
+
"loss": 0.1712,
|
| 623 |
+
"step": 440
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 34.98039215686274,
|
| 627 |
+
"eval_accuracy": 0.8,
|
| 628 |
+
"eval_loss": 0.6795583367347717,
|
| 629 |
+
"eval_runtime": 3.7971,
|
| 630 |
+
"eval_samples_per_second": 47.404,
|
| 631 |
+
"eval_steps_per_second": 1.58,
|
| 632 |
+
"step": 446
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 35.294117647058826,
|
| 636 |
+
"grad_norm": 20.480487823486328,
|
| 637 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 638 |
+
"loss": 0.1813,
|
| 639 |
+
"step": 450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 36.0,
|
| 643 |
+
"eval_accuracy": 0.8111111111111111,
|
| 644 |
+
"eval_loss": 0.6653857827186584,
|
| 645 |
+
"eval_runtime": 3.8151,
|
| 646 |
+
"eval_samples_per_second": 47.181,
|
| 647 |
+
"eval_steps_per_second": 1.573,
|
| 648 |
+
"step": 459
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 36.07843137254902,
|
| 652 |
+
"grad_norm": 15.032731056213379,
|
| 653 |
+
"learning_rate": 3.780864197530865e-05,
|
| 654 |
+
"loss": 0.1625,
|
| 655 |
+
"step": 460
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 36.86274509803921,
|
| 659 |
+
"grad_norm": 12.346388816833496,
|
| 660 |
+
"learning_rate": 3.742283950617284e-05,
|
| 661 |
+
"loss": 0.1678,
|
| 662 |
+
"step": 470
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 36.94117647058823,
|
| 666 |
+
"eval_accuracy": 0.7888888888888889,
|
| 667 |
+
"eval_loss": 0.6851311326026917,
|
| 668 |
+
"eval_runtime": 3.8058,
|
| 669 |
+
"eval_samples_per_second": 47.296,
|
| 670 |
+
"eval_steps_per_second": 1.577,
|
| 671 |
+
"step": 471
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 37.64705882352941,
|
| 675 |
+
"grad_norm": 16.994136810302734,
|
| 676 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 677 |
+
"loss": 0.1461,
|
| 678 |
+
"step": 480
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 37.96078431372549,
|
| 682 |
+
"eval_accuracy": 0.7833333333333333,
|
| 683 |
+
"eval_loss": 0.7054334878921509,
|
| 684 |
+
"eval_runtime": 3.847,
|
| 685 |
+
"eval_samples_per_second": 46.79,
|
| 686 |
+
"eval_steps_per_second": 1.56,
|
| 687 |
+
"step": 484
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 38.431372549019606,
|
| 691 |
+
"grad_norm": 9.07701587677002,
|
| 692 |
+
"learning_rate": 3.665123456790124e-05,
|
| 693 |
+
"loss": 0.1244,
|
| 694 |
+
"step": 490
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 38.98039215686274,
|
| 698 |
+
"eval_accuracy": 0.8055555555555556,
|
| 699 |
+
"eval_loss": 0.7013460993766785,
|
| 700 |
+
"eval_runtime": 3.8047,
|
| 701 |
+
"eval_samples_per_second": 47.31,
|
| 702 |
+
"eval_steps_per_second": 1.577,
|
| 703 |
+
"step": 497
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 39.21568627450981,
|
| 707 |
+
"grad_norm": 9.217803955078125,
|
| 708 |
+
"learning_rate": 3.626543209876543e-05,
|
| 709 |
+
"loss": 0.1385,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 40.0,
|
| 714 |
+
"grad_norm": 18.938865661621094,
|
| 715 |
+
"learning_rate": 3.587962962962963e-05,
|
| 716 |
+
"loss": 0.1329,
|
| 717 |
+
"step": 510
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 40.0,
|
| 721 |
+
"eval_accuracy": 0.8,
|
| 722 |
+
"eval_loss": 0.6785274147987366,
|
| 723 |
+
"eval_runtime": 3.86,
|
| 724 |
+
"eval_samples_per_second": 46.632,
|
| 725 |
+
"eval_steps_per_second": 1.554,
|
| 726 |
+
"step": 510
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 40.78431372549019,
|
| 730 |
+
"grad_norm": 12.516762733459473,
|
| 731 |
+
"learning_rate": 3.5493827160493834e-05,
|
| 732 |
+
"loss": 0.1186,
|
| 733 |
+
"step": 520
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 40.94117647058823,
|
| 737 |
+
"eval_accuracy": 0.7777777777777778,
|
| 738 |
+
"eval_loss": 0.7499803900718689,
|
| 739 |
+
"eval_runtime": 3.8115,
|
| 740 |
+
"eval_samples_per_second": 47.225,
|
| 741 |
+
"eval_steps_per_second": 1.574,
|
| 742 |
+
"step": 522
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 41.568627450980394,
|
| 746 |
+
"grad_norm": 9.269219398498535,
|
| 747 |
+
"learning_rate": 3.5108024691358025e-05,
|
| 748 |
+
"loss": 0.1397,
|
| 749 |
+
"step": 530
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 41.96078431372549,
|
| 753 |
+
"eval_accuracy": 0.8166666666666667,
|
| 754 |
+
"eval_loss": 0.6819199919700623,
|
| 755 |
+
"eval_runtime": 3.8462,
|
| 756 |
+
"eval_samples_per_second": 46.799,
|
| 757 |
+
"eval_steps_per_second": 1.56,
|
| 758 |
+
"step": 535
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 42.35294117647059,
|
| 762 |
+
"grad_norm": 23.982585906982422,
|
| 763 |
+
"learning_rate": 3.472222222222222e-05,
|
| 764 |
+
"loss": 0.1324,
|
| 765 |
+
"step": 540
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 42.98039215686274,
|
| 769 |
+
"eval_accuracy": 0.8111111111111111,
|
| 770 |
+
"eval_loss": 0.6256746649742126,
|
| 771 |
+
"eval_runtime": 3.8195,
|
| 772 |
+
"eval_samples_per_second": 47.126,
|
| 773 |
+
"eval_steps_per_second": 1.571,
|
| 774 |
+
"step": 548
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 43.13725490196079,
|
| 778 |
+
"grad_norm": 11.348409652709961,
|
| 779 |
+
"learning_rate": 3.4336419753086427e-05,
|
| 780 |
+
"loss": 0.1461,
|
| 781 |
+
"step": 550
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 43.92156862745098,
|
| 785 |
+
"grad_norm": 14.504171371459961,
|
| 786 |
+
"learning_rate": 3.395061728395062e-05,
|
| 787 |
+
"loss": 0.111,
|
| 788 |
+
"step": 560
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 44.0,
|
| 792 |
+
"eval_accuracy": 0.8277777777777777,
|
| 793 |
+
"eval_loss": 0.5938891172409058,
|
| 794 |
+
"eval_runtime": 3.8255,
|
| 795 |
+
"eval_samples_per_second": 47.053,
|
| 796 |
+
"eval_steps_per_second": 1.568,
|
| 797 |
+
"step": 561
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 44.705882352941174,
|
| 801 |
+
"grad_norm": 15.88039493560791,
|
| 802 |
+
"learning_rate": 3.3564814814814815e-05,
|
| 803 |
+
"loss": 0.1228,
|
| 804 |
+
"step": 570
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 44.94117647058823,
|
| 808 |
+
"eval_accuracy": 0.8222222222222222,
|
| 809 |
+
"eval_loss": 0.6379250288009644,
|
| 810 |
+
"eval_runtime": 3.8691,
|
| 811 |
+
"eval_samples_per_second": 46.522,
|
| 812 |
+
"eval_steps_per_second": 1.551,
|
| 813 |
+
"step": 573
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 45.490196078431374,
|
| 817 |
+
"grad_norm": 14.967761993408203,
|
| 818 |
+
"learning_rate": 3.317901234567901e-05,
|
| 819 |
+
"loss": 0.1085,
|
| 820 |
+
"step": 580
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 45.96078431372549,
|
| 824 |
+
"eval_accuracy": 0.8222222222222222,
|
| 825 |
+
"eval_loss": 0.6788524389266968,
|
| 826 |
+
"eval_runtime": 3.8236,
|
| 827 |
+
"eval_samples_per_second": 47.077,
|
| 828 |
+
"eval_steps_per_second": 1.569,
|
| 829 |
+
"step": 586
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 46.27450980392157,
|
| 833 |
+
"grad_norm": 7.978495121002197,
|
| 834 |
+
"learning_rate": 3.279320987654321e-05,
|
| 835 |
+
"loss": 0.1234,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 46.98039215686274,
|
| 840 |
+
"eval_accuracy": 0.8277777777777777,
|
| 841 |
+
"eval_loss": 0.624097466468811,
|
| 842 |
+
"eval_runtime": 3.7905,
|
| 843 |
+
"eval_samples_per_second": 47.487,
|
| 844 |
+
"eval_steps_per_second": 1.583,
|
| 845 |
+
"step": 599
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 47.05882352941177,
|
| 849 |
+
"grad_norm": 21.228994369506836,
|
| 850 |
+
"learning_rate": 3.240740740740741e-05,
|
| 851 |
+
"loss": 0.1007,
|
| 852 |
+
"step": 600
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 47.84313725490196,
|
| 856 |
+
"grad_norm": 16.632568359375,
|
| 857 |
+
"learning_rate": 3.2021604938271605e-05,
|
| 858 |
+
"loss": 0.1129,
|
| 859 |
+
"step": 610
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 48.0,
|
| 863 |
+
"eval_accuracy": 0.7888888888888889,
|
| 864 |
+
"eval_loss": 0.750299334526062,
|
| 865 |
+
"eval_runtime": 3.8266,
|
| 866 |
+
"eval_samples_per_second": 47.039,
|
| 867 |
+
"eval_steps_per_second": 1.568,
|
| 868 |
+
"step": 612
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 48.627450980392155,
|
| 872 |
+
"grad_norm": 8.629143714904785,
|
| 873 |
+
"learning_rate": 3.16358024691358e-05,
|
| 874 |
+
"loss": 0.1197,
|
| 875 |
+
"step": 620
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 48.94117647058823,
|
| 879 |
+
"eval_accuracy": 0.7944444444444444,
|
| 880 |
+
"eval_loss": 0.6861774325370789,
|
| 881 |
+
"eval_runtime": 3.8119,
|
| 882 |
+
"eval_samples_per_second": 47.22,
|
| 883 |
+
"eval_steps_per_second": 1.574,
|
| 884 |
+
"step": 624
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 49.411764705882355,
|
| 888 |
+
"grad_norm": 7.733061790466309,
|
| 889 |
+
"learning_rate": 3.125e-05,
|
| 890 |
+
"loss": 0.0898,
|
| 891 |
+
"step": 630
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 49.96078431372549,
|
| 895 |
+
"eval_accuracy": 0.7888888888888889,
|
| 896 |
+
"eval_loss": 0.6763875484466553,
|
| 897 |
+
"eval_runtime": 3.818,
|
| 898 |
+
"eval_samples_per_second": 47.145,
|
| 899 |
+
"eval_steps_per_second": 1.571,
|
| 900 |
+
"step": 637
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 50.19607843137255,
|
| 904 |
+
"grad_norm": 4.7213454246521,
|
| 905 |
+
"learning_rate": 3.08641975308642e-05,
|
| 906 |
+
"loss": 0.1021,
|
| 907 |
+
"step": 640
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 50.98039215686274,
|
| 911 |
+
"grad_norm": 7.109160423278809,
|
| 912 |
+
"learning_rate": 3.04783950617284e-05,
|
| 913 |
+
"loss": 0.1057,
|
| 914 |
+
"step": 650
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 50.98039215686274,
|
| 918 |
+
"eval_accuracy": 0.8166666666666667,
|
| 919 |
+
"eval_loss": 0.6338934898376465,
|
| 920 |
+
"eval_runtime": 3.8669,
|
| 921 |
+
"eval_samples_per_second": 46.549,
|
| 922 |
+
"eval_steps_per_second": 1.552,
|
| 923 |
+
"step": 650
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 51.76470588235294,
|
| 927 |
+
"grad_norm": 16.793262481689453,
|
| 928 |
+
"learning_rate": 3.0092592592592593e-05,
|
| 929 |
+
"loss": 0.0893,
|
| 930 |
+
"step": 660
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 52.0,
|
| 934 |
+
"eval_accuracy": 0.85,
|
| 935 |
+
"eval_loss": 0.5828067064285278,
|
| 936 |
+
"eval_runtime": 3.8135,
|
| 937 |
+
"eval_samples_per_second": 47.2,
|
| 938 |
+
"eval_steps_per_second": 1.573,
|
| 939 |
+
"step": 663
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 52.549019607843135,
|
| 943 |
+
"grad_norm": 15.305388450622559,
|
| 944 |
+
"learning_rate": 2.970679012345679e-05,
|
| 945 |
+
"loss": 0.0736,
|
| 946 |
+
"step": 670
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 52.94117647058823,
|
| 950 |
+
"eval_accuracy": 0.8111111111111111,
|
| 951 |
+
"eval_loss": 0.6572611331939697,
|
| 952 |
+
"eval_runtime": 3.8338,
|
| 953 |
+
"eval_samples_per_second": 46.951,
|
| 954 |
+
"eval_steps_per_second": 1.565,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 53.333333333333336,
|
| 959 |
+
"grad_norm": 13.537842750549316,
|
| 960 |
+
"learning_rate": 2.9320987654320992e-05,
|
| 961 |
+
"loss": 0.0752,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 53.96078431372549,
|
| 966 |
+
"eval_accuracy": 0.7944444444444444,
|
| 967 |
+
"eval_loss": 0.6806420087814331,
|
| 968 |
+
"eval_runtime": 3.821,
|
| 969 |
+
"eval_samples_per_second": 47.108,
|
| 970 |
+
"eval_steps_per_second": 1.57,
|
| 971 |
+
"step": 688
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 54.11764705882353,
|
| 975 |
+
"grad_norm": 21.195058822631836,
|
| 976 |
+
"learning_rate": 2.8935185185185186e-05,
|
| 977 |
+
"loss": 0.081,
|
| 978 |
+
"step": 690
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 54.90196078431372,
|
| 982 |
+
"grad_norm": 4.959319591522217,
|
| 983 |
+
"learning_rate": 2.8549382716049384e-05,
|
| 984 |
+
"loss": 0.1127,
|
| 985 |
+
"step": 700
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 54.98039215686274,
|
| 989 |
+
"eval_accuracy": 0.8111111111111111,
|
| 990 |
+
"eval_loss": 0.6222459673881531,
|
| 991 |
+
"eval_runtime": 3.8138,
|
| 992 |
+
"eval_samples_per_second": 47.197,
|
| 993 |
+
"eval_steps_per_second": 1.573,
|
| 994 |
+
"step": 701
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 55.68627450980392,
|
| 998 |
+
"grad_norm": 15.941388130187988,
|
| 999 |
+
"learning_rate": 2.8163580246913578e-05,
|
| 1000 |
+
"loss": 0.1126,
|
| 1001 |
+
"step": 710
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 56.0,
|
| 1005 |
+
"eval_accuracy": 0.8166666666666667,
|
| 1006 |
+
"eval_loss": 0.6305037140846252,
|
| 1007 |
+
"eval_runtime": 3.7889,
|
| 1008 |
+
"eval_samples_per_second": 47.507,
|
| 1009 |
+
"eval_steps_per_second": 1.584,
|
| 1010 |
+
"step": 714
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 56.470588235294116,
|
| 1014 |
+
"grad_norm": 12.527265548706055,
|
| 1015 |
+
"learning_rate": 2.777777777777778e-05,
|
| 1016 |
+
"loss": 0.0874,
|
| 1017 |
+
"step": 720
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 56.94117647058823,
|
| 1021 |
+
"eval_accuracy": 0.8111111111111111,
|
| 1022 |
+
"eval_loss": 0.6593422293663025,
|
| 1023 |
+
"eval_runtime": 3.7695,
|
| 1024 |
+
"eval_samples_per_second": 47.751,
|
| 1025 |
+
"eval_steps_per_second": 1.592,
|
| 1026 |
+
"step": 726
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 57.254901960784316,
|
| 1030 |
+
"grad_norm": 7.021444797515869,
|
| 1031 |
+
"learning_rate": 2.7391975308641977e-05,
|
| 1032 |
+
"loss": 0.0806,
|
| 1033 |
+
"step": 730
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 57.96078431372549,
|
| 1037 |
+
"eval_accuracy": 0.8166666666666667,
|
| 1038 |
+
"eval_loss": 0.7005773782730103,
|
| 1039 |
+
"eval_runtime": 3.7654,
|
| 1040 |
+
"eval_samples_per_second": 47.804,
|
| 1041 |
+
"eval_steps_per_second": 1.593,
|
| 1042 |
+
"step": 739
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 58.03921568627451,
|
| 1046 |
+
"grad_norm": 13.148822784423828,
|
| 1047 |
+
"learning_rate": 2.700617283950617e-05,
|
| 1048 |
+
"loss": 0.0862,
|
| 1049 |
+
"step": 740
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 58.8235294117647,
|
| 1053 |
+
"grad_norm": 21.20357322692871,
|
| 1054 |
+
"learning_rate": 2.6620370370370372e-05,
|
| 1055 |
+
"loss": 0.0978,
|
| 1056 |
+
"step": 750
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 58.98039215686274,
|
| 1060 |
+
"eval_accuracy": 0.8055555555555556,
|
| 1061 |
+
"eval_loss": 0.6680053472518921,
|
| 1062 |
+
"eval_runtime": 3.8444,
|
| 1063 |
+
"eval_samples_per_second": 46.821,
|
| 1064 |
+
"eval_steps_per_second": 1.561,
|
| 1065 |
+
"step": 752
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 59.6078431372549,
|
| 1069 |
+
"grad_norm": 14.901837348937988,
|
| 1070 |
+
"learning_rate": 2.623456790123457e-05,
|
| 1071 |
+
"loss": 0.0875,
|
| 1072 |
+
"step": 760
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 60.0,
|
| 1076 |
+
"eval_accuracy": 0.8166666666666667,
|
| 1077 |
+
"eval_loss": 0.67389976978302,
|
| 1078 |
+
"eval_runtime": 3.8169,
|
| 1079 |
+
"eval_samples_per_second": 47.158,
|
| 1080 |
+
"eval_steps_per_second": 1.572,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 60.3921568627451,
|
| 1085 |
+
"grad_norm": 7.75632905960083,
|
| 1086 |
+
"learning_rate": 2.5848765432098764e-05,
|
| 1087 |
+
"loss": 0.0722,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 60.94117647058823,
|
| 1092 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1093 |
+
"eval_loss": 0.6340806484222412,
|
| 1094 |
+
"eval_runtime": 3.804,
|
| 1095 |
+
"eval_samples_per_second": 47.318,
|
| 1096 |
+
"eval_steps_per_second": 1.577,
|
| 1097 |
+
"step": 777
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 61.1764705882353,
|
| 1101 |
+
"grad_norm": 15.415738105773926,
|
| 1102 |
+
"learning_rate": 2.5462962962962965e-05,
|
| 1103 |
+
"loss": 0.0901,
|
| 1104 |
+
"step": 780
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 61.96078431372549,
|
| 1108 |
+
"grad_norm": 4.349020004272461,
|
| 1109 |
+
"learning_rate": 2.5077160493827162e-05,
|
| 1110 |
+
"loss": 0.0942,
|
| 1111 |
+
"step": 790
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 61.96078431372549,
|
| 1115 |
+
"eval_accuracy": 0.8,
|
| 1116 |
+
"eval_loss": 0.6428362727165222,
|
| 1117 |
+
"eval_runtime": 3.7936,
|
| 1118 |
+
"eval_samples_per_second": 47.448,
|
| 1119 |
+
"eval_steps_per_second": 1.582,
|
| 1120 |
+
"step": 790
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 62.745098039215684,
|
| 1124 |
+
"grad_norm": 9.049278259277344,
|
| 1125 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 1126 |
+
"loss": 0.0957,
|
| 1127 |
+
"step": 800
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 62.98039215686274,
|
| 1131 |
+
"eval_accuracy": 0.8,
|
| 1132 |
+
"eval_loss": 0.6757560968399048,
|
| 1133 |
+
"eval_runtime": 3.8348,
|
| 1134 |
+
"eval_samples_per_second": 46.938,
|
| 1135 |
+
"eval_steps_per_second": 1.565,
|
| 1136 |
+
"step": 803
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 63.529411764705884,
|
| 1140 |
+
"grad_norm": 11.159144401550293,
|
| 1141 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 1142 |
+
"loss": 0.0814,
|
| 1143 |
+
"step": 810
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 64.0,
|
| 1147 |
+
"eval_accuracy": 0.8166666666666667,
|
| 1148 |
+
"eval_loss": 0.6104480028152466,
|
| 1149 |
+
"eval_runtime": 3.8591,
|
| 1150 |
+
"eval_samples_per_second": 46.643,
|
| 1151 |
+
"eval_steps_per_second": 1.555,
|
| 1152 |
+
"step": 816
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 64.31372549019608,
|
| 1156 |
+
"grad_norm": 11.834258079528809,
|
| 1157 |
+
"learning_rate": 2.3919753086419755e-05,
|
| 1158 |
+
"loss": 0.077,
|
| 1159 |
+
"step": 820
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 64.94117647058823,
|
| 1163 |
+
"eval_accuracy": 0.8111111111111111,
|
| 1164 |
+
"eval_loss": 0.6226403713226318,
|
| 1165 |
+
"eval_runtime": 3.8932,
|
| 1166 |
+
"eval_samples_per_second": 46.235,
|
| 1167 |
+
"eval_steps_per_second": 1.541,
|
| 1168 |
+
"step": 828
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 65.09803921568627,
|
| 1172 |
+
"grad_norm": 11.226044654846191,
|
| 1173 |
+
"learning_rate": 2.353395061728395e-05,
|
| 1174 |
+
"loss": 0.0862,
|
| 1175 |
+
"step": 830
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 65.88235294117646,
|
| 1179 |
+
"grad_norm": 14.373990058898926,
|
| 1180 |
+
"learning_rate": 2.314814814814815e-05,
|
| 1181 |
+
"loss": 0.1004,
|
| 1182 |
+
"step": 840
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 65.96078431372548,
|
| 1186 |
+
"eval_accuracy": 0.8055555555555556,
|
| 1187 |
+
"eval_loss": 0.6898564696311951,
|
| 1188 |
+
"eval_runtime": 3.8229,
|
| 1189 |
+
"eval_samples_per_second": 47.085,
|
| 1190 |
+
"eval_steps_per_second": 1.569,
|
| 1191 |
+
"step": 841
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 66.66666666666667,
|
| 1195 |
+
"grad_norm": 8.56983757019043,
|
| 1196 |
+
"learning_rate": 2.2762345679012348e-05,
|
| 1197 |
+
"loss": 0.0697,
|
| 1198 |
+
"step": 850
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 66.98039215686275,
|
| 1202 |
+
"eval_accuracy": 0.8166666666666667,
|
| 1203 |
+
"eval_loss": 0.7104570865631104,
|
| 1204 |
+
"eval_runtime": 3.7843,
|
| 1205 |
+
"eval_samples_per_second": 47.565,
|
| 1206 |
+
"eval_steps_per_second": 1.585,
|
| 1207 |
+
"step": 854
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 67.45098039215686,
|
| 1211 |
+
"grad_norm": 7.092602729797363,
|
| 1212 |
+
"learning_rate": 2.2376543209876542e-05,
|
| 1213 |
+
"loss": 0.0754,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 68.0,
|
| 1218 |
+
"eval_accuracy": 0.8111111111111111,
|
| 1219 |
+
"eval_loss": 0.675083339214325,
|
| 1220 |
+
"eval_runtime": 3.8377,
|
| 1221 |
+
"eval_samples_per_second": 46.903,
|
| 1222 |
+
"eval_steps_per_second": 1.563,
|
| 1223 |
+
"step": 867
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 68.23529411764706,
|
| 1227 |
+
"grad_norm": 21.711984634399414,
|
| 1228 |
+
"learning_rate": 2.1990740740740743e-05,
|
| 1229 |
+
"loss": 0.0842,
|
| 1230 |
+
"step": 870
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 68.94117647058823,
|
| 1234 |
+
"eval_accuracy": 0.7833333333333333,
|
| 1235 |
+
"eval_loss": 0.6912497878074646,
|
| 1236 |
+
"eval_runtime": 4.1438,
|
| 1237 |
+
"eval_samples_per_second": 43.438,
|
| 1238 |
+
"eval_steps_per_second": 1.448,
|
| 1239 |
+
"step": 879
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 69.01960784313725,
|
| 1243 |
+
"grad_norm": 17.59021759033203,
|
| 1244 |
+
"learning_rate": 2.1604938271604937e-05,
|
| 1245 |
+
"loss": 0.0815,
|
| 1246 |
+
"step": 880
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 69.80392156862744,
|
| 1250 |
+
"grad_norm": 6.925079822540283,
|
| 1251 |
+
"learning_rate": 2.1219135802469135e-05,
|
| 1252 |
+
"loss": 0.0684,
|
| 1253 |
+
"step": 890
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 69.96078431372548,
|
| 1257 |
+
"eval_accuracy": 0.8166666666666667,
|
| 1258 |
+
"eval_loss": 0.7235284447669983,
|
| 1259 |
+
"eval_runtime": 3.8887,
|
| 1260 |
+
"eval_samples_per_second": 46.288,
|
| 1261 |
+
"eval_steps_per_second": 1.543,
|
| 1262 |
+
"step": 892
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 70.58823529411765,
|
| 1266 |
+
"grad_norm": 10.211894989013672,
|
| 1267 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 1268 |
+
"loss": 0.0684,
|
| 1269 |
+
"step": 900
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 70.98039215686275,
|
| 1273 |
+
"eval_accuracy": 0.8277777777777777,
|
| 1274 |
+
"eval_loss": 0.5839894413948059,
|
| 1275 |
+
"eval_runtime": 3.8698,
|
| 1276 |
+
"eval_samples_per_second": 46.514,
|
| 1277 |
+
"eval_steps_per_second": 1.55,
|
| 1278 |
+
"step": 905
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 71.37254901960785,
|
| 1282 |
+
"grad_norm": 7.931591987609863,
|
| 1283 |
+
"learning_rate": 2.044753086419753e-05,
|
| 1284 |
+
"loss": 0.0705,
|
| 1285 |
+
"step": 910
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 72.0,
|
| 1289 |
+
"eval_accuracy": 0.8222222222222222,
|
| 1290 |
+
"eval_loss": 0.6635811924934387,
|
| 1291 |
+
"eval_runtime": 3.899,
|
| 1292 |
+
"eval_samples_per_second": 46.165,
|
| 1293 |
+
"eval_steps_per_second": 1.539,
|
| 1294 |
+
"step": 918
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 72.15686274509804,
|
| 1298 |
+
"grad_norm": 8.439017295837402,
|
| 1299 |
+
"learning_rate": 2.006172839506173e-05,
|
| 1300 |
+
"loss": 0.0532,
|
| 1301 |
+
"step": 920
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 72.94117647058823,
|
| 1305 |
+
"grad_norm": 20.3321475982666,
|
| 1306 |
+
"learning_rate": 1.967592592592593e-05,
|
| 1307 |
+
"loss": 0.0681,
|
| 1308 |
+
"step": 930
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 72.94117647058823,
|
| 1312 |
+
"eval_accuracy": 0.8,
|
| 1313 |
+
"eval_loss": 0.678679883480072,
|
| 1314 |
+
"eval_runtime": 3.8456,
|
| 1315 |
+
"eval_samples_per_second": 46.807,
|
| 1316 |
+
"eval_steps_per_second": 1.56,
|
| 1317 |
+
"step": 930
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 73.72549019607843,
|
| 1321 |
+
"grad_norm": 16.518983840942383,
|
| 1322 |
+
"learning_rate": 1.9290123456790123e-05,
|
| 1323 |
+
"loss": 0.0906,
|
| 1324 |
+
"step": 940
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 73.96078431372548,
|
| 1328 |
+
"eval_accuracy": 0.8388888888888889,
|
| 1329 |
+
"eval_loss": 0.6242751479148865,
|
| 1330 |
+
"eval_runtime": 3.8813,
|
| 1331 |
+
"eval_samples_per_second": 46.376,
|
| 1332 |
+
"eval_steps_per_second": 1.546,
|
| 1333 |
+
"step": 943
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 74.50980392156863,
|
| 1337 |
+
"grad_norm": 10.190762519836426,
|
| 1338 |
+
"learning_rate": 1.8904320987654324e-05,
|
| 1339 |
+
"loss": 0.0453,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 74.98039215686275,
|
| 1344 |
+
"eval_accuracy": 0.8222222222222222,
|
| 1345 |
+
"eval_loss": 0.6786649823188782,
|
| 1346 |
+
"eval_runtime": 3.8468,
|
| 1347 |
+
"eval_samples_per_second": 46.793,
|
| 1348 |
+
"eval_steps_per_second": 1.56,
|
| 1349 |
+
"step": 956
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 75.29411764705883,
|
| 1353 |
+
"grad_norm": 12.627336502075195,
|
| 1354 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 1355 |
+
"loss": 0.0874,
|
| 1356 |
+
"step": 960
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 76.0,
|
| 1360 |
+
"eval_accuracy": 0.8277777777777777,
|
| 1361 |
+
"eval_loss": 0.6259381771087646,
|
| 1362 |
+
"eval_runtime": 3.9491,
|
| 1363 |
+
"eval_samples_per_second": 45.58,
|
| 1364 |
+
"eval_steps_per_second": 1.519,
|
| 1365 |
+
"step": 969
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 76.07843137254902,
|
| 1369 |
+
"grad_norm": 15.190587997436523,
|
| 1370 |
+
"learning_rate": 1.8132716049382716e-05,
|
| 1371 |
+
"loss": 0.0668,
|
| 1372 |
+
"step": 970
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 76.86274509803921,
|
| 1376 |
+
"grad_norm": 4.534496307373047,
|
| 1377 |
+
"learning_rate": 1.7746913580246917e-05,
|
| 1378 |
+
"loss": 0.051,
|
| 1379 |
+
"step": 980
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 76.94117647058823,
|
| 1383 |
+
"eval_accuracy": 0.8277777777777777,
|
| 1384 |
+
"eval_loss": 0.6590437293052673,
|
| 1385 |
+
"eval_runtime": 3.8024,
|
| 1386 |
+
"eval_samples_per_second": 47.339,
|
| 1387 |
+
"eval_steps_per_second": 1.578,
|
| 1388 |
+
"step": 981
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 77.6470588235294,
|
| 1392 |
+
"grad_norm": 12.094006538391113,
|
| 1393 |
+
"learning_rate": 1.736111111111111e-05,
|
| 1394 |
+
"loss": 0.0858,
|
| 1395 |
+
"step": 990
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 77.96078431372548,
|
| 1399 |
+
"eval_accuracy": 0.8277777777777777,
|
| 1400 |
+
"eval_loss": 0.6306740045547485,
|
| 1401 |
+
"eval_runtime": 4.0063,
|
| 1402 |
+
"eval_samples_per_second": 44.929,
|
| 1403 |
+
"eval_steps_per_second": 1.498,
|
| 1404 |
+
"step": 994
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 78.43137254901961,
|
| 1408 |
+
"grad_norm": 12.669979095458984,
|
| 1409 |
+
"learning_rate": 1.697530864197531e-05,
|
| 1410 |
+
"loss": 0.0601,
|
| 1411 |
+
"step": 1000
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 78.98039215686275,
|
| 1415 |
+
"eval_accuracy": 0.8444444444444444,
|
| 1416 |
+
"eval_loss": 0.6041626334190369,
|
| 1417 |
+
"eval_runtime": 3.9261,
|
| 1418 |
+
"eval_samples_per_second": 45.847,
|
| 1419 |
+
"eval_steps_per_second": 1.528,
|
| 1420 |
+
"step": 1007
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 79.2156862745098,
|
| 1424 |
+
"grad_norm": 13.32419490814209,
|
| 1425 |
+
"learning_rate": 1.6589506172839506e-05,
|
| 1426 |
+
"loss": 0.0596,
|
| 1427 |
+
"step": 1010
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 80.0,
|
| 1431 |
+
"grad_norm": 17.491554260253906,
|
| 1432 |
+
"learning_rate": 1.6203703703703704e-05,
|
| 1433 |
+
"loss": 0.0601,
|
| 1434 |
+
"step": 1020
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 80.0,
|
| 1438 |
+
"eval_accuracy": 0.8388888888888889,
|
| 1439 |
+
"eval_loss": 0.5874945521354675,
|
| 1440 |
+
"eval_runtime": 4.0068,
|
| 1441 |
+
"eval_samples_per_second": 44.923,
|
| 1442 |
+
"eval_steps_per_second": 1.497,
|
| 1443 |
+
"step": 1020
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 80.7843137254902,
|
| 1447 |
+
"grad_norm": 7.148036956787109,
|
| 1448 |
+
"learning_rate": 1.58179012345679e-05,
|
| 1449 |
+
"loss": 0.067,
|
| 1450 |
+
"step": 1030
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 80.94117647058823,
|
| 1454 |
+
"eval_accuracy": 0.8388888888888889,
|
| 1455 |
+
"eval_loss": 0.6078370809555054,
|
| 1456 |
+
"eval_runtime": 3.7634,
|
| 1457 |
+
"eval_samples_per_second": 47.829,
|
| 1458 |
+
"eval_steps_per_second": 1.594,
|
| 1459 |
+
"step": 1032
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 81.56862745098039,
|
| 1463 |
+
"grad_norm": 6.120352745056152,
|
| 1464 |
+
"learning_rate": 1.54320987654321e-05,
|
| 1465 |
+
"loss": 0.0556,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 81.96078431372548,
|
| 1470 |
+
"eval_accuracy": 0.8444444444444444,
|
| 1471 |
+
"eval_loss": 0.6006819605827332,
|
| 1472 |
+
"eval_runtime": 3.8921,
|
| 1473 |
+
"eval_samples_per_second": 46.248,
|
| 1474 |
+
"eval_steps_per_second": 1.542,
|
| 1475 |
+
"step": 1045
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 82.3529411764706,
|
| 1479 |
+
"grad_norm": 9.7392578125,
|
| 1480 |
+
"learning_rate": 1.5046296296296297e-05,
|
| 1481 |
+
"loss": 0.0661,
|
| 1482 |
+
"step": 1050
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 82.98039215686275,
|
| 1486 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1487 |
+
"eval_loss": 0.6062378287315369,
|
| 1488 |
+
"eval_runtime": 3.7924,
|
| 1489 |
+
"eval_samples_per_second": 47.464,
|
| 1490 |
+
"eval_steps_per_second": 1.582,
|
| 1491 |
+
"step": 1058
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 83.13725490196079,
|
| 1495 |
+
"grad_norm": 7.788672924041748,
|
| 1496 |
+
"learning_rate": 1.4660493827160496e-05,
|
| 1497 |
+
"loss": 0.0594,
|
| 1498 |
+
"step": 1060
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 83.92156862745098,
|
| 1502 |
+
"grad_norm": 3.5243284702301025,
|
| 1503 |
+
"learning_rate": 1.4274691358024692e-05,
|
| 1504 |
+
"loss": 0.0651,
|
| 1505 |
+
"step": 1070
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 84.0,
|
| 1509 |
+
"eval_accuracy": 0.8111111111111111,
|
| 1510 |
+
"eval_loss": 0.6387273669242859,
|
| 1511 |
+
"eval_runtime": 3.9274,
|
| 1512 |
+
"eval_samples_per_second": 45.832,
|
| 1513 |
+
"eval_steps_per_second": 1.528,
|
| 1514 |
+
"step": 1071
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 84.70588235294117,
|
| 1518 |
+
"grad_norm": 10.037181854248047,
|
| 1519 |
+
"learning_rate": 1.388888888888889e-05,
|
| 1520 |
+
"loss": 0.0546,
|
| 1521 |
+
"step": 1080
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 84.94117647058823,
|
| 1525 |
+
"eval_accuracy": 0.8166666666666667,
|
| 1526 |
+
"eval_loss": 0.6861324906349182,
|
| 1527 |
+
"eval_runtime": 3.8238,
|
| 1528 |
+
"eval_samples_per_second": 47.074,
|
| 1529 |
+
"eval_steps_per_second": 1.569,
|
| 1530 |
+
"step": 1083
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 85.49019607843137,
|
| 1534 |
+
"grad_norm": 10.713313102722168,
|
| 1535 |
+
"learning_rate": 1.3503086419753085e-05,
|
| 1536 |
+
"loss": 0.0827,
|
| 1537 |
+
"step": 1090
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 85.96078431372548,
|
| 1541 |
+
"eval_accuracy": 0.8388888888888889,
|
| 1542 |
+
"eval_loss": 0.6072664260864258,
|
| 1543 |
+
"eval_runtime": 4.2373,
|
| 1544 |
+
"eval_samples_per_second": 42.479,
|
| 1545 |
+
"eval_steps_per_second": 1.416,
|
| 1546 |
+
"step": 1096
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 86.27450980392157,
|
| 1550 |
+
"grad_norm": 7.2301201820373535,
|
| 1551 |
+
"learning_rate": 1.3117283950617285e-05,
|
| 1552 |
+
"loss": 0.052,
|
| 1553 |
+
"step": 1100
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 86.98039215686275,
|
| 1557 |
+
"eval_accuracy": 0.85,
|
| 1558 |
+
"eval_loss": 0.593485951423645,
|
| 1559 |
+
"eval_runtime": 3.8302,
|
| 1560 |
+
"eval_samples_per_second": 46.995,
|
| 1561 |
+
"eval_steps_per_second": 1.566,
|
| 1562 |
+
"step": 1109
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 87.05882352941177,
|
| 1566 |
+
"grad_norm": 4.73368501663208,
|
| 1567 |
+
"learning_rate": 1.2731481481481482e-05,
|
| 1568 |
+
"loss": 0.0442,
|
| 1569 |
+
"step": 1110
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 87.84313725490196,
|
| 1573 |
+
"grad_norm": 18.29523277282715,
|
| 1574 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 1575 |
+
"loss": 0.0524,
|
| 1576 |
+
"step": 1120
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 88.0,
|
| 1580 |
+
"eval_accuracy": 0.8388888888888889,
|
| 1581 |
+
"eval_loss": 0.5899335145950317,
|
| 1582 |
+
"eval_runtime": 3.8551,
|
| 1583 |
+
"eval_samples_per_second": 46.692,
|
| 1584 |
+
"eval_steps_per_second": 1.556,
|
| 1585 |
+
"step": 1122
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 88.62745098039215,
|
| 1589 |
+
"grad_norm": 5.7875494956970215,
|
| 1590 |
+
"learning_rate": 1.1959876543209878e-05,
|
| 1591 |
+
"loss": 0.066,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 88.94117647058823,
|
| 1596 |
+
"eval_accuracy": 0.8444444444444444,
|
| 1597 |
+
"eval_loss": 0.5954256057739258,
|
| 1598 |
+
"eval_runtime": 3.8582,
|
| 1599 |
+
"eval_samples_per_second": 46.654,
|
| 1600 |
+
"eval_steps_per_second": 1.555,
|
| 1601 |
+
"step": 1134
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 89.41176470588235,
|
| 1605 |
+
"grad_norm": 7.960011005401611,
|
| 1606 |
+
"learning_rate": 1.1574074074074075e-05,
|
| 1607 |
+
"loss": 0.0617,
|
| 1608 |
+
"step": 1140
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 89.96078431372548,
|
| 1612 |
+
"eval_accuracy": 0.8444444444444444,
|
| 1613 |
+
"eval_loss": 0.6145300269126892,
|
| 1614 |
+
"eval_runtime": 3.8594,
|
| 1615 |
+
"eval_samples_per_second": 46.639,
|
| 1616 |
+
"eval_steps_per_second": 1.555,
|
| 1617 |
+
"step": 1147
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 90.19607843137256,
|
| 1621 |
+
"grad_norm": 5.9040350914001465,
|
| 1622 |
+
"learning_rate": 1.1188271604938271e-05,
|
| 1623 |
+
"loss": 0.0373,
|
| 1624 |
+
"step": 1150
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 90.98039215686275,
|
| 1628 |
+
"grad_norm": 7.361179828643799,
|
| 1629 |
+
"learning_rate": 1.0802469135802469e-05,
|
| 1630 |
+
"loss": 0.0572,
|
| 1631 |
+
"step": 1160
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 90.98039215686275,
|
| 1635 |
+
"eval_accuracy": 0.8444444444444444,
|
| 1636 |
+
"eval_loss": 0.6176372766494751,
|
| 1637 |
+
"eval_runtime": 3.825,
|
| 1638 |
+
"eval_samples_per_second": 47.059,
|
| 1639 |
+
"eval_steps_per_second": 1.569,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 91.76470588235294,
|
| 1644 |
+
"grad_norm": 14.031915664672852,
|
| 1645 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 1646 |
+
"loss": 0.0719,
|
| 1647 |
+
"step": 1170
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 92.0,
|
| 1651 |
+
"eval_accuracy": 0.8277777777777777,
|
| 1652 |
+
"eval_loss": 0.6406115889549255,
|
| 1653 |
+
"eval_runtime": 3.7626,
|
| 1654 |
+
"eval_samples_per_second": 47.839,
|
| 1655 |
+
"eval_steps_per_second": 1.595,
|
| 1656 |
+
"step": 1173
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 92.54901960784314,
|
| 1660 |
+
"grad_norm": 12.152432441711426,
|
| 1661 |
+
"learning_rate": 1.0030864197530866e-05,
|
| 1662 |
+
"loss": 0.0734,
|
| 1663 |
+
"step": 1180
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 92.94117647058823,
|
| 1667 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1668 |
+
"eval_loss": 0.6484689712524414,
|
| 1669 |
+
"eval_runtime": 3.8146,
|
| 1670 |
+
"eval_samples_per_second": 47.187,
|
| 1671 |
+
"eval_steps_per_second": 1.573,
|
| 1672 |
+
"step": 1185
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 93.33333333333333,
|
| 1676 |
+
"grad_norm": 7.38240385055542,
|
| 1677 |
+
"learning_rate": 9.645061728395062e-06,
|
| 1678 |
+
"loss": 0.0616,
|
| 1679 |
+
"step": 1190
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 93.96078431372548,
|
| 1683 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1684 |
+
"eval_loss": 0.619816243648529,
|
| 1685 |
+
"eval_runtime": 3.8069,
|
| 1686 |
+
"eval_samples_per_second": 47.282,
|
| 1687 |
+
"eval_steps_per_second": 1.576,
|
| 1688 |
+
"step": 1198
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 94.11764705882354,
|
| 1692 |
+
"grad_norm": 15.435483932495117,
|
| 1693 |
+
"learning_rate": 9.259259259259259e-06,
|
| 1694 |
+
"loss": 0.047,
|
| 1695 |
+
"step": 1200
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 94.90196078431373,
|
| 1699 |
+
"grad_norm": 3.8711276054382324,
|
| 1700 |
+
"learning_rate": 8.873456790123458e-06,
|
| 1701 |
+
"loss": 0.0557,
|
| 1702 |
+
"step": 1210
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 94.98039215686275,
|
| 1706 |
+
"eval_accuracy": 0.8388888888888889,
|
| 1707 |
+
"eval_loss": 0.6167161464691162,
|
| 1708 |
+
"eval_runtime": 3.7712,
|
| 1709 |
+
"eval_samples_per_second": 47.73,
|
| 1710 |
+
"eval_steps_per_second": 1.591,
|
| 1711 |
+
"step": 1211
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 95.68627450980392,
|
| 1715 |
+
"grad_norm": 6.233323574066162,
|
| 1716 |
+
"learning_rate": 8.487654320987654e-06,
|
| 1717 |
+
"loss": 0.0494,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 96.0,
|
| 1722 |
+
"eval_accuracy": 0.8444444444444444,
|
| 1723 |
+
"eval_loss": 0.6479634642601013,
|
| 1724 |
+
"eval_runtime": 3.8139,
|
| 1725 |
+
"eval_samples_per_second": 47.196,
|
| 1726 |
+
"eval_steps_per_second": 1.573,
|
| 1727 |
+
"step": 1224
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 96.47058823529412,
|
| 1731 |
+
"grad_norm": 2.76275897026062,
|
| 1732 |
+
"learning_rate": 8.101851851851852e-06,
|
| 1733 |
+
"loss": 0.0587,
|
| 1734 |
+
"step": 1230
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 96.94117647058823,
|
| 1738 |
+
"eval_accuracy": 0.85,
|
| 1739 |
+
"eval_loss": 0.6075512170791626,
|
| 1740 |
+
"eval_runtime": 3.8781,
|
| 1741 |
+
"eval_samples_per_second": 46.414,
|
| 1742 |
+
"eval_steps_per_second": 1.547,
|
| 1743 |
+
"step": 1236
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 97.25490196078431,
|
| 1747 |
+
"grad_norm": 6.258754730224609,
|
| 1748 |
+
"learning_rate": 7.71604938271605e-06,
|
| 1749 |
+
"loss": 0.052,
|
| 1750 |
+
"step": 1240
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 97.96078431372548,
|
| 1754 |
+
"eval_accuracy": 0.8388888888888889,
|
| 1755 |
+
"eval_loss": 0.6511959433555603,
|
| 1756 |
+
"eval_runtime": 3.7767,
|
| 1757 |
+
"eval_samples_per_second": 47.661,
|
| 1758 |
+
"eval_steps_per_second": 1.589,
|
| 1759 |
+
"step": 1249
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 98.03921568627452,
|
| 1763 |
+
"grad_norm": 2.6569933891296387,
|
| 1764 |
+
"learning_rate": 7.330246913580248e-06,
|
| 1765 |
+
"loss": 0.0511,
|
| 1766 |
+
"step": 1250
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 98.82352941176471,
|
| 1770 |
+
"grad_norm": 6.5559306144714355,
|
| 1771 |
+
"learning_rate": 6.944444444444445e-06,
|
| 1772 |
+
"loss": 0.0383,
|
| 1773 |
+
"step": 1260
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 98.98039215686275,
|
| 1777 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1778 |
+
"eval_loss": 0.6781744360923767,
|
| 1779 |
+
"eval_runtime": 3.7667,
|
| 1780 |
+
"eval_samples_per_second": 47.787,
|
| 1781 |
+
"eval_steps_per_second": 1.593,
|
| 1782 |
+
"step": 1262
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 99.6078431372549,
|
| 1786 |
+
"grad_norm": 2.813370704650879,
|
| 1787 |
+
"learning_rate": 6.558641975308642e-06,
|
| 1788 |
+
"loss": 0.0499,
|
| 1789 |
+
"step": 1270
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 100.0,
|
| 1793 |
+
"eval_accuracy": 0.8277777777777777,
|
| 1794 |
+
"eval_loss": 0.6542291641235352,
|
| 1795 |
+
"eval_runtime": 3.8026,
|
| 1796 |
+
"eval_samples_per_second": 47.337,
|
| 1797 |
+
"eval_steps_per_second": 1.578,
|
| 1798 |
+
"step": 1275
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 100.3921568627451,
|
| 1802 |
+
"grad_norm": 16.95922088623047,
|
| 1803 |
+
"learning_rate": 6.172839506172839e-06,
|
| 1804 |
+
"loss": 0.0511,
|
| 1805 |
+
"step": 1280
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 100.94117647058823,
|
| 1809 |
+
"eval_accuracy": 0.8388888888888889,
|
| 1810 |
+
"eval_loss": 0.6794776320457458,
|
| 1811 |
+
"eval_runtime": 3.8468,
|
| 1812 |
+
"eval_samples_per_second": 46.793,
|
| 1813 |
+
"eval_steps_per_second": 1.56,
|
| 1814 |
+
"step": 1287
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 101.17647058823529,
|
| 1818 |
+
"grad_norm": 15.969926834106445,
|
| 1819 |
+
"learning_rate": 5.787037037037038e-06,
|
| 1820 |
+
"loss": 0.0527,
|
| 1821 |
+
"step": 1290
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 101.96078431372548,
|
| 1825 |
+
"grad_norm": 15.459400177001953,
|
| 1826 |
+
"learning_rate": 5.401234567901234e-06,
|
| 1827 |
+
"loss": 0.0452,
|
| 1828 |
+
"step": 1300
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 101.96078431372548,
|
| 1832 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1833 |
+
"eval_loss": 0.6739789247512817,
|
| 1834 |
+
"eval_runtime": 3.7395,
|
| 1835 |
+
"eval_samples_per_second": 48.135,
|
| 1836 |
+
"eval_steps_per_second": 1.605,
|
| 1837 |
+
"step": 1300
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 102.74509803921569,
|
| 1841 |
+
"grad_norm": 5.437152862548828,
|
| 1842 |
+
"learning_rate": 5.015432098765433e-06,
|
| 1843 |
+
"loss": 0.0475,
|
| 1844 |
+
"step": 1310
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 102.98039215686275,
|
| 1848 |
+
"eval_accuracy": 0.8388888888888889,
|
| 1849 |
+
"eval_loss": 0.6615740656852722,
|
| 1850 |
+
"eval_runtime": 3.7883,
|
| 1851 |
+
"eval_samples_per_second": 47.515,
|
| 1852 |
+
"eval_steps_per_second": 1.584,
|
| 1853 |
+
"step": 1313
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 103.52941176470588,
|
| 1857 |
+
"grad_norm": 12.730355262756348,
|
| 1858 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 1859 |
+
"loss": 0.0455,
|
| 1860 |
+
"step": 1320
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 104.0,
|
| 1864 |
+
"eval_accuracy": 0.8277777777777777,
|
| 1865 |
+
"eval_loss": 0.6490476131439209,
|
| 1866 |
+
"eval_runtime": 3.8157,
|
| 1867 |
+
"eval_samples_per_second": 47.173,
|
| 1868 |
+
"eval_steps_per_second": 1.572,
|
| 1869 |
+
"step": 1326
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 104.31372549019608,
|
| 1873 |
+
"grad_norm": 10.348357200622559,
|
| 1874 |
+
"learning_rate": 4.243827160493827e-06,
|
| 1875 |
+
"loss": 0.0486,
|
| 1876 |
+
"step": 1330
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 104.94117647058823,
|
| 1880 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1881 |
+
"eval_loss": 0.6331196427345276,
|
| 1882 |
+
"eval_runtime": 3.7919,
|
| 1883 |
+
"eval_samples_per_second": 47.469,
|
| 1884 |
+
"eval_steps_per_second": 1.582,
|
| 1885 |
+
"step": 1338
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 105.09803921568627,
|
| 1889 |
+
"grad_norm": 16.444259643554688,
|
| 1890 |
+
"learning_rate": 3.858024691358025e-06,
|
| 1891 |
+
"loss": 0.0442,
|
| 1892 |
+
"step": 1340
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 105.88235294117646,
|
| 1896 |
+
"grad_norm": 7.596277236938477,
|
| 1897 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 1898 |
+
"loss": 0.0585,
|
| 1899 |
+
"step": 1350
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 105.96078431372548,
|
| 1903 |
+
"eval_accuracy": 0.8333333333333334,
|
| 1904 |
+
"eval_loss": 0.6298839449882507,
|
| 1905 |
+
"eval_runtime": 3.7758,
|
| 1906 |
+
"eval_samples_per_second": 47.672,
|
| 1907 |
+
"eval_steps_per_second": 1.589,
|
| 1908 |
+
"step": 1351
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 106.66666666666667,
|
| 1912 |
+
"grad_norm": 13.853099822998047,
|
| 1913 |
+
"learning_rate": 3.0864197530864196e-06,
|
| 1914 |
+
"loss": 0.0549,
|
| 1915 |
+
"step": 1360
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 106.98039215686275,
|
| 1919 |
+
"eval_accuracy": 0.8277777777777777,
|
| 1920 |
+
"eval_loss": 0.6397578120231628,
|
| 1921 |
+
"eval_runtime": 3.7676,
|
| 1922 |
+
"eval_samples_per_second": 47.776,
|
| 1923 |
+
"eval_steps_per_second": 1.593,
|
| 1924 |
+
"step": 1364
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 107.45098039215686,
|
| 1928 |
+
"grad_norm": 10.11983871459961,
|
| 1929 |
+
"learning_rate": 2.700617283950617e-06,
|
| 1930 |
+
"loss": 0.0436,
|
| 1931 |
+
"step": 1370
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 108.0,
|
| 1935 |
+
"eval_accuracy": 0.8444444444444444,
|
| 1936 |
+
"eval_loss": 0.6338447332382202,
|
| 1937 |
+
"eval_runtime": 3.8768,
|
| 1938 |
+
"eval_samples_per_second": 46.43,
|
| 1939 |
+
"eval_steps_per_second": 1.548,
|
| 1940 |
+
"step": 1377
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 108.23529411764706,
|
| 1944 |
+
"grad_norm": 7.749964237213135,
|
| 1945 |
+
"learning_rate": 2.3148148148148148e-06,
|
| 1946 |
+
"loss": 0.0429,
|
| 1947 |
+
"step": 1380
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 108.94117647058823,
|
| 1951 |
+
"eval_accuracy": 0.8388888888888889,
|
| 1952 |
+
"eval_loss": 0.6458715796470642,
|
| 1953 |
+
"eval_runtime": 3.7687,
|
| 1954 |
+
"eval_samples_per_second": 47.762,
|
| 1955 |
+
"eval_steps_per_second": 1.592,
|
| 1956 |
+
"step": 1389
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 109.01960784313725,
|
| 1960 |
+
"grad_norm": 5.384810447692871,
|
| 1961 |
+
"learning_rate": 1.9290123456790124e-06,
|
| 1962 |
+
"loss": 0.047,
|
| 1963 |
+
"step": 1390
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 109.80392156862744,
|
| 1967 |
+
"grad_norm": 14.666231155395508,
|
| 1968 |
+
"learning_rate": 1.5432098765432098e-06,
|
| 1969 |
+
"loss": 0.0449,
|
| 1970 |
+
"step": 1400
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 109.96078431372548,
|
| 1974 |
+
"eval_accuracy": 0.8444444444444444,
|
| 1975 |
+
"eval_loss": 0.6469634175300598,
|
| 1976 |
+
"eval_runtime": 3.785,
|
| 1977 |
+
"eval_samples_per_second": 47.556,
|
| 1978 |
+
"eval_steps_per_second": 1.585,
|
| 1979 |
+
"step": 1402
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 110.58823529411765,
|
| 1983 |
+
"grad_norm": 11.94315242767334,
|
| 1984 |
+
"learning_rate": 1.1574074074074074e-06,
|
| 1985 |
+
"loss": 0.0559,
|
| 1986 |
+
"step": 1410
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 110.98039215686275,
|
| 1990 |
+
"eval_accuracy": 0.8388888888888889,
|
| 1991 |
+
"eval_loss": 0.646262526512146,
|
| 1992 |
+
"eval_runtime": 3.8809,
|
| 1993 |
+
"eval_samples_per_second": 46.381,
|
| 1994 |
+
"eval_steps_per_second": 1.546,
|
| 1995 |
+
"step": 1415
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 111.37254901960785,
|
| 1999 |
+
"grad_norm": 8.830354690551758,
|
| 2000 |
+
"learning_rate": 7.716049382716049e-07,
|
| 2001 |
+
"loss": 0.0378,
|
| 2002 |
+
"step": 1420
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 112.0,
|
| 2006 |
+
"eval_accuracy": 0.8388888888888889,
|
| 2007 |
+
"eval_loss": 0.6480041742324829,
|
| 2008 |
+
"eval_runtime": 3.8373,
|
| 2009 |
+
"eval_samples_per_second": 46.908,
|
| 2010 |
+
"eval_steps_per_second": 1.564,
|
| 2011 |
+
"step": 1428
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 112.15686274509804,
|
| 2015 |
+
"grad_norm": 16.867820739746094,
|
| 2016 |
+
"learning_rate": 3.8580246913580245e-07,
|
| 2017 |
+
"loss": 0.0509,
|
| 2018 |
+
"step": 1430
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 112.94117647058823,
|
| 2022 |
+
"grad_norm": 13.072942733764648,
|
| 2023 |
+
"learning_rate": 0.0,
|
| 2024 |
+
"loss": 0.0476,
|
| 2025 |
+
"step": 1440
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 112.94117647058823,
|
| 2029 |
+
"eval_accuracy": 0.8388888888888889,
|
| 2030 |
+
"eval_loss": 0.6477780342102051,
|
| 2031 |
+
"eval_runtime": 3.8103,
|
| 2032 |
+
"eval_samples_per_second": 47.24,
|
| 2033 |
+
"eval_steps_per_second": 1.575,
|
| 2034 |
+
"step": 1440
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 112.94117647058823,
|
| 2038 |
+
"step": 1440,
|
| 2039 |
+
"total_flos": 4.607069541812011e+18,
|
| 2040 |
+
"train_loss": 0.33674598841203585,
|
| 2041 |
+
"train_runtime": 5395.5485,
|
| 2042 |
+
"train_samples_per_second": 36.03,
|
| 2043 |
+
"train_steps_per_second": 0.267
|
| 2044 |
+
}
|
| 2045 |
+
],
|
| 2046 |
+
"logging_steps": 10,
|
| 2047 |
+
"max_steps": 1440,
|
| 2048 |
+
"num_input_tokens_seen": 0,
|
| 2049 |
+
"num_train_epochs": 120,
|
| 2050 |
+
"save_steps": 500,
|
| 2051 |
+
"stateful_callbacks": {
|
| 2052 |
+
"TrainerControl": {
|
| 2053 |
+
"args": {
|
| 2054 |
+
"should_epoch_stop": false,
|
| 2055 |
+
"should_evaluate": false,
|
| 2056 |
+
"should_log": false,
|
| 2057 |
+
"should_save": false,
|
| 2058 |
+
"should_training_stop": false
|
| 2059 |
+
},
|
| 2060 |
+
"attributes": {}
|
| 2061 |
+
}
|
| 2062 |
+
},
|
| 2063 |
+
"total_flos": 4.607069541812011e+18,
|
| 2064 |
+
"train_batch_size": 32,
|
| 2065 |
+
"trial_name": null,
|
| 2066 |
+
"trial_params": null
|
| 2067 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ffe697454969fea42d8c94b5e89fcef1b5d6a8daae4cb3b569683e18b42b2bd
|
| 3 |
+
size 5240
|