End of training
Browse files- README.md +277 -0
- all_results.json +13 -0
- config.json +63 -0
- eval_results.json +8 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- train_results.json +8 -0
- trainer_state.json +2068 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,277 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/swin-tiny-patch4-window7-224
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: swin-tiny-patch4-window7-224-finetuned-ADC-3cls-0922
|
| 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: test
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.8142857142857143
|
| 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 |
+
# swin-tiny-patch4-window7-224-finetuned-ADC-3cls-0922
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.6875
|
| 36 |
+
- Accuracy: 0.8143
|
| 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: 0.0001
|
| 56 |
+
- train_batch_size: 64
|
| 57 |
+
- eval_batch_size: 64
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 256
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_ratio: 0.2
|
| 64 |
+
- num_epochs: 200
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 1.0 | 2 | 1.0694 | 0.4143 |
|
| 71 |
+
| No log | 2.0 | 4 | 1.0689 | 0.4143 |
|
| 72 |
+
| No log | 3.0 | 6 | 1.0682 | 0.4143 |
|
| 73 |
+
| No log | 4.0 | 8 | 1.0671 | 0.4143 |
|
| 74 |
+
| 1.096 | 5.0 | 10 | 1.0657 | 0.4286 |
|
| 75 |
+
| 1.096 | 6.0 | 12 | 1.0640 | 0.4286 |
|
| 76 |
+
| 1.096 | 7.0 | 14 | 1.0621 | 0.4143 |
|
| 77 |
+
| 1.096 | 8.0 | 16 | 1.0598 | 0.4 |
|
| 78 |
+
| 1.096 | 9.0 | 18 | 1.0572 | 0.4 |
|
| 79 |
+
| 1.0906 | 10.0 | 20 | 1.0545 | 0.4 |
|
| 80 |
+
| 1.0906 | 11.0 | 22 | 1.0517 | 0.4143 |
|
| 81 |
+
| 1.0906 | 12.0 | 24 | 1.0486 | 0.4143 |
|
| 82 |
+
| 1.0906 | 13.0 | 26 | 1.0453 | 0.4143 |
|
| 83 |
+
| 1.0906 | 14.0 | 28 | 1.0418 | 0.4143 |
|
| 84 |
+
| 1.0647 | 15.0 | 30 | 1.0380 | 0.4143 |
|
| 85 |
+
| 1.0647 | 16.0 | 32 | 1.0343 | 0.4143 |
|
| 86 |
+
| 1.0647 | 17.0 | 34 | 1.0307 | 0.4143 |
|
| 87 |
+
| 1.0647 | 18.0 | 36 | 1.0268 | 0.4286 |
|
| 88 |
+
| 1.0647 | 19.0 | 38 | 1.0229 | 0.4286 |
|
| 89 |
+
| 1.0451 | 20.0 | 40 | 1.0191 | 0.4429 |
|
| 90 |
+
| 1.0451 | 21.0 | 42 | 1.0153 | 0.4571 |
|
| 91 |
+
| 1.0451 | 22.0 | 44 | 1.0116 | 0.4714 |
|
| 92 |
+
| 1.0451 | 23.0 | 46 | 1.0082 | 0.4714 |
|
| 93 |
+
| 1.0451 | 24.0 | 48 | 1.0049 | 0.4714 |
|
| 94 |
+
| 1.037 | 25.0 | 50 | 1.0016 | 0.4714 |
|
| 95 |
+
| 1.037 | 26.0 | 52 | 0.9979 | 0.4714 |
|
| 96 |
+
| 1.037 | 27.0 | 54 | 0.9944 | 0.4714 |
|
| 97 |
+
| 1.037 | 28.0 | 56 | 0.9913 | 0.4714 |
|
| 98 |
+
| 1.037 | 29.0 | 58 | 0.9883 | 0.4714 |
|
| 99 |
+
| 1.0214 | 30.0 | 60 | 0.9847 | 0.4714 |
|
| 100 |
+
| 1.0214 | 31.0 | 62 | 0.9809 | 0.4571 |
|
| 101 |
+
| 1.0214 | 32.0 | 64 | 0.9768 | 0.4714 |
|
| 102 |
+
| 1.0214 | 33.0 | 66 | 0.9723 | 0.4714 |
|
| 103 |
+
| 1.0214 | 34.0 | 68 | 0.9671 | 0.4714 |
|
| 104 |
+
| 1.0181 | 35.0 | 70 | 0.9616 | 0.4714 |
|
| 105 |
+
| 1.0181 | 36.0 | 72 | 0.9561 | 0.4857 |
|
| 106 |
+
| 1.0181 | 37.0 | 74 | 0.9505 | 0.5 |
|
| 107 |
+
| 1.0181 | 38.0 | 76 | 0.9446 | 0.5286 |
|
| 108 |
+
| 1.0181 | 39.0 | 78 | 0.9388 | 0.5286 |
|
| 109 |
+
| 0.9646 | 40.0 | 80 | 0.9331 | 0.5286 |
|
| 110 |
+
| 0.9646 | 41.0 | 82 | 0.9276 | 0.5143 |
|
| 111 |
+
| 0.9646 | 42.0 | 84 | 0.9224 | 0.5286 |
|
| 112 |
+
| 0.9646 | 43.0 | 86 | 0.9172 | 0.5286 |
|
| 113 |
+
| 0.9646 | 44.0 | 88 | 0.9120 | 0.5286 |
|
| 114 |
+
| 0.946 | 45.0 | 90 | 0.9070 | 0.5143 |
|
| 115 |
+
| 0.946 | 46.0 | 92 | 0.9021 | 0.5286 |
|
| 116 |
+
| 0.946 | 47.0 | 94 | 0.8976 | 0.5429 |
|
| 117 |
+
| 0.946 | 48.0 | 96 | 0.8933 | 0.5429 |
|
| 118 |
+
| 0.946 | 49.0 | 98 | 0.8891 | 0.5714 |
|
| 119 |
+
| 0.9244 | 50.0 | 100 | 0.8846 | 0.5714 |
|
| 120 |
+
| 0.9244 | 51.0 | 102 | 0.8803 | 0.5714 |
|
| 121 |
+
| 0.9244 | 52.0 | 104 | 0.8759 | 0.5714 |
|
| 122 |
+
| 0.9244 | 53.0 | 106 | 0.8716 | 0.5714 |
|
| 123 |
+
| 0.9244 | 54.0 | 108 | 0.8674 | 0.5714 |
|
| 124 |
+
| 0.9228 | 55.0 | 110 | 0.8634 | 0.5857 |
|
| 125 |
+
| 0.9228 | 56.0 | 112 | 0.8598 | 0.6 |
|
| 126 |
+
| 0.9228 | 57.0 | 114 | 0.8562 | 0.5857 |
|
| 127 |
+
| 0.9228 | 58.0 | 116 | 0.8527 | 0.6 |
|
| 128 |
+
| 0.9228 | 59.0 | 118 | 0.8492 | 0.6 |
|
| 129 |
+
| 0.8956 | 60.0 | 120 | 0.8456 | 0.6143 |
|
| 130 |
+
| 0.8956 | 61.0 | 122 | 0.8421 | 0.6 |
|
| 131 |
+
| 0.8956 | 62.0 | 124 | 0.8385 | 0.6 |
|
| 132 |
+
| 0.8956 | 63.0 | 126 | 0.8351 | 0.6 |
|
| 133 |
+
| 0.8956 | 64.0 | 128 | 0.8318 | 0.6143 |
|
| 134 |
+
| 0.8943 | 65.0 | 130 | 0.8286 | 0.6143 |
|
| 135 |
+
| 0.8943 | 66.0 | 132 | 0.8255 | 0.6 |
|
| 136 |
+
| 0.8943 | 67.0 | 134 | 0.8223 | 0.6286 |
|
| 137 |
+
| 0.8943 | 68.0 | 136 | 0.8191 | 0.6429 |
|
| 138 |
+
| 0.8943 | 69.0 | 138 | 0.8159 | 0.6286 |
|
| 139 |
+
| 0.854 | 70.0 | 140 | 0.8129 | 0.6429 |
|
| 140 |
+
| 0.854 | 71.0 | 142 | 0.8100 | 0.6714 |
|
| 141 |
+
| 0.854 | 72.0 | 144 | 0.8073 | 0.6714 |
|
| 142 |
+
| 0.854 | 73.0 | 146 | 0.8048 | 0.6571 |
|
| 143 |
+
| 0.854 | 74.0 | 148 | 0.8025 | 0.6714 |
|
| 144 |
+
| 0.8615 | 75.0 | 150 | 0.8001 | 0.6571 |
|
| 145 |
+
| 0.8615 | 76.0 | 152 | 0.7976 | 0.6571 |
|
| 146 |
+
| 0.8615 | 77.0 | 154 | 0.7952 | 0.6571 |
|
| 147 |
+
| 0.8615 | 78.0 | 156 | 0.7928 | 0.6571 |
|
| 148 |
+
| 0.8615 | 79.0 | 158 | 0.7904 | 0.6571 |
|
| 149 |
+
| 0.8507 | 80.0 | 160 | 0.7882 | 0.6714 |
|
| 150 |
+
| 0.8507 | 81.0 | 162 | 0.7858 | 0.6714 |
|
| 151 |
+
| 0.8507 | 82.0 | 164 | 0.7835 | 0.6857 |
|
| 152 |
+
| 0.8507 | 83.0 | 166 | 0.7811 | 0.6857 |
|
| 153 |
+
| 0.8507 | 84.0 | 168 | 0.7788 | 0.6857 |
|
| 154 |
+
| 0.838 | 85.0 | 170 | 0.7765 | 0.6857 |
|
| 155 |
+
| 0.838 | 86.0 | 172 | 0.7743 | 0.6857 |
|
| 156 |
+
| 0.838 | 87.0 | 174 | 0.7723 | 0.6857 |
|
| 157 |
+
| 0.838 | 88.0 | 176 | 0.7703 | 0.6857 |
|
| 158 |
+
| 0.838 | 89.0 | 178 | 0.7684 | 0.6857 |
|
| 159 |
+
| 0.8245 | 90.0 | 180 | 0.7664 | 0.6857 |
|
| 160 |
+
| 0.8245 | 91.0 | 182 | 0.7644 | 0.6857 |
|
| 161 |
+
| 0.8245 | 92.0 | 184 | 0.7625 | 0.6857 |
|
| 162 |
+
| 0.8245 | 93.0 | 186 | 0.7606 | 0.7143 |
|
| 163 |
+
| 0.8245 | 94.0 | 188 | 0.7587 | 0.7143 |
|
| 164 |
+
| 0.8124 | 95.0 | 190 | 0.7569 | 0.7143 |
|
| 165 |
+
| 0.8124 | 96.0 | 192 | 0.7551 | 0.7286 |
|
| 166 |
+
| 0.8124 | 97.0 | 194 | 0.7533 | 0.7286 |
|
| 167 |
+
| 0.8124 | 98.0 | 196 | 0.7517 | 0.7286 |
|
| 168 |
+
| 0.8124 | 99.0 | 198 | 0.7500 | 0.7429 |
|
| 169 |
+
| 0.8102 | 100.0 | 200 | 0.7483 | 0.7429 |
|
| 170 |
+
| 0.8102 | 101.0 | 202 | 0.7465 | 0.7429 |
|
| 171 |
+
| 0.8102 | 102.0 | 204 | 0.7450 | 0.7429 |
|
| 172 |
+
| 0.8102 | 103.0 | 206 | 0.7434 | 0.7429 |
|
| 173 |
+
| 0.8102 | 104.0 | 208 | 0.7419 | 0.7429 |
|
| 174 |
+
| 0.821 | 105.0 | 210 | 0.7404 | 0.7571 |
|
| 175 |
+
| 0.821 | 106.0 | 212 | 0.7389 | 0.7571 |
|
| 176 |
+
| 0.821 | 107.0 | 214 | 0.7374 | 0.7571 |
|
| 177 |
+
| 0.821 | 108.0 | 216 | 0.7359 | 0.7571 |
|
| 178 |
+
| 0.821 | 109.0 | 218 | 0.7345 | 0.7571 |
|
| 179 |
+
| 0.7918 | 110.0 | 220 | 0.7330 | 0.7571 |
|
| 180 |
+
| 0.7918 | 111.0 | 222 | 0.7316 | 0.7571 |
|
| 181 |
+
| 0.7918 | 112.0 | 224 | 0.7302 | 0.7571 |
|
| 182 |
+
| 0.7918 | 113.0 | 226 | 0.7289 | 0.7571 |
|
| 183 |
+
| 0.7918 | 114.0 | 228 | 0.7275 | 0.7571 |
|
| 184 |
+
| 0.8063 | 115.0 | 230 | 0.7262 | 0.7714 |
|
| 185 |
+
| 0.8063 | 116.0 | 232 | 0.7247 | 0.7714 |
|
| 186 |
+
| 0.8063 | 117.0 | 234 | 0.7232 | 0.7571 |
|
| 187 |
+
| 0.8063 | 118.0 | 236 | 0.7218 | 0.7571 |
|
| 188 |
+
| 0.8063 | 119.0 | 238 | 0.7204 | 0.7571 |
|
| 189 |
+
| 0.7897 | 120.0 | 240 | 0.7192 | 0.7571 |
|
| 190 |
+
| 0.7897 | 121.0 | 242 | 0.7180 | 0.7571 |
|
| 191 |
+
| 0.7897 | 122.0 | 244 | 0.7168 | 0.7571 |
|
| 192 |
+
| 0.7897 | 123.0 | 246 | 0.7158 | 0.7571 |
|
| 193 |
+
| 0.7897 | 124.0 | 248 | 0.7149 | 0.7714 |
|
| 194 |
+
| 0.7845 | 125.0 | 250 | 0.7140 | 0.7571 |
|
| 195 |
+
| 0.7845 | 126.0 | 252 | 0.7131 | 0.7571 |
|
| 196 |
+
| 0.7845 | 127.0 | 254 | 0.7121 | 0.7571 |
|
| 197 |
+
| 0.7845 | 128.0 | 256 | 0.7110 | 0.7571 |
|
| 198 |
+
| 0.7845 | 129.0 | 258 | 0.7099 | 0.7571 |
|
| 199 |
+
| 0.7781 | 130.0 | 260 | 0.7088 | 0.7571 |
|
| 200 |
+
| 0.7781 | 131.0 | 262 | 0.7076 | 0.7571 |
|
| 201 |
+
| 0.7781 | 132.0 | 264 | 0.7066 | 0.7571 |
|
| 202 |
+
| 0.7781 | 133.0 | 266 | 0.7055 | 0.7571 |
|
| 203 |
+
| 0.7781 | 134.0 | 268 | 0.7045 | 0.7714 |
|
| 204 |
+
| 0.7708 | 135.0 | 270 | 0.7034 | 0.7714 |
|
| 205 |
+
| 0.7708 | 136.0 | 272 | 0.7025 | 0.7571 |
|
| 206 |
+
| 0.7708 | 137.0 | 274 | 0.7016 | 0.7571 |
|
| 207 |
+
| 0.7708 | 138.0 | 276 | 0.7008 | 0.7571 |
|
| 208 |
+
| 0.7708 | 139.0 | 278 | 0.6999 | 0.7571 |
|
| 209 |
+
| 0.797 | 140.0 | 280 | 0.6990 | 0.7571 |
|
| 210 |
+
| 0.797 | 141.0 | 282 | 0.6981 | 0.7714 |
|
| 211 |
+
| 0.797 | 142.0 | 284 | 0.6973 | 0.7714 |
|
| 212 |
+
| 0.797 | 143.0 | 286 | 0.6966 | 0.7714 |
|
| 213 |
+
| 0.797 | 144.0 | 288 | 0.6959 | 0.7714 |
|
| 214 |
+
| 0.7768 | 145.0 | 290 | 0.6952 | 0.7714 |
|
| 215 |
+
| 0.7768 | 146.0 | 292 | 0.6944 | 0.7714 |
|
| 216 |
+
| 0.7768 | 147.0 | 294 | 0.6936 | 0.7714 |
|
| 217 |
+
| 0.7768 | 148.0 | 296 | 0.6928 | 0.7857 |
|
| 218 |
+
| 0.7768 | 149.0 | 298 | 0.6920 | 0.7857 |
|
| 219 |
+
| 0.7569 | 150.0 | 300 | 0.6912 | 0.7857 |
|
| 220 |
+
| 0.7569 | 151.0 | 302 | 0.6904 | 0.8 |
|
| 221 |
+
| 0.7569 | 152.0 | 304 | 0.6897 | 0.8 |
|
| 222 |
+
| 0.7569 | 153.0 | 306 | 0.6890 | 0.8 |
|
| 223 |
+
| 0.7569 | 154.0 | 308 | 0.6882 | 0.8 |
|
| 224 |
+
| 0.7807 | 155.0 | 310 | 0.6875 | 0.8143 |
|
| 225 |
+
| 0.7807 | 156.0 | 312 | 0.6868 | 0.8143 |
|
| 226 |
+
| 0.7807 | 157.0 | 314 | 0.6861 | 0.8143 |
|
| 227 |
+
| 0.7807 | 158.0 | 316 | 0.6854 | 0.8143 |
|
| 228 |
+
| 0.7807 | 159.0 | 318 | 0.6848 | 0.8143 |
|
| 229 |
+
| 0.7472 | 160.0 | 320 | 0.6842 | 0.8143 |
|
| 230 |
+
| 0.7472 | 161.0 | 322 | 0.6836 | 0.8143 |
|
| 231 |
+
| 0.7472 | 162.0 | 324 | 0.6831 | 0.8143 |
|
| 232 |
+
| 0.7472 | 163.0 | 326 | 0.6826 | 0.8143 |
|
| 233 |
+
| 0.7472 | 164.0 | 328 | 0.6822 | 0.8143 |
|
| 234 |
+
| 0.7665 | 165.0 | 330 | 0.6818 | 0.8 |
|
| 235 |
+
| 0.7665 | 166.0 | 332 | 0.6814 | 0.8 |
|
| 236 |
+
| 0.7665 | 167.0 | 334 | 0.6810 | 0.8 |
|
| 237 |
+
| 0.7665 | 168.0 | 336 | 0.6807 | 0.7857 |
|
| 238 |
+
| 0.7665 | 169.0 | 338 | 0.6803 | 0.7857 |
|
| 239 |
+
| 0.7684 | 170.0 | 340 | 0.6800 | 0.7857 |
|
| 240 |
+
| 0.7684 | 171.0 | 342 | 0.6797 | 0.7857 |
|
| 241 |
+
| 0.7684 | 172.0 | 344 | 0.6794 | 0.7857 |
|
| 242 |
+
| 0.7684 | 173.0 | 346 | 0.6790 | 0.7857 |
|
| 243 |
+
| 0.7684 | 174.0 | 348 | 0.6787 | 0.7857 |
|
| 244 |
+
| 0.7459 | 175.0 | 350 | 0.6784 | 0.7857 |
|
| 245 |
+
| 0.7459 | 176.0 | 352 | 0.6781 | 0.7857 |
|
| 246 |
+
| 0.7459 | 177.0 | 354 | 0.6778 | 0.7857 |
|
| 247 |
+
| 0.7459 | 178.0 | 356 | 0.6775 | 0.7857 |
|
| 248 |
+
| 0.7459 | 179.0 | 358 | 0.6772 | 0.7857 |
|
| 249 |
+
| 0.742 | 180.0 | 360 | 0.6769 | 0.7857 |
|
| 250 |
+
| 0.742 | 181.0 | 362 | 0.6766 | 0.7857 |
|
| 251 |
+
| 0.742 | 182.0 | 364 | 0.6764 | 0.7857 |
|
| 252 |
+
| 0.742 | 183.0 | 366 | 0.6762 | 0.7857 |
|
| 253 |
+
| 0.742 | 184.0 | 368 | 0.6760 | 0.7857 |
|
| 254 |
+
| 0.7642 | 185.0 | 370 | 0.6758 | 0.7857 |
|
| 255 |
+
| 0.7642 | 186.0 | 372 | 0.6756 | 0.7857 |
|
| 256 |
+
| 0.7642 | 187.0 | 374 | 0.6754 | 0.7857 |
|
| 257 |
+
| 0.7642 | 188.0 | 376 | 0.6752 | 0.7857 |
|
| 258 |
+
| 0.7642 | 189.0 | 378 | 0.6750 | 0.7857 |
|
| 259 |
+
| 0.7277 | 190.0 | 380 | 0.6749 | 0.7857 |
|
| 260 |
+
| 0.7277 | 191.0 | 382 | 0.6748 | 0.7857 |
|
| 261 |
+
| 0.7277 | 192.0 | 384 | 0.6746 | 0.7857 |
|
| 262 |
+
| 0.7277 | 193.0 | 386 | 0.6745 | 0.7857 |
|
| 263 |
+
| 0.7277 | 194.0 | 388 | 0.6745 | 0.7857 |
|
| 264 |
+
| 0.764 | 195.0 | 390 | 0.6744 | 0.7857 |
|
| 265 |
+
| 0.764 | 196.0 | 392 | 0.6743 | 0.7857 |
|
| 266 |
+
| 0.764 | 197.0 | 394 | 0.6742 | 0.7857 |
|
| 267 |
+
| 0.764 | 198.0 | 396 | 0.6742 | 0.8 |
|
| 268 |
+
| 0.764 | 199.0 | 398 | 0.6742 | 0.8 |
|
| 269 |
+
| 0.7444 | 200.0 | 400 | 0.6742 | 0.8 |
|
| 270 |
+
|
| 271 |
+
|
| 272 |
+
### Framework versions
|
| 273 |
+
|
| 274 |
+
- Transformers 4.33.2
|
| 275 |
+
- Pytorch 2.0.1+cu118
|
| 276 |
+
- Datasets 2.14.5
|
| 277 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 200.0,
|
| 3 |
+
"eval_accuracy": 0.8142857142857143,
|
| 4 |
+
"eval_loss": 0.6875176429748535,
|
| 5 |
+
"eval_runtime": 0.839,
|
| 6 |
+
"eval_samples_per_second": 83.432,
|
| 7 |
+
"eval_steps_per_second": 2.384,
|
| 8 |
+
"total_flos": 2.23710151698432e+18,
|
| 9 |
+
"train_loss": 0.8548950719833374,
|
| 10 |
+
"train_runtime": 1030.1946,
|
| 11 |
+
"train_samples_per_second": 87.362,
|
| 12 |
+
"train_steps_per_second": 0.388
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SwinForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"depths": [
|
| 8 |
+
2,
|
| 9 |
+
2,
|
| 10 |
+
6,
|
| 11 |
+
2
|
| 12 |
+
],
|
| 13 |
+
"drop_path_rate": 0.1,
|
| 14 |
+
"embed_dim": 96,
|
| 15 |
+
"encoder_stride": 32,
|
| 16 |
+
"hidden_act": "gelu",
|
| 17 |
+
"hidden_dropout_prob": 0.0,
|
| 18 |
+
"hidden_size": 768,
|
| 19 |
+
"id2label": {
|
| 20 |
+
"0": "Color",
|
| 21 |
+
"1": "Pattern_fail",
|
| 22 |
+
"2": "Residue"
|
| 23 |
+
},
|
| 24 |
+
"image_size": 224,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"label2id": {
|
| 27 |
+
"Color": 0,
|
| 28 |
+
"Pattern_fail": 1,
|
| 29 |
+
"Residue": 2
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-05,
|
| 32 |
+
"mlp_ratio": 4.0,
|
| 33 |
+
"model_type": "swin",
|
| 34 |
+
"num_channels": 3,
|
| 35 |
+
"num_heads": [
|
| 36 |
+
3,
|
| 37 |
+
6,
|
| 38 |
+
12,
|
| 39 |
+
24
|
| 40 |
+
],
|
| 41 |
+
"num_layers": 4,
|
| 42 |
+
"out_features": [
|
| 43 |
+
"stage4"
|
| 44 |
+
],
|
| 45 |
+
"out_indices": [
|
| 46 |
+
4
|
| 47 |
+
],
|
| 48 |
+
"patch_size": 4,
|
| 49 |
+
"path_norm": true,
|
| 50 |
+
"problem_type": "single_label_classification",
|
| 51 |
+
"qkv_bias": true,
|
| 52 |
+
"stage_names": [
|
| 53 |
+
"stem",
|
| 54 |
+
"stage1",
|
| 55 |
+
"stage2",
|
| 56 |
+
"stage3",
|
| 57 |
+
"stage4"
|
| 58 |
+
],
|
| 59 |
+
"torch_dtype": "float32",
|
| 60 |
+
"transformers_version": "4.33.2",
|
| 61 |
+
"use_absolute_embeddings": false,
|
| 62 |
+
"window_size": 7
|
| 63 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 200.0,
|
| 3 |
+
"eval_accuracy": 0.8142857142857143,
|
| 4 |
+
"eval_loss": 0.6875176429748535,
|
| 5 |
+
"eval_runtime": 0.839,
|
| 6 |
+
"eval_samples_per_second": 83.432,
|
| 7 |
+
"eval_steps_per_second": 2.384
|
| 8 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.485,
|
| 7 |
+
0.456,
|
| 8 |
+
0.406
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
+
],
|
| 16 |
+
"resample": 3,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b62d9ef2983c93a25662930965516fed575d4b4bf9ef9e40f118fd77873bd11f
|
| 3 |
+
size 110397937
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 200.0,
|
| 3 |
+
"total_flos": 2.23710151698432e+18,
|
| 4 |
+
"train_loss": 0.8548950719833374,
|
| 5 |
+
"train_runtime": 1030.1946,
|
| 6 |
+
"train_samples_per_second": 87.362,
|
| 7 |
+
"train_steps_per_second": 0.388
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2068 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8142857142857143,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-ADC-3cls-0922/checkpoint-310",
|
| 4 |
+
"epoch": 200.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.4142857142857143,
|
| 14 |
+
"eval_loss": 1.0693532228469849,
|
| 15 |
+
"eval_runtime": 1.0286,
|
| 16 |
+
"eval_samples_per_second": 68.056,
|
| 17 |
+
"eval_steps_per_second": 1.944,
|
| 18 |
+
"step": 2
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.4142857142857143,
|
| 23 |
+
"eval_loss": 1.0689432621002197,
|
| 24 |
+
"eval_runtime": 1.4012,
|
| 25 |
+
"eval_samples_per_second": 49.956,
|
| 26 |
+
"eval_steps_per_second": 1.427,
|
| 27 |
+
"step": 4
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.4142857142857143,
|
| 32 |
+
"eval_loss": 1.0682058334350586,
|
| 33 |
+
"eval_runtime": 0.8857,
|
| 34 |
+
"eval_samples_per_second": 79.031,
|
| 35 |
+
"eval_steps_per_second": 2.258,
|
| 36 |
+
"step": 6
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.4142857142857143,
|
| 41 |
+
"eval_loss": 1.0670955181121826,
|
| 42 |
+
"eval_runtime": 1.6997,
|
| 43 |
+
"eval_samples_per_second": 41.183,
|
| 44 |
+
"eval_steps_per_second": 1.177,
|
| 45 |
+
"step": 8
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.0,
|
| 49 |
+
"learning_rate": 1.25e-05,
|
| 50 |
+
"loss": 1.096,
|
| 51 |
+
"step": 10
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 5.0,
|
| 55 |
+
"eval_accuracy": 0.42857142857142855,
|
| 56 |
+
"eval_loss": 1.065665602684021,
|
| 57 |
+
"eval_runtime": 0.6117,
|
| 58 |
+
"eval_samples_per_second": 114.441,
|
| 59 |
+
"eval_steps_per_second": 3.27,
|
| 60 |
+
"step": 10
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 6.0,
|
| 64 |
+
"eval_accuracy": 0.42857142857142855,
|
| 65 |
+
"eval_loss": 1.0639806985855103,
|
| 66 |
+
"eval_runtime": 0.6447,
|
| 67 |
+
"eval_samples_per_second": 108.583,
|
| 68 |
+
"eval_steps_per_second": 3.102,
|
| 69 |
+
"step": 12
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 7.0,
|
| 73 |
+
"eval_accuracy": 0.4142857142857143,
|
| 74 |
+
"eval_loss": 1.0620665550231934,
|
| 75 |
+
"eval_runtime": 0.806,
|
| 76 |
+
"eval_samples_per_second": 86.844,
|
| 77 |
+
"eval_steps_per_second": 2.481,
|
| 78 |
+
"step": 14
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 8.0,
|
| 82 |
+
"eval_accuracy": 0.4,
|
| 83 |
+
"eval_loss": 1.0598403215408325,
|
| 84 |
+
"eval_runtime": 0.6374,
|
| 85 |
+
"eval_samples_per_second": 109.817,
|
| 86 |
+
"eval_steps_per_second": 3.138,
|
| 87 |
+
"step": 16
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 9.0,
|
| 91 |
+
"eval_accuracy": 0.4,
|
| 92 |
+
"eval_loss": 1.0572247505187988,
|
| 93 |
+
"eval_runtime": 0.6352,
|
| 94 |
+
"eval_samples_per_second": 110.2,
|
| 95 |
+
"eval_steps_per_second": 3.149,
|
| 96 |
+
"step": 18
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 10.0,
|
| 100 |
+
"learning_rate": 2.5e-05,
|
| 101 |
+
"loss": 1.0906,
|
| 102 |
+
"step": 20
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 10.0,
|
| 106 |
+
"eval_accuracy": 0.4,
|
| 107 |
+
"eval_loss": 1.0545086860656738,
|
| 108 |
+
"eval_runtime": 0.8412,
|
| 109 |
+
"eval_samples_per_second": 83.211,
|
| 110 |
+
"eval_steps_per_second": 2.377,
|
| 111 |
+
"step": 20
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 11.0,
|
| 115 |
+
"eval_accuracy": 0.4142857142857143,
|
| 116 |
+
"eval_loss": 1.0516999959945679,
|
| 117 |
+
"eval_runtime": 0.6382,
|
| 118 |
+
"eval_samples_per_second": 109.685,
|
| 119 |
+
"eval_steps_per_second": 3.134,
|
| 120 |
+
"step": 22
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 12.0,
|
| 124 |
+
"eval_accuracy": 0.4142857142857143,
|
| 125 |
+
"eval_loss": 1.0486340522766113,
|
| 126 |
+
"eval_runtime": 0.6383,
|
| 127 |
+
"eval_samples_per_second": 109.67,
|
| 128 |
+
"eval_steps_per_second": 3.133,
|
| 129 |
+
"step": 24
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 13.0,
|
| 133 |
+
"eval_accuracy": 0.4142857142857143,
|
| 134 |
+
"eval_loss": 1.045298457145691,
|
| 135 |
+
"eval_runtime": 0.8655,
|
| 136 |
+
"eval_samples_per_second": 80.883,
|
| 137 |
+
"eval_steps_per_second": 2.311,
|
| 138 |
+
"step": 26
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 14.0,
|
| 142 |
+
"eval_accuracy": 0.4142857142857143,
|
| 143 |
+
"eval_loss": 1.0417920351028442,
|
| 144 |
+
"eval_runtime": 0.64,
|
| 145 |
+
"eval_samples_per_second": 109.372,
|
| 146 |
+
"eval_steps_per_second": 3.125,
|
| 147 |
+
"step": 28
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 15.0,
|
| 151 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 152 |
+
"loss": 1.0647,
|
| 153 |
+
"step": 30
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 15.0,
|
| 157 |
+
"eval_accuracy": 0.4142857142857143,
|
| 158 |
+
"eval_loss": 1.0380207300186157,
|
| 159 |
+
"eval_runtime": 0.6461,
|
| 160 |
+
"eval_samples_per_second": 108.335,
|
| 161 |
+
"eval_steps_per_second": 3.095,
|
| 162 |
+
"step": 30
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 16.0,
|
| 166 |
+
"eval_accuracy": 0.4142857142857143,
|
| 167 |
+
"eval_loss": 1.0343334674835205,
|
| 168 |
+
"eval_runtime": 0.8283,
|
| 169 |
+
"eval_samples_per_second": 84.515,
|
| 170 |
+
"eval_steps_per_second": 2.415,
|
| 171 |
+
"step": 32
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 17.0,
|
| 175 |
+
"eval_accuracy": 0.4142857142857143,
|
| 176 |
+
"eval_loss": 1.030653953552246,
|
| 177 |
+
"eval_runtime": 0.6353,
|
| 178 |
+
"eval_samples_per_second": 110.181,
|
| 179 |
+
"eval_steps_per_second": 3.148,
|
| 180 |
+
"step": 34
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 18.0,
|
| 184 |
+
"eval_accuracy": 0.42857142857142855,
|
| 185 |
+
"eval_loss": 1.0267900228500366,
|
| 186 |
+
"eval_runtime": 0.6316,
|
| 187 |
+
"eval_samples_per_second": 110.829,
|
| 188 |
+
"eval_steps_per_second": 3.167,
|
| 189 |
+
"step": 36
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 19.0,
|
| 193 |
+
"eval_accuracy": 0.42857142857142855,
|
| 194 |
+
"eval_loss": 1.0229403972625732,
|
| 195 |
+
"eval_runtime": 1.4107,
|
| 196 |
+
"eval_samples_per_second": 49.619,
|
| 197 |
+
"eval_steps_per_second": 1.418,
|
| 198 |
+
"step": 38
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 20.0,
|
| 202 |
+
"learning_rate": 5e-05,
|
| 203 |
+
"loss": 1.0451,
|
| 204 |
+
"step": 40
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 20.0,
|
| 208 |
+
"eval_accuracy": 0.44285714285714284,
|
| 209 |
+
"eval_loss": 1.0190969705581665,
|
| 210 |
+
"eval_runtime": 0.6384,
|
| 211 |
+
"eval_samples_per_second": 109.648,
|
| 212 |
+
"eval_steps_per_second": 3.133,
|
| 213 |
+
"step": 40
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 21.0,
|
| 217 |
+
"eval_accuracy": 0.45714285714285713,
|
| 218 |
+
"eval_loss": 1.0152583122253418,
|
| 219 |
+
"eval_runtime": 0.6302,
|
| 220 |
+
"eval_samples_per_second": 111.074,
|
| 221 |
+
"eval_steps_per_second": 3.174,
|
| 222 |
+
"step": 42
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 22.0,
|
| 226 |
+
"eval_accuracy": 0.4714285714285714,
|
| 227 |
+
"eval_loss": 1.011588454246521,
|
| 228 |
+
"eval_runtime": 0.8016,
|
| 229 |
+
"eval_samples_per_second": 87.325,
|
| 230 |
+
"eval_steps_per_second": 2.495,
|
| 231 |
+
"step": 44
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 23.0,
|
| 235 |
+
"eval_accuracy": 0.4714285714285714,
|
| 236 |
+
"eval_loss": 1.0081889629364014,
|
| 237 |
+
"eval_runtime": 0.6258,
|
| 238 |
+
"eval_samples_per_second": 111.852,
|
| 239 |
+
"eval_steps_per_second": 3.196,
|
| 240 |
+
"step": 46
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 24.0,
|
| 244 |
+
"eval_accuracy": 0.4714285714285714,
|
| 245 |
+
"eval_loss": 1.0049412250518799,
|
| 246 |
+
"eval_runtime": 0.6247,
|
| 247 |
+
"eval_samples_per_second": 112.06,
|
| 248 |
+
"eval_steps_per_second": 3.202,
|
| 249 |
+
"step": 48
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 25.0,
|
| 253 |
+
"learning_rate": 6.25e-05,
|
| 254 |
+
"loss": 1.037,
|
| 255 |
+
"step": 50
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 25.0,
|
| 259 |
+
"eval_accuracy": 0.4714285714285714,
|
| 260 |
+
"eval_loss": 1.0015885829925537,
|
| 261 |
+
"eval_runtime": 0.8268,
|
| 262 |
+
"eval_samples_per_second": 84.66,
|
| 263 |
+
"eval_steps_per_second": 2.419,
|
| 264 |
+
"step": 50
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 26.0,
|
| 268 |
+
"eval_accuracy": 0.4714285714285714,
|
| 269 |
+
"eval_loss": 0.9978756308555603,
|
| 270 |
+
"eval_runtime": 0.635,
|
| 271 |
+
"eval_samples_per_second": 110.241,
|
| 272 |
+
"eval_steps_per_second": 3.15,
|
| 273 |
+
"step": 52
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 27.0,
|
| 277 |
+
"eval_accuracy": 0.4714285714285714,
|
| 278 |
+
"eval_loss": 0.9943951368331909,
|
| 279 |
+
"eval_runtime": 0.6443,
|
| 280 |
+
"eval_samples_per_second": 108.649,
|
| 281 |
+
"eval_steps_per_second": 3.104,
|
| 282 |
+
"step": 54
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 28.0,
|
| 286 |
+
"eval_accuracy": 0.4714285714285714,
|
| 287 |
+
"eval_loss": 0.9912726283073425,
|
| 288 |
+
"eval_runtime": 0.8063,
|
| 289 |
+
"eval_samples_per_second": 86.821,
|
| 290 |
+
"eval_steps_per_second": 2.481,
|
| 291 |
+
"step": 56
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 29.0,
|
| 295 |
+
"eval_accuracy": 0.4714285714285714,
|
| 296 |
+
"eval_loss": 0.9882513880729675,
|
| 297 |
+
"eval_runtime": 0.635,
|
| 298 |
+
"eval_samples_per_second": 110.236,
|
| 299 |
+
"eval_steps_per_second": 3.15,
|
| 300 |
+
"step": 58
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 30.0,
|
| 304 |
+
"learning_rate": 7.500000000000001e-05,
|
| 305 |
+
"loss": 1.0214,
|
| 306 |
+
"step": 60
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 30.0,
|
| 310 |
+
"eval_accuracy": 0.4714285714285714,
|
| 311 |
+
"eval_loss": 0.9846696257591248,
|
| 312 |
+
"eval_runtime": 0.6341,
|
| 313 |
+
"eval_samples_per_second": 110.395,
|
| 314 |
+
"eval_steps_per_second": 3.154,
|
| 315 |
+
"step": 60
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 31.0,
|
| 319 |
+
"eval_accuracy": 0.45714285714285713,
|
| 320 |
+
"eval_loss": 0.9809077382087708,
|
| 321 |
+
"eval_runtime": 0.8112,
|
| 322 |
+
"eval_samples_per_second": 86.297,
|
| 323 |
+
"eval_steps_per_second": 2.466,
|
| 324 |
+
"step": 62
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 32.0,
|
| 328 |
+
"eval_accuracy": 0.4714285714285714,
|
| 329 |
+
"eval_loss": 0.9768250584602356,
|
| 330 |
+
"eval_runtime": 0.6357,
|
| 331 |
+
"eval_samples_per_second": 110.106,
|
| 332 |
+
"eval_steps_per_second": 3.146,
|
| 333 |
+
"step": 64
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 33.0,
|
| 337 |
+
"eval_accuracy": 0.4714285714285714,
|
| 338 |
+
"eval_loss": 0.9722528457641602,
|
| 339 |
+
"eval_runtime": 0.6387,
|
| 340 |
+
"eval_samples_per_second": 109.603,
|
| 341 |
+
"eval_steps_per_second": 3.132,
|
| 342 |
+
"step": 66
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 34.0,
|
| 346 |
+
"eval_accuracy": 0.4714285714285714,
|
| 347 |
+
"eval_loss": 0.9670786261558533,
|
| 348 |
+
"eval_runtime": 0.83,
|
| 349 |
+
"eval_samples_per_second": 84.335,
|
| 350 |
+
"eval_steps_per_second": 2.41,
|
| 351 |
+
"step": 68
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 35.0,
|
| 355 |
+
"learning_rate": 8.75e-05,
|
| 356 |
+
"loss": 1.0181,
|
| 357 |
+
"step": 70
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 35.0,
|
| 361 |
+
"eval_accuracy": 0.4714285714285714,
|
| 362 |
+
"eval_loss": 0.9616244435310364,
|
| 363 |
+
"eval_runtime": 0.6343,
|
| 364 |
+
"eval_samples_per_second": 110.364,
|
| 365 |
+
"eval_steps_per_second": 3.153,
|
| 366 |
+
"step": 70
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 36.0,
|
| 370 |
+
"eval_accuracy": 0.4857142857142857,
|
| 371 |
+
"eval_loss": 0.9561253190040588,
|
| 372 |
+
"eval_runtime": 0.6551,
|
| 373 |
+
"eval_samples_per_second": 106.853,
|
| 374 |
+
"eval_steps_per_second": 3.053,
|
| 375 |
+
"step": 72
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 37.0,
|
| 379 |
+
"eval_accuracy": 0.5,
|
| 380 |
+
"eval_loss": 0.950469434261322,
|
| 381 |
+
"eval_runtime": 0.8176,
|
| 382 |
+
"eval_samples_per_second": 85.619,
|
| 383 |
+
"eval_steps_per_second": 2.446,
|
| 384 |
+
"step": 74
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 38.0,
|
| 388 |
+
"eval_accuracy": 0.5285714285714286,
|
| 389 |
+
"eval_loss": 0.9445714950561523,
|
| 390 |
+
"eval_runtime": 0.6352,
|
| 391 |
+
"eval_samples_per_second": 110.194,
|
| 392 |
+
"eval_steps_per_second": 3.148,
|
| 393 |
+
"step": 76
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 39.0,
|
| 397 |
+
"eval_accuracy": 0.5285714285714286,
|
| 398 |
+
"eval_loss": 0.9387871026992798,
|
| 399 |
+
"eval_runtime": 0.629,
|
| 400 |
+
"eval_samples_per_second": 111.283,
|
| 401 |
+
"eval_steps_per_second": 3.18,
|
| 402 |
+
"step": 78
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 40.0,
|
| 406 |
+
"learning_rate": 0.0001,
|
| 407 |
+
"loss": 0.9646,
|
| 408 |
+
"step": 80
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 40.0,
|
| 412 |
+
"eval_accuracy": 0.5285714285714286,
|
| 413 |
+
"eval_loss": 0.9331315159797668,
|
| 414 |
+
"eval_runtime": 0.8121,
|
| 415 |
+
"eval_samples_per_second": 86.194,
|
| 416 |
+
"eval_steps_per_second": 2.463,
|
| 417 |
+
"step": 80
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 41.0,
|
| 421 |
+
"eval_accuracy": 0.5142857142857142,
|
| 422 |
+
"eval_loss": 0.9276390075683594,
|
| 423 |
+
"eval_runtime": 0.6356,
|
| 424 |
+
"eval_samples_per_second": 110.129,
|
| 425 |
+
"eval_steps_per_second": 3.147,
|
| 426 |
+
"step": 82
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 42.0,
|
| 430 |
+
"eval_accuracy": 0.5285714285714286,
|
| 431 |
+
"eval_loss": 0.9224144220352173,
|
| 432 |
+
"eval_runtime": 0.6341,
|
| 433 |
+
"eval_samples_per_second": 110.396,
|
| 434 |
+
"eval_steps_per_second": 3.154,
|
| 435 |
+
"step": 84
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 43.0,
|
| 439 |
+
"eval_accuracy": 0.5285714285714286,
|
| 440 |
+
"eval_loss": 0.917235791683197,
|
| 441 |
+
"eval_runtime": 0.8135,
|
| 442 |
+
"eval_samples_per_second": 86.048,
|
| 443 |
+
"eval_steps_per_second": 2.459,
|
| 444 |
+
"step": 86
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 44.0,
|
| 448 |
+
"eval_accuracy": 0.5285714285714286,
|
| 449 |
+
"eval_loss": 0.9120003581047058,
|
| 450 |
+
"eval_runtime": 0.6333,
|
| 451 |
+
"eval_samples_per_second": 110.541,
|
| 452 |
+
"eval_steps_per_second": 3.158,
|
| 453 |
+
"step": 88
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 45.0,
|
| 457 |
+
"learning_rate": 9.687500000000001e-05,
|
| 458 |
+
"loss": 0.946,
|
| 459 |
+
"step": 90
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 45.0,
|
| 463 |
+
"eval_accuracy": 0.5142857142857142,
|
| 464 |
+
"eval_loss": 0.9070144891738892,
|
| 465 |
+
"eval_runtime": 0.6382,
|
| 466 |
+
"eval_samples_per_second": 109.685,
|
| 467 |
+
"eval_steps_per_second": 3.134,
|
| 468 |
+
"step": 90
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 46.0,
|
| 472 |
+
"eval_accuracy": 0.5285714285714286,
|
| 473 |
+
"eval_loss": 0.9021272659301758,
|
| 474 |
+
"eval_runtime": 0.8166,
|
| 475 |
+
"eval_samples_per_second": 85.719,
|
| 476 |
+
"eval_steps_per_second": 2.449,
|
| 477 |
+
"step": 92
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 47.0,
|
| 481 |
+
"eval_accuracy": 0.5428571428571428,
|
| 482 |
+
"eval_loss": 0.897597074508667,
|
| 483 |
+
"eval_runtime": 0.634,
|
| 484 |
+
"eval_samples_per_second": 110.411,
|
| 485 |
+
"eval_steps_per_second": 3.155,
|
| 486 |
+
"step": 94
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 48.0,
|
| 490 |
+
"eval_accuracy": 0.5428571428571428,
|
| 491 |
+
"eval_loss": 0.8932848572731018,
|
| 492 |
+
"eval_runtime": 0.6408,
|
| 493 |
+
"eval_samples_per_second": 109.231,
|
| 494 |
+
"eval_steps_per_second": 3.121,
|
| 495 |
+
"step": 96
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 49.0,
|
| 499 |
+
"eval_accuracy": 0.5714285714285714,
|
| 500 |
+
"eval_loss": 0.8890884518623352,
|
| 501 |
+
"eval_runtime": 0.8162,
|
| 502 |
+
"eval_samples_per_second": 85.76,
|
| 503 |
+
"eval_steps_per_second": 2.45,
|
| 504 |
+
"step": 98
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 50.0,
|
| 508 |
+
"learning_rate": 9.375e-05,
|
| 509 |
+
"loss": 0.9244,
|
| 510 |
+
"step": 100
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 50.0,
|
| 514 |
+
"eval_accuracy": 0.5714285714285714,
|
| 515 |
+
"eval_loss": 0.8845995664596558,
|
| 516 |
+
"eval_runtime": 0.6368,
|
| 517 |
+
"eval_samples_per_second": 109.929,
|
| 518 |
+
"eval_steps_per_second": 3.141,
|
| 519 |
+
"step": 100
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 51.0,
|
| 523 |
+
"eval_accuracy": 0.5714285714285714,
|
| 524 |
+
"eval_loss": 0.8802858591079712,
|
| 525 |
+
"eval_runtime": 0.6401,
|
| 526 |
+
"eval_samples_per_second": 109.353,
|
| 527 |
+
"eval_steps_per_second": 3.124,
|
| 528 |
+
"step": 102
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 52.0,
|
| 532 |
+
"eval_accuracy": 0.5714285714285714,
|
| 533 |
+
"eval_loss": 0.8758621215820312,
|
| 534 |
+
"eval_runtime": 0.8118,
|
| 535 |
+
"eval_samples_per_second": 86.227,
|
| 536 |
+
"eval_steps_per_second": 2.464,
|
| 537 |
+
"step": 104
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 53.0,
|
| 541 |
+
"eval_accuracy": 0.5714285714285714,
|
| 542 |
+
"eval_loss": 0.8715727925300598,
|
| 543 |
+
"eval_runtime": 0.6434,
|
| 544 |
+
"eval_samples_per_second": 108.8,
|
| 545 |
+
"eval_steps_per_second": 3.109,
|
| 546 |
+
"step": 106
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 54.0,
|
| 550 |
+
"eval_accuracy": 0.5714285714285714,
|
| 551 |
+
"eval_loss": 0.8674018383026123,
|
| 552 |
+
"eval_runtime": 0.63,
|
| 553 |
+
"eval_samples_per_second": 111.108,
|
| 554 |
+
"eval_steps_per_second": 3.175,
|
| 555 |
+
"step": 108
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 55.0,
|
| 559 |
+
"learning_rate": 9.062500000000001e-05,
|
| 560 |
+
"loss": 0.9228,
|
| 561 |
+
"step": 110
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 55.0,
|
| 565 |
+
"eval_accuracy": 0.5857142857142857,
|
| 566 |
+
"eval_loss": 0.86343914270401,
|
| 567 |
+
"eval_runtime": 0.7324,
|
| 568 |
+
"eval_samples_per_second": 95.574,
|
| 569 |
+
"eval_steps_per_second": 2.731,
|
| 570 |
+
"step": 110
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 56.0,
|
| 574 |
+
"eval_accuracy": 0.6,
|
| 575 |
+
"eval_loss": 0.8597754240036011,
|
| 576 |
+
"eval_runtime": 0.6359,
|
| 577 |
+
"eval_samples_per_second": 110.082,
|
| 578 |
+
"eval_steps_per_second": 3.145,
|
| 579 |
+
"step": 112
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 57.0,
|
| 583 |
+
"eval_accuracy": 0.5857142857142857,
|
| 584 |
+
"eval_loss": 0.8562148213386536,
|
| 585 |
+
"eval_runtime": 0.6308,
|
| 586 |
+
"eval_samples_per_second": 110.969,
|
| 587 |
+
"eval_steps_per_second": 3.171,
|
| 588 |
+
"step": 114
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 58.0,
|
| 592 |
+
"eval_accuracy": 0.6,
|
| 593 |
+
"eval_loss": 0.852704644203186,
|
| 594 |
+
"eval_runtime": 0.6483,
|
| 595 |
+
"eval_samples_per_second": 107.968,
|
| 596 |
+
"eval_steps_per_second": 3.085,
|
| 597 |
+
"step": 116
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 59.0,
|
| 601 |
+
"eval_accuracy": 0.6,
|
| 602 |
+
"eval_loss": 0.8491949439048767,
|
| 603 |
+
"eval_runtime": 0.7037,
|
| 604 |
+
"eval_samples_per_second": 99.48,
|
| 605 |
+
"eval_steps_per_second": 2.842,
|
| 606 |
+
"step": 118
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 60.0,
|
| 610 |
+
"learning_rate": 8.75e-05,
|
| 611 |
+
"loss": 0.8956,
|
| 612 |
+
"step": 120
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 60.0,
|
| 616 |
+
"eval_accuracy": 0.6142857142857143,
|
| 617 |
+
"eval_loss": 0.8456201553344727,
|
| 618 |
+
"eval_runtime": 0.6463,
|
| 619 |
+
"eval_samples_per_second": 108.309,
|
| 620 |
+
"eval_steps_per_second": 3.095,
|
| 621 |
+
"step": 120
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 61.0,
|
| 625 |
+
"eval_accuracy": 0.6,
|
| 626 |
+
"eval_loss": 0.8420506715774536,
|
| 627 |
+
"eval_runtime": 0.63,
|
| 628 |
+
"eval_samples_per_second": 111.119,
|
| 629 |
+
"eval_steps_per_second": 3.175,
|
| 630 |
+
"step": 122
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 62.0,
|
| 634 |
+
"eval_accuracy": 0.6,
|
| 635 |
+
"eval_loss": 0.8385196924209595,
|
| 636 |
+
"eval_runtime": 0.7958,
|
| 637 |
+
"eval_samples_per_second": 87.963,
|
| 638 |
+
"eval_steps_per_second": 2.513,
|
| 639 |
+
"step": 124
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 63.0,
|
| 643 |
+
"eval_accuracy": 0.6,
|
| 644 |
+
"eval_loss": 0.8351073861122131,
|
| 645 |
+
"eval_runtime": 0.6308,
|
| 646 |
+
"eval_samples_per_second": 110.971,
|
| 647 |
+
"eval_steps_per_second": 3.171,
|
| 648 |
+
"step": 126
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 64.0,
|
| 652 |
+
"eval_accuracy": 0.6142857142857143,
|
| 653 |
+
"eval_loss": 0.8317676186561584,
|
| 654 |
+
"eval_runtime": 0.6457,
|
| 655 |
+
"eval_samples_per_second": 108.412,
|
| 656 |
+
"eval_steps_per_second": 3.097,
|
| 657 |
+
"step": 128
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 65.0,
|
| 661 |
+
"learning_rate": 8.4375e-05,
|
| 662 |
+
"loss": 0.8943,
|
| 663 |
+
"step": 130
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 65.0,
|
| 667 |
+
"eval_accuracy": 0.6142857142857143,
|
| 668 |
+
"eval_loss": 0.8285678029060364,
|
| 669 |
+
"eval_runtime": 0.8132,
|
| 670 |
+
"eval_samples_per_second": 86.08,
|
| 671 |
+
"eval_steps_per_second": 2.459,
|
| 672 |
+
"step": 130
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 66.0,
|
| 676 |
+
"eval_accuracy": 0.6,
|
| 677 |
+
"eval_loss": 0.825462281703949,
|
| 678 |
+
"eval_runtime": 0.6417,
|
| 679 |
+
"eval_samples_per_second": 109.078,
|
| 680 |
+
"eval_steps_per_second": 3.117,
|
| 681 |
+
"step": 132
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 67.0,
|
| 685 |
+
"eval_accuracy": 0.6285714285714286,
|
| 686 |
+
"eval_loss": 0.8222988247871399,
|
| 687 |
+
"eval_runtime": 0.6393,
|
| 688 |
+
"eval_samples_per_second": 109.486,
|
| 689 |
+
"eval_steps_per_second": 3.128,
|
| 690 |
+
"step": 134
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 68.0,
|
| 694 |
+
"eval_accuracy": 0.6428571428571429,
|
| 695 |
+
"eval_loss": 0.8190925121307373,
|
| 696 |
+
"eval_runtime": 0.8213,
|
| 697 |
+
"eval_samples_per_second": 85.231,
|
| 698 |
+
"eval_steps_per_second": 2.435,
|
| 699 |
+
"step": 136
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 69.0,
|
| 703 |
+
"eval_accuracy": 0.6285714285714286,
|
| 704 |
+
"eval_loss": 0.8158699870109558,
|
| 705 |
+
"eval_runtime": 0.6409,
|
| 706 |
+
"eval_samples_per_second": 109.217,
|
| 707 |
+
"eval_steps_per_second": 3.12,
|
| 708 |
+
"step": 138
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 70.0,
|
| 712 |
+
"learning_rate": 8.125000000000001e-05,
|
| 713 |
+
"loss": 0.854,
|
| 714 |
+
"step": 140
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 70.0,
|
| 718 |
+
"eval_accuracy": 0.6428571428571429,
|
| 719 |
+
"eval_loss": 0.8128588199615479,
|
| 720 |
+
"eval_runtime": 0.6403,
|
| 721 |
+
"eval_samples_per_second": 109.332,
|
| 722 |
+
"eval_steps_per_second": 3.124,
|
| 723 |
+
"step": 140
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 71.0,
|
| 727 |
+
"eval_accuracy": 0.6714285714285714,
|
| 728 |
+
"eval_loss": 0.8099709749221802,
|
| 729 |
+
"eval_runtime": 0.8076,
|
| 730 |
+
"eval_samples_per_second": 86.675,
|
| 731 |
+
"eval_steps_per_second": 2.476,
|
| 732 |
+
"step": 142
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 72.0,
|
| 736 |
+
"eval_accuracy": 0.6714285714285714,
|
| 737 |
+
"eval_loss": 0.8072643280029297,
|
| 738 |
+
"eval_runtime": 0.6395,
|
| 739 |
+
"eval_samples_per_second": 109.469,
|
| 740 |
+
"eval_steps_per_second": 3.128,
|
| 741 |
+
"step": 144
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 73.0,
|
| 745 |
+
"eval_accuracy": 0.6571428571428571,
|
| 746 |
+
"eval_loss": 0.804807722568512,
|
| 747 |
+
"eval_runtime": 0.6346,
|
| 748 |
+
"eval_samples_per_second": 110.311,
|
| 749 |
+
"eval_steps_per_second": 3.152,
|
| 750 |
+
"step": 146
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 74.0,
|
| 754 |
+
"eval_accuracy": 0.6714285714285714,
|
| 755 |
+
"eval_loss": 0.8025286793708801,
|
| 756 |
+
"eval_runtime": 0.7964,
|
| 757 |
+
"eval_samples_per_second": 87.9,
|
| 758 |
+
"eval_steps_per_second": 2.511,
|
| 759 |
+
"step": 148
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 75.0,
|
| 763 |
+
"learning_rate": 7.8125e-05,
|
| 764 |
+
"loss": 0.8615,
|
| 765 |
+
"step": 150
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 75.0,
|
| 769 |
+
"eval_accuracy": 0.6571428571428571,
|
| 770 |
+
"eval_loss": 0.8000553250312805,
|
| 771 |
+
"eval_runtime": 0.6302,
|
| 772 |
+
"eval_samples_per_second": 111.077,
|
| 773 |
+
"eval_steps_per_second": 3.174,
|
| 774 |
+
"step": 150
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 76.0,
|
| 778 |
+
"eval_accuracy": 0.6571428571428571,
|
| 779 |
+
"eval_loss": 0.797595739364624,
|
| 780 |
+
"eval_runtime": 0.6315,
|
| 781 |
+
"eval_samples_per_second": 110.841,
|
| 782 |
+
"eval_steps_per_second": 3.167,
|
| 783 |
+
"step": 152
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 77.0,
|
| 787 |
+
"eval_accuracy": 0.6571428571428571,
|
| 788 |
+
"eval_loss": 0.795224130153656,
|
| 789 |
+
"eval_runtime": 0.7988,
|
| 790 |
+
"eval_samples_per_second": 87.627,
|
| 791 |
+
"eval_steps_per_second": 2.504,
|
| 792 |
+
"step": 154
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 78.0,
|
| 796 |
+
"eval_accuracy": 0.6571428571428571,
|
| 797 |
+
"eval_loss": 0.7928095459938049,
|
| 798 |
+
"eval_runtime": 0.6405,
|
| 799 |
+
"eval_samples_per_second": 109.291,
|
| 800 |
+
"eval_steps_per_second": 3.123,
|
| 801 |
+
"step": 156
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 79.0,
|
| 805 |
+
"eval_accuracy": 0.6571428571428571,
|
| 806 |
+
"eval_loss": 0.7904472351074219,
|
| 807 |
+
"eval_runtime": 0.6375,
|
| 808 |
+
"eval_samples_per_second": 109.802,
|
| 809 |
+
"eval_steps_per_second": 3.137,
|
| 810 |
+
"step": 158
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 80.0,
|
| 814 |
+
"learning_rate": 7.500000000000001e-05,
|
| 815 |
+
"loss": 0.8507,
|
| 816 |
+
"step": 160
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 80.0,
|
| 820 |
+
"eval_accuracy": 0.6714285714285714,
|
| 821 |
+
"eval_loss": 0.7881516218185425,
|
| 822 |
+
"eval_runtime": 0.8024,
|
| 823 |
+
"eval_samples_per_second": 87.237,
|
| 824 |
+
"eval_steps_per_second": 2.492,
|
| 825 |
+
"step": 160
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 81.0,
|
| 829 |
+
"eval_accuracy": 0.6714285714285714,
|
| 830 |
+
"eval_loss": 0.7857871055603027,
|
| 831 |
+
"eval_runtime": 0.6344,
|
| 832 |
+
"eval_samples_per_second": 110.338,
|
| 833 |
+
"eval_steps_per_second": 3.153,
|
| 834 |
+
"step": 162
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 82.0,
|
| 838 |
+
"eval_accuracy": 0.6857142857142857,
|
| 839 |
+
"eval_loss": 0.7834708094596863,
|
| 840 |
+
"eval_runtime": 0.6376,
|
| 841 |
+
"eval_samples_per_second": 109.781,
|
| 842 |
+
"eval_steps_per_second": 3.137,
|
| 843 |
+
"step": 164
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 83.0,
|
| 847 |
+
"eval_accuracy": 0.6857142857142857,
|
| 848 |
+
"eval_loss": 0.7811411023139954,
|
| 849 |
+
"eval_runtime": 0.8171,
|
| 850 |
+
"eval_samples_per_second": 85.665,
|
| 851 |
+
"eval_steps_per_second": 2.448,
|
| 852 |
+
"step": 166
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 84.0,
|
| 856 |
+
"eval_accuracy": 0.6857142857142857,
|
| 857 |
+
"eval_loss": 0.7788016200065613,
|
| 858 |
+
"eval_runtime": 0.6448,
|
| 859 |
+
"eval_samples_per_second": 108.552,
|
| 860 |
+
"eval_steps_per_second": 3.101,
|
| 861 |
+
"step": 168
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 85.0,
|
| 865 |
+
"learning_rate": 7.1875e-05,
|
| 866 |
+
"loss": 0.838,
|
| 867 |
+
"step": 170
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 85.0,
|
| 871 |
+
"eval_accuracy": 0.6857142857142857,
|
| 872 |
+
"eval_loss": 0.7765094041824341,
|
| 873 |
+
"eval_runtime": 0.6436,
|
| 874 |
+
"eval_samples_per_second": 108.77,
|
| 875 |
+
"eval_steps_per_second": 3.108,
|
| 876 |
+
"step": 170
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 86.0,
|
| 880 |
+
"eval_accuracy": 0.6857142857142857,
|
| 881 |
+
"eval_loss": 0.7743098139762878,
|
| 882 |
+
"eval_runtime": 0.8392,
|
| 883 |
+
"eval_samples_per_second": 83.412,
|
| 884 |
+
"eval_steps_per_second": 2.383,
|
| 885 |
+
"step": 172
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 87.0,
|
| 889 |
+
"eval_accuracy": 0.6857142857142857,
|
| 890 |
+
"eval_loss": 0.7722915410995483,
|
| 891 |
+
"eval_runtime": 0.6421,
|
| 892 |
+
"eval_samples_per_second": 109.013,
|
| 893 |
+
"eval_steps_per_second": 3.115,
|
| 894 |
+
"step": 174
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 88.0,
|
| 898 |
+
"eval_accuracy": 0.6857142857142857,
|
| 899 |
+
"eval_loss": 0.7703205943107605,
|
| 900 |
+
"eval_runtime": 0.6583,
|
| 901 |
+
"eval_samples_per_second": 106.337,
|
| 902 |
+
"eval_steps_per_second": 3.038,
|
| 903 |
+
"step": 176
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 89.0,
|
| 907 |
+
"eval_accuracy": 0.6857142857142857,
|
| 908 |
+
"eval_loss": 0.768402636051178,
|
| 909 |
+
"eval_runtime": 0.8092,
|
| 910 |
+
"eval_samples_per_second": 86.507,
|
| 911 |
+
"eval_steps_per_second": 2.472,
|
| 912 |
+
"step": 178
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 90.0,
|
| 916 |
+
"learning_rate": 6.875e-05,
|
| 917 |
+
"loss": 0.8245,
|
| 918 |
+
"step": 180
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 90.0,
|
| 922 |
+
"eval_accuracy": 0.6857142857142857,
|
| 923 |
+
"eval_loss": 0.7664420008659363,
|
| 924 |
+
"eval_runtime": 0.6321,
|
| 925 |
+
"eval_samples_per_second": 110.749,
|
| 926 |
+
"eval_steps_per_second": 3.164,
|
| 927 |
+
"step": 180
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 91.0,
|
| 931 |
+
"eval_accuracy": 0.6857142857142857,
|
| 932 |
+
"eval_loss": 0.7643933296203613,
|
| 933 |
+
"eval_runtime": 0.6416,
|
| 934 |
+
"eval_samples_per_second": 109.102,
|
| 935 |
+
"eval_steps_per_second": 3.117,
|
| 936 |
+
"step": 182
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 92.0,
|
| 940 |
+
"eval_accuracy": 0.6857142857142857,
|
| 941 |
+
"eval_loss": 0.7624573111534119,
|
| 942 |
+
"eval_runtime": 0.8206,
|
| 943 |
+
"eval_samples_per_second": 85.305,
|
| 944 |
+
"eval_steps_per_second": 2.437,
|
| 945 |
+
"step": 184
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 93.0,
|
| 949 |
+
"eval_accuracy": 0.7142857142857143,
|
| 950 |
+
"eval_loss": 0.7605774998664856,
|
| 951 |
+
"eval_runtime": 0.6303,
|
| 952 |
+
"eval_samples_per_second": 111.066,
|
| 953 |
+
"eval_steps_per_second": 3.173,
|
| 954 |
+
"step": 186
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 94.0,
|
| 958 |
+
"eval_accuracy": 0.7142857142857143,
|
| 959 |
+
"eval_loss": 0.7587181329727173,
|
| 960 |
+
"eval_runtime": 0.6487,
|
| 961 |
+
"eval_samples_per_second": 107.907,
|
| 962 |
+
"eval_steps_per_second": 3.083,
|
| 963 |
+
"step": 188
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 95.0,
|
| 967 |
+
"learning_rate": 6.562500000000001e-05,
|
| 968 |
+
"loss": 0.8124,
|
| 969 |
+
"step": 190
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 95.0,
|
| 973 |
+
"eval_accuracy": 0.7142857142857143,
|
| 974 |
+
"eval_loss": 0.75688236951828,
|
| 975 |
+
"eval_runtime": 0.83,
|
| 976 |
+
"eval_samples_per_second": 84.337,
|
| 977 |
+
"eval_steps_per_second": 2.41,
|
| 978 |
+
"step": 190
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 96.0,
|
| 982 |
+
"eval_accuracy": 0.7285714285714285,
|
| 983 |
+
"eval_loss": 0.755053699016571,
|
| 984 |
+
"eval_runtime": 0.6434,
|
| 985 |
+
"eval_samples_per_second": 108.8,
|
| 986 |
+
"eval_steps_per_second": 3.109,
|
| 987 |
+
"step": 192
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 97.0,
|
| 991 |
+
"eval_accuracy": 0.7285714285714285,
|
| 992 |
+
"eval_loss": 0.7533228993415833,
|
| 993 |
+
"eval_runtime": 0.6338,
|
| 994 |
+
"eval_samples_per_second": 110.439,
|
| 995 |
+
"eval_steps_per_second": 3.155,
|
| 996 |
+
"step": 194
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 98.0,
|
| 1000 |
+
"eval_accuracy": 0.7285714285714285,
|
| 1001 |
+
"eval_loss": 0.7516511082649231,
|
| 1002 |
+
"eval_runtime": 0.8125,
|
| 1003 |
+
"eval_samples_per_second": 86.157,
|
| 1004 |
+
"eval_steps_per_second": 2.462,
|
| 1005 |
+
"step": 196
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 99.0,
|
| 1009 |
+
"eval_accuracy": 0.7428571428571429,
|
| 1010 |
+
"eval_loss": 0.7499614953994751,
|
| 1011 |
+
"eval_runtime": 0.6565,
|
| 1012 |
+
"eval_samples_per_second": 106.632,
|
| 1013 |
+
"eval_steps_per_second": 3.047,
|
| 1014 |
+
"step": 198
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 100.0,
|
| 1018 |
+
"learning_rate": 6.25e-05,
|
| 1019 |
+
"loss": 0.8102,
|
| 1020 |
+
"step": 200
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 100.0,
|
| 1024 |
+
"eval_accuracy": 0.7428571428571429,
|
| 1025 |
+
"eval_loss": 0.7482544183731079,
|
| 1026 |
+
"eval_runtime": 0.6344,
|
| 1027 |
+
"eval_samples_per_second": 110.346,
|
| 1028 |
+
"eval_steps_per_second": 3.153,
|
| 1029 |
+
"step": 200
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 101.0,
|
| 1033 |
+
"eval_accuracy": 0.7428571428571429,
|
| 1034 |
+
"eval_loss": 0.7465088963508606,
|
| 1035 |
+
"eval_runtime": 0.8175,
|
| 1036 |
+
"eval_samples_per_second": 85.623,
|
| 1037 |
+
"eval_steps_per_second": 2.446,
|
| 1038 |
+
"step": 202
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 102.0,
|
| 1042 |
+
"eval_accuracy": 0.7428571428571429,
|
| 1043 |
+
"eval_loss": 0.7449584007263184,
|
| 1044 |
+
"eval_runtime": 0.6372,
|
| 1045 |
+
"eval_samples_per_second": 109.854,
|
| 1046 |
+
"eval_steps_per_second": 3.139,
|
| 1047 |
+
"step": 204
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 103.0,
|
| 1051 |
+
"eval_accuracy": 0.7428571428571429,
|
| 1052 |
+
"eval_loss": 0.7434430718421936,
|
| 1053 |
+
"eval_runtime": 0.6379,
|
| 1054 |
+
"eval_samples_per_second": 109.741,
|
| 1055 |
+
"eval_steps_per_second": 3.135,
|
| 1056 |
+
"step": 206
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 104.0,
|
| 1060 |
+
"eval_accuracy": 0.7428571428571429,
|
| 1061 |
+
"eval_loss": 0.7419188618659973,
|
| 1062 |
+
"eval_runtime": 0.8331,
|
| 1063 |
+
"eval_samples_per_second": 84.027,
|
| 1064 |
+
"eval_steps_per_second": 2.401,
|
| 1065 |
+
"step": 208
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 105.0,
|
| 1069 |
+
"learning_rate": 5.9375e-05,
|
| 1070 |
+
"loss": 0.821,
|
| 1071 |
+
"step": 210
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 105.0,
|
| 1075 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1076 |
+
"eval_loss": 0.7403832674026489,
|
| 1077 |
+
"eval_runtime": 0.6317,
|
| 1078 |
+
"eval_samples_per_second": 110.817,
|
| 1079 |
+
"eval_steps_per_second": 3.166,
|
| 1080 |
+
"step": 210
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 106.0,
|
| 1084 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1085 |
+
"eval_loss": 0.7388736605644226,
|
| 1086 |
+
"eval_runtime": 0.638,
|
| 1087 |
+
"eval_samples_per_second": 109.722,
|
| 1088 |
+
"eval_steps_per_second": 3.135,
|
| 1089 |
+
"step": 212
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 107.0,
|
| 1093 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1094 |
+
"eval_loss": 0.7374056577682495,
|
| 1095 |
+
"eval_runtime": 0.8271,
|
| 1096 |
+
"eval_samples_per_second": 84.63,
|
| 1097 |
+
"eval_steps_per_second": 2.418,
|
| 1098 |
+
"step": 214
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 108.0,
|
| 1102 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1103 |
+
"eval_loss": 0.7359411120414734,
|
| 1104 |
+
"eval_runtime": 0.6382,
|
| 1105 |
+
"eval_samples_per_second": 109.678,
|
| 1106 |
+
"eval_steps_per_second": 3.134,
|
| 1107 |
+
"step": 216
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 109.0,
|
| 1111 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1112 |
+
"eval_loss": 0.734478235244751,
|
| 1113 |
+
"eval_runtime": 0.6424,
|
| 1114 |
+
"eval_samples_per_second": 108.966,
|
| 1115 |
+
"eval_steps_per_second": 3.113,
|
| 1116 |
+
"step": 218
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 110.0,
|
| 1120 |
+
"learning_rate": 5.6250000000000005e-05,
|
| 1121 |
+
"loss": 0.7918,
|
| 1122 |
+
"step": 220
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 110.0,
|
| 1126 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1127 |
+
"eval_loss": 0.7330225110054016,
|
| 1128 |
+
"eval_runtime": 0.8294,
|
| 1129 |
+
"eval_samples_per_second": 84.398,
|
| 1130 |
+
"eval_steps_per_second": 2.411,
|
| 1131 |
+
"step": 220
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 111.0,
|
| 1135 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1136 |
+
"eval_loss": 0.7315928339958191,
|
| 1137 |
+
"eval_runtime": 0.6456,
|
| 1138 |
+
"eval_samples_per_second": 108.432,
|
| 1139 |
+
"eval_steps_per_second": 3.098,
|
| 1140 |
+
"step": 222
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 112.0,
|
| 1144 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1145 |
+
"eval_loss": 0.7302229404449463,
|
| 1146 |
+
"eval_runtime": 0.6368,
|
| 1147 |
+
"eval_samples_per_second": 109.931,
|
| 1148 |
+
"eval_steps_per_second": 3.141,
|
| 1149 |
+
"step": 224
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 113.0,
|
| 1153 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1154 |
+
"eval_loss": 0.7288532257080078,
|
| 1155 |
+
"eval_runtime": 0.8298,
|
| 1156 |
+
"eval_samples_per_second": 84.362,
|
| 1157 |
+
"eval_steps_per_second": 2.41,
|
| 1158 |
+
"step": 226
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 114.0,
|
| 1162 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1163 |
+
"eval_loss": 0.7275059223175049,
|
| 1164 |
+
"eval_runtime": 0.6447,
|
| 1165 |
+
"eval_samples_per_second": 108.584,
|
| 1166 |
+
"eval_steps_per_second": 3.102,
|
| 1167 |
+
"step": 228
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 115.0,
|
| 1171 |
+
"learning_rate": 5.3125000000000004e-05,
|
| 1172 |
+
"loss": 0.8063,
|
| 1173 |
+
"step": 230
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 115.0,
|
| 1177 |
+
"eval_accuracy": 0.7714285714285715,
|
| 1178 |
+
"eval_loss": 0.7261765599250793,
|
| 1179 |
+
"eval_runtime": 0.6376,
|
| 1180 |
+
"eval_samples_per_second": 109.779,
|
| 1181 |
+
"eval_steps_per_second": 3.137,
|
| 1182 |
+
"step": 230
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 116.0,
|
| 1186 |
+
"eval_accuracy": 0.7714285714285715,
|
| 1187 |
+
"eval_loss": 0.7246890068054199,
|
| 1188 |
+
"eval_runtime": 0.8093,
|
| 1189 |
+
"eval_samples_per_second": 86.498,
|
| 1190 |
+
"eval_steps_per_second": 2.471,
|
| 1191 |
+
"step": 232
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 117.0,
|
| 1195 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1196 |
+
"eval_loss": 0.7232338190078735,
|
| 1197 |
+
"eval_runtime": 0.6473,
|
| 1198 |
+
"eval_samples_per_second": 108.146,
|
| 1199 |
+
"eval_steps_per_second": 3.09,
|
| 1200 |
+
"step": 234
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 118.0,
|
| 1204 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1205 |
+
"eval_loss": 0.7218143939971924,
|
| 1206 |
+
"eval_runtime": 0.639,
|
| 1207 |
+
"eval_samples_per_second": 109.553,
|
| 1208 |
+
"eval_steps_per_second": 3.13,
|
| 1209 |
+
"step": 236
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 119.0,
|
| 1213 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1214 |
+
"eval_loss": 0.7204232811927795,
|
| 1215 |
+
"eval_runtime": 0.8245,
|
| 1216 |
+
"eval_samples_per_second": 84.902,
|
| 1217 |
+
"eval_steps_per_second": 2.426,
|
| 1218 |
+
"step": 238
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 120.0,
|
| 1222 |
+
"learning_rate": 5e-05,
|
| 1223 |
+
"loss": 0.7897,
|
| 1224 |
+
"step": 240
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 120.0,
|
| 1228 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1229 |
+
"eval_loss": 0.7191569209098816,
|
| 1230 |
+
"eval_runtime": 0.639,
|
| 1231 |
+
"eval_samples_per_second": 109.548,
|
| 1232 |
+
"eval_steps_per_second": 3.13,
|
| 1233 |
+
"step": 240
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 121.0,
|
| 1237 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1238 |
+
"eval_loss": 0.7179904580116272,
|
| 1239 |
+
"eval_runtime": 0.6313,
|
| 1240 |
+
"eval_samples_per_second": 110.887,
|
| 1241 |
+
"eval_steps_per_second": 3.168,
|
| 1242 |
+
"step": 242
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 122.0,
|
| 1246 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1247 |
+
"eval_loss": 0.7168429493904114,
|
| 1248 |
+
"eval_runtime": 0.8342,
|
| 1249 |
+
"eval_samples_per_second": 83.908,
|
| 1250 |
+
"eval_steps_per_second": 2.397,
|
| 1251 |
+
"step": 244
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 123.0,
|
| 1255 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1256 |
+
"eval_loss": 0.7157979011535645,
|
| 1257 |
+
"eval_runtime": 0.6333,
|
| 1258 |
+
"eval_samples_per_second": 110.541,
|
| 1259 |
+
"eval_steps_per_second": 3.158,
|
| 1260 |
+
"step": 246
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 124.0,
|
| 1264 |
+
"eval_accuracy": 0.7714285714285715,
|
| 1265 |
+
"eval_loss": 0.714880645275116,
|
| 1266 |
+
"eval_runtime": 0.6368,
|
| 1267 |
+
"eval_samples_per_second": 109.924,
|
| 1268 |
+
"eval_steps_per_second": 3.141,
|
| 1269 |
+
"step": 248
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 125.0,
|
| 1273 |
+
"learning_rate": 4.6875e-05,
|
| 1274 |
+
"loss": 0.7845,
|
| 1275 |
+
"step": 250
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 125.0,
|
| 1279 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1280 |
+
"eval_loss": 0.7140344381332397,
|
| 1281 |
+
"eval_runtime": 0.8287,
|
| 1282 |
+
"eval_samples_per_second": 84.466,
|
| 1283 |
+
"eval_steps_per_second": 2.413,
|
| 1284 |
+
"step": 250
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 126.0,
|
| 1288 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1289 |
+
"eval_loss": 0.7130730152130127,
|
| 1290 |
+
"eval_runtime": 0.6617,
|
| 1291 |
+
"eval_samples_per_second": 105.79,
|
| 1292 |
+
"eval_steps_per_second": 3.023,
|
| 1293 |
+
"step": 252
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 127.0,
|
| 1297 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1298 |
+
"eval_loss": 0.7120916247367859,
|
| 1299 |
+
"eval_runtime": 0.6392,
|
| 1300 |
+
"eval_samples_per_second": 109.509,
|
| 1301 |
+
"eval_steps_per_second": 3.129,
|
| 1302 |
+
"step": 254
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 128.0,
|
| 1306 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1307 |
+
"eval_loss": 0.7110173106193542,
|
| 1308 |
+
"eval_runtime": 0.8272,
|
| 1309 |
+
"eval_samples_per_second": 84.623,
|
| 1310 |
+
"eval_steps_per_second": 2.418,
|
| 1311 |
+
"step": 256
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 129.0,
|
| 1315 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1316 |
+
"eval_loss": 0.7099365592002869,
|
| 1317 |
+
"eval_runtime": 0.8513,
|
| 1318 |
+
"eval_samples_per_second": 82.229,
|
| 1319 |
+
"eval_steps_per_second": 2.349,
|
| 1320 |
+
"step": 258
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 130.0,
|
| 1324 |
+
"learning_rate": 4.375e-05,
|
| 1325 |
+
"loss": 0.7781,
|
| 1326 |
+
"step": 260
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 130.0,
|
| 1330 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1331 |
+
"eval_loss": 0.7087655663490295,
|
| 1332 |
+
"eval_runtime": 0.6529,
|
| 1333 |
+
"eval_samples_per_second": 107.222,
|
| 1334 |
+
"eval_steps_per_second": 3.063,
|
| 1335 |
+
"step": 260
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 131.0,
|
| 1339 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1340 |
+
"eval_loss": 0.7076297402381897,
|
| 1341 |
+
"eval_runtime": 0.633,
|
| 1342 |
+
"eval_samples_per_second": 110.582,
|
| 1343 |
+
"eval_steps_per_second": 3.159,
|
| 1344 |
+
"step": 262
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 132.0,
|
| 1348 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1349 |
+
"eval_loss": 0.706558883190155,
|
| 1350 |
+
"eval_runtime": 0.8161,
|
| 1351 |
+
"eval_samples_per_second": 85.772,
|
| 1352 |
+
"eval_steps_per_second": 2.451,
|
| 1353 |
+
"step": 264
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 133.0,
|
| 1357 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1358 |
+
"eval_loss": 0.7055317759513855,
|
| 1359 |
+
"eval_runtime": 0.6432,
|
| 1360 |
+
"eval_samples_per_second": 108.834,
|
| 1361 |
+
"eval_steps_per_second": 3.11,
|
| 1362 |
+
"step": 266
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 134.0,
|
| 1366 |
+
"eval_accuracy": 0.7714285714285715,
|
| 1367 |
+
"eval_loss": 0.7044604420661926,
|
| 1368 |
+
"eval_runtime": 0.6426,
|
| 1369 |
+
"eval_samples_per_second": 108.936,
|
| 1370 |
+
"eval_steps_per_second": 3.112,
|
| 1371 |
+
"step": 268
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 135.0,
|
| 1375 |
+
"learning_rate": 4.0625000000000005e-05,
|
| 1376 |
+
"loss": 0.7708,
|
| 1377 |
+
"step": 270
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 135.0,
|
| 1381 |
+
"eval_accuracy": 0.7714285714285715,
|
| 1382 |
+
"eval_loss": 0.7034193873405457,
|
| 1383 |
+
"eval_runtime": 0.8178,
|
| 1384 |
+
"eval_samples_per_second": 85.591,
|
| 1385 |
+
"eval_steps_per_second": 2.445,
|
| 1386 |
+
"step": 270
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 136.0,
|
| 1390 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1391 |
+
"eval_loss": 0.7024958729743958,
|
| 1392 |
+
"eval_runtime": 0.6353,
|
| 1393 |
+
"eval_samples_per_second": 110.186,
|
| 1394 |
+
"eval_steps_per_second": 3.148,
|
| 1395 |
+
"step": 272
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 137.0,
|
| 1399 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1400 |
+
"eval_loss": 0.7016207575798035,
|
| 1401 |
+
"eval_runtime": 0.632,
|
| 1402 |
+
"eval_samples_per_second": 110.758,
|
| 1403 |
+
"eval_steps_per_second": 3.165,
|
| 1404 |
+
"step": 274
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 138.0,
|
| 1408 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1409 |
+
"eval_loss": 0.7007526755332947,
|
| 1410 |
+
"eval_runtime": 0.8281,
|
| 1411 |
+
"eval_samples_per_second": 84.534,
|
| 1412 |
+
"eval_steps_per_second": 2.415,
|
| 1413 |
+
"step": 276
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 139.0,
|
| 1417 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1418 |
+
"eval_loss": 0.6998603343963623,
|
| 1419 |
+
"eval_runtime": 0.6379,
|
| 1420 |
+
"eval_samples_per_second": 109.736,
|
| 1421 |
+
"eval_steps_per_second": 3.135,
|
| 1422 |
+
"step": 278
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 140.0,
|
| 1426 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 1427 |
+
"loss": 0.797,
|
| 1428 |
+
"step": 280
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 140.0,
|
| 1432 |
+
"eval_accuracy": 0.7571428571428571,
|
| 1433 |
+
"eval_loss": 0.6989655494689941,
|
| 1434 |
+
"eval_runtime": 0.6404,
|
| 1435 |
+
"eval_samples_per_second": 109.303,
|
| 1436 |
+
"eval_steps_per_second": 3.123,
|
| 1437 |
+
"step": 280
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 141.0,
|
| 1441 |
+
"eval_accuracy": 0.7714285714285715,
|
| 1442 |
+
"eval_loss": 0.6981316804885864,
|
| 1443 |
+
"eval_runtime": 0.8143,
|
| 1444 |
+
"eval_samples_per_second": 85.963,
|
| 1445 |
+
"eval_steps_per_second": 2.456,
|
| 1446 |
+
"step": 282
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 142.0,
|
| 1450 |
+
"eval_accuracy": 0.7714285714285715,
|
| 1451 |
+
"eval_loss": 0.6973427534103394,
|
| 1452 |
+
"eval_runtime": 0.6382,
|
| 1453 |
+
"eval_samples_per_second": 109.681,
|
| 1454 |
+
"eval_steps_per_second": 3.134,
|
| 1455 |
+
"step": 284
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 143.0,
|
| 1459 |
+
"eval_accuracy": 0.7714285714285715,
|
| 1460 |
+
"eval_loss": 0.6966080069541931,
|
| 1461 |
+
"eval_runtime": 0.6394,
|
| 1462 |
+
"eval_samples_per_second": 109.471,
|
| 1463 |
+
"eval_steps_per_second": 3.128,
|
| 1464 |
+
"step": 286
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 144.0,
|
| 1468 |
+
"eval_accuracy": 0.7714285714285715,
|
| 1469 |
+
"eval_loss": 0.6958935856819153,
|
| 1470 |
+
"eval_runtime": 0.8183,
|
| 1471 |
+
"eval_samples_per_second": 85.546,
|
| 1472 |
+
"eval_steps_per_second": 2.444,
|
| 1473 |
+
"step": 288
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 145.0,
|
| 1477 |
+
"learning_rate": 3.4375e-05,
|
| 1478 |
+
"loss": 0.7768,
|
| 1479 |
+
"step": 290
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 145.0,
|
| 1483 |
+
"eval_accuracy": 0.7714285714285715,
|
| 1484 |
+
"eval_loss": 0.695166289806366,
|
| 1485 |
+
"eval_runtime": 0.6458,
|
| 1486 |
+
"eval_samples_per_second": 108.386,
|
| 1487 |
+
"eval_steps_per_second": 3.097,
|
| 1488 |
+
"step": 290
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 146.0,
|
| 1492 |
+
"eval_accuracy": 0.7714285714285715,
|
| 1493 |
+
"eval_loss": 0.694381833076477,
|
| 1494 |
+
"eval_runtime": 0.6351,
|
| 1495 |
+
"eval_samples_per_second": 110.21,
|
| 1496 |
+
"eval_steps_per_second": 3.149,
|
| 1497 |
+
"step": 292
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 147.0,
|
| 1501 |
+
"eval_accuracy": 0.7714285714285715,
|
| 1502 |
+
"eval_loss": 0.6935797333717346,
|
| 1503 |
+
"eval_runtime": 0.8207,
|
| 1504 |
+
"eval_samples_per_second": 85.29,
|
| 1505 |
+
"eval_steps_per_second": 2.437,
|
| 1506 |
+
"step": 294
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 148.0,
|
| 1510 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1511 |
+
"eval_loss": 0.6927558779716492,
|
| 1512 |
+
"eval_runtime": 0.6395,
|
| 1513 |
+
"eval_samples_per_second": 109.463,
|
| 1514 |
+
"eval_steps_per_second": 3.128,
|
| 1515 |
+
"step": 296
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 149.0,
|
| 1519 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1520 |
+
"eval_loss": 0.6919543147087097,
|
| 1521 |
+
"eval_runtime": 0.6322,
|
| 1522 |
+
"eval_samples_per_second": 110.727,
|
| 1523 |
+
"eval_steps_per_second": 3.164,
|
| 1524 |
+
"step": 298
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 150.0,
|
| 1528 |
+
"learning_rate": 3.125e-05,
|
| 1529 |
+
"loss": 0.7569,
|
| 1530 |
+
"step": 300
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 150.0,
|
| 1534 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1535 |
+
"eval_loss": 0.6911686658859253,
|
| 1536 |
+
"eval_runtime": 0.8112,
|
| 1537 |
+
"eval_samples_per_second": 86.294,
|
| 1538 |
+
"eval_steps_per_second": 2.466,
|
| 1539 |
+
"step": 300
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 151.0,
|
| 1543 |
+
"eval_accuracy": 0.8,
|
| 1544 |
+
"eval_loss": 0.6904271841049194,
|
| 1545 |
+
"eval_runtime": 0.6485,
|
| 1546 |
+
"eval_samples_per_second": 107.942,
|
| 1547 |
+
"eval_steps_per_second": 3.084,
|
| 1548 |
+
"step": 302
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 152.0,
|
| 1552 |
+
"eval_accuracy": 0.8,
|
| 1553 |
+
"eval_loss": 0.6896898150444031,
|
| 1554 |
+
"eval_runtime": 0.6429,
|
| 1555 |
+
"eval_samples_per_second": 108.878,
|
| 1556 |
+
"eval_steps_per_second": 3.111,
|
| 1557 |
+
"step": 304
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 153.0,
|
| 1561 |
+
"eval_accuracy": 0.8,
|
| 1562 |
+
"eval_loss": 0.688970148563385,
|
| 1563 |
+
"eval_runtime": 0.8248,
|
| 1564 |
+
"eval_samples_per_second": 84.872,
|
| 1565 |
+
"eval_steps_per_second": 2.425,
|
| 1566 |
+
"step": 306
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 154.0,
|
| 1570 |
+
"eval_accuracy": 0.8,
|
| 1571 |
+
"eval_loss": 0.6882473826408386,
|
| 1572 |
+
"eval_runtime": 0.6473,
|
| 1573 |
+
"eval_samples_per_second": 108.141,
|
| 1574 |
+
"eval_steps_per_second": 3.09,
|
| 1575 |
+
"step": 308
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 155.0,
|
| 1579 |
+
"learning_rate": 2.8125000000000003e-05,
|
| 1580 |
+
"loss": 0.7807,
|
| 1581 |
+
"step": 310
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 155.0,
|
| 1585 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1586 |
+
"eval_loss": 0.6875176429748535,
|
| 1587 |
+
"eval_runtime": 0.6211,
|
| 1588 |
+
"eval_samples_per_second": 112.707,
|
| 1589 |
+
"eval_steps_per_second": 3.22,
|
| 1590 |
+
"step": 310
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 156.0,
|
| 1594 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1595 |
+
"eval_loss": 0.6867862939834595,
|
| 1596 |
+
"eval_runtime": 0.8104,
|
| 1597 |
+
"eval_samples_per_second": 86.38,
|
| 1598 |
+
"eval_steps_per_second": 2.468,
|
| 1599 |
+
"step": 312
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 157.0,
|
| 1603 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1604 |
+
"eval_loss": 0.6860566139221191,
|
| 1605 |
+
"eval_runtime": 0.6376,
|
| 1606 |
+
"eval_samples_per_second": 109.79,
|
| 1607 |
+
"eval_steps_per_second": 3.137,
|
| 1608 |
+
"step": 314
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 158.0,
|
| 1612 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1613 |
+
"eval_loss": 0.6853832006454468,
|
| 1614 |
+
"eval_runtime": 0.6414,
|
| 1615 |
+
"eval_samples_per_second": 109.144,
|
| 1616 |
+
"eval_steps_per_second": 3.118,
|
| 1617 |
+
"step": 316
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 159.0,
|
| 1621 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1622 |
+
"eval_loss": 0.684758186340332,
|
| 1623 |
+
"eval_runtime": 0.8168,
|
| 1624 |
+
"eval_samples_per_second": 85.701,
|
| 1625 |
+
"eval_steps_per_second": 2.449,
|
| 1626 |
+
"step": 318
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 160.0,
|
| 1630 |
+
"learning_rate": 2.5e-05,
|
| 1631 |
+
"loss": 0.7472,
|
| 1632 |
+
"step": 320
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 160.0,
|
| 1636 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1637 |
+
"eval_loss": 0.6841580867767334,
|
| 1638 |
+
"eval_runtime": 0.6398,
|
| 1639 |
+
"eval_samples_per_second": 109.413,
|
| 1640 |
+
"eval_steps_per_second": 3.126,
|
| 1641 |
+
"step": 320
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 161.0,
|
| 1645 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1646 |
+
"eval_loss": 0.6836223006248474,
|
| 1647 |
+
"eval_runtime": 0.6529,
|
| 1648 |
+
"eval_samples_per_second": 107.211,
|
| 1649 |
+
"eval_steps_per_second": 3.063,
|
| 1650 |
+
"step": 322
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 162.0,
|
| 1654 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1655 |
+
"eval_loss": 0.683104932308197,
|
| 1656 |
+
"eval_runtime": 0.8258,
|
| 1657 |
+
"eval_samples_per_second": 84.764,
|
| 1658 |
+
"eval_steps_per_second": 2.422,
|
| 1659 |
+
"step": 324
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 163.0,
|
| 1663 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1664 |
+
"eval_loss": 0.6826251745223999,
|
| 1665 |
+
"eval_runtime": 0.6361,
|
| 1666 |
+
"eval_samples_per_second": 110.054,
|
| 1667 |
+
"eval_steps_per_second": 3.144,
|
| 1668 |
+
"step": 326
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 164.0,
|
| 1672 |
+
"eval_accuracy": 0.8142857142857143,
|
| 1673 |
+
"eval_loss": 0.6821797490119934,
|
| 1674 |
+
"eval_runtime": 0.6381,
|
| 1675 |
+
"eval_samples_per_second": 109.703,
|
| 1676 |
+
"eval_steps_per_second": 3.134,
|
| 1677 |
+
"step": 328
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 165.0,
|
| 1681 |
+
"learning_rate": 2.1875e-05,
|
| 1682 |
+
"loss": 0.7665,
|
| 1683 |
+
"step": 330
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 165.0,
|
| 1687 |
+
"eval_accuracy": 0.8,
|
| 1688 |
+
"eval_loss": 0.6817546486854553,
|
| 1689 |
+
"eval_runtime": 0.8246,
|
| 1690 |
+
"eval_samples_per_second": 84.889,
|
| 1691 |
+
"eval_steps_per_second": 2.425,
|
| 1692 |
+
"step": 330
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 166.0,
|
| 1696 |
+
"eval_accuracy": 0.8,
|
| 1697 |
+
"eval_loss": 0.6813837885856628,
|
| 1698 |
+
"eval_runtime": 0.6625,
|
| 1699 |
+
"eval_samples_per_second": 105.654,
|
| 1700 |
+
"eval_steps_per_second": 3.019,
|
| 1701 |
+
"step": 332
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 167.0,
|
| 1705 |
+
"eval_accuracy": 0.8,
|
| 1706 |
+
"eval_loss": 0.681039035320282,
|
| 1707 |
+
"eval_runtime": 0.6385,
|
| 1708 |
+
"eval_samples_per_second": 109.638,
|
| 1709 |
+
"eval_steps_per_second": 3.133,
|
| 1710 |
+
"step": 334
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 168.0,
|
| 1714 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1715 |
+
"eval_loss": 0.6806796193122864,
|
| 1716 |
+
"eval_runtime": 0.8294,
|
| 1717 |
+
"eval_samples_per_second": 84.403,
|
| 1718 |
+
"eval_steps_per_second": 2.412,
|
| 1719 |
+
"step": 336
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 169.0,
|
| 1723 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1724 |
+
"eval_loss": 0.680313766002655,
|
| 1725 |
+
"eval_runtime": 0.6312,
|
| 1726 |
+
"eval_samples_per_second": 110.896,
|
| 1727 |
+
"eval_steps_per_second": 3.168,
|
| 1728 |
+
"step": 338
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 170.0,
|
| 1732 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 1733 |
+
"loss": 0.7684,
|
| 1734 |
+
"step": 340
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 170.0,
|
| 1738 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1739 |
+
"eval_loss": 0.6799898743629456,
|
| 1740 |
+
"eval_runtime": 0.6322,
|
| 1741 |
+
"eval_samples_per_second": 110.721,
|
| 1742 |
+
"eval_steps_per_second": 3.163,
|
| 1743 |
+
"step": 340
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 171.0,
|
| 1747 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1748 |
+
"eval_loss": 0.6796825528144836,
|
| 1749 |
+
"eval_runtime": 0.8381,
|
| 1750 |
+
"eval_samples_per_second": 83.525,
|
| 1751 |
+
"eval_steps_per_second": 2.386,
|
| 1752 |
+
"step": 342
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 172.0,
|
| 1756 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1757 |
+
"eval_loss": 0.6793543696403503,
|
| 1758 |
+
"eval_runtime": 0.6493,
|
| 1759 |
+
"eval_samples_per_second": 107.81,
|
| 1760 |
+
"eval_steps_per_second": 3.08,
|
| 1761 |
+
"step": 344
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 173.0,
|
| 1765 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1766 |
+
"eval_loss": 0.6790363192558289,
|
| 1767 |
+
"eval_runtime": 0.6451,
|
| 1768 |
+
"eval_samples_per_second": 108.504,
|
| 1769 |
+
"eval_steps_per_second": 3.1,
|
| 1770 |
+
"step": 346
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 174.0,
|
| 1774 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1775 |
+
"eval_loss": 0.6787369847297668,
|
| 1776 |
+
"eval_runtime": 0.8298,
|
| 1777 |
+
"eval_samples_per_second": 84.361,
|
| 1778 |
+
"eval_steps_per_second": 2.41,
|
| 1779 |
+
"step": 348
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 175.0,
|
| 1783 |
+
"learning_rate": 1.5625e-05,
|
| 1784 |
+
"loss": 0.7459,
|
| 1785 |
+
"step": 350
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 175.0,
|
| 1789 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1790 |
+
"eval_loss": 0.6784414052963257,
|
| 1791 |
+
"eval_runtime": 0.6607,
|
| 1792 |
+
"eval_samples_per_second": 105.953,
|
| 1793 |
+
"eval_steps_per_second": 3.027,
|
| 1794 |
+
"step": 350
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 176.0,
|
| 1798 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1799 |
+
"eval_loss": 0.6781107783317566,
|
| 1800 |
+
"eval_runtime": 0.681,
|
| 1801 |
+
"eval_samples_per_second": 102.789,
|
| 1802 |
+
"eval_steps_per_second": 2.937,
|
| 1803 |
+
"step": 352
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 177.0,
|
| 1807 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1808 |
+
"eval_loss": 0.677795946598053,
|
| 1809 |
+
"eval_runtime": 0.8379,
|
| 1810 |
+
"eval_samples_per_second": 83.54,
|
| 1811 |
+
"eval_steps_per_second": 2.387,
|
| 1812 |
+
"step": 354
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 178.0,
|
| 1816 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1817 |
+
"eval_loss": 0.6774783730506897,
|
| 1818 |
+
"eval_runtime": 0.6408,
|
| 1819 |
+
"eval_samples_per_second": 109.247,
|
| 1820 |
+
"eval_steps_per_second": 3.121,
|
| 1821 |
+
"step": 356
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 179.0,
|
| 1825 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1826 |
+
"eval_loss": 0.6771765351295471,
|
| 1827 |
+
"eval_runtime": 0.6403,
|
| 1828 |
+
"eval_samples_per_second": 109.315,
|
| 1829 |
+
"eval_steps_per_second": 3.123,
|
| 1830 |
+
"step": 358
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 180.0,
|
| 1834 |
+
"learning_rate": 1.25e-05,
|
| 1835 |
+
"loss": 0.742,
|
| 1836 |
+
"step": 360
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 180.0,
|
| 1840 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1841 |
+
"eval_loss": 0.6768958568572998,
|
| 1842 |
+
"eval_runtime": 0.8321,
|
| 1843 |
+
"eval_samples_per_second": 84.126,
|
| 1844 |
+
"eval_steps_per_second": 2.404,
|
| 1845 |
+
"step": 360
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 181.0,
|
| 1849 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1850 |
+
"eval_loss": 0.6766448616981506,
|
| 1851 |
+
"eval_runtime": 0.6364,
|
| 1852 |
+
"eval_samples_per_second": 110.0,
|
| 1853 |
+
"eval_steps_per_second": 3.143,
|
| 1854 |
+
"step": 362
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 182.0,
|
| 1858 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1859 |
+
"eval_loss": 0.6764284372329712,
|
| 1860 |
+
"eval_runtime": 0.647,
|
| 1861 |
+
"eval_samples_per_second": 108.196,
|
| 1862 |
+
"eval_steps_per_second": 3.091,
|
| 1863 |
+
"step": 364
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 183.0,
|
| 1867 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1868 |
+
"eval_loss": 0.6762242913246155,
|
| 1869 |
+
"eval_runtime": 0.8597,
|
| 1870 |
+
"eval_samples_per_second": 81.422,
|
| 1871 |
+
"eval_steps_per_second": 2.326,
|
| 1872 |
+
"step": 366
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 184.0,
|
| 1876 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1877 |
+
"eval_loss": 0.6760057806968689,
|
| 1878 |
+
"eval_runtime": 0.651,
|
| 1879 |
+
"eval_samples_per_second": 107.527,
|
| 1880 |
+
"eval_steps_per_second": 3.072,
|
| 1881 |
+
"step": 368
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 185.0,
|
| 1885 |
+
"learning_rate": 9.375000000000001e-06,
|
| 1886 |
+
"loss": 0.7642,
|
| 1887 |
+
"step": 370
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 185.0,
|
| 1891 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1892 |
+
"eval_loss": 0.6757904291152954,
|
| 1893 |
+
"eval_runtime": 0.6445,
|
| 1894 |
+
"eval_samples_per_second": 108.618,
|
| 1895 |
+
"eval_steps_per_second": 3.103,
|
| 1896 |
+
"step": 370
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 186.0,
|
| 1900 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1901 |
+
"eval_loss": 0.6755796670913696,
|
| 1902 |
+
"eval_runtime": 0.8335,
|
| 1903 |
+
"eval_samples_per_second": 83.986,
|
| 1904 |
+
"eval_steps_per_second": 2.4,
|
| 1905 |
+
"step": 372
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 187.0,
|
| 1909 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1910 |
+
"eval_loss": 0.6753801107406616,
|
| 1911 |
+
"eval_runtime": 0.6394,
|
| 1912 |
+
"eval_samples_per_second": 109.479,
|
| 1913 |
+
"eval_steps_per_second": 3.128,
|
| 1914 |
+
"step": 374
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 188.0,
|
| 1918 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1919 |
+
"eval_loss": 0.6752031445503235,
|
| 1920 |
+
"eval_runtime": 0.658,
|
| 1921 |
+
"eval_samples_per_second": 106.386,
|
| 1922 |
+
"eval_steps_per_second": 3.04,
|
| 1923 |
+
"step": 376
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 189.0,
|
| 1927 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1928 |
+
"eval_loss": 0.6750344634056091,
|
| 1929 |
+
"eval_runtime": 0.8422,
|
| 1930 |
+
"eval_samples_per_second": 83.112,
|
| 1931 |
+
"eval_steps_per_second": 2.375,
|
| 1932 |
+
"step": 378
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 190.0,
|
| 1936 |
+
"learning_rate": 6.25e-06,
|
| 1937 |
+
"loss": 0.7277,
|
| 1938 |
+
"step": 380
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 190.0,
|
| 1942 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1943 |
+
"eval_loss": 0.674885094165802,
|
| 1944 |
+
"eval_runtime": 0.6493,
|
| 1945 |
+
"eval_samples_per_second": 107.808,
|
| 1946 |
+
"eval_steps_per_second": 3.08,
|
| 1947 |
+
"step": 380
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 191.0,
|
| 1951 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1952 |
+
"eval_loss": 0.6747546195983887,
|
| 1953 |
+
"eval_runtime": 0.6429,
|
| 1954 |
+
"eval_samples_per_second": 108.875,
|
| 1955 |
+
"eval_steps_per_second": 3.111,
|
| 1956 |
+
"step": 382
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 192.0,
|
| 1960 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1961 |
+
"eval_loss": 0.6746455430984497,
|
| 1962 |
+
"eval_runtime": 0.8305,
|
| 1963 |
+
"eval_samples_per_second": 84.289,
|
| 1964 |
+
"eval_steps_per_second": 2.408,
|
| 1965 |
+
"step": 384
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 193.0,
|
| 1969 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1970 |
+
"eval_loss": 0.6745493412017822,
|
| 1971 |
+
"eval_runtime": 0.6551,
|
| 1972 |
+
"eval_samples_per_second": 106.855,
|
| 1973 |
+
"eval_steps_per_second": 3.053,
|
| 1974 |
+
"step": 386
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 194.0,
|
| 1978 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1979 |
+
"eval_loss": 0.6744527816772461,
|
| 1980 |
+
"eval_runtime": 0.6428,
|
| 1981 |
+
"eval_samples_per_second": 108.896,
|
| 1982 |
+
"eval_steps_per_second": 3.111,
|
| 1983 |
+
"step": 388
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 195.0,
|
| 1987 |
+
"learning_rate": 3.125e-06,
|
| 1988 |
+
"loss": 0.764,
|
| 1989 |
+
"step": 390
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 195.0,
|
| 1993 |
+
"eval_accuracy": 0.7857142857142857,
|
| 1994 |
+
"eval_loss": 0.6743654608726501,
|
| 1995 |
+
"eval_runtime": 0.8334,
|
| 1996 |
+
"eval_samples_per_second": 83.991,
|
| 1997 |
+
"eval_steps_per_second": 2.4,
|
| 1998 |
+
"step": 390
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 196.0,
|
| 2002 |
+
"eval_accuracy": 0.7857142857142857,
|
| 2003 |
+
"eval_loss": 0.674295961856842,
|
| 2004 |
+
"eval_runtime": 0.652,
|
| 2005 |
+
"eval_samples_per_second": 107.363,
|
| 2006 |
+
"eval_steps_per_second": 3.068,
|
| 2007 |
+
"step": 392
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 197.0,
|
| 2011 |
+
"eval_accuracy": 0.7857142857142857,
|
| 2012 |
+
"eval_loss": 0.6742398142814636,
|
| 2013 |
+
"eval_runtime": 0.6659,
|
| 2014 |
+
"eval_samples_per_second": 105.127,
|
| 2015 |
+
"eval_steps_per_second": 3.004,
|
| 2016 |
+
"step": 394
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 198.0,
|
| 2020 |
+
"eval_accuracy": 0.8,
|
| 2021 |
+
"eval_loss": 0.6741960644721985,
|
| 2022 |
+
"eval_runtime": 0.8894,
|
| 2023 |
+
"eval_samples_per_second": 78.703,
|
| 2024 |
+
"eval_steps_per_second": 2.249,
|
| 2025 |
+
"step": 396
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 199.0,
|
| 2029 |
+
"eval_accuracy": 0.8,
|
| 2030 |
+
"eval_loss": 0.674168586730957,
|
| 2031 |
+
"eval_runtime": 0.6565,
|
| 2032 |
+
"eval_samples_per_second": 106.623,
|
| 2033 |
+
"eval_steps_per_second": 3.046,
|
| 2034 |
+
"step": 398
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 200.0,
|
| 2038 |
+
"learning_rate": 0.0,
|
| 2039 |
+
"loss": 0.7444,
|
| 2040 |
+
"step": 400
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 200.0,
|
| 2044 |
+
"eval_accuracy": 0.8,
|
| 2045 |
+
"eval_loss": 0.6741567850112915,
|
| 2046 |
+
"eval_runtime": 0.6417,
|
| 2047 |
+
"eval_samples_per_second": 109.09,
|
| 2048 |
+
"eval_steps_per_second": 3.117,
|
| 2049 |
+
"step": 400
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 200.0,
|
| 2053 |
+
"step": 400,
|
| 2054 |
+
"total_flos": 2.23710151698432e+18,
|
| 2055 |
+
"train_loss": 0.8548950719833374,
|
| 2056 |
+
"train_runtime": 1030.1946,
|
| 2057 |
+
"train_samples_per_second": 87.362,
|
| 2058 |
+
"train_steps_per_second": 0.388
|
| 2059 |
+
}
|
| 2060 |
+
],
|
| 2061 |
+
"logging_steps": 10,
|
| 2062 |
+
"max_steps": 400,
|
| 2063 |
+
"num_train_epochs": 200,
|
| 2064 |
+
"save_steps": 500,
|
| 2065 |
+
"total_flos": 2.23710151698432e+18,
|
| 2066 |
+
"trial_name": null,
|
| 2067 |
+
"trial_params": null
|
| 2068 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6a4a960807b7fb07f8a631fd1b39ee2cb704b4fe6c091d2903ecaeb412bcc7f
|
| 3 |
+
size 4091
|