Upload 13 files
Browse files- README.md +212 -2
- all_results.json +15 -0
- config.json +27 -0
- eval_results.json +10 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- train_results.json +8 -0
- trainer_state.json +2530 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,213 @@
|
|
| 1 |
-
---
|
| 2 |
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
license: mit
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
# roberta-large-movies
|
| 6 |
+
|
| 7 |
+
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the movie competition dataset.
|
| 8 |
+
link: https://huggingface.co/spaces/competitions/movie-genre-prediction
|
| 9 |
+
This model is nased on a MLM (Mask language modeling) finetuning. The goal is to apply a domain transfer. It needs then to be finetuned on labels.
|
| 10 |
+
|
| 11 |
+
It achieves the following results on the evaluation set:
|
| 12 |
+
- Loss: 1.3261
|
| 13 |
+
- Accuracy: 0.7375
|
| 14 |
+
|
| 15 |
+
## Model description
|
| 16 |
+
|
| 17 |
+
roberta-large
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
## Training procedure
|
| 22 |
+
|
| 23 |
+
### Training hyperparameters
|
| 24 |
+
|
| 25 |
+
The following hyperparameters were used during training:
|
| 26 |
+
- learning_rate: 5e-05
|
| 27 |
+
- train_batch_size: 32
|
| 28 |
+
- eval_batch_size: 16
|
| 29 |
+
- seed: 42
|
| 30 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 31 |
+
- lr_scheduler_type: linear
|
| 32 |
+
- num_epochs: 30.0
|
| 33 |
+
- mixed_precision_training: Native AMP
|
| 34 |
+
|
| 35 |
+
### Training results
|
| 36 |
+
|
| 37 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 38 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 39 |
+
| 1.7698 | 0.18 | 500 | 1.6168 | 0.6738 |
|
| 40 |
+
| 1.7761 | 0.36 | 1000 | 1.6522 | 0.6830 |
|
| 41 |
+
| 1.7626 | 0.54 | 1500 | 1.6534 | 0.6660 |
|
| 42 |
+
| 1.7602 | 0.72 | 2000 | 1.6576 | 0.6787 |
|
| 43 |
+
| 1.7587 | 0.89 | 2500 | 1.6266 | 0.6773 |
|
| 44 |
+
| 1.7047 | 1.07 | 3000 | 1.6060 | 0.6852 |
|
| 45 |
+
| 1.6782 | 1.25 | 3500 | 1.5990 | 0.6906 |
|
| 46 |
+
| 1.6733 | 1.43 | 4000 | 1.5377 | 0.6967 |
|
| 47 |
+
| 1.6664 | 1.61 | 4500 | 1.6435 | 0.6747 |
|
| 48 |
+
| 1.6719 | 1.79 | 5000 | 1.4839 | 0.6907 |
|
| 49 |
+
| 1.6502 | 1.97 | 5500 | 1.5351 | 0.6897 |
|
| 50 |
+
| 1.6233 | 2.15 | 6000 | 1.6818 | 0.6763 |
|
| 51 |
+
| 1.6127 | 2.32 | 6500 | 1.5865 | 0.6853 |
|
| 52 |
+
| 1.6274 | 2.5 | 7000 | 1.5004 | 0.7004 |
|
| 53 |
+
| 1.601 | 2.68 | 7500 | 1.4522 | 0.6930 |
|
| 54 |
+
| 1.6123 | 2.86 | 8000 | 1.5371 | 0.6894 |
|
| 55 |
+
| 1.6074 | 3.04 | 8500 | 1.5342 | 0.6952 |
|
| 56 |
+
| 1.563 | 3.22 | 9000 | 1.5682 | 0.6876 |
|
| 57 |
+
| 1.5746 | 3.4 | 9500 | 1.5705 | 0.6958 |
|
| 58 |
+
| 1.5539 | 3.58 | 10000 | 1.4711 | 0.7041 |
|
| 59 |
+
| 1.578 | 3.75 | 10500 | 1.5466 | 0.6889 |
|
| 60 |
+
| 1.5492 | 3.93 | 11000 | 1.4629 | 0.6969 |
|
| 61 |
+
| 1.5291 | 4.11 | 11500 | 1.4265 | 0.7200 |
|
| 62 |
+
| 1.5079 | 4.29 | 12000 | 1.5053 | 0.6966 |
|
| 63 |
+
| 1.5283 | 4.47 | 12500 | 1.5257 | 0.6903 |
|
| 64 |
+
| 1.5141 | 4.65 | 13000 | 1.5063 | 0.6950 |
|
| 65 |
+
| 1.4979 | 4.83 | 13500 | 1.5636 | 0.6956 |
|
| 66 |
+
| 1.5294 | 5.01 | 14000 | 1.5878 | 0.6835 |
|
| 67 |
+
| 1.4641 | 5.18 | 14500 | 1.5575 | 0.6962 |
|
| 68 |
+
| 1.4754 | 5.36 | 15000 | 1.4779 | 0.7007 |
|
| 69 |
+
| 1.4696 | 5.54 | 15500 | 1.4520 | 0.6965 |
|
| 70 |
+
| 1.4655 | 5.72 | 16000 | 1.6320 | 0.6830 |
|
| 71 |
+
| 1.4792 | 5.9 | 16500 | 1.4152 | 0.7134 |
|
| 72 |
+
| 1.4379 | 6.08 | 17000 | 1.4900 | 0.7042 |
|
| 73 |
+
| 1.4281 | 6.26 | 17500 | 1.5407 | 0.6990 |
|
| 74 |
+
| 1.436 | 6.44 | 18000 | 1.5343 | 0.6914 |
|
| 75 |
+
| 1.4342 | 6.61 | 18500 | 1.5324 | 0.7024 |
|
| 76 |
+
| 1.4176 | 6.79 | 19000 | 1.4486 | 0.7133 |
|
| 77 |
+
| 1.4308 | 6.97 | 19500 | 1.4598 | 0.7032 |
|
| 78 |
+
| 1.4014 | 7.15 | 20000 | 1.5750 | 0.6938 |
|
| 79 |
+
| 1.3661 | 7.33 | 20500 | 1.5404 | 0.6985 |
|
| 80 |
+
| 1.3857 | 7.51 | 21000 | 1.4692 | 0.7037 |
|
| 81 |
+
| 1.3846 | 7.69 | 21500 | 1.5511 | 0.6941 |
|
| 82 |
+
| 1.3867 | 7.87 | 22000 | 1.5321 | 0.6925 |
|
| 83 |
+
| 1.3658 | 8.04 | 22500 | 1.5500 | 0.7021 |
|
| 84 |
+
| 1.3406 | 8.22 | 23000 | 1.5239 | 0.6960 |
|
| 85 |
+
| 1.3405 | 8.4 | 23500 | 1.4414 | 0.7055 |
|
| 86 |
+
| 1.3373 | 8.58 | 24000 | 1.5994 | 0.6784 |
|
| 87 |
+
| 1.3527 | 8.76 | 24500 | 1.5106 | 0.6970 |
|
| 88 |
+
| 1.3436 | 8.94 | 25000 | 1.4714 | 0.7080 |
|
| 89 |
+
| 1.3069 | 9.12 | 25500 | 1.4990 | 0.6953 |
|
| 90 |
+
| 1.2969 | 9.3 | 26000 | 1.4810 | 0.6964 |
|
| 91 |
+
| 1.3009 | 9.47 | 26500 | 1.5965 | 0.6876 |
|
| 92 |
+
| 1.3227 | 9.65 | 27000 | 1.4296 | 0.7014 |
|
| 93 |
+
| 1.3259 | 9.83 | 27500 | 1.4137 | 0.7189 |
|
| 94 |
+
| 1.3131 | 10.01 | 28000 | 1.5342 | 0.7020 |
|
| 95 |
+
| 1.271 | 10.19 | 28500 | 1.4708 | 0.7113 |
|
| 96 |
+
| 1.2684 | 10.37 | 29000 | 1.4342 | 0.7046 |
|
| 97 |
+
| 1.2767 | 10.55 | 29500 | 1.4703 | 0.7094 |
|
| 98 |
+
| 1.2861 | 10.73 | 30000 | 1.3323 | 0.7309 |
|
| 99 |
+
| 1.2617 | 10.9 | 30500 | 1.4562 | 0.7003 |
|
| 100 |
+
| 1.2551 | 11.08 | 31000 | 1.4361 | 0.7170 |
|
| 101 |
+
| 1.2404 | 11.26 | 31500 | 1.4537 | 0.7035 |
|
| 102 |
+
| 1.2562 | 11.44 | 32000 | 1.4039 | 0.7132 |
|
| 103 |
+
| 1.2489 | 11.62 | 32500 | 1.4372 | 0.7064 |
|
| 104 |
+
| 1.2406 | 11.8 | 33000 | 1.4926 | 0.7087 |
|
| 105 |
+
| 1.2285 | 11.98 | 33500 | 1.4080 | 0.7152 |
|
| 106 |
+
| 1.2213 | 12.16 | 34000 | 1.4031 | 0.7170 |
|
| 107 |
+
| 1.1998 | 12.33 | 34500 | 1.3541 | 0.7223 |
|
| 108 |
+
| 1.2184 | 12.51 | 35000 | 1.3630 | 0.7308 |
|
| 109 |
+
| 1.2195 | 12.69 | 35500 | 1.3125 | 0.7281 |
|
| 110 |
+
| 1.2178 | 12.87 | 36000 | 1.4257 | 0.7119 |
|
| 111 |
+
| 1.1918 | 13.05 | 36500 | 1.4108 | 0.7153 |
|
| 112 |
+
| 1.1664 | 13.23 | 37000 | 1.3577 | 0.7227 |
|
| 113 |
+
| 1.1754 | 13.41 | 37500 | 1.3777 | 0.7206 |
|
| 114 |
+
| 1.1855 | 13.59 | 38000 | 1.3501 | 0.7354 |
|
| 115 |
+
| 1.1644 | 13.76 | 38500 | 1.3747 | 0.7207 |
|
| 116 |
+
| 1.1709 | 13.94 | 39000 | 1.3704 | 0.7184 |
|
| 117 |
+
| 1.1613 | 14.12 | 39500 | 1.4307 | 0.7247 |
|
| 118 |
+
| 1.1443 | 14.3 | 40000 | 1.3190 | 0.7221 |
|
| 119 |
+
| 1.1356 | 14.48 | 40500 | 1.3288 | 0.7331 |
|
| 120 |
+
| 1.1493 | 14.66 | 41000 | 1.3505 | 0.7240 |
|
| 121 |
+
| 1.1417 | 14.84 | 41500 | 1.3146 | 0.7320 |
|
| 122 |
+
| 1.1349 | 15.02 | 42000 | 1.3546 | 0.7333 |
|
| 123 |
+
| 1.1169 | 15.19 | 42500 | 1.3709 | 0.7247 |
|
| 124 |
+
| 1.1187 | 15.37 | 43000 | 1.4243 | 0.7218 |
|
| 125 |
+
| 1.118 | 15.55 | 43500 | 1.3835 | 0.7264 |
|
| 126 |
+
| 1.1165 | 15.73 | 44000 | 1.3240 | 0.7254 |
|
| 127 |
+
| 1.114 | 15.91 | 44500 | 1.3264 | 0.7382 |
|
| 128 |
+
| 1.105 | 16.09 | 45000 | 1.3214 | 0.7334 |
|
| 129 |
+
| 1.0924 | 16.27 | 45500 | 1.3847 | 0.7282 |
|
| 130 |
+
| 1.0915 | 16.45 | 46000 | 1.3604 | 0.7317 |
|
| 131 |
+
| 1.0968 | 16.62 | 46500 | 1.3540 | 0.7319 |
|
| 132 |
+
| 1.0772 | 16.8 | 47000 | 1.2475 | 0.7306 |
|
| 133 |
+
| 1.0975 | 16.98 | 47500 | 1.2636 | 0.7448 |
|
| 134 |
+
| 1.0708 | 17.16 | 48000 | 1.4056 | 0.7182 |
|
| 135 |
+
| 1.0654 | 17.34 | 48500 | 1.3769 | 0.7276 |
|
| 136 |
+
| 1.0676 | 17.52 | 49000 | 1.3357 | 0.7224 |
|
| 137 |
+
| 1.0507 | 17.7 | 49500 | 1.4088 | 0.7124 |
|
| 138 |
+
| 1.0424 | 17.88 | 50000 | 1.3146 | 0.7315 |
|
| 139 |
+
| 1.0524 | 18.06 | 50500 | 1.2896 | 0.7393 |
|
| 140 |
+
| 1.0349 | 18.23 | 51000 | 1.3987 | 0.7192 |
|
| 141 |
+
| 1.0217 | 18.41 | 51500 | 1.2938 | 0.7381 |
|
| 142 |
+
| 1.0238 | 18.59 | 52000 | 1.2962 | 0.7387 |
|
| 143 |
+
| 1.0292 | 18.77 | 52500 | 1.3195 | 0.7371 |
|
| 144 |
+
| 1.0426 | 18.95 | 53000 | 1.2835 | 0.7412 |
|
| 145 |
+
| 1.0196 | 19.13 | 53500 | 1.2346 | 0.7473 |
|
| 146 |
+
| 1.012 | 19.31 | 54000 | 1.3666 | 0.7338 |
|
| 147 |
+
| 1.0256 | 19.49 | 54500 | 1.3140 | 0.7365 |
|
| 148 |
+
| 0.9824 | 19.66 | 55000 | 1.2764 | 0.7416 |
|
| 149 |
+
| 1.0048 | 19.84 | 55500 | 1.2514 | 0.7488 |
|
| 150 |
+
| 0.9947 | 20.02 | 56000 | 1.3351 | 0.7432 |
|
| 151 |
+
| 0.977 | 20.2 | 56500 | 1.2854 | 0.7451 |
|
| 152 |
+
| 0.9862 | 20.38 | 57000 | 1.3666 | 0.7285 |
|
| 153 |
+
| 0.9699 | 20.56 | 57500 | 1.3123 | 0.7348 |
|
| 154 |
+
| 0.977 | 20.74 | 58000 | 1.3426 | 0.7255 |
|
| 155 |
+
| 0.9749 | 20.92 | 58500 | 1.3763 | 0.7297 |
|
| 156 |
+
| 0.9505 | 21.09 | 59000 | 1.2372 | 0.7434 |
|
| 157 |
+
| 0.9438 | 21.27 | 59500 | 1.4334 | 0.7159 |
|
| 158 |
+
| 0.944 | 21.45 | 60000 | 1.2690 | 0.7508 |
|
| 159 |
+
| 0.9427 | 21.63 | 60500 | 1.2186 | 0.7486 |
|
| 160 |
+
| 0.9553 | 21.81 | 61000 | 1.3941 | 0.7269 |
|
| 161 |
+
| 0.9571 | 21.99 | 61500 | 1.4163 | 0.7274 |
|
| 162 |
+
| 0.932 | 22.17 | 62000 | 1.2717 | 0.7523 |
|
| 163 |
+
| 0.9166 | 22.35 | 62500 | 1.2177 | 0.7396 |
|
| 164 |
+
| 0.9301 | 22.52 | 63000 | 1.3264 | 0.7378 |
|
| 165 |
+
| 0.9351 | 22.7 | 63500 | 1.2570 | 0.7520 |
|
| 166 |
+
| 0.9211 | 22.88 | 64000 | 1.2639 | 0.75 |
|
| 167 |
+
| 0.9211 | 23.06 | 64500 | 1.2377 | 0.7606 |
|
| 168 |
+
| 0.9196 | 23.24 | 65000 | 1.2739 | 0.7485 |
|
| 169 |
+
| 0.9062 | 23.42 | 65500 | 1.3263 | 0.7365 |
|
| 170 |
+
| 0.8965 | 23.6 | 66000 | 1.2814 | 0.7455 |
|
| 171 |
+
| 0.9004 | 23.78 | 66500 | 1.2109 | 0.7562 |
|
| 172 |
+
| 0.9094 | 23.95 | 67000 | 1.2629 | 0.7528 |
|
| 173 |
+
| 0.8937 | 24.13 | 67500 | 1.2771 | 0.7375 |
|
| 174 |
+
| 0.8711 | 24.31 | 68000 | 1.3746 | 0.7353 |
|
| 175 |
+
| 0.8972 | 24.49 | 68500 | 1.2529 | 0.7454 |
|
| 176 |
+
| 0.8863 | 24.67 | 69000 | 1.3219 | 0.7359 |
|
| 177 |
+
| 0.8823 | 24.85 | 69500 | 1.3136 | 0.7367 |
|
| 178 |
+
| 0.8759 | 25.03 | 70000 | 1.3152 | 0.7428 |
|
| 179 |
+
| 0.8722 | 25.21 | 70500 | 1.3108 | 0.7570 |
|
| 180 |
+
| 0.8548 | 25.38 | 71000 | 1.3503 | 0.7368 |
|
| 181 |
+
| 0.8728 | 25.56 | 71500 | 1.3091 | 0.7403 |
|
| 182 |
+
| 0.8633 | 25.74 | 72000 | 1.2952 | 0.7416 |
|
| 183 |
+
| 0.8612 | 25.92 | 72500 | 1.1612 | 0.7719 |
|
| 184 |
+
| 0.8677 | 26.1 | 73000 | 1.2855 | 0.7450 |
|
| 185 |
+
| 0.8526 | 26.28 | 73500 | 1.2979 | 0.7545 |
|
| 186 |
+
| 0.8594 | 26.46 | 74000 | 1.2570 | 0.7598 |
|
| 187 |
+
| 0.8481 | 26.64 | 74500 | 1.2337 | 0.7492 |
|
| 188 |
+
| 0.855 | 26.81 | 75000 | 1.2875 | 0.7444 |
|
| 189 |
+
| 0.835 | 26.99 | 75500 | 1.2270 | 0.7585 |
|
| 190 |
+
| 0.8309 | 27.17 | 76000 | 1.2540 | 0.7389 |
|
| 191 |
+
| 0.8326 | 27.35 | 76500 | 1.3611 | 0.7375 |
|
| 192 |
+
| 0.8398 | 27.53 | 77000 | 1.2248 | 0.7505 |
|
| 193 |
+
| 0.8304 | 27.71 | 77500 | 1.2403 | 0.7607 |
|
| 194 |
+
| 0.8373 | 27.89 | 78000 | 1.1709 | 0.7611 |
|
| 195 |
+
| 0.8462 | 28.07 | 78500 | 1.2891 | 0.7508 |
|
| 196 |
+
| 0.8259 | 28.24 | 79000 | 1.2452 | 0.7501 |
|
| 197 |
+
| 0.8334 | 28.42 | 79500 | 1.2986 | 0.7468 |
|
| 198 |
+
| 0.8115 | 28.6 | 80000 | 1.2880 | 0.7515 |
|
| 199 |
+
| 0.8205 | 28.78 | 80500 | 1.2728 | 0.7562 |
|
| 200 |
+
| 0.8261 | 28.96 | 81000 | 1.2661 | 0.7524 |
|
| 201 |
+
| 0.8299 | 29.14 | 81500 | 1.2592 | 0.7486 |
|
| 202 |
+
| 0.8276 | 29.32 | 82000 | 1.2325 | 0.7530 |
|
| 203 |
+
| 0.8112 | 29.5 | 82500 | 1.3154 | 0.7478 |
|
| 204 |
+
| 0.8111 | 29.67 | 83000 | 1.3343 | 0.7405 |
|
| 205 |
+
| 0.8148 | 29.85 | 83500 | 1.2806 | 0.7485 |
|
| 206 |
+
|
| 207 |
+
|
| 208 |
+
### Framework versions
|
| 209 |
+
|
| 210 |
+
- Transformers 4.21.3
|
| 211 |
+
- Pytorch 1.12.1+cu116
|
| 212 |
+
- Datasets 2.4.0
|
| 213 |
+
- Tokenizers 0.12.1
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.737508327781479,
|
| 4 |
+
"eval_loss": 1.3261024951934814,
|
| 5 |
+
"eval_runtime": 0.7869,
|
| 6 |
+
"eval_samples": 500,
|
| 7 |
+
"eval_samples_per_second": 635.414,
|
| 8 |
+
"eval_steps_per_second": 40.666,
|
| 9 |
+
"perplexity": 3.766335433571256,
|
| 10 |
+
"train_loss": 1.1746184680817338,
|
| 11 |
+
"train_runtime": 16410.0948,
|
| 12 |
+
"train_samples": 89500,
|
| 13 |
+
"train_samples_per_second": 163.619,
|
| 14 |
+
"train_steps_per_second": 5.113
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.21.3",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50265
|
| 27 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.737508327781479,
|
| 4 |
+
"eval_loss": 1.3261024951934814,
|
| 5 |
+
"eval_runtime": 0.7869,
|
| 6 |
+
"eval_samples": 500,
|
| 7 |
+
"eval_samples_per_second": 635.414,
|
| 8 |
+
"eval_steps_per_second": 40.666,
|
| 9 |
+
"perplexity": 3.766335433571256
|
| 10 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fb916109c43901c88702eb47544190f727b4267dfdee854887f87b50224c07a
|
| 3 |
+
size 1421785643
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"name_or_path": "roberta-large",
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"special_tokens_map_file": null,
|
| 13 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 14 |
+
"trim_offsets": true,
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"train_loss": 1.1746184680817338,
|
| 4 |
+
"train_runtime": 16410.0948,
|
| 5 |
+
"train_samples": 89500,
|
| 6 |
+
"train_samples_per_second": 163.619,
|
| 7 |
+
"train_steps_per_second": 5.113
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2530 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7719072164948454,
|
| 3 |
+
"best_model_checkpoint": "roberta-large-movies/checkpoint-72500",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"global_step": 83910,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.18,
|
| 12 |
+
"learning_rate": 4.970504111548088e-05,
|
| 13 |
+
"loss": 1.7698,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"eval_accuracy": 0.6738421395955643,
|
| 19 |
+
"eval_loss": 1.6167851686477661,
|
| 20 |
+
"eval_runtime": 0.8246,
|
| 21 |
+
"eval_samples_per_second": 606.37,
|
| 22 |
+
"eval_steps_per_second": 38.808,
|
| 23 |
+
"step": 500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.36,
|
| 27 |
+
"learning_rate": 4.94082946013586e-05,
|
| 28 |
+
"loss": 1.7761,
|
| 29 |
+
"step": 1000
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.36,
|
| 33 |
+
"eval_accuracy": 0.6829508196721311,
|
| 34 |
+
"eval_loss": 1.6522468328475952,
|
| 35 |
+
"eval_runtime": 0.7873,
|
| 36 |
+
"eval_samples_per_second": 635.049,
|
| 37 |
+
"eval_steps_per_second": 40.643,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.54,
|
| 42 |
+
"learning_rate": 4.9110356334167565e-05,
|
| 43 |
+
"loss": 1.7626,
|
| 44 |
+
"step": 1500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.54,
|
| 48 |
+
"eval_accuracy": 0.6660117878192534,
|
| 49 |
+
"eval_loss": 1.6534239053726196,
|
| 50 |
+
"eval_runtime": 0.7869,
|
| 51 |
+
"eval_samples_per_second": 635.425,
|
| 52 |
+
"eval_steps_per_second": 40.667,
|
| 53 |
+
"step": 1500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.72,
|
| 57 |
+
"learning_rate": 4.8812418066976524e-05,
|
| 58 |
+
"loss": 1.7602,
|
| 59 |
+
"step": 2000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.72,
|
| 63 |
+
"eval_accuracy": 0.6787299419597133,
|
| 64 |
+
"eval_loss": 1.6575504541397095,
|
| 65 |
+
"eval_runtime": 0.7882,
|
| 66 |
+
"eval_samples_per_second": 634.385,
|
| 67 |
+
"eval_steps_per_second": 40.601,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.89,
|
| 72 |
+
"learning_rate": 4.851447979978549e-05,
|
| 73 |
+
"loss": 1.7587,
|
| 74 |
+
"step": 2500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.89,
|
| 78 |
+
"eval_accuracy": 0.6772697150430749,
|
| 79 |
+
"eval_loss": 1.6266298294067383,
|
| 80 |
+
"eval_runtime": 0.7893,
|
| 81 |
+
"eval_samples_per_second": 633.509,
|
| 82 |
+
"eval_steps_per_second": 40.545,
|
| 83 |
+
"step": 2500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.07,
|
| 87 |
+
"learning_rate": 4.821654153259445e-05,
|
| 88 |
+
"loss": 1.7047,
|
| 89 |
+
"step": 3000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.07,
|
| 93 |
+
"eval_accuracy": 0.6851971557853911,
|
| 94 |
+
"eval_loss": 1.605985164642334,
|
| 95 |
+
"eval_runtime": 0.8181,
|
| 96 |
+
"eval_samples_per_second": 611.179,
|
| 97 |
+
"eval_steps_per_second": 39.115,
|
| 98 |
+
"step": 3000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.25,
|
| 102 |
+
"learning_rate": 4.791860326540341e-05,
|
| 103 |
+
"loss": 1.6782,
|
| 104 |
+
"step": 3500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.25,
|
| 108 |
+
"eval_accuracy": 0.6906354515050167,
|
| 109 |
+
"eval_loss": 1.599035382270813,
|
| 110 |
+
"eval_runtime": 0.8184,
|
| 111 |
+
"eval_samples_per_second": 610.967,
|
| 112 |
+
"eval_steps_per_second": 39.102,
|
| 113 |
+
"step": 3500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.43,
|
| 117 |
+
"learning_rate": 4.7620664998212375e-05,
|
| 118 |
+
"loss": 1.6733,
|
| 119 |
+
"step": 4000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.43,
|
| 123 |
+
"eval_accuracy": 0.6967426710097719,
|
| 124 |
+
"eval_loss": 1.5377483367919922,
|
| 125 |
+
"eval_runtime": 0.819,
|
| 126 |
+
"eval_samples_per_second": 610.521,
|
| 127 |
+
"eval_steps_per_second": 39.073,
|
| 128 |
+
"step": 4000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.61,
|
| 132 |
+
"learning_rate": 4.7322726731021334e-05,
|
| 133 |
+
"loss": 1.6664,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.61,
|
| 138 |
+
"eval_accuracy": 0.6746607762701168,
|
| 139 |
+
"eval_loss": 1.6434643268585205,
|
| 140 |
+
"eval_runtime": 0.7966,
|
| 141 |
+
"eval_samples_per_second": 627.631,
|
| 142 |
+
"eval_steps_per_second": 40.168,
|
| 143 |
+
"step": 4500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.79,
|
| 147 |
+
"learning_rate": 4.70247884638303e-05,
|
| 148 |
+
"loss": 1.6719,
|
| 149 |
+
"step": 5000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.79,
|
| 153 |
+
"eval_accuracy": 0.6907181571815718,
|
| 154 |
+
"eval_loss": 1.483905553817749,
|
| 155 |
+
"eval_runtime": 0.7989,
|
| 156 |
+
"eval_samples_per_second": 625.841,
|
| 157 |
+
"eval_steps_per_second": 40.054,
|
| 158 |
+
"step": 5000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.97,
|
| 162 |
+
"learning_rate": 4.672685019663926e-05,
|
| 163 |
+
"loss": 1.6502,
|
| 164 |
+
"step": 5500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.97,
|
| 168 |
+
"eval_accuracy": 0.6896661367249602,
|
| 169 |
+
"eval_loss": 1.535127878189087,
|
| 170 |
+
"eval_runtime": 0.823,
|
| 171 |
+
"eval_samples_per_second": 607.558,
|
| 172 |
+
"eval_steps_per_second": 38.884,
|
| 173 |
+
"step": 5500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.15,
|
| 177 |
+
"learning_rate": 4.642891192944822e-05,
|
| 178 |
+
"loss": 1.6233,
|
| 179 |
+
"step": 6000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.15,
|
| 183 |
+
"eval_accuracy": 0.6763219939373526,
|
| 184 |
+
"eval_loss": 1.6817570924758911,
|
| 185 |
+
"eval_runtime": 0.7881,
|
| 186 |
+
"eval_samples_per_second": 634.403,
|
| 187 |
+
"eval_steps_per_second": 40.602,
|
| 188 |
+
"step": 6000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.32,
|
| 192 |
+
"learning_rate": 4.6130973662257184e-05,
|
| 193 |
+
"loss": 1.6127,
|
| 194 |
+
"step": 6500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.32,
|
| 198 |
+
"eval_accuracy": 0.685335059889932,
|
| 199 |
+
"eval_loss": 1.5865211486816406,
|
| 200 |
+
"eval_runtime": 0.787,
|
| 201 |
+
"eval_samples_per_second": 635.291,
|
| 202 |
+
"eval_steps_per_second": 40.659,
|
| 203 |
+
"step": 6500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.5,
|
| 207 |
+
"learning_rate": 4.5833035395066143e-05,
|
| 208 |
+
"loss": 1.6274,
|
| 209 |
+
"step": 7000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.5,
|
| 213 |
+
"eval_accuracy": 0.7003633961017509,
|
| 214 |
+
"eval_loss": 1.5004233121871948,
|
| 215 |
+
"eval_runtime": 0.8009,
|
| 216 |
+
"eval_samples_per_second": 624.318,
|
| 217 |
+
"eval_steps_per_second": 39.956,
|
| 218 |
+
"step": 7000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.68,
|
| 222 |
+
"learning_rate": 4.553628888094387e-05,
|
| 223 |
+
"loss": 1.601,
|
| 224 |
+
"step": 7500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.68,
|
| 228 |
+
"eval_accuracy": 0.6929970129439097,
|
| 229 |
+
"eval_loss": 1.452188491821289,
|
| 230 |
+
"eval_runtime": 0.7898,
|
| 231 |
+
"eval_samples_per_second": 633.056,
|
| 232 |
+
"eval_steps_per_second": 40.516,
|
| 233 |
+
"step": 7500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.86,
|
| 237 |
+
"learning_rate": 4.523835061375284e-05,
|
| 238 |
+
"loss": 1.6123,
|
| 239 |
+
"step": 8000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.86,
|
| 243 |
+
"eval_accuracy": 0.689419795221843,
|
| 244 |
+
"eval_loss": 1.5370689630508423,
|
| 245 |
+
"eval_runtime": 0.8546,
|
| 246 |
+
"eval_samples_per_second": 585.05,
|
| 247 |
+
"eval_steps_per_second": 37.443,
|
| 248 |
+
"step": 8000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.04,
|
| 252 |
+
"learning_rate": 4.4940412346561796e-05,
|
| 253 |
+
"loss": 1.6074,
|
| 254 |
+
"step": 8500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.04,
|
| 258 |
+
"eval_accuracy": 0.6952157912345266,
|
| 259 |
+
"eval_loss": 1.5342369079589844,
|
| 260 |
+
"eval_runtime": 0.8214,
|
| 261 |
+
"eval_samples_per_second": 608.68,
|
| 262 |
+
"eval_steps_per_second": 38.956,
|
| 263 |
+
"step": 8500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.22,
|
| 267 |
+
"learning_rate": 4.4642474079370755e-05,
|
| 268 |
+
"loss": 1.563,
|
| 269 |
+
"step": 9000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.22,
|
| 273 |
+
"eval_accuracy": 0.6875834445927904,
|
| 274 |
+
"eval_loss": 1.568178415298462,
|
| 275 |
+
"eval_runtime": 0.8488,
|
| 276 |
+
"eval_samples_per_second": 589.06,
|
| 277 |
+
"eval_steps_per_second": 37.7,
|
| 278 |
+
"step": 9000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.4,
|
| 282 |
+
"learning_rate": 4.4344535812179714e-05,
|
| 283 |
+
"loss": 1.5746,
|
| 284 |
+
"step": 9500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.4,
|
| 288 |
+
"eval_accuracy": 0.6957663275352806,
|
| 289 |
+
"eval_loss": 1.5704632997512817,
|
| 290 |
+
"eval_runtime": 0.852,
|
| 291 |
+
"eval_samples_per_second": 586.84,
|
| 292 |
+
"eval_steps_per_second": 37.558,
|
| 293 |
+
"step": 9500
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.58,
|
| 297 |
+
"learning_rate": 4.404778929805745e-05,
|
| 298 |
+
"loss": 1.5539,
|
| 299 |
+
"step": 10000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.58,
|
| 303 |
+
"eval_accuracy": 0.7040711597673623,
|
| 304 |
+
"eval_loss": 1.4710707664489746,
|
| 305 |
+
"eval_runtime": 0.85,
|
| 306 |
+
"eval_samples_per_second": 588.248,
|
| 307 |
+
"eval_steps_per_second": 37.648,
|
| 308 |
+
"step": 10000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.75,
|
| 312 |
+
"learning_rate": 4.374985103086641e-05,
|
| 313 |
+
"loss": 1.578,
|
| 314 |
+
"step": 10500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.75,
|
| 318 |
+
"eval_accuracy": 0.6888888888888889,
|
| 319 |
+
"eval_loss": 1.5465725660324097,
|
| 320 |
+
"eval_runtime": 0.8902,
|
| 321 |
+
"eval_samples_per_second": 561.645,
|
| 322 |
+
"eval_steps_per_second": 35.945,
|
| 323 |
+
"step": 10500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.93,
|
| 327 |
+
"learning_rate": 4.345191276367537e-05,
|
| 328 |
+
"loss": 1.5492,
|
| 329 |
+
"step": 11000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.93,
|
| 333 |
+
"eval_accuracy": 0.6968894771674388,
|
| 334 |
+
"eval_loss": 1.4628891944885254,
|
| 335 |
+
"eval_runtime": 0.8368,
|
| 336 |
+
"eval_samples_per_second": 597.487,
|
| 337 |
+
"eval_steps_per_second": 38.239,
|
| 338 |
+
"step": 11000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.11,
|
| 342 |
+
"learning_rate": 4.3153974496484326e-05,
|
| 343 |
+
"loss": 1.5291,
|
| 344 |
+
"step": 11500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.11,
|
| 348 |
+
"eval_accuracy": 0.7200132538104705,
|
| 349 |
+
"eval_loss": 1.4264894723892212,
|
| 350 |
+
"eval_runtime": 0.8798,
|
| 351 |
+
"eval_samples_per_second": 568.319,
|
| 352 |
+
"eval_steps_per_second": 36.372,
|
| 353 |
+
"step": 11500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.29,
|
| 357 |
+
"learning_rate": 4.285603622929329e-05,
|
| 358 |
+
"loss": 1.5079,
|
| 359 |
+
"step": 12000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 4.29,
|
| 363 |
+
"eval_accuracy": 0.6966074313408723,
|
| 364 |
+
"eval_loss": 1.5052707195281982,
|
| 365 |
+
"eval_runtime": 0.8186,
|
| 366 |
+
"eval_samples_per_second": 610.796,
|
| 367 |
+
"eval_steps_per_second": 39.091,
|
| 368 |
+
"step": 12000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.47,
|
| 372 |
+
"learning_rate": 4.255809796210226e-05,
|
| 373 |
+
"loss": 1.5283,
|
| 374 |
+
"step": 12500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.47,
|
| 378 |
+
"eval_accuracy": 0.6902654867256637,
|
| 379 |
+
"eval_loss": 1.5257039070129395,
|
| 380 |
+
"eval_runtime": 0.8002,
|
| 381 |
+
"eval_samples_per_second": 624.861,
|
| 382 |
+
"eval_steps_per_second": 39.991,
|
| 383 |
+
"step": 12500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 4.65,
|
| 387 |
+
"learning_rate": 4.226015969491122e-05,
|
| 388 |
+
"loss": 1.5141,
|
| 389 |
+
"step": 13000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 4.65,
|
| 393 |
+
"eval_accuracy": 0.6949898442789438,
|
| 394 |
+
"eval_loss": 1.5063292980194092,
|
| 395 |
+
"eval_runtime": 0.8654,
|
| 396 |
+
"eval_samples_per_second": 577.759,
|
| 397 |
+
"eval_steps_per_second": 36.977,
|
| 398 |
+
"step": 13000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.83,
|
| 402 |
+
"learning_rate": 4.1962221427720176e-05,
|
| 403 |
+
"loss": 1.4979,
|
| 404 |
+
"step": 13500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.83,
|
| 408 |
+
"eval_accuracy": 0.6955945677376615,
|
| 409 |
+
"eval_loss": 1.5636450052261353,
|
| 410 |
+
"eval_runtime": 0.8149,
|
| 411 |
+
"eval_samples_per_second": 613.582,
|
| 412 |
+
"eval_steps_per_second": 39.269,
|
| 413 |
+
"step": 13500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 5.01,
|
| 417 |
+
"learning_rate": 4.1664283160529136e-05,
|
| 418 |
+
"loss": 1.5294,
|
| 419 |
+
"step": 14000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.01,
|
| 423 |
+
"eval_accuracy": 0.6835193696651346,
|
| 424 |
+
"eval_loss": 1.587847113609314,
|
| 425 |
+
"eval_runtime": 0.8296,
|
| 426 |
+
"eval_samples_per_second": 602.733,
|
| 427 |
+
"eval_steps_per_second": 38.575,
|
| 428 |
+
"step": 14000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 5.18,
|
| 432 |
+
"learning_rate": 4.13663448933381e-05,
|
| 433 |
+
"loss": 1.4641,
|
| 434 |
+
"step": 14500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 5.18,
|
| 438 |
+
"eval_accuracy": 0.6962067807989258,
|
| 439 |
+
"eval_loss": 1.5574804544448853,
|
| 440 |
+
"eval_runtime": 0.81,
|
| 441 |
+
"eval_samples_per_second": 617.287,
|
| 442 |
+
"eval_steps_per_second": 39.506,
|
| 443 |
+
"step": 14500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 5.36,
|
| 447 |
+
"learning_rate": 4.106840662614707e-05,
|
| 448 |
+
"loss": 1.4754,
|
| 449 |
+
"step": 15000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 5.36,
|
| 453 |
+
"eval_accuracy": 0.7006847081838931,
|
| 454 |
+
"eval_loss": 1.4779187440872192,
|
| 455 |
+
"eval_runtime": 0.8312,
|
| 456 |
+
"eval_samples_per_second": 601.557,
|
| 457 |
+
"eval_steps_per_second": 38.5,
|
| 458 |
+
"step": 15000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 5.54,
|
| 462 |
+
"learning_rate": 4.077046835895603e-05,
|
| 463 |
+
"loss": 1.4696,
|
| 464 |
+
"step": 15500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 5.54,
|
| 468 |
+
"eval_accuracy": 0.6965271015903928,
|
| 469 |
+
"eval_loss": 1.451996922492981,
|
| 470 |
+
"eval_runtime": 0.7909,
|
| 471 |
+
"eval_samples_per_second": 632.19,
|
| 472 |
+
"eval_steps_per_second": 40.46,
|
| 473 |
+
"step": 15500
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 5.72,
|
| 477 |
+
"learning_rate": 4.0472530091764986e-05,
|
| 478 |
+
"loss": 1.4655,
|
| 479 |
+
"step": 16000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 5.72,
|
| 483 |
+
"eval_accuracy": 0.683049147442327,
|
| 484 |
+
"eval_loss": 1.6320295333862305,
|
| 485 |
+
"eval_runtime": 0.8309,
|
| 486 |
+
"eval_samples_per_second": 601.76,
|
| 487 |
+
"eval_steps_per_second": 38.513,
|
| 488 |
+
"step": 16000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.9,
|
| 492 |
+
"learning_rate": 4.0174591824573945e-05,
|
| 493 |
+
"loss": 1.4792,
|
| 494 |
+
"step": 16500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 5.9,
|
| 498 |
+
"eval_accuracy": 0.7134165866154338,
|
| 499 |
+
"eval_loss": 1.415226697921753,
|
| 500 |
+
"eval_runtime": 0.8575,
|
| 501 |
+
"eval_samples_per_second": 583.097,
|
| 502 |
+
"eval_steps_per_second": 37.318,
|
| 503 |
+
"step": 16500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 6.08,
|
| 507 |
+
"learning_rate": 3.98772494339173e-05,
|
| 508 |
+
"loss": 1.4379,
|
| 509 |
+
"step": 17000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 6.08,
|
| 513 |
+
"eval_accuracy": 0.7041935483870968,
|
| 514 |
+
"eval_loss": 1.4900156259536743,
|
| 515 |
+
"eval_runtime": 0.8413,
|
| 516 |
+
"eval_samples_per_second": 594.352,
|
| 517 |
+
"eval_steps_per_second": 38.039,
|
| 518 |
+
"step": 17000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.26,
|
| 522 |
+
"learning_rate": 3.957931116672626e-05,
|
| 523 |
+
"loss": 1.4281,
|
| 524 |
+
"step": 17500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 6.26,
|
| 528 |
+
"eval_accuracy": 0.6989864864864865,
|
| 529 |
+
"eval_loss": 1.5407416820526123,
|
| 530 |
+
"eval_runtime": 0.8677,
|
| 531 |
+
"eval_samples_per_second": 576.232,
|
| 532 |
+
"eval_steps_per_second": 36.879,
|
| 533 |
+
"step": 17500
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 6.44,
|
| 537 |
+
"learning_rate": 3.928137289953522e-05,
|
| 538 |
+
"loss": 1.436,
|
| 539 |
+
"step": 18000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 6.44,
|
| 543 |
+
"eval_accuracy": 0.6914175506268081,
|
| 544 |
+
"eval_loss": 1.534258246421814,
|
| 545 |
+
"eval_runtime": 0.843,
|
| 546 |
+
"eval_samples_per_second": 593.143,
|
| 547 |
+
"eval_steps_per_second": 37.961,
|
| 548 |
+
"step": 18000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 6.61,
|
| 552 |
+
"learning_rate": 3.8983434632344176e-05,
|
| 553 |
+
"loss": 1.4342,
|
| 554 |
+
"step": 18500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 6.61,
|
| 558 |
+
"eval_accuracy": 0.7023696682464455,
|
| 559 |
+
"eval_loss": 1.5323561429977417,
|
| 560 |
+
"eval_runtime": 0.7874,
|
| 561 |
+
"eval_samples_per_second": 635.024,
|
| 562 |
+
"eval_steps_per_second": 40.642,
|
| 563 |
+
"step": 18500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 6.79,
|
| 567 |
+
"learning_rate": 3.868549636515314e-05,
|
| 568 |
+
"loss": 1.4176,
|
| 569 |
+
"step": 19000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 6.79,
|
| 573 |
+
"eval_accuracy": 0.7132913490222075,
|
| 574 |
+
"eval_loss": 1.4485751390457153,
|
| 575 |
+
"eval_runtime": 0.8567,
|
| 576 |
+
"eval_samples_per_second": 583.665,
|
| 577 |
+
"eval_steps_per_second": 37.355,
|
| 578 |
+
"step": 19000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 6.97,
|
| 582 |
+
"learning_rate": 3.838755809796211e-05,
|
| 583 |
+
"loss": 1.4308,
|
| 584 |
+
"step": 19500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 6.97,
|
| 588 |
+
"eval_accuracy": 0.7031503734978889,
|
| 589 |
+
"eval_loss": 1.4598056077957153,
|
| 590 |
+
"eval_runtime": 0.79,
|
| 591 |
+
"eval_samples_per_second": 632.872,
|
| 592 |
+
"eval_steps_per_second": 40.504,
|
| 593 |
+
"step": 19500
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 7.15,
|
| 597 |
+
"learning_rate": 3.809021570730545e-05,
|
| 598 |
+
"loss": 1.4014,
|
| 599 |
+
"step": 20000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 7.15,
|
| 603 |
+
"eval_accuracy": 0.6938435940099834,
|
| 604 |
+
"eval_loss": 1.575023889541626,
|
| 605 |
+
"eval_runtime": 0.8292,
|
| 606 |
+
"eval_samples_per_second": 603.024,
|
| 607 |
+
"eval_steps_per_second": 38.594,
|
| 608 |
+
"step": 20000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 7.33,
|
| 612 |
+
"learning_rate": 3.779227744011441e-05,
|
| 613 |
+
"loss": 1.3661,
|
| 614 |
+
"step": 20500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 7.33,
|
| 618 |
+
"eval_accuracy": 0.6985221674876847,
|
| 619 |
+
"eval_loss": 1.5403505563735962,
|
| 620 |
+
"eval_runtime": 0.8319,
|
| 621 |
+
"eval_samples_per_second": 601.063,
|
| 622 |
+
"eval_steps_per_second": 38.468,
|
| 623 |
+
"step": 20500
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 7.51,
|
| 627 |
+
"learning_rate": 3.7494935049457754e-05,
|
| 628 |
+
"loss": 1.3857,
|
| 629 |
+
"step": 21000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 7.51,
|
| 633 |
+
"eval_accuracy": 0.7037155669442665,
|
| 634 |
+
"eval_loss": 1.4692307710647583,
|
| 635 |
+
"eval_runtime": 0.8177,
|
| 636 |
+
"eval_samples_per_second": 611.5,
|
| 637 |
+
"eval_steps_per_second": 39.136,
|
| 638 |
+
"step": 21000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 7.69,
|
| 642 |
+
"learning_rate": 3.719699678226672e-05,
|
| 643 |
+
"loss": 1.3846,
|
| 644 |
+
"step": 21500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 7.69,
|
| 648 |
+
"eval_accuracy": 0.6941445861956166,
|
| 649 |
+
"eval_loss": 1.5511342287063599,
|
| 650 |
+
"eval_runtime": 0.7898,
|
| 651 |
+
"eval_samples_per_second": 633.076,
|
| 652 |
+
"eval_steps_per_second": 40.517,
|
| 653 |
+
"step": 21500
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 7.87,
|
| 657 |
+
"learning_rate": 3.689905851507568e-05,
|
| 658 |
+
"loss": 1.3867,
|
| 659 |
+
"step": 22000
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 7.87,
|
| 663 |
+
"eval_accuracy": 0.6925124792013311,
|
| 664 |
+
"eval_loss": 1.5321439504623413,
|
| 665 |
+
"eval_runtime": 0.8379,
|
| 666 |
+
"eval_samples_per_second": 596.713,
|
| 667 |
+
"eval_steps_per_second": 38.19,
|
| 668 |
+
"step": 22000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 8.04,
|
| 672 |
+
"learning_rate": 3.660112024788464e-05,
|
| 673 |
+
"loss": 1.3658,
|
| 674 |
+
"step": 22500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 8.04,
|
| 678 |
+
"eval_accuracy": 0.7020917678812416,
|
| 679 |
+
"eval_loss": 1.5499885082244873,
|
| 680 |
+
"eval_runtime": 0.8209,
|
| 681 |
+
"eval_samples_per_second": 609.075,
|
| 682 |
+
"eval_steps_per_second": 38.981,
|
| 683 |
+
"step": 22500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 8.22,
|
| 687 |
+
"learning_rate": 3.6303181980693604e-05,
|
| 688 |
+
"loss": 1.3406,
|
| 689 |
+
"step": 23000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 8.22,
|
| 693 |
+
"eval_accuracy": 0.6959503592423253,
|
| 694 |
+
"eval_loss": 1.523918628692627,
|
| 695 |
+
"eval_runtime": 0.8298,
|
| 696 |
+
"eval_samples_per_second": 602.525,
|
| 697 |
+
"eval_steps_per_second": 38.562,
|
| 698 |
+
"step": 23000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 8.4,
|
| 702 |
+
"learning_rate": 3.600524371350256e-05,
|
| 703 |
+
"loss": 1.3405,
|
| 704 |
+
"step": 23500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 8.4,
|
| 708 |
+
"eval_accuracy": 0.7055256064690026,
|
| 709 |
+
"eval_loss": 1.4414023160934448,
|
| 710 |
+
"eval_runtime": 0.8516,
|
| 711 |
+
"eval_samples_per_second": 587.105,
|
| 712 |
+
"eval_steps_per_second": 37.575,
|
| 713 |
+
"step": 23500
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 8.58,
|
| 717 |
+
"learning_rate": 3.570730544631153e-05,
|
| 718 |
+
"loss": 1.3373,
|
| 719 |
+
"step": 24000
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 8.58,
|
| 723 |
+
"eval_accuracy": 0.6784238957737527,
|
| 724 |
+
"eval_loss": 1.599377155303955,
|
| 725 |
+
"eval_runtime": 0.791,
|
| 726 |
+
"eval_samples_per_second": 632.109,
|
| 727 |
+
"eval_steps_per_second": 40.455,
|
| 728 |
+
"step": 24000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 8.76,
|
| 732 |
+
"learning_rate": 3.540936717912049e-05,
|
| 733 |
+
"loss": 1.3527,
|
| 734 |
+
"step": 24500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 8.76,
|
| 738 |
+
"eval_accuracy": 0.6970387243735763,
|
| 739 |
+
"eval_loss": 1.5105814933776855,
|
| 740 |
+
"eval_runtime": 0.8594,
|
| 741 |
+
"eval_samples_per_second": 581.797,
|
| 742 |
+
"eval_steps_per_second": 37.235,
|
| 743 |
+
"step": 24500
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 8.94,
|
| 747 |
+
"learning_rate": 3.511142891192945e-05,
|
| 748 |
+
"loss": 1.3436,
|
| 749 |
+
"step": 25000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 8.94,
|
| 753 |
+
"eval_accuracy": 0.7079758500158881,
|
| 754 |
+
"eval_loss": 1.471426010131836,
|
| 755 |
+
"eval_runtime": 0.8427,
|
| 756 |
+
"eval_samples_per_second": 593.355,
|
| 757 |
+
"eval_steps_per_second": 37.975,
|
| 758 |
+
"step": 25000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 9.12,
|
| 762 |
+
"learning_rate": 3.4813490644738414e-05,
|
| 763 |
+
"loss": 1.3069,
|
| 764 |
+
"step": 25500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 9.12,
|
| 768 |
+
"eval_accuracy": 0.6953099376844867,
|
| 769 |
+
"eval_loss": 1.4990392923355103,
|
| 770 |
+
"eval_runtime": 0.8575,
|
| 771 |
+
"eval_samples_per_second": 583.12,
|
| 772 |
+
"eval_steps_per_second": 37.32,
|
| 773 |
+
"step": 25500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 9.3,
|
| 777 |
+
"learning_rate": 3.451555237754737e-05,
|
| 778 |
+
"loss": 1.2969,
|
| 779 |
+
"step": 26000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 9.3,
|
| 783 |
+
"eval_accuracy": 0.6964285714285714,
|
| 784 |
+
"eval_loss": 1.4809668064117432,
|
| 785 |
+
"eval_runtime": 0.8312,
|
| 786 |
+
"eval_samples_per_second": 601.512,
|
| 787 |
+
"eval_steps_per_second": 38.497,
|
| 788 |
+
"step": 26000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 9.47,
|
| 792 |
+
"learning_rate": 3.421761411035634e-05,
|
| 793 |
+
"loss": 1.3009,
|
| 794 |
+
"step": 26500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 9.47,
|
| 798 |
+
"eval_accuracy": 0.6875602700096431,
|
| 799 |
+
"eval_loss": 1.5964903831481934,
|
| 800 |
+
"eval_runtime": 0.8752,
|
| 801 |
+
"eval_samples_per_second": 571.296,
|
| 802 |
+
"eval_steps_per_second": 36.563,
|
| 803 |
+
"step": 26500
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 9.65,
|
| 807 |
+
"learning_rate": 3.392086759623406e-05,
|
| 808 |
+
"loss": 1.3227,
|
| 809 |
+
"step": 27000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 9.65,
|
| 813 |
+
"eval_accuracy": 0.7013662979830839,
|
| 814 |
+
"eval_loss": 1.429559588432312,
|
| 815 |
+
"eval_runtime": 0.7904,
|
| 816 |
+
"eval_samples_per_second": 632.561,
|
| 817 |
+
"eval_steps_per_second": 40.484,
|
| 818 |
+
"step": 27000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 9.83,
|
| 822 |
+
"learning_rate": 3.3622929329043025e-05,
|
| 823 |
+
"loss": 1.3259,
|
| 824 |
+
"step": 27500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 9.83,
|
| 828 |
+
"eval_accuracy": 0.7189224277831873,
|
| 829 |
+
"eval_loss": 1.413652777671814,
|
| 830 |
+
"eval_runtime": 0.8134,
|
| 831 |
+
"eval_samples_per_second": 614.697,
|
| 832 |
+
"eval_steps_per_second": 39.341,
|
| 833 |
+
"step": 27500
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 10.01,
|
| 837 |
+
"learning_rate": 3.3324991061851985e-05,
|
| 838 |
+
"loss": 1.3131,
|
| 839 |
+
"step": 28000
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 10.01,
|
| 843 |
+
"eval_accuracy": 0.7019570099454604,
|
| 844 |
+
"eval_loss": 1.534200668334961,
|
| 845 |
+
"eval_runtime": 0.8056,
|
| 846 |
+
"eval_samples_per_second": 620.653,
|
| 847 |
+
"eval_steps_per_second": 39.722,
|
| 848 |
+
"step": 28000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 10.19,
|
| 852 |
+
"learning_rate": 3.3027052794660944e-05,
|
| 853 |
+
"loss": 1.271,
|
| 854 |
+
"step": 28500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 10.19,
|
| 858 |
+
"eval_accuracy": 0.711340206185567,
|
| 859 |
+
"eval_loss": 1.470828890800476,
|
| 860 |
+
"eval_runtime": 0.7815,
|
| 861 |
+
"eval_samples_per_second": 639.779,
|
| 862 |
+
"eval_steps_per_second": 40.946,
|
| 863 |
+
"step": 28500
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 10.37,
|
| 867 |
+
"learning_rate": 3.272911452746991e-05,
|
| 868 |
+
"loss": 1.2684,
|
| 869 |
+
"step": 29000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 10.37,
|
| 873 |
+
"eval_accuracy": 0.7045747422680413,
|
| 874 |
+
"eval_loss": 1.4341672658920288,
|
| 875 |
+
"eval_runtime": 0.7954,
|
| 876 |
+
"eval_samples_per_second": 628.629,
|
| 877 |
+
"eval_steps_per_second": 40.232,
|
| 878 |
+
"step": 29000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 10.55,
|
| 882 |
+
"learning_rate": 3.2431176260278876e-05,
|
| 883 |
+
"loss": 1.2767,
|
| 884 |
+
"step": 29500
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 10.55,
|
| 888 |
+
"eval_accuracy": 0.709353000335233,
|
| 889 |
+
"eval_loss": 1.4703407287597656,
|
| 890 |
+
"eval_runtime": 0.8179,
|
| 891 |
+
"eval_samples_per_second": 611.351,
|
| 892 |
+
"eval_steps_per_second": 39.126,
|
| 893 |
+
"step": 29500
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 10.73,
|
| 897 |
+
"learning_rate": 3.2133237993087835e-05,
|
| 898 |
+
"loss": 1.2861,
|
| 899 |
+
"step": 30000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 10.73,
|
| 903 |
+
"eval_accuracy": 0.7308937823834197,
|
| 904 |
+
"eval_loss": 1.3323109149932861,
|
| 905 |
+
"eval_runtime": 0.7855,
|
| 906 |
+
"eval_samples_per_second": 636.523,
|
| 907 |
+
"eval_steps_per_second": 40.737,
|
| 908 |
+
"step": 30000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 10.9,
|
| 912 |
+
"learning_rate": 3.1835299725896794e-05,
|
| 913 |
+
"loss": 1.2617,
|
| 914 |
+
"step": 30500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 10.9,
|
| 918 |
+
"eval_accuracy": 0.7003344481605351,
|
| 919 |
+
"eval_loss": 1.4562044143676758,
|
| 920 |
+
"eval_runtime": 0.7951,
|
| 921 |
+
"eval_samples_per_second": 628.826,
|
| 922 |
+
"eval_steps_per_second": 40.245,
|
| 923 |
+
"step": 30500
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 11.08,
|
| 927 |
+
"learning_rate": 3.153736145870575e-05,
|
| 928 |
+
"loss": 1.2551,
|
| 929 |
+
"step": 31000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 11.08,
|
| 933 |
+
"eval_accuracy": 0.7169689119170984,
|
| 934 |
+
"eval_loss": 1.4361472129821777,
|
| 935 |
+
"eval_runtime": 0.8647,
|
| 936 |
+
"eval_samples_per_second": 578.22,
|
| 937 |
+
"eval_steps_per_second": 37.006,
|
| 938 |
+
"step": 31000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 11.26,
|
| 942 |
+
"learning_rate": 3.124001906804911e-05,
|
| 943 |
+
"loss": 1.2404,
|
| 944 |
+
"step": 31500
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 11.26,
|
| 948 |
+
"eval_accuracy": 0.7034617896799478,
|
| 949 |
+
"eval_loss": 1.4536628723144531,
|
| 950 |
+
"eval_runtime": 0.7907,
|
| 951 |
+
"eval_samples_per_second": 632.325,
|
| 952 |
+
"eval_steps_per_second": 40.469,
|
| 953 |
+
"step": 31500
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 11.44,
|
| 957 |
+
"learning_rate": 3.0942080800858066e-05,
|
| 958 |
+
"loss": 1.2562,
|
| 959 |
+
"step": 32000
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 11.44,
|
| 963 |
+
"eval_accuracy": 0.7132209980557356,
|
| 964 |
+
"eval_loss": 1.4038574695587158,
|
| 965 |
+
"eval_runtime": 0.7924,
|
| 966 |
+
"eval_samples_per_second": 631.001,
|
| 967 |
+
"eval_steps_per_second": 40.384,
|
| 968 |
+
"step": 32000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 11.62,
|
| 972 |
+
"learning_rate": 3.0644142533667025e-05,
|
| 973 |
+
"loss": 1.2489,
|
| 974 |
+
"step": 32500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 11.62,
|
| 978 |
+
"eval_accuracy": 0.706418918918919,
|
| 979 |
+
"eval_loss": 1.4372212886810303,
|
| 980 |
+
"eval_runtime": 0.8024,
|
| 981 |
+
"eval_samples_per_second": 623.122,
|
| 982 |
+
"eval_steps_per_second": 39.88,
|
| 983 |
+
"step": 32500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 11.8,
|
| 987 |
+
"learning_rate": 3.0346204266475984e-05,
|
| 988 |
+
"loss": 1.2406,
|
| 989 |
+
"step": 33000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 11.8,
|
| 993 |
+
"eval_accuracy": 0.7087442472057857,
|
| 994 |
+
"eval_loss": 1.4926137924194336,
|
| 995 |
+
"eval_runtime": 0.8525,
|
| 996 |
+
"eval_samples_per_second": 586.532,
|
| 997 |
+
"eval_steps_per_second": 37.538,
|
| 998 |
+
"step": 33000
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 11.98,
|
| 1002 |
+
"learning_rate": 3.0048265999284947e-05,
|
| 1003 |
+
"loss": 1.2285,
|
| 1004 |
+
"step": 33500
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 11.98,
|
| 1008 |
+
"eval_accuracy": 0.7152005392652511,
|
| 1009 |
+
"eval_loss": 1.4080321788787842,
|
| 1010 |
+
"eval_runtime": 0.8108,
|
| 1011 |
+
"eval_samples_per_second": 616.703,
|
| 1012 |
+
"eval_steps_per_second": 39.469,
|
| 1013 |
+
"step": 33500
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 12.16,
|
| 1017 |
+
"learning_rate": 2.9750327732093913e-05,
|
| 1018 |
+
"loss": 1.2213,
|
| 1019 |
+
"step": 34000
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 12.16,
|
| 1023 |
+
"eval_accuracy": 0.7170240415854451,
|
| 1024 |
+
"eval_loss": 1.403072476387024,
|
| 1025 |
+
"eval_runtime": 0.8459,
|
| 1026 |
+
"eval_samples_per_second": 591.089,
|
| 1027 |
+
"eval_steps_per_second": 37.83,
|
| 1028 |
+
"step": 34000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 12.33,
|
| 1032 |
+
"learning_rate": 2.9452389464902875e-05,
|
| 1033 |
+
"loss": 1.1998,
|
| 1034 |
+
"step": 34500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 12.33,
|
| 1038 |
+
"eval_accuracy": 0.7222584856396866,
|
| 1039 |
+
"eval_loss": 1.3541438579559326,
|
| 1040 |
+
"eval_runtime": 0.7909,
|
| 1041 |
+
"eval_samples_per_second": 632.16,
|
| 1042 |
+
"eval_steps_per_second": 40.458,
|
| 1043 |
+
"step": 34500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 12.51,
|
| 1047 |
+
"learning_rate": 2.9154451197711835e-05,
|
| 1048 |
+
"loss": 1.2184,
|
| 1049 |
+
"step": 35000
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 12.51,
|
| 1053 |
+
"eval_accuracy": 0.7308441558441559,
|
| 1054 |
+
"eval_loss": 1.3629957437515259,
|
| 1055 |
+
"eval_runtime": 0.8716,
|
| 1056 |
+
"eval_samples_per_second": 573.677,
|
| 1057 |
+
"eval_steps_per_second": 36.715,
|
| 1058 |
+
"step": 35000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 12.69,
|
| 1062 |
+
"learning_rate": 2.8856512930520797e-05,
|
| 1063 |
+
"loss": 1.2195,
|
| 1064 |
+
"step": 35500
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 12.69,
|
| 1068 |
+
"eval_accuracy": 0.7281362594169669,
|
| 1069 |
+
"eval_loss": 1.312456488609314,
|
| 1070 |
+
"eval_runtime": 0.852,
|
| 1071 |
+
"eval_samples_per_second": 586.847,
|
| 1072 |
+
"eval_steps_per_second": 37.558,
|
| 1073 |
+
"step": 35500
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 12.87,
|
| 1077 |
+
"learning_rate": 2.8558574663329756e-05,
|
| 1078 |
+
"loss": 1.2178,
|
| 1079 |
+
"step": 36000
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 12.87,
|
| 1083 |
+
"eval_accuracy": 0.7119236883942767,
|
| 1084 |
+
"eval_loss": 1.4257023334503174,
|
| 1085 |
+
"eval_runtime": 0.8597,
|
| 1086 |
+
"eval_samples_per_second": 581.571,
|
| 1087 |
+
"eval_steps_per_second": 37.221,
|
| 1088 |
+
"step": 36000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 13.05,
|
| 1092 |
+
"learning_rate": 2.8260636396138722e-05,
|
| 1093 |
+
"loss": 1.1918,
|
| 1094 |
+
"step": 36500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 13.05,
|
| 1098 |
+
"eval_accuracy": 0.7152686762778506,
|
| 1099 |
+
"eval_loss": 1.4108035564422607,
|
| 1100 |
+
"eval_runtime": 0.9192,
|
| 1101 |
+
"eval_samples_per_second": 543.96,
|
| 1102 |
+
"eval_steps_per_second": 34.813,
|
| 1103 |
+
"step": 36500
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 13.23,
|
| 1107 |
+
"learning_rate": 2.7963294005482066e-05,
|
| 1108 |
+
"loss": 1.1664,
|
| 1109 |
+
"step": 37000
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 13.23,
|
| 1113 |
+
"eval_accuracy": 0.7226588081204977,
|
| 1114 |
+
"eval_loss": 1.3577048778533936,
|
| 1115 |
+
"eval_runtime": 0.7887,
|
| 1116 |
+
"eval_samples_per_second": 633.948,
|
| 1117 |
+
"eval_steps_per_second": 40.573,
|
| 1118 |
+
"step": 37000
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 13.41,
|
| 1122 |
+
"learning_rate": 2.7665355738291028e-05,
|
| 1123 |
+
"loss": 1.1754,
|
| 1124 |
+
"step": 37500
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 13.41,
|
| 1128 |
+
"eval_accuracy": 0.720593191776205,
|
| 1129 |
+
"eval_loss": 1.377700924873352,
|
| 1130 |
+
"eval_runtime": 0.8445,
|
| 1131 |
+
"eval_samples_per_second": 592.06,
|
| 1132 |
+
"eval_steps_per_second": 37.892,
|
| 1133 |
+
"step": 37500
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 13.59,
|
| 1137 |
+
"learning_rate": 2.7367417471099987e-05,
|
| 1138 |
+
"loss": 1.1855,
|
| 1139 |
+
"step": 38000
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 13.59,
|
| 1143 |
+
"eval_accuracy": 0.7354008578027054,
|
| 1144 |
+
"eval_loss": 1.350059151649475,
|
| 1145 |
+
"eval_runtime": 0.8109,
|
| 1146 |
+
"eval_samples_per_second": 616.607,
|
| 1147 |
+
"eval_steps_per_second": 39.463,
|
| 1148 |
+
"step": 38000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 13.76,
|
| 1152 |
+
"learning_rate": 2.7070075080443334e-05,
|
| 1153 |
+
"loss": 1.1644,
|
| 1154 |
+
"step": 38500
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 13.76,
|
| 1158 |
+
"eval_accuracy": 0.7206685953069752,
|
| 1159 |
+
"eval_loss": 1.374656081199646,
|
| 1160 |
+
"eval_runtime": 0.8397,
|
| 1161 |
+
"eval_samples_per_second": 595.482,
|
| 1162 |
+
"eval_steps_per_second": 38.111,
|
| 1163 |
+
"step": 38500
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 13.94,
|
| 1167 |
+
"learning_rate": 2.6772136813252297e-05,
|
| 1168 |
+
"loss": 1.1709,
|
| 1169 |
+
"step": 39000
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 13.94,
|
| 1173 |
+
"eval_accuracy": 0.7183739837398374,
|
| 1174 |
+
"eval_loss": 1.3703839778900146,
|
| 1175 |
+
"eval_runtime": 0.8025,
|
| 1176 |
+
"eval_samples_per_second": 623.038,
|
| 1177 |
+
"eval_steps_per_second": 39.874,
|
| 1178 |
+
"step": 39000
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 14.12,
|
| 1182 |
+
"learning_rate": 2.6474198546061256e-05,
|
| 1183 |
+
"loss": 1.1613,
|
| 1184 |
+
"step": 39500
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 14.12,
|
| 1188 |
+
"eval_accuracy": 0.7246875,
|
| 1189 |
+
"eval_loss": 1.4306718111038208,
|
| 1190 |
+
"eval_runtime": 0.8499,
|
| 1191 |
+
"eval_samples_per_second": 588.275,
|
| 1192 |
+
"eval_steps_per_second": 37.65,
|
| 1193 |
+
"step": 39500
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 14.3,
|
| 1197 |
+
"learning_rate": 2.617626027887022e-05,
|
| 1198 |
+
"loss": 1.1443,
|
| 1199 |
+
"step": 40000
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 14.3,
|
| 1203 |
+
"eval_accuracy": 0.7220978573712824,
|
| 1204 |
+
"eval_loss": 1.3189983367919922,
|
| 1205 |
+
"eval_runtime": 0.7903,
|
| 1206 |
+
"eval_samples_per_second": 632.651,
|
| 1207 |
+
"eval_steps_per_second": 40.49,
|
| 1208 |
+
"step": 40000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 14.48,
|
| 1212 |
+
"learning_rate": 2.5878322011679178e-05,
|
| 1213 |
+
"loss": 1.1356,
|
| 1214 |
+
"step": 40500
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 14.48,
|
| 1218 |
+
"eval_accuracy": 0.7331329325317302,
|
| 1219 |
+
"eval_loss": 1.3287793397903442,
|
| 1220 |
+
"eval_runtime": 0.7921,
|
| 1221 |
+
"eval_samples_per_second": 631.257,
|
| 1222 |
+
"eval_steps_per_second": 40.4,
|
| 1223 |
+
"step": 40500
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 14.66,
|
| 1227 |
+
"learning_rate": 2.5580383744488147e-05,
|
| 1228 |
+
"loss": 1.1493,
|
| 1229 |
+
"step": 41000
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 14.66,
|
| 1233 |
+
"eval_accuracy": 0.7240227196792516,
|
| 1234 |
+
"eval_loss": 1.3504801988601685,
|
| 1235 |
+
"eval_runtime": 0.8432,
|
| 1236 |
+
"eval_samples_per_second": 592.975,
|
| 1237 |
+
"eval_steps_per_second": 37.95,
|
| 1238 |
+
"step": 41000
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 14.84,
|
| 1242 |
+
"learning_rate": 2.5283041353831487e-05,
|
| 1243 |
+
"loss": 1.1417,
|
| 1244 |
+
"step": 41500
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 14.84,
|
| 1248 |
+
"eval_accuracy": 0.7320369149637442,
|
| 1249 |
+
"eval_loss": 1.31459379196167,
|
| 1250 |
+
"eval_runtime": 0.8272,
|
| 1251 |
+
"eval_samples_per_second": 604.463,
|
| 1252 |
+
"eval_steps_per_second": 38.686,
|
| 1253 |
+
"step": 41500
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 15.02,
|
| 1257 |
+
"learning_rate": 2.498569896317483e-05,
|
| 1258 |
+
"loss": 1.1349,
|
| 1259 |
+
"step": 42000
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 15.02,
|
| 1263 |
+
"eval_accuracy": 0.7333114107201578,
|
| 1264 |
+
"eval_loss": 1.3545522689819336,
|
| 1265 |
+
"eval_runtime": 0.8634,
|
| 1266 |
+
"eval_samples_per_second": 579.106,
|
| 1267 |
+
"eval_steps_per_second": 37.063,
|
| 1268 |
+
"step": 42000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 15.19,
|
| 1272 |
+
"learning_rate": 2.4687760695983793e-05,
|
| 1273 |
+
"loss": 1.1169,
|
| 1274 |
+
"step": 42500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 15.19,
|
| 1278 |
+
"eval_accuracy": 0.7246922024623803,
|
| 1279 |
+
"eval_loss": 1.37086021900177,
|
| 1280 |
+
"eval_runtime": 0.8611,
|
| 1281 |
+
"eval_samples_per_second": 580.685,
|
| 1282 |
+
"eval_steps_per_second": 37.164,
|
| 1283 |
+
"step": 42500
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 15.37,
|
| 1287 |
+
"learning_rate": 2.4390418305327136e-05,
|
| 1288 |
+
"loss": 1.1187,
|
| 1289 |
+
"step": 43000
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 15.37,
|
| 1293 |
+
"eval_accuracy": 0.7217795484727756,
|
| 1294 |
+
"eval_loss": 1.4242717027664185,
|
| 1295 |
+
"eval_runtime": 0.8265,
|
| 1296 |
+
"eval_samples_per_second": 604.985,
|
| 1297 |
+
"eval_steps_per_second": 38.719,
|
| 1298 |
+
"step": 43000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 15.55,
|
| 1302 |
+
"learning_rate": 2.4092480038136102e-05,
|
| 1303 |
+
"loss": 1.118,
|
| 1304 |
+
"step": 43500
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 15.55,
|
| 1308 |
+
"eval_accuracy": 0.7264245251582806,
|
| 1309 |
+
"eval_loss": 1.3835431337356567,
|
| 1310 |
+
"eval_runtime": 0.8374,
|
| 1311 |
+
"eval_samples_per_second": 597.064,
|
| 1312 |
+
"eval_steps_per_second": 38.212,
|
| 1313 |
+
"step": 43500
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 15.73,
|
| 1317 |
+
"learning_rate": 2.379454177094506e-05,
|
| 1318 |
+
"loss": 1.1165,
|
| 1319 |
+
"step": 44000
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 15.73,
|
| 1323 |
+
"eval_accuracy": 0.7253818654533637,
|
| 1324 |
+
"eval_loss": 1.3239895105361938,
|
| 1325 |
+
"eval_runtime": 0.8499,
|
| 1326 |
+
"eval_samples_per_second": 588.29,
|
| 1327 |
+
"eval_steps_per_second": 37.651,
|
| 1328 |
+
"step": 44000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 15.91,
|
| 1332 |
+
"learning_rate": 2.3496603503754024e-05,
|
| 1333 |
+
"loss": 1.114,
|
| 1334 |
+
"step": 44500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 15.91,
|
| 1338 |
+
"eval_accuracy": 0.7382113821138211,
|
| 1339 |
+
"eval_loss": 1.3263858556747437,
|
| 1340 |
+
"eval_runtime": 0.8424,
|
| 1341 |
+
"eval_samples_per_second": 593.546,
|
| 1342 |
+
"eval_steps_per_second": 37.987,
|
| 1343 |
+
"step": 44500
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 16.09,
|
| 1347 |
+
"learning_rate": 2.3198665236562986e-05,
|
| 1348 |
+
"loss": 1.105,
|
| 1349 |
+
"step": 45000
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 16.09,
|
| 1353 |
+
"eval_accuracy": 0.7333548804137039,
|
| 1354 |
+
"eval_loss": 1.3213739395141602,
|
| 1355 |
+
"eval_runtime": 0.8677,
|
| 1356 |
+
"eval_samples_per_second": 576.224,
|
| 1357 |
+
"eval_steps_per_second": 36.878,
|
| 1358 |
+
"step": 45000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 16.27,
|
| 1362 |
+
"learning_rate": 2.2900726969371946e-05,
|
| 1363 |
+
"loss": 1.0924,
|
| 1364 |
+
"step": 45500
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 16.27,
|
| 1368 |
+
"eval_accuracy": 0.7282392026578073,
|
| 1369 |
+
"eval_loss": 1.384667992591858,
|
| 1370 |
+
"eval_runtime": 0.9421,
|
| 1371 |
+
"eval_samples_per_second": 530.704,
|
| 1372 |
+
"eval_steps_per_second": 33.965,
|
| 1373 |
+
"step": 45500
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 16.45,
|
| 1377 |
+
"learning_rate": 2.260278870218091e-05,
|
| 1378 |
+
"loss": 1.0915,
|
| 1379 |
+
"step": 46000
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 16.45,
|
| 1383 |
+
"eval_accuracy": 0.7317073170731707,
|
| 1384 |
+
"eval_loss": 1.3603721857070923,
|
| 1385 |
+
"eval_runtime": 0.7951,
|
| 1386 |
+
"eval_samples_per_second": 628.874,
|
| 1387 |
+
"eval_steps_per_second": 40.248,
|
| 1388 |
+
"step": 46000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 16.62,
|
| 1392 |
+
"learning_rate": 2.230485043498987e-05,
|
| 1393 |
+
"loss": 1.0968,
|
| 1394 |
+
"step": 46500
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 16.62,
|
| 1398 |
+
"eval_accuracy": 0.7319177173191772,
|
| 1399 |
+
"eval_loss": 1.3539705276489258,
|
| 1400 |
+
"eval_runtime": 0.8815,
|
| 1401 |
+
"eval_samples_per_second": 567.187,
|
| 1402 |
+
"eval_steps_per_second": 36.3,
|
| 1403 |
+
"step": 46500
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 16.8,
|
| 1407 |
+
"learning_rate": 2.2006912167798833e-05,
|
| 1408 |
+
"loss": 1.0772,
|
| 1409 |
+
"step": 47000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 16.8,
|
| 1413 |
+
"eval_accuracy": 0.7306332369013179,
|
| 1414 |
+
"eval_loss": 1.2475004196166992,
|
| 1415 |
+
"eval_runtime": 0.8301,
|
| 1416 |
+
"eval_samples_per_second": 602.308,
|
| 1417 |
+
"eval_steps_per_second": 38.548,
|
| 1418 |
+
"step": 47000
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 16.98,
|
| 1422 |
+
"learning_rate": 2.1708973900607796e-05,
|
| 1423 |
+
"loss": 1.0975,
|
| 1424 |
+
"step": 47500
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 16.98,
|
| 1428 |
+
"eval_accuracy": 0.7448207826372903,
|
| 1429 |
+
"eval_loss": 1.2635700702667236,
|
| 1430 |
+
"eval_runtime": 0.8269,
|
| 1431 |
+
"eval_samples_per_second": 604.655,
|
| 1432 |
+
"eval_steps_per_second": 38.698,
|
| 1433 |
+
"step": 47500
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 17.16,
|
| 1437 |
+
"learning_rate": 2.1411035633416755e-05,
|
| 1438 |
+
"loss": 1.0708,
|
| 1439 |
+
"step": 48000
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 17.16,
|
| 1443 |
+
"eval_accuracy": 0.7182085648904871,
|
| 1444 |
+
"eval_loss": 1.4056382179260254,
|
| 1445 |
+
"eval_runtime": 0.8973,
|
| 1446 |
+
"eval_samples_per_second": 557.236,
|
| 1447 |
+
"eval_steps_per_second": 35.663,
|
| 1448 |
+
"step": 48000
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 17.34,
|
| 1452 |
+
"learning_rate": 2.111309736622572e-05,
|
| 1453 |
+
"loss": 1.0654,
|
| 1454 |
+
"step": 48500
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 17.34,
|
| 1458 |
+
"eval_accuracy": 0.727630285152409,
|
| 1459 |
+
"eval_loss": 1.3769292831420898,
|
| 1460 |
+
"eval_runtime": 0.8377,
|
| 1461 |
+
"eval_samples_per_second": 596.886,
|
| 1462 |
+
"eval_steps_per_second": 38.201,
|
| 1463 |
+
"step": 48500
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 17.52,
|
| 1467 |
+
"learning_rate": 2.081515909903468e-05,
|
| 1468 |
+
"loss": 1.0676,
|
| 1469 |
+
"step": 49000
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 17.52,
|
| 1473 |
+
"eval_accuracy": 0.7224234441883438,
|
| 1474 |
+
"eval_loss": 1.33571457862854,
|
| 1475 |
+
"eval_runtime": 0.7909,
|
| 1476 |
+
"eval_samples_per_second": 632.166,
|
| 1477 |
+
"eval_steps_per_second": 40.459,
|
| 1478 |
+
"step": 49000
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 17.7,
|
| 1482 |
+
"learning_rate": 2.0517220831843643e-05,
|
| 1483 |
+
"loss": 1.0507,
|
| 1484 |
+
"step": 49500
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 17.7,
|
| 1488 |
+
"eval_accuracy": 0.712369109947644,
|
| 1489 |
+
"eval_loss": 1.4087713956832886,
|
| 1490 |
+
"eval_runtime": 0.7955,
|
| 1491 |
+
"eval_samples_per_second": 628.504,
|
| 1492 |
+
"eval_steps_per_second": 40.224,
|
| 1493 |
+
"step": 49500
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 17.88,
|
| 1497 |
+
"learning_rate": 2.0219282564652605e-05,
|
| 1498 |
+
"loss": 1.0424,
|
| 1499 |
+
"step": 50000
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 17.88,
|
| 1503 |
+
"eval_accuracy": 0.7314667515112949,
|
| 1504 |
+
"eval_loss": 1.3146371841430664,
|
| 1505 |
+
"eval_runtime": 0.7881,
|
| 1506 |
+
"eval_samples_per_second": 634.428,
|
| 1507 |
+
"eval_steps_per_second": 40.603,
|
| 1508 |
+
"step": 50000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 18.06,
|
| 1512 |
+
"learning_rate": 1.9921344297461568e-05,
|
| 1513 |
+
"loss": 1.0524,
|
| 1514 |
+
"step": 50500
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 18.06,
|
| 1518 |
+
"eval_accuracy": 0.7393395319012503,
|
| 1519 |
+
"eval_loss": 1.28960382938385,
|
| 1520 |
+
"eval_runtime": 0.8581,
|
| 1521 |
+
"eval_samples_per_second": 582.683,
|
| 1522 |
+
"eval_steps_per_second": 37.292,
|
| 1523 |
+
"step": 50500
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 18.23,
|
| 1527 |
+
"learning_rate": 1.962340603027053e-05,
|
| 1528 |
+
"loss": 1.0349,
|
| 1529 |
+
"step": 51000
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 18.23,
|
| 1533 |
+
"eval_accuracy": 0.7191558441558441,
|
| 1534 |
+
"eval_loss": 1.3986730575561523,
|
| 1535 |
+
"eval_runtime": 0.7904,
|
| 1536 |
+
"eval_samples_per_second": 632.599,
|
| 1537 |
+
"eval_steps_per_second": 40.486,
|
| 1538 |
+
"step": 51000
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 18.41,
|
| 1542 |
+
"learning_rate": 1.932546776307949e-05,
|
| 1543 |
+
"loss": 1.0217,
|
| 1544 |
+
"step": 51500
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 18.41,
|
| 1548 |
+
"eval_accuracy": 0.7380645161290322,
|
| 1549 |
+
"eval_loss": 1.2937612533569336,
|
| 1550 |
+
"eval_runtime": 0.8575,
|
| 1551 |
+
"eval_samples_per_second": 583.089,
|
| 1552 |
+
"eval_steps_per_second": 37.318,
|
| 1553 |
+
"step": 51500
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 18.59,
|
| 1557 |
+
"learning_rate": 1.9028125372422833e-05,
|
| 1558 |
+
"loss": 1.0238,
|
| 1559 |
+
"step": 52000
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 18.59,
|
| 1563 |
+
"eval_accuracy": 0.738654650788542,
|
| 1564 |
+
"eval_loss": 1.296163558959961,
|
| 1565 |
+
"eval_runtime": 0.8423,
|
| 1566 |
+
"eval_samples_per_second": 593.617,
|
| 1567 |
+
"eval_steps_per_second": 37.992,
|
| 1568 |
+
"step": 52000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 18.77,
|
| 1572 |
+
"learning_rate": 1.87301871052318e-05,
|
| 1573 |
+
"loss": 1.0292,
|
| 1574 |
+
"step": 52500
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 18.77,
|
| 1578 |
+
"eval_accuracy": 0.737131757850437,
|
| 1579 |
+
"eval_loss": 1.3194587230682373,
|
| 1580 |
+
"eval_runtime": 0.8232,
|
| 1581 |
+
"eval_samples_per_second": 607.358,
|
| 1582 |
+
"eval_steps_per_second": 38.871,
|
| 1583 |
+
"step": 52500
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 18.95,
|
| 1587 |
+
"learning_rate": 1.8433440591109523e-05,
|
| 1588 |
+
"loss": 1.0426,
|
| 1589 |
+
"step": 53000
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 18.95,
|
| 1593 |
+
"eval_accuracy": 0.7411687025420931,
|
| 1594 |
+
"eval_loss": 1.2835460901260376,
|
| 1595 |
+
"eval_runtime": 0.7859,
|
| 1596 |
+
"eval_samples_per_second": 636.221,
|
| 1597 |
+
"eval_steps_per_second": 40.718,
|
| 1598 |
+
"step": 53000
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 19.13,
|
| 1602 |
+
"learning_rate": 1.8135502323918486e-05,
|
| 1603 |
+
"loss": 1.0196,
|
| 1604 |
+
"step": 53500
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 19.13,
|
| 1608 |
+
"eval_accuracy": 0.747275204359673,
|
| 1609 |
+
"eval_loss": 1.234621524810791,
|
| 1610 |
+
"eval_runtime": 0.8361,
|
| 1611 |
+
"eval_samples_per_second": 597.997,
|
| 1612 |
+
"eval_steps_per_second": 38.272,
|
| 1613 |
+
"step": 53500
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 19.31,
|
| 1617 |
+
"learning_rate": 1.7837564056727445e-05,
|
| 1618 |
+
"loss": 1.012,
|
| 1619 |
+
"step": 54000
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 19.31,
|
| 1623 |
+
"eval_accuracy": 0.7338292367399741,
|
| 1624 |
+
"eval_loss": 1.3665757179260254,
|
| 1625 |
+
"eval_runtime": 0.8157,
|
| 1626 |
+
"eval_samples_per_second": 612.938,
|
| 1627 |
+
"eval_steps_per_second": 39.228,
|
| 1628 |
+
"step": 54000
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 19.49,
|
| 1632 |
+
"learning_rate": 1.753962578953641e-05,
|
| 1633 |
+
"loss": 1.0256,
|
| 1634 |
+
"step": 54500
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 19.49,
|
| 1638 |
+
"eval_accuracy": 0.7364842991259307,
|
| 1639 |
+
"eval_loss": 1.3140363693237305,
|
| 1640 |
+
"eval_runtime": 0.7949,
|
| 1641 |
+
"eval_samples_per_second": 628.974,
|
| 1642 |
+
"eval_steps_per_second": 40.254,
|
| 1643 |
+
"step": 54500
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 19.66,
|
| 1647 |
+
"learning_rate": 1.724168752234537e-05,
|
| 1648 |
+
"loss": 0.9824,
|
| 1649 |
+
"step": 55000
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 19.66,
|
| 1653 |
+
"eval_accuracy": 0.7416496250852079,
|
| 1654 |
+
"eval_loss": 1.2764383554458618,
|
| 1655 |
+
"eval_runtime": 0.8178,
|
| 1656 |
+
"eval_samples_per_second": 611.417,
|
| 1657 |
+
"eval_steps_per_second": 39.131,
|
| 1658 |
+
"step": 55000
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 19.84,
|
| 1662 |
+
"learning_rate": 1.6943749255154336e-05,
|
| 1663 |
+
"loss": 1.0048,
|
| 1664 |
+
"step": 55500
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 19.84,
|
| 1668 |
+
"eval_accuracy": 0.7487891507910881,
|
| 1669 |
+
"eval_loss": 1.2514091730117798,
|
| 1670 |
+
"eval_runtime": 0.8164,
|
| 1671 |
+
"eval_samples_per_second": 612.474,
|
| 1672 |
+
"eval_steps_per_second": 39.198,
|
| 1673 |
+
"step": 55500
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 20.02,
|
| 1677 |
+
"learning_rate": 1.6645810987963295e-05,
|
| 1678 |
+
"loss": 0.9947,
|
| 1679 |
+
"step": 56000
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 20.02,
|
| 1683 |
+
"eval_accuracy": 0.7431572246976448,
|
| 1684 |
+
"eval_loss": 1.3350915908813477,
|
| 1685 |
+
"eval_runtime": 0.7912,
|
| 1686 |
+
"eval_samples_per_second": 631.988,
|
| 1687 |
+
"eval_steps_per_second": 40.447,
|
| 1688 |
+
"step": 56000
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 20.2,
|
| 1692 |
+
"learning_rate": 1.634846859730664e-05,
|
| 1693 |
+
"loss": 0.977,
|
| 1694 |
+
"step": 56500
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 20.2,
|
| 1698 |
+
"eval_accuracy": 0.7451045469631596,
|
| 1699 |
+
"eval_loss": 1.2854044437408447,
|
| 1700 |
+
"eval_runtime": 0.8499,
|
| 1701 |
+
"eval_samples_per_second": 588.28,
|
| 1702 |
+
"eval_steps_per_second": 37.65,
|
| 1703 |
+
"step": 56500
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 20.38,
|
| 1707 |
+
"learning_rate": 1.60505303301156e-05,
|
| 1708 |
+
"loss": 0.9862,
|
| 1709 |
+
"step": 57000
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 20.38,
|
| 1713 |
+
"eval_accuracy": 0.7285475792988314,
|
| 1714 |
+
"eval_loss": 1.366584300994873,
|
| 1715 |
+
"eval_runtime": 0.816,
|
| 1716 |
+
"eval_samples_per_second": 612.774,
|
| 1717 |
+
"eval_steps_per_second": 39.218,
|
| 1718 |
+
"step": 57000
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 20.56,
|
| 1722 |
+
"learning_rate": 1.5752592062924564e-05,
|
| 1723 |
+
"loss": 0.9699,
|
| 1724 |
+
"step": 57500
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 20.56,
|
| 1728 |
+
"eval_accuracy": 0.7347811780190853,
|
| 1729 |
+
"eval_loss": 1.3123427629470825,
|
| 1730 |
+
"eval_runtime": 0.7779,
|
| 1731 |
+
"eval_samples_per_second": 642.731,
|
| 1732 |
+
"eval_steps_per_second": 41.135,
|
| 1733 |
+
"step": 57500
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 20.74,
|
| 1737 |
+
"learning_rate": 1.5454653795733526e-05,
|
| 1738 |
+
"loss": 0.977,
|
| 1739 |
+
"step": 58000
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 20.74,
|
| 1743 |
+
"eval_accuracy": 0.7254770672915969,
|
| 1744 |
+
"eval_loss": 1.3425793647766113,
|
| 1745 |
+
"eval_runtime": 0.8285,
|
| 1746 |
+
"eval_samples_per_second": 603.485,
|
| 1747 |
+
"eval_steps_per_second": 38.623,
|
| 1748 |
+
"step": 58000
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 20.92,
|
| 1752 |
+
"learning_rate": 1.5157311405076868e-05,
|
| 1753 |
+
"loss": 0.9749,
|
| 1754 |
+
"step": 58500
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 20.92,
|
| 1758 |
+
"eval_accuracy": 0.7296604740550929,
|
| 1759 |
+
"eval_loss": 1.3763371706008911,
|
| 1760 |
+
"eval_runtime": 0.7855,
|
| 1761 |
+
"eval_samples_per_second": 636.556,
|
| 1762 |
+
"eval_steps_per_second": 40.74,
|
| 1763 |
+
"step": 58500
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 21.09,
|
| 1767 |
+
"learning_rate": 1.4859373137885832e-05,
|
| 1768 |
+
"loss": 0.9505,
|
| 1769 |
+
"step": 59000
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 21.09,
|
| 1773 |
+
"eval_accuracy": 0.7434469200524246,
|
| 1774 |
+
"eval_loss": 1.2372225522994995,
|
| 1775 |
+
"eval_runtime": 0.7967,
|
| 1776 |
+
"eval_samples_per_second": 627.592,
|
| 1777 |
+
"eval_steps_per_second": 40.166,
|
| 1778 |
+
"step": 59000
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 21.27,
|
| 1782 |
+
"learning_rate": 1.4561434870694793e-05,
|
| 1783 |
+
"loss": 0.9438,
|
| 1784 |
+
"step": 59500
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 21.27,
|
| 1788 |
+
"eval_accuracy": 0.7159090909090909,
|
| 1789 |
+
"eval_loss": 1.433412790298462,
|
| 1790 |
+
"eval_runtime": 0.7929,
|
| 1791 |
+
"eval_samples_per_second": 630.567,
|
| 1792 |
+
"eval_steps_per_second": 40.356,
|
| 1793 |
+
"step": 59500
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 21.45,
|
| 1797 |
+
"learning_rate": 1.4263496603503754e-05,
|
| 1798 |
+
"loss": 0.944,
|
| 1799 |
+
"step": 60000
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 21.45,
|
| 1803 |
+
"eval_accuracy": 0.7507936507936508,
|
| 1804 |
+
"eval_loss": 1.269033432006836,
|
| 1805 |
+
"eval_runtime": 0.8274,
|
| 1806 |
+
"eval_samples_per_second": 604.314,
|
| 1807 |
+
"eval_steps_per_second": 38.676,
|
| 1808 |
+
"step": 60000
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 21.63,
|
| 1812 |
+
"learning_rate": 1.3965558336312718e-05,
|
| 1813 |
+
"loss": 0.9427,
|
| 1814 |
+
"step": 60500
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 21.63,
|
| 1818 |
+
"eval_accuracy": 0.7485941118094608,
|
| 1819 |
+
"eval_loss": 1.2185914516448975,
|
| 1820 |
+
"eval_runtime": 0.7923,
|
| 1821 |
+
"eval_samples_per_second": 631.05,
|
| 1822 |
+
"eval_steps_per_second": 40.387,
|
| 1823 |
+
"step": 60500
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 21.81,
|
| 1827 |
+
"learning_rate": 1.3667620069121679e-05,
|
| 1828 |
+
"loss": 0.9553,
|
| 1829 |
+
"step": 61000
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 21.81,
|
| 1833 |
+
"eval_accuracy": 0.726882430647292,
|
| 1834 |
+
"eval_loss": 1.3940554857254028,
|
| 1835 |
+
"eval_runtime": 0.7961,
|
| 1836 |
+
"eval_samples_per_second": 628.083,
|
| 1837 |
+
"eval_steps_per_second": 40.197,
|
| 1838 |
+
"step": 61000
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 21.99,
|
| 1842 |
+
"learning_rate": 1.3369681801930641e-05,
|
| 1843 |
+
"loss": 0.9571,
|
| 1844 |
+
"step": 61500
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 21.99,
|
| 1848 |
+
"eval_accuracy": 0.7273940607273941,
|
| 1849 |
+
"eval_loss": 1.4162867069244385,
|
| 1850 |
+
"eval_runtime": 0.791,
|
| 1851 |
+
"eval_samples_per_second": 632.128,
|
| 1852 |
+
"eval_steps_per_second": 40.456,
|
| 1853 |
+
"step": 61500
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 22.17,
|
| 1857 |
+
"learning_rate": 1.3071743534739602e-05,
|
| 1858 |
+
"loss": 0.932,
|
| 1859 |
+
"step": 62000
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 22.17,
|
| 1863 |
+
"eval_accuracy": 0.7522727272727273,
|
| 1864 |
+
"eval_loss": 1.2717351913452148,
|
| 1865 |
+
"eval_runtime": 0.796,
|
| 1866 |
+
"eval_samples_per_second": 628.103,
|
| 1867 |
+
"eval_steps_per_second": 40.199,
|
| 1868 |
+
"step": 62000
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 22.35,
|
| 1872 |
+
"learning_rate": 1.2773805267548563e-05,
|
| 1873 |
+
"loss": 0.9166,
|
| 1874 |
+
"step": 62500
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 22.35,
|
| 1878 |
+
"eval_accuracy": 0.73956326268465,
|
| 1879 |
+
"eval_loss": 1.217714786529541,
|
| 1880 |
+
"eval_runtime": 0.8289,
|
| 1881 |
+
"eval_samples_per_second": 603.185,
|
| 1882 |
+
"eval_steps_per_second": 38.604,
|
| 1883 |
+
"step": 62500
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 22.52,
|
| 1887 |
+
"learning_rate": 1.2475867000357526e-05,
|
| 1888 |
+
"loss": 0.9301,
|
| 1889 |
+
"step": 63000
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 22.52,
|
| 1893 |
+
"eval_accuracy": 0.7377950210151956,
|
| 1894 |
+
"eval_loss": 1.3264496326446533,
|
| 1895 |
+
"eval_runtime": 0.8524,
|
| 1896 |
+
"eval_samples_per_second": 586.56,
|
| 1897 |
+
"eval_steps_per_second": 37.54,
|
| 1898 |
+
"step": 63000
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 22.7,
|
| 1902 |
+
"learning_rate": 1.2177928733166488e-05,
|
| 1903 |
+
"loss": 0.9351,
|
| 1904 |
+
"step": 63500
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 22.7,
|
| 1908 |
+
"eval_accuracy": 0.752010292698617,
|
| 1909 |
+
"eval_loss": 1.2570440769195557,
|
| 1910 |
+
"eval_runtime": 0.785,
|
| 1911 |
+
"eval_samples_per_second": 636.94,
|
| 1912 |
+
"eval_steps_per_second": 40.764,
|
| 1913 |
+
"step": 63500
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 22.88,
|
| 1917 |
+
"learning_rate": 1.1879990465975451e-05,
|
| 1918 |
+
"loss": 0.9211,
|
| 1919 |
+
"step": 64000
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 22.88,
|
| 1923 |
+
"eval_accuracy": 0.75,
|
| 1924 |
+
"eval_loss": 1.2638896703720093,
|
| 1925 |
+
"eval_runtime": 0.8753,
|
| 1926 |
+
"eval_samples_per_second": 571.265,
|
| 1927 |
+
"eval_steps_per_second": 36.561,
|
| 1928 |
+
"step": 64000
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 23.06,
|
| 1932 |
+
"learning_rate": 1.1582052198784414e-05,
|
| 1933 |
+
"loss": 0.9211,
|
| 1934 |
+
"step": 64500
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 23.06,
|
| 1938 |
+
"eval_accuracy": 0.7605543022881083,
|
| 1939 |
+
"eval_loss": 1.2376515865325928,
|
| 1940 |
+
"eval_runtime": 0.7946,
|
| 1941 |
+
"eval_samples_per_second": 629.265,
|
| 1942 |
+
"eval_steps_per_second": 40.273,
|
| 1943 |
+
"step": 64500
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 23.24,
|
| 1947 |
+
"learning_rate": 1.1284113931593374e-05,
|
| 1948 |
+
"loss": 0.9196,
|
| 1949 |
+
"step": 65000
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 23.24,
|
| 1953 |
+
"eval_accuracy": 0.7485168094924193,
|
| 1954 |
+
"eval_loss": 1.2738728523254395,
|
| 1955 |
+
"eval_runtime": 0.8576,
|
| 1956 |
+
"eval_samples_per_second": 583.036,
|
| 1957 |
+
"eval_steps_per_second": 37.314,
|
| 1958 |
+
"step": 65000
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 23.42,
|
| 1962 |
+
"learning_rate": 1.098677154093672e-05,
|
| 1963 |
+
"loss": 0.9062,
|
| 1964 |
+
"step": 65500
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 23.42,
|
| 1968 |
+
"eval_accuracy": 0.7365366010964205,
|
| 1969 |
+
"eval_loss": 1.3262896537780762,
|
| 1970 |
+
"eval_runtime": 0.8401,
|
| 1971 |
+
"eval_samples_per_second": 595.164,
|
| 1972 |
+
"eval_steps_per_second": 38.09,
|
| 1973 |
+
"step": 65500
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 23.6,
|
| 1977 |
+
"learning_rate": 1.068883327374568e-05,
|
| 1978 |
+
"loss": 0.8965,
|
| 1979 |
+
"step": 66000
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 23.6,
|
| 1983 |
+
"eval_accuracy": 0.7455209024552091,
|
| 1984 |
+
"eval_loss": 1.2814128398895264,
|
| 1985 |
+
"eval_runtime": 0.778,
|
| 1986 |
+
"eval_samples_per_second": 642.691,
|
| 1987 |
+
"eval_steps_per_second": 41.132,
|
| 1988 |
+
"step": 66000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 23.78,
|
| 1992 |
+
"learning_rate": 1.0392086759623406e-05,
|
| 1993 |
+
"loss": 0.9004,
|
| 1994 |
+
"step": 66500
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 23.78,
|
| 1998 |
+
"eval_accuracy": 0.7561779242174629,
|
| 1999 |
+
"eval_loss": 1.2108628749847412,
|
| 2000 |
+
"eval_runtime": 0.8669,
|
| 2001 |
+
"eval_samples_per_second": 576.736,
|
| 2002 |
+
"eval_steps_per_second": 36.911,
|
| 2003 |
+
"step": 66500
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 23.95,
|
| 2007 |
+
"learning_rate": 1.0094148492432369e-05,
|
| 2008 |
+
"loss": 0.9094,
|
| 2009 |
+
"step": 67000
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 23.95,
|
| 2013 |
+
"eval_accuracy": 0.7528089887640449,
|
| 2014 |
+
"eval_loss": 1.2629289627075195,
|
| 2015 |
+
"eval_runtime": 0.8653,
|
| 2016 |
+
"eval_samples_per_second": 577.859,
|
| 2017 |
+
"eval_steps_per_second": 36.983,
|
| 2018 |
+
"step": 67000
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 24.13,
|
| 2022 |
+
"learning_rate": 9.79621022524133e-06,
|
| 2023 |
+
"loss": 0.8937,
|
| 2024 |
+
"step": 67500
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 24.13,
|
| 2028 |
+
"eval_accuracy": 0.7375168690958165,
|
| 2029 |
+
"eval_loss": 1.2770532369613647,
|
| 2030 |
+
"eval_runtime": 0.8492,
|
| 2031 |
+
"eval_samples_per_second": 588.814,
|
| 2032 |
+
"eval_steps_per_second": 37.684,
|
| 2033 |
+
"step": 67500
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 24.31,
|
| 2037 |
+
"learning_rate": 9.498271958050292e-06,
|
| 2038 |
+
"loss": 0.8711,
|
| 2039 |
+
"step": 68000
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 24.31,
|
| 2043 |
+
"eval_accuracy": 0.7353233830845771,
|
| 2044 |
+
"eval_loss": 1.3746039867401123,
|
| 2045 |
+
"eval_runtime": 0.7929,
|
| 2046 |
+
"eval_samples_per_second": 630.629,
|
| 2047 |
+
"eval_steps_per_second": 40.36,
|
| 2048 |
+
"step": 68000
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 24.49,
|
| 2052 |
+
"learning_rate": 9.200333690859255e-06,
|
| 2053 |
+
"loss": 0.8972,
|
| 2054 |
+
"step": 68500
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 24.49,
|
| 2058 |
+
"eval_accuracy": 0.7453750420450723,
|
| 2059 |
+
"eval_loss": 1.2529133558273315,
|
| 2060 |
+
"eval_runtime": 0.8497,
|
| 2061 |
+
"eval_samples_per_second": 588.462,
|
| 2062 |
+
"eval_steps_per_second": 37.662,
|
| 2063 |
+
"step": 68500
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 24.67,
|
| 2067 |
+
"learning_rate": 8.902395423668217e-06,
|
| 2068 |
+
"loss": 0.8863,
|
| 2069 |
+
"step": 69000
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 24.67,
|
| 2073 |
+
"eval_accuracy": 0.7359154929577465,
|
| 2074 |
+
"eval_loss": 1.3219196796417236,
|
| 2075 |
+
"eval_runtime": 0.8149,
|
| 2076 |
+
"eval_samples_per_second": 613.598,
|
| 2077 |
+
"eval_steps_per_second": 39.27,
|
| 2078 |
+
"step": 69000
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 24.85,
|
| 2082 |
+
"learning_rate": 8.604457156477178e-06,
|
| 2083 |
+
"loss": 0.8823,
|
| 2084 |
+
"step": 69500
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 24.85,
|
| 2088 |
+
"eval_accuracy": 0.7367235275185066,
|
| 2089 |
+
"eval_loss": 1.313620924949646,
|
| 2090 |
+
"eval_runtime": 0.8311,
|
| 2091 |
+
"eval_samples_per_second": 601.621,
|
| 2092 |
+
"eval_steps_per_second": 38.504,
|
| 2093 |
+
"step": 69500
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 25.03,
|
| 2097 |
+
"learning_rate": 8.306518889286139e-06,
|
| 2098 |
+
"loss": 0.8759,
|
| 2099 |
+
"step": 70000
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 25.03,
|
| 2103 |
+
"eval_accuracy": 0.7427812811151676,
|
| 2104 |
+
"eval_loss": 1.3151708841323853,
|
| 2105 |
+
"eval_runtime": 0.7986,
|
| 2106 |
+
"eval_samples_per_second": 626.093,
|
| 2107 |
+
"eval_steps_per_second": 40.07,
|
| 2108 |
+
"step": 70000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 25.21,
|
| 2112 |
+
"learning_rate": 8.008580622095102e-06,
|
| 2113 |
+
"loss": 0.8722,
|
| 2114 |
+
"step": 70500
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 25.21,
|
| 2118 |
+
"eval_accuracy": 0.7569644572526417,
|
| 2119 |
+
"eval_loss": 1.3108021020889282,
|
| 2120 |
+
"eval_runtime": 0.8281,
|
| 2121 |
+
"eval_samples_per_second": 603.782,
|
| 2122 |
+
"eval_steps_per_second": 38.642,
|
| 2123 |
+
"step": 70500
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 25.38,
|
| 2127 |
+
"learning_rate": 7.710642354904064e-06,
|
| 2128 |
+
"loss": 0.8548,
|
| 2129 |
+
"step": 71000
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 25.38,
|
| 2133 |
+
"eval_accuracy": 0.7367716008037508,
|
| 2134 |
+
"eval_loss": 1.3503183126449585,
|
| 2135 |
+
"eval_runtime": 0.7871,
|
| 2136 |
+
"eval_samples_per_second": 635.233,
|
| 2137 |
+
"eval_steps_per_second": 40.655,
|
| 2138 |
+
"step": 71000
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 25.56,
|
| 2142 |
+
"learning_rate": 7.412704087713027e-06,
|
| 2143 |
+
"loss": 0.8728,
|
| 2144 |
+
"step": 71500
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 25.56,
|
| 2148 |
+
"eval_accuracy": 0.7402768622280818,
|
| 2149 |
+
"eval_loss": 1.3091211318969727,
|
| 2150 |
+
"eval_runtime": 0.8581,
|
| 2151 |
+
"eval_samples_per_second": 582.712,
|
| 2152 |
+
"eval_steps_per_second": 37.294,
|
| 2153 |
+
"step": 71500
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 25.74,
|
| 2157 |
+
"learning_rate": 7.114765820521989e-06,
|
| 2158 |
+
"loss": 0.8633,
|
| 2159 |
+
"step": 72000
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 25.74,
|
| 2163 |
+
"eval_accuracy": 0.7416481069042317,
|
| 2164 |
+
"eval_loss": 1.2952070236206055,
|
| 2165 |
+
"eval_runtime": 0.8515,
|
| 2166 |
+
"eval_samples_per_second": 587.213,
|
| 2167 |
+
"eval_steps_per_second": 37.582,
|
| 2168 |
+
"step": 72000
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 25.92,
|
| 2172 |
+
"learning_rate": 6.816827553330949e-06,
|
| 2173 |
+
"loss": 0.8612,
|
| 2174 |
+
"step": 72500
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 25.92,
|
| 2178 |
+
"eval_accuracy": 0.7719072164948454,
|
| 2179 |
+
"eval_loss": 1.1612097024917603,
|
| 2180 |
+
"eval_runtime": 0.7967,
|
| 2181 |
+
"eval_samples_per_second": 627.618,
|
| 2182 |
+
"eval_steps_per_second": 40.168,
|
| 2183 |
+
"step": 72500
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 26.1,
|
| 2187 |
+
"learning_rate": 6.5194851626742935e-06,
|
| 2188 |
+
"loss": 0.8677,
|
| 2189 |
+
"step": 73000
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 26.1,
|
| 2193 |
+
"eval_accuracy": 0.7449731903485255,
|
| 2194 |
+
"eval_loss": 1.2855061292648315,
|
| 2195 |
+
"eval_runtime": 0.8112,
|
| 2196 |
+
"eval_samples_per_second": 616.391,
|
| 2197 |
+
"eval_steps_per_second": 39.449,
|
| 2198 |
+
"step": 73000
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 26.28,
|
| 2202 |
+
"learning_rate": 6.2221427720176384e-06,
|
| 2203 |
+
"loss": 0.8526,
|
| 2204 |
+
"step": 73500
|
| 2205 |
+
},
|
| 2206 |
+
{
|
| 2207 |
+
"epoch": 26.28,
|
| 2208 |
+
"eval_accuracy": 0.7544929396662388,
|
| 2209 |
+
"eval_loss": 1.297914981842041,
|
| 2210 |
+
"eval_runtime": 0.8472,
|
| 2211 |
+
"eval_samples_per_second": 590.203,
|
| 2212 |
+
"eval_steps_per_second": 37.773,
|
| 2213 |
+
"step": 73500
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 26.46,
|
| 2217 |
+
"learning_rate": 5.9242045048266e-06,
|
| 2218 |
+
"loss": 0.8594,
|
| 2219 |
+
"step": 74000
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 26.46,
|
| 2223 |
+
"eval_accuracy": 0.7598070739549839,
|
| 2224 |
+
"eval_loss": 1.2569819688796997,
|
| 2225 |
+
"eval_runtime": 0.7923,
|
| 2226 |
+
"eval_samples_per_second": 631.066,
|
| 2227 |
+
"eval_steps_per_second": 40.388,
|
| 2228 |
+
"step": 74000
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 26.64,
|
| 2232 |
+
"learning_rate": 5.626266237635562e-06,
|
| 2233 |
+
"loss": 0.8481,
|
| 2234 |
+
"step": 74500
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 26.64,
|
| 2238 |
+
"eval_accuracy": 0.7491992312620115,
|
| 2239 |
+
"eval_loss": 1.2336714267730713,
|
| 2240 |
+
"eval_runtime": 0.8668,
|
| 2241 |
+
"eval_samples_per_second": 576.839,
|
| 2242 |
+
"eval_steps_per_second": 36.918,
|
| 2243 |
+
"step": 74500
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 26.81,
|
| 2247 |
+
"learning_rate": 5.3283279704445245e-06,
|
| 2248 |
+
"loss": 0.855,
|
| 2249 |
+
"step": 75000
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 26.81,
|
| 2253 |
+
"eval_accuracy": 0.7443507588532884,
|
| 2254 |
+
"eval_loss": 1.2874828577041626,
|
| 2255 |
+
"eval_runtime": 0.7926,
|
| 2256 |
+
"eval_samples_per_second": 630.803,
|
| 2257 |
+
"eval_steps_per_second": 40.371,
|
| 2258 |
+
"step": 75000
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 26.99,
|
| 2262 |
+
"learning_rate": 5.030389703253486e-06,
|
| 2263 |
+
"loss": 0.835,
|
| 2264 |
+
"step": 75500
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 26.99,
|
| 2268 |
+
"eval_accuracy": 0.7584731819677526,
|
| 2269 |
+
"eval_loss": 1.2270281314849854,
|
| 2270 |
+
"eval_runtime": 0.8172,
|
| 2271 |
+
"eval_samples_per_second": 611.826,
|
| 2272 |
+
"eval_steps_per_second": 39.157,
|
| 2273 |
+
"step": 75500
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 27.17,
|
| 2277 |
+
"learning_rate": 4.732451436062448e-06,
|
| 2278 |
+
"loss": 0.8309,
|
| 2279 |
+
"step": 76000
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 27.17,
|
| 2283 |
+
"eval_accuracy": 0.7389322916666666,
|
| 2284 |
+
"eval_loss": 1.2539992332458496,
|
| 2285 |
+
"eval_runtime": 0.8357,
|
| 2286 |
+
"eval_samples_per_second": 598.292,
|
| 2287 |
+
"eval_steps_per_second": 38.291,
|
| 2288 |
+
"step": 76000
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 27.35,
|
| 2292 |
+
"learning_rate": 4.43451316887141e-06,
|
| 2293 |
+
"loss": 0.8326,
|
| 2294 |
+
"step": 76500
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 27.35,
|
| 2298 |
+
"eval_accuracy": 0.7374631268436578,
|
| 2299 |
+
"eval_loss": 1.3610546588897705,
|
| 2300 |
+
"eval_runtime": 0.7953,
|
| 2301 |
+
"eval_samples_per_second": 628.676,
|
| 2302 |
+
"eval_steps_per_second": 40.235,
|
| 2303 |
+
"step": 76500
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"epoch": 27.53,
|
| 2307 |
+
"learning_rate": 4.136574901680372e-06,
|
| 2308 |
+
"loss": 0.8398,
|
| 2309 |
+
"step": 77000
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 27.53,
|
| 2313 |
+
"eval_accuracy": 0.7504918032786885,
|
| 2314 |
+
"eval_loss": 1.2247506380081177,
|
| 2315 |
+
"eval_runtime": 0.859,
|
| 2316 |
+
"eval_samples_per_second": 582.099,
|
| 2317 |
+
"eval_steps_per_second": 37.254,
|
| 2318 |
+
"step": 77000
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 27.71,
|
| 2322 |
+
"learning_rate": 3.838636634489334e-06,
|
| 2323 |
+
"loss": 0.8304,
|
| 2324 |
+
"step": 77500
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 27.71,
|
| 2328 |
+
"eval_accuracy": 0.7607282184655396,
|
| 2329 |
+
"eval_loss": 1.2403171062469482,
|
| 2330 |
+
"eval_runtime": 0.9471,
|
| 2331 |
+
"eval_samples_per_second": 527.922,
|
| 2332 |
+
"eval_steps_per_second": 33.787,
|
| 2333 |
+
"step": 77500
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 27.89,
|
| 2337 |
+
"learning_rate": 3.5406983672982957e-06,
|
| 2338 |
+
"loss": 0.8373,
|
| 2339 |
+
"step": 78000
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 27.89,
|
| 2343 |
+
"eval_accuracy": 0.7611295681063123,
|
| 2344 |
+
"eval_loss": 1.1708660125732422,
|
| 2345 |
+
"eval_runtime": 0.8284,
|
| 2346 |
+
"eval_samples_per_second": 603.609,
|
| 2347 |
+
"eval_steps_per_second": 38.631,
|
| 2348 |
+
"step": 78000
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 28.07,
|
| 2352 |
+
"learning_rate": 3.2427601001072583e-06,
|
| 2353 |
+
"loss": 0.8462,
|
| 2354 |
+
"step": 78500
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 28.07,
|
| 2358 |
+
"eval_accuracy": 0.7508185985592666,
|
| 2359 |
+
"eval_loss": 1.289104700088501,
|
| 2360 |
+
"eval_runtime": 0.8603,
|
| 2361 |
+
"eval_samples_per_second": 581.16,
|
| 2362 |
+
"eval_steps_per_second": 37.194,
|
| 2363 |
+
"step": 78500
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 28.24,
|
| 2367 |
+
"learning_rate": 2.945417709450602e-06,
|
| 2368 |
+
"loss": 0.8259,
|
| 2369 |
+
"step": 79000
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 28.24,
|
| 2373 |
+
"eval_accuracy": 0.7500814597588791,
|
| 2374 |
+
"eval_loss": 1.2452012300491333,
|
| 2375 |
+
"eval_runtime": 0.8046,
|
| 2376 |
+
"eval_samples_per_second": 621.394,
|
| 2377 |
+
"eval_steps_per_second": 39.769,
|
| 2378 |
+
"step": 79000
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 28.42,
|
| 2382 |
+
"learning_rate": 2.647479442259564e-06,
|
| 2383 |
+
"loss": 0.8334,
|
| 2384 |
+
"step": 79500
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 28.42,
|
| 2388 |
+
"eval_accuracy": 0.746810598626104,
|
| 2389 |
+
"eval_loss": 1.2985996007919312,
|
| 2390 |
+
"eval_runtime": 0.9197,
|
| 2391 |
+
"eval_samples_per_second": 543.676,
|
| 2392 |
+
"eval_steps_per_second": 34.795,
|
| 2393 |
+
"step": 79500
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 28.6,
|
| 2397 |
+
"learning_rate": 2.349541175068526e-06,
|
| 2398 |
+
"loss": 0.8115,
|
| 2399 |
+
"step": 80000
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 28.6,
|
| 2403 |
+
"eval_accuracy": 0.7514638906961614,
|
| 2404 |
+
"eval_loss": 1.2879589796066284,
|
| 2405 |
+
"eval_runtime": 0.7986,
|
| 2406 |
+
"eval_samples_per_second": 626.129,
|
| 2407 |
+
"eval_steps_per_second": 40.072,
|
| 2408 |
+
"step": 80000
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 28.78,
|
| 2412 |
+
"learning_rate": 2.0516029078774876e-06,
|
| 2413 |
+
"loss": 0.8205,
|
| 2414 |
+
"step": 80500
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 28.78,
|
| 2418 |
+
"eval_accuracy": 0.75615359369872,
|
| 2419 |
+
"eval_loss": 1.2727956771850586,
|
| 2420 |
+
"eval_runtime": 0.8652,
|
| 2421 |
+
"eval_samples_per_second": 577.899,
|
| 2422 |
+
"eval_steps_per_second": 36.986,
|
| 2423 |
+
"step": 80500
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 28.96,
|
| 2427 |
+
"learning_rate": 1.7536646406864498e-06,
|
| 2428 |
+
"loss": 0.8261,
|
| 2429 |
+
"step": 81000
|
| 2430 |
+
},
|
| 2431 |
+
{
|
| 2432 |
+
"epoch": 28.96,
|
| 2433 |
+
"eval_accuracy": 0.7523561910952227,
|
| 2434 |
+
"eval_loss": 1.2660555839538574,
|
| 2435 |
+
"eval_runtime": 0.7893,
|
| 2436 |
+
"eval_samples_per_second": 633.494,
|
| 2437 |
+
"eval_steps_per_second": 40.544,
|
| 2438 |
+
"step": 81000
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 29.14,
|
| 2442 |
+
"learning_rate": 1.4563222500297937e-06,
|
| 2443 |
+
"loss": 0.8299,
|
| 2444 |
+
"step": 81500
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 29.14,
|
| 2448 |
+
"eval_accuracy": 0.7486106570774763,
|
| 2449 |
+
"eval_loss": 1.25924813747406,
|
| 2450 |
+
"eval_runtime": 0.8513,
|
| 2451 |
+
"eval_samples_per_second": 587.342,
|
| 2452 |
+
"eval_steps_per_second": 37.59,
|
| 2453 |
+
"step": 81500
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 29.32,
|
| 2457 |
+
"learning_rate": 1.1583839828387559e-06,
|
| 2458 |
+
"loss": 0.8276,
|
| 2459 |
+
"step": 82000
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 29.32,
|
| 2463 |
+
"eval_accuracy": 0.7529644268774703,
|
| 2464 |
+
"eval_loss": 1.2325080633163452,
|
| 2465 |
+
"eval_runtime": 0.8587,
|
| 2466 |
+
"eval_samples_per_second": 582.291,
|
| 2467 |
+
"eval_steps_per_second": 37.267,
|
| 2468 |
+
"step": 82000
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 29.5,
|
| 2472 |
+
"learning_rate": 8.604457156477178e-07,
|
| 2473 |
+
"loss": 0.8112,
|
| 2474 |
+
"step": 82500
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 29.5,
|
| 2478 |
+
"eval_accuracy": 0.7477890599410416,
|
| 2479 |
+
"eval_loss": 1.3154096603393555,
|
| 2480 |
+
"eval_runtime": 0.8166,
|
| 2481 |
+
"eval_samples_per_second": 612.267,
|
| 2482 |
+
"eval_steps_per_second": 39.185,
|
| 2483 |
+
"step": 82500
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 29.67,
|
| 2487 |
+
"learning_rate": 5.625074484566799e-07,
|
| 2488 |
+
"loss": 0.8111,
|
| 2489 |
+
"step": 83000
|
| 2490 |
+
},
|
| 2491 |
+
{
|
| 2492 |
+
"epoch": 29.67,
|
| 2493 |
+
"eval_accuracy": 0.740531561461794,
|
| 2494 |
+
"eval_loss": 1.3342524766921997,
|
| 2495 |
+
"eval_runtime": 0.8076,
|
| 2496 |
+
"eval_samples_per_second": 619.083,
|
| 2497 |
+
"eval_steps_per_second": 39.621,
|
| 2498 |
+
"step": 83000
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 29.85,
|
| 2502 |
+
"learning_rate": 2.645691812656418e-07,
|
| 2503 |
+
"loss": 0.8148,
|
| 2504 |
+
"step": 83500
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 29.85,
|
| 2508 |
+
"eval_accuracy": 0.7484622855292975,
|
| 2509 |
+
"eval_loss": 1.2806158065795898,
|
| 2510 |
+
"eval_runtime": 0.8122,
|
| 2511 |
+
"eval_samples_per_second": 615.596,
|
| 2512 |
+
"eval_steps_per_second": 39.398,
|
| 2513 |
+
"step": 83500
|
| 2514 |
+
},
|
| 2515 |
+
{
|
| 2516 |
+
"epoch": 30.0,
|
| 2517 |
+
"step": 83910,
|
| 2518 |
+
"total_flos": 3.583580261367381e+17,
|
| 2519 |
+
"train_loss": 1.1746184680817338,
|
| 2520 |
+
"train_runtime": 16410.0948,
|
| 2521 |
+
"train_samples_per_second": 163.619,
|
| 2522 |
+
"train_steps_per_second": 5.113
|
| 2523 |
+
}
|
| 2524 |
+
],
|
| 2525 |
+
"max_steps": 83910,
|
| 2526 |
+
"num_train_epochs": 30,
|
| 2527 |
+
"total_flos": 3.583580261367381e+17,
|
| 2528 |
+
"trial_name": null,
|
| 2529 |
+
"trial_params": null
|
| 2530 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f45b37904a4dc306c6f60adc2099b53a85a7087592415bc16975aeb7298b9aa0
|
| 3 |
+
size 3375
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|