Pushing deberta-v3-large-sentiment to hub
Browse files- README.md +203 -0
- added_tokens.json +3 -0
- all_results.json +14 -0
- config.json +45 -0
- eval_results.json +8 -0
- pytorch_model.bin +3 -0
- run_test.sh +1 -0
- run_train.sh +1 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- test_results.json +8 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +2155 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: deberta-v3-large-sentiment-lr5e-6-gas2-ls0.0
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# deberta-v3-large-sentiment-lr5e-6-gas2-ls0.0
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.3253
|
| 20 |
+
- Accuracy: 0.7365
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-06
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 16
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 50
|
| 48 |
+
- num_epochs: 10.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 54 |
+
| 1.0614 | 0.07 | 100 | 1.0196 | 0.4345 |
|
| 55 |
+
| 0.8601 | 0.14 | 200 | 0.7561 | 0.6460 |
|
| 56 |
+
| 0.734 | 0.21 | 300 | 0.6796 | 0.6955 |
|
| 57 |
+
| 0.6753 | 0.28 | 400 | 0.6521 | 0.7000 |
|
| 58 |
+
| 0.6408 | 0.35 | 500 | 0.6119 | 0.7440 |
|
| 59 |
+
| 0.5991 | 0.42 | 600 | 0.6034 | 0.7370 |
|
| 60 |
+
| 0.6069 | 0.49 | 700 | 0.5976 | 0.7375 |
|
| 61 |
+
| 0.6122 | 0.56 | 800 | 0.5871 | 0.7425 |
|
| 62 |
+
| 0.5908 | 0.63 | 900 | 0.5935 | 0.7445 |
|
| 63 |
+
| 0.5884 | 0.7 | 1000 | 0.5792 | 0.7520 |
|
| 64 |
+
| 0.5839 | 0.77 | 1100 | 0.5780 | 0.7555 |
|
| 65 |
+
| 0.5772 | 0.84 | 1200 | 0.5727 | 0.7570 |
|
| 66 |
+
| 0.5895 | 0.91 | 1300 | 0.5601 | 0.7550 |
|
| 67 |
+
| 0.5757 | 0.98 | 1400 | 0.5613 | 0.7525 |
|
| 68 |
+
| 0.5121 | 1.05 | 1500 | 0.5867 | 0.7600 |
|
| 69 |
+
| 0.5254 | 1.12 | 1600 | 0.5595 | 0.7630 |
|
| 70 |
+
| 0.5074 | 1.19 | 1700 | 0.5594 | 0.7585 |
|
| 71 |
+
| 0.4947 | 1.26 | 1800 | 0.5697 | 0.7575 |
|
| 72 |
+
| 0.5019 | 1.33 | 1900 | 0.5665 | 0.7580 |
|
| 73 |
+
| 0.5005 | 1.4 | 2000 | 0.5484 | 0.7655 |
|
| 74 |
+
| 0.5125 | 1.47 | 2100 | 0.5626 | 0.7605 |
|
| 75 |
+
| 0.5241 | 1.54 | 2200 | 0.5561 | 0.7560 |
|
| 76 |
+
| 0.5198 | 1.61 | 2300 | 0.5602 | 0.7600 |
|
| 77 |
+
| 0.5124 | 1.68 | 2400 | 0.5654 | 0.7490 |
|
| 78 |
+
| 0.5096 | 1.75 | 2500 | 0.5803 | 0.7515 |
|
| 79 |
+
| 0.4885 | 1.82 | 2600 | 0.5889 | 0.75 |
|
| 80 |
+
| 0.5111 | 1.89 | 2700 | 0.5508 | 0.7665 |
|
| 81 |
+
| 0.4868 | 1.96 | 2800 | 0.5621 | 0.7635 |
|
| 82 |
+
| 0.4599 | 2.04 | 2900 | 0.5995 | 0.7615 |
|
| 83 |
+
| 0.4147 | 2.11 | 3000 | 0.6202 | 0.7530 |
|
| 84 |
+
| 0.4233 | 2.18 | 3100 | 0.5875 | 0.7625 |
|
| 85 |
+
| 0.4324 | 2.25 | 3200 | 0.5794 | 0.7610 |
|
| 86 |
+
| 0.4141 | 2.32 | 3300 | 0.5902 | 0.7460 |
|
| 87 |
+
| 0.4306 | 2.39 | 3400 | 0.6053 | 0.7545 |
|
| 88 |
+
| 0.4266 | 2.46 | 3500 | 0.5979 | 0.7570 |
|
| 89 |
+
| 0.4227 | 2.53 | 3600 | 0.5920 | 0.7650 |
|
| 90 |
+
| 0.4226 | 2.6 | 3700 | 0.6166 | 0.7455 |
|
| 91 |
+
| 0.3978 | 2.67 | 3800 | 0.6126 | 0.7560 |
|
| 92 |
+
| 0.3954 | 2.74 | 3900 | 0.6152 | 0.7550 |
|
| 93 |
+
| 0.4209 | 2.81 | 4000 | 0.5980 | 0.75 |
|
| 94 |
+
| 0.3982 | 2.88 | 4100 | 0.6096 | 0.7490 |
|
| 95 |
+
| 0.4016 | 2.95 | 4200 | 0.6541 | 0.7425 |
|
| 96 |
+
| 0.3966 | 3.02 | 4300 | 0.6377 | 0.7545 |
|
| 97 |
+
| 0.3074 | 3.09 | 4400 | 0.6860 | 0.75 |
|
| 98 |
+
| 0.3551 | 3.16 | 4500 | 0.6160 | 0.7550 |
|
| 99 |
+
| 0.3323 | 3.23 | 4600 | 0.6714 | 0.7520 |
|
| 100 |
+
| 0.3171 | 3.3 | 4700 | 0.6538 | 0.7535 |
|
| 101 |
+
| 0.3403 | 3.37 | 4800 | 0.6774 | 0.7465 |
|
| 102 |
+
| 0.3396 | 3.44 | 4900 | 0.6726 | 0.7465 |
|
| 103 |
+
| 0.3259 | 3.51 | 5000 | 0.6465 | 0.7480 |
|
| 104 |
+
| 0.3392 | 3.58 | 5100 | 0.6860 | 0.7460 |
|
| 105 |
+
| 0.3251 | 3.65 | 5200 | 0.6697 | 0.7495 |
|
| 106 |
+
| 0.3253 | 3.72 | 5300 | 0.6770 | 0.7430 |
|
| 107 |
+
| 0.3455 | 3.79 | 5400 | 0.7177 | 0.7360 |
|
| 108 |
+
| 0.3323 | 3.86 | 5500 | 0.6943 | 0.7400 |
|
| 109 |
+
| 0.3335 | 3.93 | 5600 | 0.6507 | 0.7555 |
|
| 110 |
+
| 0.3368 | 4.0 | 5700 | 0.6580 | 0.7485 |
|
| 111 |
+
| 0.2479 | 4.07 | 5800 | 0.7667 | 0.7430 |
|
| 112 |
+
| 0.2613 | 4.14 | 5900 | 0.7513 | 0.7505 |
|
| 113 |
+
| 0.2557 | 4.21 | 6000 | 0.7927 | 0.7485 |
|
| 114 |
+
| 0.243 | 4.28 | 6100 | 0.7792 | 0.7450 |
|
| 115 |
+
| 0.2473 | 4.35 | 6200 | 0.8107 | 0.7355 |
|
| 116 |
+
| 0.2447 | 4.42 | 6300 | 0.7851 | 0.7370 |
|
| 117 |
+
| 0.2515 | 4.49 | 6400 | 0.7529 | 0.7465 |
|
| 118 |
+
| 0.274 | 4.56 | 6500 | 0.7390 | 0.7465 |
|
| 119 |
+
| 0.2674 | 4.63 | 6600 | 0.7658 | 0.7460 |
|
| 120 |
+
| 0.2416 | 4.7 | 6700 | 0.7915 | 0.7485 |
|
| 121 |
+
| 0.2432 | 4.77 | 6800 | 0.7989 | 0.7435 |
|
| 122 |
+
| 0.2595 | 4.84 | 6900 | 0.7850 | 0.7380 |
|
| 123 |
+
| 0.2736 | 4.91 | 7000 | 0.7577 | 0.7395 |
|
| 124 |
+
| 0.2783 | 4.98 | 7100 | 0.7650 | 0.7405 |
|
| 125 |
+
| 0.2304 | 5.05 | 7200 | 0.8542 | 0.7385 |
|
| 126 |
+
| 0.1937 | 5.12 | 7300 | 0.8390 | 0.7345 |
|
| 127 |
+
| 0.1878 | 5.19 | 7400 | 0.9150 | 0.7330 |
|
| 128 |
+
| 0.1921 | 5.26 | 7500 | 0.8792 | 0.7405 |
|
| 129 |
+
| 0.1916 | 5.33 | 7600 | 0.8892 | 0.7410 |
|
| 130 |
+
| 0.2011 | 5.4 | 7700 | 0.9012 | 0.7325 |
|
| 131 |
+
| 0.211 | 5.47 | 7800 | 0.8608 | 0.7420 |
|
| 132 |
+
| 0.2194 | 5.54 | 7900 | 0.8852 | 0.7320 |
|
| 133 |
+
| 0.205 | 5.61 | 8000 | 0.8803 | 0.7385 |
|
| 134 |
+
| 0.1981 | 5.68 | 8100 | 0.8681 | 0.7330 |
|
| 135 |
+
| 0.1908 | 5.75 | 8200 | 0.9020 | 0.7435 |
|
| 136 |
+
| 0.1942 | 5.82 | 8300 | 0.8780 | 0.7410 |
|
| 137 |
+
| 0.1958 | 5.89 | 8400 | 0.8937 | 0.7345 |
|
| 138 |
+
| 0.1883 | 5.96 | 8500 | 0.9121 | 0.7360 |
|
| 139 |
+
| 0.1819 | 6.04 | 8600 | 0.9409 | 0.7430 |
|
| 140 |
+
| 0.145 | 6.11 | 8700 | 1.1390 | 0.7265 |
|
| 141 |
+
| 0.1696 | 6.18 | 8800 | 0.9189 | 0.7430 |
|
| 142 |
+
| 0.1488 | 6.25 | 8900 | 0.9718 | 0.7400 |
|
| 143 |
+
| 0.1637 | 6.32 | 9000 | 0.9702 | 0.7450 |
|
| 144 |
+
| 0.1547 | 6.39 | 9100 | 1.0033 | 0.7410 |
|
| 145 |
+
| 0.1605 | 6.46 | 9200 | 0.9973 | 0.7355 |
|
| 146 |
+
| 0.1552 | 6.53 | 9300 | 1.0491 | 0.7290 |
|
| 147 |
+
| 0.1731 | 6.6 | 9400 | 1.0271 | 0.7335 |
|
| 148 |
+
| 0.1738 | 6.67 | 9500 | 0.9575 | 0.7430 |
|
| 149 |
+
| 0.1669 | 6.74 | 9600 | 0.9614 | 0.7350 |
|
| 150 |
+
| 0.1347 | 6.81 | 9700 | 1.0263 | 0.7365 |
|
| 151 |
+
| 0.1593 | 6.88 | 9800 | 1.0173 | 0.7360 |
|
| 152 |
+
| 0.1549 | 6.95 | 9900 | 1.0398 | 0.7350 |
|
| 153 |
+
| 0.1675 | 7.02 | 10000 | 0.9975 | 0.7380 |
|
| 154 |
+
| 0.1182 | 7.09 | 10100 | 1.1059 | 0.7350 |
|
| 155 |
+
| 0.1351 | 7.16 | 10200 | 1.0933 | 0.7400 |
|
| 156 |
+
| 0.1496 | 7.23 | 10300 | 1.0731 | 0.7355 |
|
| 157 |
+
| 0.1197 | 7.3 | 10400 | 1.1089 | 0.7360 |
|
| 158 |
+
| 0.1111 | 7.37 | 10500 | 1.1381 | 0.7405 |
|
| 159 |
+
| 0.1494 | 7.44 | 10600 | 1.0252 | 0.7425 |
|
| 160 |
+
| 0.1235 | 7.51 | 10700 | 1.0906 | 0.7360 |
|
| 161 |
+
| 0.133 | 7.58 | 10800 | 1.1796 | 0.7375 |
|
| 162 |
+
| 0.1248 | 7.65 | 10900 | 1.1332 | 0.7420 |
|
| 163 |
+
| 0.1268 | 7.72 | 11000 | 1.1304 | 0.7415 |
|
| 164 |
+
| 0.1368 | 7.79 | 11100 | 1.1345 | 0.7380 |
|
| 165 |
+
| 0.1228 | 7.86 | 11200 | 1.2018 | 0.7320 |
|
| 166 |
+
| 0.1281 | 7.93 | 11300 | 1.1884 | 0.7350 |
|
| 167 |
+
| 0.1449 | 8.0 | 11400 | 1.1571 | 0.7345 |
|
| 168 |
+
| 0.1025 | 8.07 | 11500 | 1.1538 | 0.7345 |
|
| 169 |
+
| 0.1199 | 8.14 | 11600 | 1.2113 | 0.7390 |
|
| 170 |
+
| 0.1016 | 8.21 | 11700 | 1.2882 | 0.7370 |
|
| 171 |
+
| 0.114 | 8.28 | 11800 | 1.2872 | 0.7390 |
|
| 172 |
+
| 0.1019 | 8.35 | 11900 | 1.2876 | 0.7380 |
|
| 173 |
+
| 0.1142 | 8.42 | 12000 | 1.2791 | 0.7385 |
|
| 174 |
+
| 0.1135 | 8.49 | 12100 | 1.2883 | 0.7380 |
|
| 175 |
+
| 0.1139 | 8.56 | 12200 | 1.2829 | 0.7360 |
|
| 176 |
+
| 0.1107 | 8.63 | 12300 | 1.2698 | 0.7365 |
|
| 177 |
+
| 0.1183 | 8.7 | 12400 | 1.2660 | 0.7345 |
|
| 178 |
+
| 0.1064 | 8.77 | 12500 | 1.2889 | 0.7365 |
|
| 179 |
+
| 0.0895 | 8.84 | 12600 | 1.3480 | 0.7330 |
|
| 180 |
+
| 0.1244 | 8.91 | 12700 | 1.2872 | 0.7325 |
|
| 181 |
+
| 0.1209 | 8.98 | 12800 | 1.2681 | 0.7375 |
|
| 182 |
+
| 0.1144 | 9.05 | 12900 | 1.2711 | 0.7370 |
|
| 183 |
+
| 0.1034 | 9.12 | 13000 | 1.2801 | 0.7360 |
|
| 184 |
+
| 0.113 | 9.19 | 13100 | 1.2801 | 0.7350 |
|
| 185 |
+
| 0.0994 | 9.26 | 13200 | 1.2920 | 0.7360 |
|
| 186 |
+
| 0.0966 | 9.33 | 13300 | 1.2761 | 0.7335 |
|
| 187 |
+
| 0.0939 | 9.4 | 13400 | 1.2909 | 0.7365 |
|
| 188 |
+
| 0.0975 | 9.47 | 13500 | 1.2953 | 0.7360 |
|
| 189 |
+
| 0.0842 | 9.54 | 13600 | 1.3179 | 0.7335 |
|
| 190 |
+
| 0.0871 | 9.61 | 13700 | 1.3149 | 0.7385 |
|
| 191 |
+
| 0.1162 | 9.68 | 13800 | 1.3124 | 0.7350 |
|
| 192 |
+
| 0.085 | 9.75 | 13900 | 1.3207 | 0.7355 |
|
| 193 |
+
| 0.0966 | 9.82 | 14000 | 1.3248 | 0.7335 |
|
| 194 |
+
| 0.1064 | 9.89 | 14100 | 1.3261 | 0.7335 |
|
| 195 |
+
| 0.1046 | 9.96 | 14200 | 1.3255 | 0.7360 |
|
| 196 |
+
|
| 197 |
+
|
| 198 |
+
### Framework versions
|
| 199 |
+
|
| 200 |
+
- Transformers 4.20.0.dev0
|
| 201 |
+
- Pytorch 1.9.0
|
| 202 |
+
- Datasets 2.2.2
|
| 203 |
+
- Tokenizers 0.11.6
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.7365000247955322,
|
| 4 |
+
"eval_loss": 1.3253138065338135,
|
| 5 |
+
"eval_runtime": 22.8646,
|
| 6 |
+
"eval_samples": 2000,
|
| 7 |
+
"eval_samples_per_second": 87.472,
|
| 8 |
+
"eval_steps_per_second": 5.467,
|
| 9 |
+
"train_loss": 0.2872312853629129,
|
| 10 |
+
"train_runtime": 13159.309,
|
| 11 |
+
"train_samples": 45615,
|
| 12 |
+
"train_samples_per_second": 34.664,
|
| 13 |
+
"train_steps_per_second": 1.083
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 1024,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": 0,
|
| 12 |
+
"1": 1,
|
| 13 |
+
"2": 2
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 4096,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"0": 0,
|
| 19 |
+
"1": 1,
|
| 20 |
+
"2": 2
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-07,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"max_relative_positions": -1,
|
| 25 |
+
"model_type": "deberta-v2",
|
| 26 |
+
"norm_rel_ebd": "layer_norm",
|
| 27 |
+
"num_attention_heads": 16,
|
| 28 |
+
"num_hidden_layers": 24,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pooler_dropout": 0,
|
| 31 |
+
"pooler_hidden_act": "gelu",
|
| 32 |
+
"pooler_hidden_size": 1024,
|
| 33 |
+
"pos_att_type": [
|
| 34 |
+
"p2c",
|
| 35 |
+
"c2p"
|
| 36 |
+
],
|
| 37 |
+
"position_biased_input": false,
|
| 38 |
+
"position_buckets": 256,
|
| 39 |
+
"relative_attention": true,
|
| 40 |
+
"share_att_key": true,
|
| 41 |
+
"torch_dtype": "float32",
|
| 42 |
+
"transformers_version": "4.20.0.dev0",
|
| 43 |
+
"type_vocab_size": 0,
|
| 44 |
+
"vocab_size": 128100
|
| 45 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.7664999961853027,
|
| 3 |
+
"eval_loss": 0.5507832169532776,
|
| 4 |
+
"eval_runtime": 19.7263,
|
| 5 |
+
"eval_samples": 2000,
|
| 6 |
+
"eval_samples_per_second": 101.388,
|
| 7 |
+
"eval_steps_per_second": 6.337
|
| 8 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f18728f5092fa44baf80f9c8962a3fccc3cf3a7cbf397fc4ca6de735d50a7f73
|
| 3 |
+
size 1740397483
|
run_test.sh
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
jbsub -queue x86_1h -cores 4+1 -mem 30g -require a100 -o outputs/train/tweet_eval2/sentiment/deberta-v3-large-sentiment-lr5e-6-gas2-ls0.0/test.log /dccstor/tslm/envs/anaconda3/envs/tslm-gen/bin/python train_clf.py --model_name_or_path outputs/train/tweet_eval2/sentiment/deberta-v3-large-sentiment-lr5e-6-gas2-ls0.0/best_checkpoint --train_file data/tweet_eval/sentiment/train.csv --validation_file data/tweet_eval/sentiment/validation.csv --test_file data/tweet_eval/sentiment/test.csv --do_eval --do_predict --report_to none --per_device_eval_batch_size 16 --max_seq_length 256 --output_dir outputs/train/tweet_eval2/sentiment/deberta-v3-large-sentiment-lr5e-6-gas2-ls0.0/best_checkpoint
|
run_train.sh
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
jbsub -queue x86_6h -cores 4+1 -mem 30g -require a100 -o outputs/train/tweet_eval2/sentiment/deberta-v3-large-sentiment-lr5e-6-gas2-ls0.0/train.log /dccstor/tslm/envs/anaconda3/envs/tslm-gen/bin/python train_clf.py --model_name_or_path microsoft/deberta-v3-large --train_file data/tweet_eval/sentiment/train.csv --validation_file data/tweet_eval/sentiment/validation.csv --do_train --do_eval --per_device_train_batch_size 16 --per_device_eval_batch_size 16 --max_seq_length 256 --learning_rate 5e-6 --output_dir outputs/train/tweet_eval2/sentiment/deberta-v3-large-sentiment-lr5e-6-gas2-ls0.0 --evaluation_strategy steps --save_strategy no --warmup_steps 50 --num_train_epochs 10 --overwrite_output_dir --logging_steps 100 --gradient_accumulation_steps 2 --label_smoothing_factor 0.0 --report_to clearml --metric_for_best_model accuracy --logging_dir outputs/train/tweet_eval2/sentiment/deberta-v3-large-sentiment-lr5e-6-gas2-ls0.0/tb \; rm -rf outputs/train/tweet_eval2/sentiment/deberta-v3-large-sentiment-lr5e-6-gas2-ls0.0/tb \; rm -rf outputs/train/tweet_eval2/sentiment/deberta-v3-large-sentiment-lr5e-6-gas2-ls0.0/checkpoint-* \; . outputs/train/tweet_eval2/sentiment/deberta-v3-large-sentiment-lr5e-6-gas2-ls0.0/run_test.sh
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_accuracy": 0.7393357157707214,
|
| 3 |
+
"eval_loss": 0.5786939859390259,
|
| 4 |
+
"eval_runtime": 134.3696,
|
| 5 |
+
"eval_samples_per_second": 91.419,
|
| 6 |
+
"eval_steps_per_second": 5.716,
|
| 7 |
+
"test_samples": 12284
|
| 8 |
+
}
|
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 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"eos_token": "[SEP]",
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"name_or_path": "microsoft/deberta-v3-large",
|
| 8 |
+
"pad_token": "[PAD]",
|
| 9 |
+
"sep_token": "[SEP]",
|
| 10 |
+
"sp_model_kwargs": {},
|
| 11 |
+
"special_tokens_map_file": null,
|
| 12 |
+
"split_by_punct": false,
|
| 13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 14 |
+
"unk_token": "[UNK]",
|
| 15 |
+
"vocab_type": "spm"
|
| 16 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.99964924587864,
|
| 5 |
+
"global_step": 14250,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 4.982394366197183e-06,
|
| 13 |
+
"loss": 1.0614,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"eval_accuracy": 0.4345000088214874,
|
| 19 |
+
"eval_loss": 1.019625186920166,
|
| 20 |
+
"eval_runtime": 18.8668,
|
| 21 |
+
"eval_samples_per_second": 106.006,
|
| 22 |
+
"eval_steps_per_second": 6.625,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.14,
|
| 27 |
+
"learning_rate": 4.94718309859155e-06,
|
| 28 |
+
"loss": 0.8601,
|
| 29 |
+
"step": 200
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.14,
|
| 33 |
+
"eval_accuracy": 0.6460000276565552,
|
| 34 |
+
"eval_loss": 0.756058931350708,
|
| 35 |
+
"eval_runtime": 19.8113,
|
| 36 |
+
"eval_samples_per_second": 100.953,
|
| 37 |
+
"eval_steps_per_second": 6.31,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.21,
|
| 42 |
+
"learning_rate": 4.911971830985916e-06,
|
| 43 |
+
"loss": 0.734,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.21,
|
| 48 |
+
"eval_accuracy": 0.6955000162124634,
|
| 49 |
+
"eval_loss": 0.6796478629112244,
|
| 50 |
+
"eval_runtime": 19.6375,
|
| 51 |
+
"eval_samples_per_second": 101.846,
|
| 52 |
+
"eval_steps_per_second": 6.365,
|
| 53 |
+
"step": 300
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.28,
|
| 57 |
+
"learning_rate": 4.876760563380282e-06,
|
| 58 |
+
"loss": 0.6753,
|
| 59 |
+
"step": 400
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.28,
|
| 63 |
+
"eval_accuracy": 0.699999988079071,
|
| 64 |
+
"eval_loss": 0.6520820260047913,
|
| 65 |
+
"eval_runtime": 18.2758,
|
| 66 |
+
"eval_samples_per_second": 109.434,
|
| 67 |
+
"eval_steps_per_second": 6.84,
|
| 68 |
+
"step": 400
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.35,
|
| 72 |
+
"learning_rate": 4.841549295774649e-06,
|
| 73 |
+
"loss": 0.6408,
|
| 74 |
+
"step": 500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.35,
|
| 78 |
+
"eval_accuracy": 0.7440000176429749,
|
| 79 |
+
"eval_loss": 0.6119081974029541,
|
| 80 |
+
"eval_runtime": 17.8217,
|
| 81 |
+
"eval_samples_per_second": 112.223,
|
| 82 |
+
"eval_steps_per_second": 7.014,
|
| 83 |
+
"step": 500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.42,
|
| 87 |
+
"learning_rate": 4.806338028169015e-06,
|
| 88 |
+
"loss": 0.5991,
|
| 89 |
+
"step": 600
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.42,
|
| 93 |
+
"eval_accuracy": 0.7369999885559082,
|
| 94 |
+
"eval_loss": 0.6033942699432373,
|
| 95 |
+
"eval_runtime": 17.3933,
|
| 96 |
+
"eval_samples_per_second": 114.986,
|
| 97 |
+
"eval_steps_per_second": 7.187,
|
| 98 |
+
"step": 600
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.49,
|
| 102 |
+
"learning_rate": 4.771126760563381e-06,
|
| 103 |
+
"loss": 0.6069,
|
| 104 |
+
"step": 700
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.49,
|
| 108 |
+
"eval_accuracy": 0.737500011920929,
|
| 109 |
+
"eval_loss": 0.597550630569458,
|
| 110 |
+
"eval_runtime": 20.251,
|
| 111 |
+
"eval_samples_per_second": 98.76,
|
| 112 |
+
"eval_steps_per_second": 6.173,
|
| 113 |
+
"step": 700
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.56,
|
| 117 |
+
"learning_rate": 4.735915492957747e-06,
|
| 118 |
+
"loss": 0.6122,
|
| 119 |
+
"step": 800
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.56,
|
| 123 |
+
"eval_accuracy": 0.7425000071525574,
|
| 124 |
+
"eval_loss": 0.5870603322982788,
|
| 125 |
+
"eval_runtime": 21.2152,
|
| 126 |
+
"eval_samples_per_second": 94.272,
|
| 127 |
+
"eval_steps_per_second": 5.892,
|
| 128 |
+
"step": 800
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.63,
|
| 132 |
+
"learning_rate": 4.7007042253521126e-06,
|
| 133 |
+
"loss": 0.5908,
|
| 134 |
+
"step": 900
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.63,
|
| 138 |
+
"eval_accuracy": 0.7444999814033508,
|
| 139 |
+
"eval_loss": 0.5935022234916687,
|
| 140 |
+
"eval_runtime": 22.0881,
|
| 141 |
+
"eval_samples_per_second": 90.546,
|
| 142 |
+
"eval_steps_per_second": 5.659,
|
| 143 |
+
"step": 900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.7,
|
| 147 |
+
"learning_rate": 4.665492957746479e-06,
|
| 148 |
+
"loss": 0.5884,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7,
|
| 153 |
+
"eval_accuracy": 0.7519999742507935,
|
| 154 |
+
"eval_loss": 0.5792337656021118,
|
| 155 |
+
"eval_runtime": 17.6606,
|
| 156 |
+
"eval_samples_per_second": 113.246,
|
| 157 |
+
"eval_steps_per_second": 7.078,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.77,
|
| 162 |
+
"learning_rate": 4.630281690140845e-06,
|
| 163 |
+
"loss": 0.5839,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.77,
|
| 168 |
+
"eval_accuracy": 0.7555000185966492,
|
| 169 |
+
"eval_loss": 0.578044056892395,
|
| 170 |
+
"eval_runtime": 15.9931,
|
| 171 |
+
"eval_samples_per_second": 125.054,
|
| 172 |
+
"eval_steps_per_second": 7.816,
|
| 173 |
+
"step": 1100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.84,
|
| 177 |
+
"learning_rate": 4.595070422535211e-06,
|
| 178 |
+
"loss": 0.5772,
|
| 179 |
+
"step": 1200
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.84,
|
| 183 |
+
"eval_accuracy": 0.7570000290870667,
|
| 184 |
+
"eval_loss": 0.5727072954177856,
|
| 185 |
+
"eval_runtime": 21.5937,
|
| 186 |
+
"eval_samples_per_second": 92.62,
|
| 187 |
+
"eval_steps_per_second": 5.789,
|
| 188 |
+
"step": 1200
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.91,
|
| 192 |
+
"learning_rate": 4.559859154929578e-06,
|
| 193 |
+
"loss": 0.5895,
|
| 194 |
+
"step": 1300
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.91,
|
| 198 |
+
"eval_accuracy": 0.7549999952316284,
|
| 199 |
+
"eval_loss": 0.5601378679275513,
|
| 200 |
+
"eval_runtime": 20.1543,
|
| 201 |
+
"eval_samples_per_second": 99.234,
|
| 202 |
+
"eval_steps_per_second": 6.202,
|
| 203 |
+
"step": 1300
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.98,
|
| 207 |
+
"learning_rate": 4.524647887323944e-06,
|
| 208 |
+
"loss": 0.5757,
|
| 209 |
+
"step": 1400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.98,
|
| 213 |
+
"eval_accuracy": 0.7524999976158142,
|
| 214 |
+
"eval_loss": 0.561326801776886,
|
| 215 |
+
"eval_runtime": 15.0299,
|
| 216 |
+
"eval_samples_per_second": 133.068,
|
| 217 |
+
"eval_steps_per_second": 8.317,
|
| 218 |
+
"step": 1400
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.05,
|
| 222 |
+
"learning_rate": 4.489436619718311e-06,
|
| 223 |
+
"loss": 0.5121,
|
| 224 |
+
"step": 1500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.05,
|
| 228 |
+
"eval_accuracy": 0.7599999904632568,
|
| 229 |
+
"eval_loss": 0.5866703987121582,
|
| 230 |
+
"eval_runtime": 18.2735,
|
| 231 |
+
"eval_samples_per_second": 109.448,
|
| 232 |
+
"eval_steps_per_second": 6.841,
|
| 233 |
+
"step": 1500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.12,
|
| 237 |
+
"learning_rate": 4.454225352112677e-06,
|
| 238 |
+
"loss": 0.5254,
|
| 239 |
+
"step": 1600
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.12,
|
| 243 |
+
"eval_accuracy": 0.7630000114440918,
|
| 244 |
+
"eval_loss": 0.5595362186431885,
|
| 245 |
+
"eval_runtime": 21.9878,
|
| 246 |
+
"eval_samples_per_second": 90.959,
|
| 247 |
+
"eval_steps_per_second": 5.685,
|
| 248 |
+
"step": 1600
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.19,
|
| 252 |
+
"learning_rate": 4.419014084507043e-06,
|
| 253 |
+
"loss": 0.5074,
|
| 254 |
+
"step": 1700
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.19,
|
| 258 |
+
"eval_accuracy": 0.7584999799728394,
|
| 259 |
+
"eval_loss": 0.559354841709137,
|
| 260 |
+
"eval_runtime": 19.9155,
|
| 261 |
+
"eval_samples_per_second": 100.424,
|
| 262 |
+
"eval_steps_per_second": 6.277,
|
| 263 |
+
"step": 1700
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.26,
|
| 267 |
+
"learning_rate": 4.383802816901409e-06,
|
| 268 |
+
"loss": 0.4947,
|
| 269 |
+
"step": 1800
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.26,
|
| 273 |
+
"eval_accuracy": 0.7574999928474426,
|
| 274 |
+
"eval_loss": 0.5696709156036377,
|
| 275 |
+
"eval_runtime": 22.8735,
|
| 276 |
+
"eval_samples_per_second": 87.438,
|
| 277 |
+
"eval_steps_per_second": 5.465,
|
| 278 |
+
"step": 1800
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.33,
|
| 282 |
+
"learning_rate": 4.3485915492957745e-06,
|
| 283 |
+
"loss": 0.5019,
|
| 284 |
+
"step": 1900
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.33,
|
| 288 |
+
"eval_accuracy": 0.7580000162124634,
|
| 289 |
+
"eval_loss": 0.5664528608322144,
|
| 290 |
+
"eval_runtime": 22.2002,
|
| 291 |
+
"eval_samples_per_second": 90.089,
|
| 292 |
+
"eval_steps_per_second": 5.631,
|
| 293 |
+
"step": 1900
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.4,
|
| 297 |
+
"learning_rate": 4.313380281690141e-06,
|
| 298 |
+
"loss": 0.5005,
|
| 299 |
+
"step": 2000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.4,
|
| 303 |
+
"eval_accuracy": 0.765500009059906,
|
| 304 |
+
"eval_loss": 0.5484071969985962,
|
| 305 |
+
"eval_runtime": 21.9941,
|
| 306 |
+
"eval_samples_per_second": 90.934,
|
| 307 |
+
"eval_steps_per_second": 5.683,
|
| 308 |
+
"step": 2000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.47,
|
| 312 |
+
"learning_rate": 4.278169014084507e-06,
|
| 313 |
+
"loss": 0.5125,
|
| 314 |
+
"step": 2100
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.47,
|
| 318 |
+
"eval_accuracy": 0.7605000138282776,
|
| 319 |
+
"eval_loss": 0.5626400709152222,
|
| 320 |
+
"eval_runtime": 17.7868,
|
| 321 |
+
"eval_samples_per_second": 112.443,
|
| 322 |
+
"eval_steps_per_second": 7.028,
|
| 323 |
+
"step": 2100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.54,
|
| 327 |
+
"learning_rate": 4.242957746478873e-06,
|
| 328 |
+
"loss": 0.5241,
|
| 329 |
+
"step": 2200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.54,
|
| 333 |
+
"eval_accuracy": 0.7559999823570251,
|
| 334 |
+
"eval_loss": 0.556066632270813,
|
| 335 |
+
"eval_runtime": 18.9121,
|
| 336 |
+
"eval_samples_per_second": 105.753,
|
| 337 |
+
"eval_steps_per_second": 6.61,
|
| 338 |
+
"step": 2200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.61,
|
| 342 |
+
"learning_rate": 4.20774647887324e-06,
|
| 343 |
+
"loss": 0.5198,
|
| 344 |
+
"step": 2300
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.61,
|
| 348 |
+
"eval_accuracy": 0.7599999904632568,
|
| 349 |
+
"eval_loss": 0.560243546962738,
|
| 350 |
+
"eval_runtime": 20.0908,
|
| 351 |
+
"eval_samples_per_second": 99.548,
|
| 352 |
+
"eval_steps_per_second": 6.222,
|
| 353 |
+
"step": 2300
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.68,
|
| 357 |
+
"learning_rate": 4.172535211267606e-06,
|
| 358 |
+
"loss": 0.5124,
|
| 359 |
+
"step": 2400
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.68,
|
| 363 |
+
"eval_accuracy": 0.7490000128746033,
|
| 364 |
+
"eval_loss": 0.5654177665710449,
|
| 365 |
+
"eval_runtime": 19.7883,
|
| 366 |
+
"eval_samples_per_second": 101.07,
|
| 367 |
+
"eval_steps_per_second": 6.317,
|
| 368 |
+
"step": 2400
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.75,
|
| 372 |
+
"learning_rate": 4.137323943661972e-06,
|
| 373 |
+
"loss": 0.5096,
|
| 374 |
+
"step": 2500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.75,
|
| 378 |
+
"eval_accuracy": 0.7515000104904175,
|
| 379 |
+
"eval_loss": 0.5803455710411072,
|
| 380 |
+
"eval_runtime": 22.0507,
|
| 381 |
+
"eval_samples_per_second": 90.7,
|
| 382 |
+
"eval_steps_per_second": 5.669,
|
| 383 |
+
"step": 2500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.82,
|
| 387 |
+
"learning_rate": 4.102112676056339e-06,
|
| 388 |
+
"loss": 0.4885,
|
| 389 |
+
"step": 2600
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.82,
|
| 393 |
+
"eval_accuracy": 0.75,
|
| 394 |
+
"eval_loss": 0.5889333486557007,
|
| 395 |
+
"eval_runtime": 21.1933,
|
| 396 |
+
"eval_samples_per_second": 94.369,
|
| 397 |
+
"eval_steps_per_second": 5.898,
|
| 398 |
+
"step": 2600
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.89,
|
| 402 |
+
"learning_rate": 4.0669014084507045e-06,
|
| 403 |
+
"loss": 0.5111,
|
| 404 |
+
"step": 2700
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.89,
|
| 408 |
+
"eval_accuracy": 0.7664999961853027,
|
| 409 |
+
"eval_loss": 0.5507832169532776,
|
| 410 |
+
"eval_runtime": 20.2761,
|
| 411 |
+
"eval_samples_per_second": 98.638,
|
| 412 |
+
"eval_steps_per_second": 6.165,
|
| 413 |
+
"step": 2700
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.96,
|
| 417 |
+
"learning_rate": 4.031690140845071e-06,
|
| 418 |
+
"loss": 0.4868,
|
| 419 |
+
"step": 2800
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.96,
|
| 423 |
+
"eval_accuracy": 0.7634999752044678,
|
| 424 |
+
"eval_loss": 0.5621495842933655,
|
| 425 |
+
"eval_runtime": 18.2341,
|
| 426 |
+
"eval_samples_per_second": 109.685,
|
| 427 |
+
"eval_steps_per_second": 6.855,
|
| 428 |
+
"step": 2800
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.04,
|
| 432 |
+
"learning_rate": 3.996478873239437e-06,
|
| 433 |
+
"loss": 0.4599,
|
| 434 |
+
"step": 2900
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.04,
|
| 438 |
+
"eval_accuracy": 0.7615000009536743,
|
| 439 |
+
"eval_loss": 0.5994852185249329,
|
| 440 |
+
"eval_runtime": 17.787,
|
| 441 |
+
"eval_samples_per_second": 112.442,
|
| 442 |
+
"eval_steps_per_second": 7.028,
|
| 443 |
+
"step": 2900
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.11,
|
| 447 |
+
"learning_rate": 3.961267605633803e-06,
|
| 448 |
+
"loss": 0.4147,
|
| 449 |
+
"step": 3000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.11,
|
| 453 |
+
"eval_accuracy": 0.753000020980835,
|
| 454 |
+
"eval_loss": 0.6202083230018616,
|
| 455 |
+
"eval_runtime": 20.5139,
|
| 456 |
+
"eval_samples_per_second": 97.495,
|
| 457 |
+
"eval_steps_per_second": 6.093,
|
| 458 |
+
"step": 3000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.18,
|
| 462 |
+
"learning_rate": 3.926056338028169e-06,
|
| 463 |
+
"loss": 0.4233,
|
| 464 |
+
"step": 3100
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.18,
|
| 468 |
+
"eval_accuracy": 0.762499988079071,
|
| 469 |
+
"eval_loss": 0.5875486135482788,
|
| 470 |
+
"eval_runtime": 19.4349,
|
| 471 |
+
"eval_samples_per_second": 102.908,
|
| 472 |
+
"eval_steps_per_second": 6.432,
|
| 473 |
+
"step": 3100
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.25,
|
| 477 |
+
"learning_rate": 3.890845070422535e-06,
|
| 478 |
+
"loss": 0.4324,
|
| 479 |
+
"step": 3200
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.25,
|
| 483 |
+
"eval_accuracy": 0.7609999775886536,
|
| 484 |
+
"eval_loss": 0.5794370174407959,
|
| 485 |
+
"eval_runtime": 18.3807,
|
| 486 |
+
"eval_samples_per_second": 108.81,
|
| 487 |
+
"eval_steps_per_second": 6.801,
|
| 488 |
+
"step": 3200
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.32,
|
| 492 |
+
"learning_rate": 3.855633802816902e-06,
|
| 493 |
+
"loss": 0.4141,
|
| 494 |
+
"step": 3300
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.32,
|
| 498 |
+
"eval_accuracy": 0.7459999918937683,
|
| 499 |
+
"eval_loss": 0.5901930928230286,
|
| 500 |
+
"eval_runtime": 20.1122,
|
| 501 |
+
"eval_samples_per_second": 99.442,
|
| 502 |
+
"eval_steps_per_second": 6.215,
|
| 503 |
+
"step": 3300
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.39,
|
| 507 |
+
"learning_rate": 3.820422535211268e-06,
|
| 508 |
+
"loss": 0.4306,
|
| 509 |
+
"step": 3400
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.39,
|
| 513 |
+
"eval_accuracy": 0.7544999718666077,
|
| 514 |
+
"eval_loss": 0.6053192019462585,
|
| 515 |
+
"eval_runtime": 20.0091,
|
| 516 |
+
"eval_samples_per_second": 99.955,
|
| 517 |
+
"eval_steps_per_second": 6.247,
|
| 518 |
+
"step": 3400
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.46,
|
| 522 |
+
"learning_rate": 3.785211267605634e-06,
|
| 523 |
+
"loss": 0.4266,
|
| 524 |
+
"step": 3500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.46,
|
| 528 |
+
"eval_accuracy": 0.7570000290870667,
|
| 529 |
+
"eval_loss": 0.5978769659996033,
|
| 530 |
+
"eval_runtime": 19.8772,
|
| 531 |
+
"eval_samples_per_second": 100.618,
|
| 532 |
+
"eval_steps_per_second": 6.289,
|
| 533 |
+
"step": 3500
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.53,
|
| 537 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 538 |
+
"loss": 0.4227,
|
| 539 |
+
"step": 3600
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.53,
|
| 543 |
+
"eval_accuracy": 0.7649999856948853,
|
| 544 |
+
"eval_loss": 0.5919951796531677,
|
| 545 |
+
"eval_runtime": 21.1736,
|
| 546 |
+
"eval_samples_per_second": 94.457,
|
| 547 |
+
"eval_steps_per_second": 5.904,
|
| 548 |
+
"step": 3600
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.6,
|
| 552 |
+
"learning_rate": 3.7147887323943665e-06,
|
| 553 |
+
"loss": 0.4226,
|
| 554 |
+
"step": 3700
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.6,
|
| 558 |
+
"eval_accuracy": 0.7455000281333923,
|
| 559 |
+
"eval_loss": 0.6165611743927002,
|
| 560 |
+
"eval_runtime": 20.5872,
|
| 561 |
+
"eval_samples_per_second": 97.148,
|
| 562 |
+
"eval_steps_per_second": 6.072,
|
| 563 |
+
"step": 3700
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.67,
|
| 567 |
+
"learning_rate": 3.679577464788733e-06,
|
| 568 |
+
"loss": 0.3978,
|
| 569 |
+
"step": 3800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.67,
|
| 573 |
+
"eval_accuracy": 0.7559999823570251,
|
| 574 |
+
"eval_loss": 0.6125866770744324,
|
| 575 |
+
"eval_runtime": 22.1514,
|
| 576 |
+
"eval_samples_per_second": 90.288,
|
| 577 |
+
"eval_steps_per_second": 5.643,
|
| 578 |
+
"step": 3800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.74,
|
| 582 |
+
"learning_rate": 3.644366197183099e-06,
|
| 583 |
+
"loss": 0.3954,
|
| 584 |
+
"step": 3900
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.74,
|
| 588 |
+
"eval_accuracy": 0.7549999952316284,
|
| 589 |
+
"eval_loss": 0.615158200263977,
|
| 590 |
+
"eval_runtime": 17.1074,
|
| 591 |
+
"eval_samples_per_second": 116.908,
|
| 592 |
+
"eval_steps_per_second": 7.307,
|
| 593 |
+
"step": 3900
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.81,
|
| 597 |
+
"learning_rate": 3.609154929577465e-06,
|
| 598 |
+
"loss": 0.4209,
|
| 599 |
+
"step": 4000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.81,
|
| 603 |
+
"eval_accuracy": 0.75,
|
| 604 |
+
"eval_loss": 0.597953736782074,
|
| 605 |
+
"eval_runtime": 22.6397,
|
| 606 |
+
"eval_samples_per_second": 88.34,
|
| 607 |
+
"eval_steps_per_second": 5.521,
|
| 608 |
+
"step": 4000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.88,
|
| 612 |
+
"learning_rate": 3.5739436619718315e-06,
|
| 613 |
+
"loss": 0.3982,
|
| 614 |
+
"step": 4100
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.88,
|
| 618 |
+
"eval_accuracy": 0.7490000128746033,
|
| 619 |
+
"eval_loss": 0.6096097230911255,
|
| 620 |
+
"eval_runtime": 22.0097,
|
| 621 |
+
"eval_samples_per_second": 90.869,
|
| 622 |
+
"eval_steps_per_second": 5.679,
|
| 623 |
+
"step": 4100
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 2.95,
|
| 627 |
+
"learning_rate": 3.538732394366197e-06,
|
| 628 |
+
"loss": 0.4016,
|
| 629 |
+
"step": 4200
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.95,
|
| 633 |
+
"eval_accuracy": 0.7425000071525574,
|
| 634 |
+
"eval_loss": 0.6540722846984863,
|
| 635 |
+
"eval_runtime": 16.1358,
|
| 636 |
+
"eval_samples_per_second": 123.948,
|
| 637 |
+
"eval_steps_per_second": 7.747,
|
| 638 |
+
"step": 4200
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.02,
|
| 642 |
+
"learning_rate": 3.5035211267605634e-06,
|
| 643 |
+
"loss": 0.3966,
|
| 644 |
+
"step": 4300
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.02,
|
| 648 |
+
"eval_accuracy": 0.7544999718666077,
|
| 649 |
+
"eval_loss": 0.6377372145652771,
|
| 650 |
+
"eval_runtime": 20.4003,
|
| 651 |
+
"eval_samples_per_second": 98.038,
|
| 652 |
+
"eval_steps_per_second": 6.127,
|
| 653 |
+
"step": 4300
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.09,
|
| 657 |
+
"learning_rate": 3.4683098591549297e-06,
|
| 658 |
+
"loss": 0.3074,
|
| 659 |
+
"step": 4400
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 3.09,
|
| 663 |
+
"eval_accuracy": 0.75,
|
| 664 |
+
"eval_loss": 0.6859884262084961,
|
| 665 |
+
"eval_runtime": 20.6366,
|
| 666 |
+
"eval_samples_per_second": 96.915,
|
| 667 |
+
"eval_steps_per_second": 6.057,
|
| 668 |
+
"step": 4400
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.16,
|
| 672 |
+
"learning_rate": 3.433098591549296e-06,
|
| 673 |
+
"loss": 0.3551,
|
| 674 |
+
"step": 4500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.16,
|
| 678 |
+
"eval_accuracy": 0.7549999952316284,
|
| 679 |
+
"eval_loss": 0.6160025596618652,
|
| 680 |
+
"eval_runtime": 21.368,
|
| 681 |
+
"eval_samples_per_second": 93.598,
|
| 682 |
+
"eval_steps_per_second": 5.85,
|
| 683 |
+
"step": 4500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.23,
|
| 687 |
+
"learning_rate": 3.397887323943662e-06,
|
| 688 |
+
"loss": 0.3323,
|
| 689 |
+
"step": 4600
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.23,
|
| 693 |
+
"eval_accuracy": 0.7519999742507935,
|
| 694 |
+
"eval_loss": 0.6714155077934265,
|
| 695 |
+
"eval_runtime": 21.1568,
|
| 696 |
+
"eval_samples_per_second": 94.532,
|
| 697 |
+
"eval_steps_per_second": 5.908,
|
| 698 |
+
"step": 4600
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.3,
|
| 702 |
+
"learning_rate": 3.3626760563380284e-06,
|
| 703 |
+
"loss": 0.3171,
|
| 704 |
+
"step": 4700
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.3,
|
| 708 |
+
"eval_accuracy": 0.7534999847412109,
|
| 709 |
+
"eval_loss": 0.6537904739379883,
|
| 710 |
+
"eval_runtime": 17.8954,
|
| 711 |
+
"eval_samples_per_second": 111.76,
|
| 712 |
+
"eval_steps_per_second": 6.985,
|
| 713 |
+
"step": 4700
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 3.37,
|
| 717 |
+
"learning_rate": 3.3274647887323947e-06,
|
| 718 |
+
"loss": 0.3403,
|
| 719 |
+
"step": 4800
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 3.37,
|
| 723 |
+
"eval_accuracy": 0.7465000152587891,
|
| 724 |
+
"eval_loss": 0.677370548248291,
|
| 725 |
+
"eval_runtime": 22.2854,
|
| 726 |
+
"eval_samples_per_second": 89.745,
|
| 727 |
+
"eval_steps_per_second": 5.609,
|
| 728 |
+
"step": 4800
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.44,
|
| 732 |
+
"learning_rate": 3.292253521126761e-06,
|
| 733 |
+
"loss": 0.3396,
|
| 734 |
+
"step": 4900
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.44,
|
| 738 |
+
"eval_accuracy": 0.7465000152587891,
|
| 739 |
+
"eval_loss": 0.6725812554359436,
|
| 740 |
+
"eval_runtime": 20.4072,
|
| 741 |
+
"eval_samples_per_second": 98.005,
|
| 742 |
+
"eval_steps_per_second": 6.125,
|
| 743 |
+
"step": 4900
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 3.51,
|
| 747 |
+
"learning_rate": 3.257042253521127e-06,
|
| 748 |
+
"loss": 0.3259,
|
| 749 |
+
"step": 5000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 3.51,
|
| 753 |
+
"eval_accuracy": 0.7480000257492065,
|
| 754 |
+
"eval_loss": 0.6465049982070923,
|
| 755 |
+
"eval_runtime": 16.3957,
|
| 756 |
+
"eval_samples_per_second": 121.983,
|
| 757 |
+
"eval_steps_per_second": 7.624,
|
| 758 |
+
"step": 5000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 3.58,
|
| 762 |
+
"learning_rate": 3.2218309859154934e-06,
|
| 763 |
+
"loss": 0.3392,
|
| 764 |
+
"step": 5100
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 3.58,
|
| 768 |
+
"eval_accuracy": 0.7459999918937683,
|
| 769 |
+
"eval_loss": 0.6860352754592896,
|
| 770 |
+
"eval_runtime": 19.1797,
|
| 771 |
+
"eval_samples_per_second": 104.277,
|
| 772 |
+
"eval_steps_per_second": 6.517,
|
| 773 |
+
"step": 5100
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 3.65,
|
| 777 |
+
"learning_rate": 3.1866197183098598e-06,
|
| 778 |
+
"loss": 0.3251,
|
| 779 |
+
"step": 5200
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 3.65,
|
| 783 |
+
"eval_accuracy": 0.7494999766349792,
|
| 784 |
+
"eval_loss": 0.6696720123291016,
|
| 785 |
+
"eval_runtime": 17.883,
|
| 786 |
+
"eval_samples_per_second": 111.838,
|
| 787 |
+
"eval_steps_per_second": 6.99,
|
| 788 |
+
"step": 5200
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 3.72,
|
| 792 |
+
"learning_rate": 3.1514084507042257e-06,
|
| 793 |
+
"loss": 0.3253,
|
| 794 |
+
"step": 5300
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.72,
|
| 798 |
+
"eval_accuracy": 0.7429999709129333,
|
| 799 |
+
"eval_loss": 0.6769505739212036,
|
| 800 |
+
"eval_runtime": 19.8341,
|
| 801 |
+
"eval_samples_per_second": 100.836,
|
| 802 |
+
"eval_steps_per_second": 6.302,
|
| 803 |
+
"step": 5300
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 3.79,
|
| 807 |
+
"learning_rate": 3.1161971830985916e-06,
|
| 808 |
+
"loss": 0.3455,
|
| 809 |
+
"step": 5400
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 3.79,
|
| 813 |
+
"eval_accuracy": 0.7360000014305115,
|
| 814 |
+
"eval_loss": 0.7176979780197144,
|
| 815 |
+
"eval_runtime": 17.9226,
|
| 816 |
+
"eval_samples_per_second": 111.591,
|
| 817 |
+
"eval_steps_per_second": 6.974,
|
| 818 |
+
"step": 5400
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 3.86,
|
| 822 |
+
"learning_rate": 3.0809859154929576e-06,
|
| 823 |
+
"loss": 0.3323,
|
| 824 |
+
"step": 5500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 3.86,
|
| 828 |
+
"eval_accuracy": 0.7400000095367432,
|
| 829 |
+
"eval_loss": 0.6943067908287048,
|
| 830 |
+
"eval_runtime": 21.4155,
|
| 831 |
+
"eval_samples_per_second": 93.39,
|
| 832 |
+
"eval_steps_per_second": 5.837,
|
| 833 |
+
"step": 5500
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 3.93,
|
| 837 |
+
"learning_rate": 3.045774647887324e-06,
|
| 838 |
+
"loss": 0.3335,
|
| 839 |
+
"step": 5600
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 3.93,
|
| 843 |
+
"eval_accuracy": 0.7555000185966492,
|
| 844 |
+
"eval_loss": 0.6506811380386353,
|
| 845 |
+
"eval_runtime": 21.6099,
|
| 846 |
+
"eval_samples_per_second": 92.55,
|
| 847 |
+
"eval_steps_per_second": 5.784,
|
| 848 |
+
"step": 5600
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 4.0,
|
| 852 |
+
"learning_rate": 3.0105633802816903e-06,
|
| 853 |
+
"loss": 0.3368,
|
| 854 |
+
"step": 5700
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 4.0,
|
| 858 |
+
"eval_accuracy": 0.7484999895095825,
|
| 859 |
+
"eval_loss": 0.6580154895782471,
|
| 860 |
+
"eval_runtime": 21.7515,
|
| 861 |
+
"eval_samples_per_second": 91.948,
|
| 862 |
+
"eval_steps_per_second": 5.747,
|
| 863 |
+
"step": 5700
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 4.07,
|
| 867 |
+
"learning_rate": 2.9753521126760567e-06,
|
| 868 |
+
"loss": 0.2479,
|
| 869 |
+
"step": 5800
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 4.07,
|
| 873 |
+
"eval_accuracy": 0.7429999709129333,
|
| 874 |
+
"eval_loss": 0.7666531801223755,
|
| 875 |
+
"eval_runtime": 15.994,
|
| 876 |
+
"eval_samples_per_second": 125.047,
|
| 877 |
+
"eval_steps_per_second": 7.815,
|
| 878 |
+
"step": 5800
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 4.14,
|
| 882 |
+
"learning_rate": 2.9401408450704226e-06,
|
| 883 |
+
"loss": 0.2613,
|
| 884 |
+
"step": 5900
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 4.14,
|
| 888 |
+
"eval_accuracy": 0.7505000233650208,
|
| 889 |
+
"eval_loss": 0.751265823841095,
|
| 890 |
+
"eval_runtime": 16.5258,
|
| 891 |
+
"eval_samples_per_second": 121.023,
|
| 892 |
+
"eval_steps_per_second": 7.564,
|
| 893 |
+
"step": 5900
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 4.21,
|
| 897 |
+
"learning_rate": 2.904929577464789e-06,
|
| 898 |
+
"loss": 0.2557,
|
| 899 |
+
"step": 6000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 4.21,
|
| 903 |
+
"eval_accuracy": 0.7484999895095825,
|
| 904 |
+
"eval_loss": 0.7926999926567078,
|
| 905 |
+
"eval_runtime": 20.2799,
|
| 906 |
+
"eval_samples_per_second": 98.62,
|
| 907 |
+
"eval_steps_per_second": 6.164,
|
| 908 |
+
"step": 6000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 4.28,
|
| 912 |
+
"learning_rate": 2.8697183098591553e-06,
|
| 913 |
+
"loss": 0.243,
|
| 914 |
+
"step": 6100
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 4.28,
|
| 918 |
+
"eval_accuracy": 0.7450000047683716,
|
| 919 |
+
"eval_loss": 0.77916020154953,
|
| 920 |
+
"eval_runtime": 19.6554,
|
| 921 |
+
"eval_samples_per_second": 101.753,
|
| 922 |
+
"eval_steps_per_second": 6.36,
|
| 923 |
+
"step": 6100
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 4.35,
|
| 927 |
+
"learning_rate": 2.8345070422535217e-06,
|
| 928 |
+
"loss": 0.2473,
|
| 929 |
+
"step": 6200
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 4.35,
|
| 933 |
+
"eval_accuracy": 0.7354999780654907,
|
| 934 |
+
"eval_loss": 0.8106710314750671,
|
| 935 |
+
"eval_runtime": 14.7909,
|
| 936 |
+
"eval_samples_per_second": 135.218,
|
| 937 |
+
"eval_steps_per_second": 8.451,
|
| 938 |
+
"step": 6200
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 4.42,
|
| 942 |
+
"learning_rate": 2.7992957746478876e-06,
|
| 943 |
+
"loss": 0.2447,
|
| 944 |
+
"step": 6300
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 4.42,
|
| 948 |
+
"eval_accuracy": 0.7369999885559082,
|
| 949 |
+
"eval_loss": 0.7850819230079651,
|
| 950 |
+
"eval_runtime": 15.145,
|
| 951 |
+
"eval_samples_per_second": 132.057,
|
| 952 |
+
"eval_steps_per_second": 8.254,
|
| 953 |
+
"step": 6300
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 4.49,
|
| 957 |
+
"learning_rate": 2.764084507042254e-06,
|
| 958 |
+
"loss": 0.2515,
|
| 959 |
+
"step": 6400
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 4.49,
|
| 963 |
+
"eval_accuracy": 0.7465000152587891,
|
| 964 |
+
"eval_loss": 0.7529160380363464,
|
| 965 |
+
"eval_runtime": 14.1294,
|
| 966 |
+
"eval_samples_per_second": 141.549,
|
| 967 |
+
"eval_steps_per_second": 8.847,
|
| 968 |
+
"step": 6400
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 4.56,
|
| 972 |
+
"learning_rate": 2.7288732394366203e-06,
|
| 973 |
+
"loss": 0.274,
|
| 974 |
+
"step": 6500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 4.56,
|
| 978 |
+
"eval_accuracy": 0.7465000152587891,
|
| 979 |
+
"eval_loss": 0.7389978170394897,
|
| 980 |
+
"eval_runtime": 18.3936,
|
| 981 |
+
"eval_samples_per_second": 108.733,
|
| 982 |
+
"eval_steps_per_second": 6.796,
|
| 983 |
+
"step": 6500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 4.63,
|
| 987 |
+
"learning_rate": 2.693661971830986e-06,
|
| 988 |
+
"loss": 0.2674,
|
| 989 |
+
"step": 6600
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 4.63,
|
| 993 |
+
"eval_accuracy": 0.7459999918937683,
|
| 994 |
+
"eval_loss": 0.7657651305198669,
|
| 995 |
+
"eval_runtime": 19.2395,
|
| 996 |
+
"eval_samples_per_second": 103.953,
|
| 997 |
+
"eval_steps_per_second": 6.497,
|
| 998 |
+
"step": 6600
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 4.7,
|
| 1002 |
+
"learning_rate": 2.6584507042253522e-06,
|
| 1003 |
+
"loss": 0.2416,
|
| 1004 |
+
"step": 6700
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 4.7,
|
| 1008 |
+
"eval_accuracy": 0.7484999895095825,
|
| 1009 |
+
"eval_loss": 0.7914510369300842,
|
| 1010 |
+
"eval_runtime": 17.7833,
|
| 1011 |
+
"eval_samples_per_second": 112.465,
|
| 1012 |
+
"eval_steps_per_second": 7.029,
|
| 1013 |
+
"step": 6700
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 4.77,
|
| 1017 |
+
"learning_rate": 2.623239436619718e-06,
|
| 1018 |
+
"loss": 0.2432,
|
| 1019 |
+
"step": 6800
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 4.77,
|
| 1023 |
+
"eval_accuracy": 0.7434999942779541,
|
| 1024 |
+
"eval_loss": 0.7988595962524414,
|
| 1025 |
+
"eval_runtime": 16.8516,
|
| 1026 |
+
"eval_samples_per_second": 118.683,
|
| 1027 |
+
"eval_steps_per_second": 7.418,
|
| 1028 |
+
"step": 6800
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 4.84,
|
| 1032 |
+
"learning_rate": 2.5880281690140845e-06,
|
| 1033 |
+
"loss": 0.2595,
|
| 1034 |
+
"step": 6900
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 4.84,
|
| 1038 |
+
"eval_accuracy": 0.7379999756813049,
|
| 1039 |
+
"eval_loss": 0.7850367426872253,
|
| 1040 |
+
"eval_runtime": 22.0351,
|
| 1041 |
+
"eval_samples_per_second": 90.764,
|
| 1042 |
+
"eval_steps_per_second": 5.673,
|
| 1043 |
+
"step": 6900
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 4.91,
|
| 1047 |
+
"learning_rate": 2.552816901408451e-06,
|
| 1048 |
+
"loss": 0.2736,
|
| 1049 |
+
"step": 7000
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.91,
|
| 1053 |
+
"eval_accuracy": 0.7394999861717224,
|
| 1054 |
+
"eval_loss": 0.7577053308486938,
|
| 1055 |
+
"eval_runtime": 22.4529,
|
| 1056 |
+
"eval_samples_per_second": 89.075,
|
| 1057 |
+
"eval_steps_per_second": 5.567,
|
| 1058 |
+
"step": 7000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 4.98,
|
| 1062 |
+
"learning_rate": 2.5176056338028172e-06,
|
| 1063 |
+
"loss": 0.2783,
|
| 1064 |
+
"step": 7100
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 4.98,
|
| 1068 |
+
"eval_accuracy": 0.7404999732971191,
|
| 1069 |
+
"eval_loss": 0.7649760842323303,
|
| 1070 |
+
"eval_runtime": 18.1063,
|
| 1071 |
+
"eval_samples_per_second": 110.459,
|
| 1072 |
+
"eval_steps_per_second": 6.904,
|
| 1073 |
+
"step": 7100
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 5.05,
|
| 1077 |
+
"learning_rate": 2.482394366197183e-06,
|
| 1078 |
+
"loss": 0.2304,
|
| 1079 |
+
"step": 7200
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 5.05,
|
| 1083 |
+
"eval_accuracy": 0.7384999990463257,
|
| 1084 |
+
"eval_loss": 0.8541684746742249,
|
| 1085 |
+
"eval_runtime": 20.2711,
|
| 1086 |
+
"eval_samples_per_second": 98.663,
|
| 1087 |
+
"eval_steps_per_second": 6.166,
|
| 1088 |
+
"step": 7200
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 5.12,
|
| 1092 |
+
"learning_rate": 2.4471830985915495e-06,
|
| 1093 |
+
"loss": 0.1937,
|
| 1094 |
+
"step": 7300
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 5.12,
|
| 1098 |
+
"eval_accuracy": 0.734499990940094,
|
| 1099 |
+
"eval_loss": 0.8389941453933716,
|
| 1100 |
+
"eval_runtime": 21.6926,
|
| 1101 |
+
"eval_samples_per_second": 92.197,
|
| 1102 |
+
"eval_steps_per_second": 5.762,
|
| 1103 |
+
"step": 7300
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 5.19,
|
| 1107 |
+
"learning_rate": 2.411971830985916e-06,
|
| 1108 |
+
"loss": 0.1878,
|
| 1109 |
+
"step": 7400
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 5.19,
|
| 1113 |
+
"eval_accuracy": 0.7329999804496765,
|
| 1114 |
+
"eval_loss": 0.9149684906005859,
|
| 1115 |
+
"eval_runtime": 19.4205,
|
| 1116 |
+
"eval_samples_per_second": 102.984,
|
| 1117 |
+
"eval_steps_per_second": 6.436,
|
| 1118 |
+
"step": 7400
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 5.26,
|
| 1122 |
+
"learning_rate": 2.376760563380282e-06,
|
| 1123 |
+
"loss": 0.1921,
|
| 1124 |
+
"step": 7500
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 5.26,
|
| 1128 |
+
"eval_accuracy": 0.7404999732971191,
|
| 1129 |
+
"eval_loss": 0.8792451024055481,
|
| 1130 |
+
"eval_runtime": 20.264,
|
| 1131 |
+
"eval_samples_per_second": 98.697,
|
| 1132 |
+
"eval_steps_per_second": 6.169,
|
| 1133 |
+
"step": 7500
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 5.33,
|
| 1137 |
+
"learning_rate": 2.341549295774648e-06,
|
| 1138 |
+
"loss": 0.1916,
|
| 1139 |
+
"step": 7600
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 5.33,
|
| 1143 |
+
"eval_accuracy": 0.7409999966621399,
|
| 1144 |
+
"eval_loss": 0.8891890645027161,
|
| 1145 |
+
"eval_runtime": 20.8102,
|
| 1146 |
+
"eval_samples_per_second": 96.107,
|
| 1147 |
+
"eval_steps_per_second": 6.007,
|
| 1148 |
+
"step": 7600
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 5.4,
|
| 1152 |
+
"learning_rate": 2.306338028169014e-06,
|
| 1153 |
+
"loss": 0.2011,
|
| 1154 |
+
"step": 7700
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 5.4,
|
| 1158 |
+
"eval_accuracy": 0.7325000166893005,
|
| 1159 |
+
"eval_loss": 0.9012252688407898,
|
| 1160 |
+
"eval_runtime": 21.4132,
|
| 1161 |
+
"eval_samples_per_second": 93.4,
|
| 1162 |
+
"eval_steps_per_second": 5.838,
|
| 1163 |
+
"step": 7700
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 5.47,
|
| 1167 |
+
"learning_rate": 2.2711267605633805e-06,
|
| 1168 |
+
"loss": 0.211,
|
| 1169 |
+
"step": 7800
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 5.47,
|
| 1173 |
+
"eval_accuracy": 0.7419999837875366,
|
| 1174 |
+
"eval_loss": 0.8607960343360901,
|
| 1175 |
+
"eval_runtime": 17.8954,
|
| 1176 |
+
"eval_samples_per_second": 111.761,
|
| 1177 |
+
"eval_steps_per_second": 6.985,
|
| 1178 |
+
"step": 7800
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 5.54,
|
| 1182 |
+
"learning_rate": 2.235915492957747e-06,
|
| 1183 |
+
"loss": 0.2194,
|
| 1184 |
+
"step": 7900
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 5.54,
|
| 1188 |
+
"eval_accuracy": 0.7319999933242798,
|
| 1189 |
+
"eval_loss": 0.8851566314697266,
|
| 1190 |
+
"eval_runtime": 12.4785,
|
| 1191 |
+
"eval_samples_per_second": 160.275,
|
| 1192 |
+
"eval_steps_per_second": 10.017,
|
| 1193 |
+
"step": 7900
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 5.61,
|
| 1197 |
+
"learning_rate": 2.200704225352113e-06,
|
| 1198 |
+
"loss": 0.205,
|
| 1199 |
+
"step": 8000
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 5.61,
|
| 1203 |
+
"eval_accuracy": 0.7384999990463257,
|
| 1204 |
+
"eval_loss": 0.8803377151489258,
|
| 1205 |
+
"eval_runtime": 17.7919,
|
| 1206 |
+
"eval_samples_per_second": 112.41,
|
| 1207 |
+
"eval_steps_per_second": 7.026,
|
| 1208 |
+
"step": 8000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 5.68,
|
| 1212 |
+
"learning_rate": 2.1654929577464787e-06,
|
| 1213 |
+
"loss": 0.1981,
|
| 1214 |
+
"step": 8100
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 5.68,
|
| 1218 |
+
"eval_accuracy": 0.7329999804496765,
|
| 1219 |
+
"eval_loss": 0.86810302734375,
|
| 1220 |
+
"eval_runtime": 15.0816,
|
| 1221 |
+
"eval_samples_per_second": 132.612,
|
| 1222 |
+
"eval_steps_per_second": 8.288,
|
| 1223 |
+
"step": 8100
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 5.75,
|
| 1227 |
+
"learning_rate": 2.130281690140845e-06,
|
| 1228 |
+
"loss": 0.1908,
|
| 1229 |
+
"step": 8200
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 5.75,
|
| 1233 |
+
"eval_accuracy": 0.7434999942779541,
|
| 1234 |
+
"eval_loss": 0.9019960761070251,
|
| 1235 |
+
"eval_runtime": 16.0702,
|
| 1236 |
+
"eval_samples_per_second": 124.454,
|
| 1237 |
+
"eval_steps_per_second": 7.778,
|
| 1238 |
+
"step": 8200
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 5.82,
|
| 1242 |
+
"learning_rate": 2.0950704225352115e-06,
|
| 1243 |
+
"loss": 0.1942,
|
| 1244 |
+
"step": 8300
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 5.82,
|
| 1248 |
+
"eval_accuracy": 0.7409999966621399,
|
| 1249 |
+
"eval_loss": 0.8780096173286438,
|
| 1250 |
+
"eval_runtime": 18.9162,
|
| 1251 |
+
"eval_samples_per_second": 105.73,
|
| 1252 |
+
"eval_steps_per_second": 6.608,
|
| 1253 |
+
"step": 8300
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 5.89,
|
| 1257 |
+
"learning_rate": 2.059859154929578e-06,
|
| 1258 |
+
"loss": 0.1958,
|
| 1259 |
+
"step": 8400
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 5.89,
|
| 1263 |
+
"eval_accuracy": 0.734499990940094,
|
| 1264 |
+
"eval_loss": 0.8936640620231628,
|
| 1265 |
+
"eval_runtime": 19.3712,
|
| 1266 |
+
"eval_samples_per_second": 103.246,
|
| 1267 |
+
"eval_steps_per_second": 6.453,
|
| 1268 |
+
"step": 8400
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 5.96,
|
| 1272 |
+
"learning_rate": 2.0246478873239438e-06,
|
| 1273 |
+
"loss": 0.1883,
|
| 1274 |
+
"step": 8500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 5.96,
|
| 1278 |
+
"eval_accuracy": 0.7360000014305115,
|
| 1279 |
+
"eval_loss": 0.9120668172836304,
|
| 1280 |
+
"eval_runtime": 17.1206,
|
| 1281 |
+
"eval_samples_per_second": 116.818,
|
| 1282 |
+
"eval_steps_per_second": 7.301,
|
| 1283 |
+
"step": 8500
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 6.04,
|
| 1287 |
+
"learning_rate": 1.98943661971831e-06,
|
| 1288 |
+
"loss": 0.1819,
|
| 1289 |
+
"step": 8600
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 6.04,
|
| 1293 |
+
"eval_accuracy": 0.7429999709129333,
|
| 1294 |
+
"eval_loss": 0.94089674949646,
|
| 1295 |
+
"eval_runtime": 22.6258,
|
| 1296 |
+
"eval_samples_per_second": 88.395,
|
| 1297 |
+
"eval_steps_per_second": 5.525,
|
| 1298 |
+
"step": 8600
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 6.11,
|
| 1302 |
+
"learning_rate": 1.954225352112676e-06,
|
| 1303 |
+
"loss": 0.145,
|
| 1304 |
+
"step": 8700
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 6.11,
|
| 1308 |
+
"eval_accuracy": 0.7264999747276306,
|
| 1309 |
+
"eval_loss": 1.1389663219451904,
|
| 1310 |
+
"eval_runtime": 15.9579,
|
| 1311 |
+
"eval_samples_per_second": 125.33,
|
| 1312 |
+
"eval_steps_per_second": 7.833,
|
| 1313 |
+
"step": 8700
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 6.18,
|
| 1317 |
+
"learning_rate": 1.9190140845070424e-06,
|
| 1318 |
+
"loss": 0.1696,
|
| 1319 |
+
"step": 8800
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 6.18,
|
| 1323 |
+
"eval_accuracy": 0.7429999709129333,
|
| 1324 |
+
"eval_loss": 0.9188500046730042,
|
| 1325 |
+
"eval_runtime": 21.2758,
|
| 1326 |
+
"eval_samples_per_second": 94.003,
|
| 1327 |
+
"eval_steps_per_second": 5.875,
|
| 1328 |
+
"step": 8800
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 6.25,
|
| 1332 |
+
"learning_rate": 1.8838028169014086e-06,
|
| 1333 |
+
"loss": 0.1488,
|
| 1334 |
+
"step": 8900
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 6.25,
|
| 1338 |
+
"eval_accuracy": 0.7400000095367432,
|
| 1339 |
+
"eval_loss": 0.9717501401901245,
|
| 1340 |
+
"eval_runtime": 17.3967,
|
| 1341 |
+
"eval_samples_per_second": 114.964,
|
| 1342 |
+
"eval_steps_per_second": 7.185,
|
| 1343 |
+
"step": 8900
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 6.32,
|
| 1347 |
+
"learning_rate": 1.848591549295775e-06,
|
| 1348 |
+
"loss": 0.1637,
|
| 1349 |
+
"step": 9000
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 6.32,
|
| 1353 |
+
"eval_accuracy": 0.7450000047683716,
|
| 1354 |
+
"eval_loss": 0.9701842069625854,
|
| 1355 |
+
"eval_runtime": 19.9143,
|
| 1356 |
+
"eval_samples_per_second": 100.43,
|
| 1357 |
+
"eval_steps_per_second": 6.277,
|
| 1358 |
+
"step": 9000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 6.39,
|
| 1362 |
+
"learning_rate": 1.813380281690141e-06,
|
| 1363 |
+
"loss": 0.1547,
|
| 1364 |
+
"step": 9100
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 6.39,
|
| 1368 |
+
"eval_accuracy": 0.7409999966621399,
|
| 1369 |
+
"eval_loss": 1.0032541751861572,
|
| 1370 |
+
"eval_runtime": 21.7985,
|
| 1371 |
+
"eval_samples_per_second": 91.749,
|
| 1372 |
+
"eval_steps_per_second": 5.734,
|
| 1373 |
+
"step": 9100
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 6.46,
|
| 1377 |
+
"learning_rate": 1.7781690140845072e-06,
|
| 1378 |
+
"loss": 0.1605,
|
| 1379 |
+
"step": 9200
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 6.46,
|
| 1383 |
+
"eval_accuracy": 0.7354999780654907,
|
| 1384 |
+
"eval_loss": 0.99726402759552,
|
| 1385 |
+
"eval_runtime": 21.688,
|
| 1386 |
+
"eval_samples_per_second": 92.217,
|
| 1387 |
+
"eval_steps_per_second": 5.764,
|
| 1388 |
+
"step": 9200
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 6.53,
|
| 1392 |
+
"learning_rate": 1.7429577464788734e-06,
|
| 1393 |
+
"loss": 0.1552,
|
| 1394 |
+
"step": 9300
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 6.53,
|
| 1398 |
+
"eval_accuracy": 0.7289999723434448,
|
| 1399 |
+
"eval_loss": 1.0491423606872559,
|
| 1400 |
+
"eval_runtime": 20.7168,
|
| 1401 |
+
"eval_samples_per_second": 96.54,
|
| 1402 |
+
"eval_steps_per_second": 6.034,
|
| 1403 |
+
"step": 9300
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 6.6,
|
| 1407 |
+
"learning_rate": 1.7077464788732395e-06,
|
| 1408 |
+
"loss": 0.1731,
|
| 1409 |
+
"step": 9400
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 6.6,
|
| 1413 |
+
"eval_accuracy": 0.7335000038146973,
|
| 1414 |
+
"eval_loss": 1.027091145515442,
|
| 1415 |
+
"eval_runtime": 21.2758,
|
| 1416 |
+
"eval_samples_per_second": 94.003,
|
| 1417 |
+
"eval_steps_per_second": 5.875,
|
| 1418 |
+
"step": 9400
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 6.67,
|
| 1422 |
+
"learning_rate": 1.6725352112676057e-06,
|
| 1423 |
+
"loss": 0.1738,
|
| 1424 |
+
"step": 9500
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 6.67,
|
| 1428 |
+
"eval_accuracy": 0.7429999709129333,
|
| 1429 |
+
"eval_loss": 0.9575192928314209,
|
| 1430 |
+
"eval_runtime": 18.6703,
|
| 1431 |
+
"eval_samples_per_second": 107.122,
|
| 1432 |
+
"eval_steps_per_second": 6.695,
|
| 1433 |
+
"step": 9500
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 6.74,
|
| 1437 |
+
"learning_rate": 1.637323943661972e-06,
|
| 1438 |
+
"loss": 0.1669,
|
| 1439 |
+
"step": 9600
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 6.74,
|
| 1443 |
+
"eval_accuracy": 0.7350000143051147,
|
| 1444 |
+
"eval_loss": 0.9613668322563171,
|
| 1445 |
+
"eval_runtime": 21.3968,
|
| 1446 |
+
"eval_samples_per_second": 93.472,
|
| 1447 |
+
"eval_steps_per_second": 5.842,
|
| 1448 |
+
"step": 9600
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 6.81,
|
| 1452 |
+
"learning_rate": 1.6021126760563382e-06,
|
| 1453 |
+
"loss": 0.1347,
|
| 1454 |
+
"step": 9700
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 6.81,
|
| 1458 |
+
"eval_accuracy": 0.7365000247955322,
|
| 1459 |
+
"eval_loss": 1.0263434648513794,
|
| 1460 |
+
"eval_runtime": 19.7329,
|
| 1461 |
+
"eval_samples_per_second": 101.353,
|
| 1462 |
+
"eval_steps_per_second": 6.335,
|
| 1463 |
+
"step": 9700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 6.88,
|
| 1467 |
+
"learning_rate": 1.5669014084507045e-06,
|
| 1468 |
+
"loss": 0.1593,
|
| 1469 |
+
"step": 9800
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 6.88,
|
| 1473 |
+
"eval_accuracy": 0.7360000014305115,
|
| 1474 |
+
"eval_loss": 1.017268180847168,
|
| 1475 |
+
"eval_runtime": 16.8592,
|
| 1476 |
+
"eval_samples_per_second": 118.63,
|
| 1477 |
+
"eval_steps_per_second": 7.414,
|
| 1478 |
+
"step": 9800
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 6.95,
|
| 1482 |
+
"learning_rate": 1.5316901408450705e-06,
|
| 1483 |
+
"loss": 0.1549,
|
| 1484 |
+
"step": 9900
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 6.95,
|
| 1488 |
+
"eval_accuracy": 0.7350000143051147,
|
| 1489 |
+
"eval_loss": 1.0397531986236572,
|
| 1490 |
+
"eval_runtime": 18.6472,
|
| 1491 |
+
"eval_samples_per_second": 107.255,
|
| 1492 |
+
"eval_steps_per_second": 6.703,
|
| 1493 |
+
"step": 9900
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 7.02,
|
| 1497 |
+
"learning_rate": 1.4964788732394366e-06,
|
| 1498 |
+
"loss": 0.1675,
|
| 1499 |
+
"step": 10000
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 7.02,
|
| 1503 |
+
"eval_accuracy": 0.7379999756813049,
|
| 1504 |
+
"eval_loss": 0.9975456595420837,
|
| 1505 |
+
"eval_runtime": 19.9355,
|
| 1506 |
+
"eval_samples_per_second": 100.323,
|
| 1507 |
+
"eval_steps_per_second": 6.27,
|
| 1508 |
+
"step": 10000
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 7.09,
|
| 1512 |
+
"learning_rate": 1.461267605633803e-06,
|
| 1513 |
+
"loss": 0.1182,
|
| 1514 |
+
"step": 10100
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 7.09,
|
| 1518 |
+
"eval_accuracy": 0.7350000143051147,
|
| 1519 |
+
"eval_loss": 1.105920672416687,
|
| 1520 |
+
"eval_runtime": 22.1229,
|
| 1521 |
+
"eval_samples_per_second": 90.404,
|
| 1522 |
+
"eval_steps_per_second": 5.65,
|
| 1523 |
+
"step": 10100
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 7.16,
|
| 1527 |
+
"learning_rate": 1.4260563380281691e-06,
|
| 1528 |
+
"loss": 0.1351,
|
| 1529 |
+
"step": 10200
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 7.16,
|
| 1533 |
+
"eval_accuracy": 0.7400000095367432,
|
| 1534 |
+
"eval_loss": 1.093347191810608,
|
| 1535 |
+
"eval_runtime": 20.9448,
|
| 1536 |
+
"eval_samples_per_second": 95.489,
|
| 1537 |
+
"eval_steps_per_second": 5.968,
|
| 1538 |
+
"step": 10200
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 7.23,
|
| 1542 |
+
"learning_rate": 1.3908450704225355e-06,
|
| 1543 |
+
"loss": 0.1496,
|
| 1544 |
+
"step": 10300
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 7.23,
|
| 1548 |
+
"eval_accuracy": 0.7354999780654907,
|
| 1549 |
+
"eval_loss": 1.0731019973754883,
|
| 1550 |
+
"eval_runtime": 17.3295,
|
| 1551 |
+
"eval_samples_per_second": 115.41,
|
| 1552 |
+
"eval_steps_per_second": 7.213,
|
| 1553 |
+
"step": 10300
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 7.3,
|
| 1557 |
+
"learning_rate": 1.3556338028169017e-06,
|
| 1558 |
+
"loss": 0.1197,
|
| 1559 |
+
"step": 10400
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 7.3,
|
| 1563 |
+
"eval_accuracy": 0.7360000014305115,
|
| 1564 |
+
"eval_loss": 1.1089140176773071,
|
| 1565 |
+
"eval_runtime": 19.6723,
|
| 1566 |
+
"eval_samples_per_second": 101.666,
|
| 1567 |
+
"eval_steps_per_second": 6.354,
|
| 1568 |
+
"step": 10400
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 7.37,
|
| 1572 |
+
"learning_rate": 1.3204225352112676e-06,
|
| 1573 |
+
"loss": 0.1111,
|
| 1574 |
+
"step": 10500
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 7.37,
|
| 1578 |
+
"eval_accuracy": 0.7404999732971191,
|
| 1579 |
+
"eval_loss": 1.1381380558013916,
|
| 1580 |
+
"eval_runtime": 18.6584,
|
| 1581 |
+
"eval_samples_per_second": 107.191,
|
| 1582 |
+
"eval_steps_per_second": 6.699,
|
| 1583 |
+
"step": 10500
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 7.44,
|
| 1587 |
+
"learning_rate": 1.285211267605634e-06,
|
| 1588 |
+
"loss": 0.1494,
|
| 1589 |
+
"step": 10600
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 7.44,
|
| 1593 |
+
"eval_accuracy": 0.7425000071525574,
|
| 1594 |
+
"eval_loss": 1.0251615047454834,
|
| 1595 |
+
"eval_runtime": 20.1427,
|
| 1596 |
+
"eval_samples_per_second": 99.292,
|
| 1597 |
+
"eval_steps_per_second": 6.206,
|
| 1598 |
+
"step": 10600
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 7.51,
|
| 1602 |
+
"learning_rate": 1.25e-06,
|
| 1603 |
+
"loss": 0.1235,
|
| 1604 |
+
"step": 10700
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 7.51,
|
| 1608 |
+
"eval_accuracy": 0.7360000014305115,
|
| 1609 |
+
"eval_loss": 1.0906413793563843,
|
| 1610 |
+
"eval_runtime": 22.5849,
|
| 1611 |
+
"eval_samples_per_second": 88.555,
|
| 1612 |
+
"eval_steps_per_second": 5.535,
|
| 1613 |
+
"step": 10700
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 7.58,
|
| 1617 |
+
"learning_rate": 1.2147887323943663e-06,
|
| 1618 |
+
"loss": 0.133,
|
| 1619 |
+
"step": 10800
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 7.58,
|
| 1623 |
+
"eval_accuracy": 0.737500011920929,
|
| 1624 |
+
"eval_loss": 1.1796296834945679,
|
| 1625 |
+
"eval_runtime": 12.3686,
|
| 1626 |
+
"eval_samples_per_second": 161.699,
|
| 1627 |
+
"eval_steps_per_second": 10.106,
|
| 1628 |
+
"step": 10800
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 7.65,
|
| 1632 |
+
"learning_rate": 1.1795774647887324e-06,
|
| 1633 |
+
"loss": 0.1248,
|
| 1634 |
+
"step": 10900
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 7.65,
|
| 1638 |
+
"eval_accuracy": 0.7419999837875366,
|
| 1639 |
+
"eval_loss": 1.1331868171691895,
|
| 1640 |
+
"eval_runtime": 21.2537,
|
| 1641 |
+
"eval_samples_per_second": 94.101,
|
| 1642 |
+
"eval_steps_per_second": 5.881,
|
| 1643 |
+
"step": 10900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 7.72,
|
| 1647 |
+
"learning_rate": 1.1443661971830988e-06,
|
| 1648 |
+
"loss": 0.1268,
|
| 1649 |
+
"step": 11000
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 7.72,
|
| 1653 |
+
"eval_accuracy": 0.7415000200271606,
|
| 1654 |
+
"eval_loss": 1.1304017305374146,
|
| 1655 |
+
"eval_runtime": 20.2304,
|
| 1656 |
+
"eval_samples_per_second": 98.861,
|
| 1657 |
+
"eval_steps_per_second": 6.179,
|
| 1658 |
+
"step": 11000
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 7.79,
|
| 1662 |
+
"learning_rate": 1.109154929577465e-06,
|
| 1663 |
+
"loss": 0.1368,
|
| 1664 |
+
"step": 11100
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 7.79,
|
| 1668 |
+
"eval_accuracy": 0.7379999756813049,
|
| 1669 |
+
"eval_loss": 1.1345131397247314,
|
| 1670 |
+
"eval_runtime": 21.0499,
|
| 1671 |
+
"eval_samples_per_second": 95.013,
|
| 1672 |
+
"eval_steps_per_second": 5.938,
|
| 1673 |
+
"step": 11100
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 7.86,
|
| 1677 |
+
"learning_rate": 1.073943661971831e-06,
|
| 1678 |
+
"loss": 0.1228,
|
| 1679 |
+
"step": 11200
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 7.86,
|
| 1683 |
+
"eval_accuracy": 0.7319999933242798,
|
| 1684 |
+
"eval_loss": 1.2018308639526367,
|
| 1685 |
+
"eval_runtime": 21.3555,
|
| 1686 |
+
"eval_samples_per_second": 93.653,
|
| 1687 |
+
"eval_steps_per_second": 5.853,
|
| 1688 |
+
"step": 11200
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 7.93,
|
| 1692 |
+
"learning_rate": 1.0387323943661972e-06,
|
| 1693 |
+
"loss": 0.1281,
|
| 1694 |
+
"step": 11300
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 7.93,
|
| 1698 |
+
"eval_accuracy": 0.7350000143051147,
|
| 1699 |
+
"eval_loss": 1.1884474754333496,
|
| 1700 |
+
"eval_runtime": 18.4277,
|
| 1701 |
+
"eval_samples_per_second": 108.532,
|
| 1702 |
+
"eval_steps_per_second": 6.783,
|
| 1703 |
+
"step": 11300
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 8.0,
|
| 1707 |
+
"learning_rate": 1.0035211267605636e-06,
|
| 1708 |
+
"loss": 0.1449,
|
| 1709 |
+
"step": 11400
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 8.0,
|
| 1713 |
+
"eval_accuracy": 0.734499990940094,
|
| 1714 |
+
"eval_loss": 1.157057762145996,
|
| 1715 |
+
"eval_runtime": 16.3477,
|
| 1716 |
+
"eval_samples_per_second": 122.341,
|
| 1717 |
+
"eval_steps_per_second": 7.646,
|
| 1718 |
+
"step": 11400
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 8.07,
|
| 1722 |
+
"learning_rate": 9.683098591549295e-07,
|
| 1723 |
+
"loss": 0.1025,
|
| 1724 |
+
"step": 11500
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 8.07,
|
| 1728 |
+
"eval_accuracy": 0.734499990940094,
|
| 1729 |
+
"eval_loss": 1.153812289237976,
|
| 1730 |
+
"eval_runtime": 15.7861,
|
| 1731 |
+
"eval_samples_per_second": 126.694,
|
| 1732 |
+
"eval_steps_per_second": 7.918,
|
| 1733 |
+
"step": 11500
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 8.14,
|
| 1737 |
+
"learning_rate": 9.330985915492959e-07,
|
| 1738 |
+
"loss": 0.1199,
|
| 1739 |
+
"step": 11600
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 8.14,
|
| 1743 |
+
"eval_accuracy": 0.7390000224113464,
|
| 1744 |
+
"eval_loss": 1.2113364934921265,
|
| 1745 |
+
"eval_runtime": 16.1478,
|
| 1746 |
+
"eval_samples_per_second": 123.856,
|
| 1747 |
+
"eval_steps_per_second": 7.741,
|
| 1748 |
+
"step": 11600
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 8.21,
|
| 1752 |
+
"learning_rate": 8.978873239436621e-07,
|
| 1753 |
+
"loss": 0.1016,
|
| 1754 |
+
"step": 11700
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 8.21,
|
| 1758 |
+
"eval_accuracy": 0.7369999885559082,
|
| 1759 |
+
"eval_loss": 1.2881745100021362,
|
| 1760 |
+
"eval_runtime": 23.0414,
|
| 1761 |
+
"eval_samples_per_second": 86.8,
|
| 1762 |
+
"eval_steps_per_second": 5.425,
|
| 1763 |
+
"step": 11700
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 8.28,
|
| 1767 |
+
"learning_rate": 8.626760563380282e-07,
|
| 1768 |
+
"loss": 0.114,
|
| 1769 |
+
"step": 11800
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 8.28,
|
| 1773 |
+
"eval_accuracy": 0.7390000224113464,
|
| 1774 |
+
"eval_loss": 1.287195086479187,
|
| 1775 |
+
"eval_runtime": 19.2083,
|
| 1776 |
+
"eval_samples_per_second": 104.122,
|
| 1777 |
+
"eval_steps_per_second": 6.508,
|
| 1778 |
+
"step": 11800
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 8.35,
|
| 1782 |
+
"learning_rate": 8.274647887323944e-07,
|
| 1783 |
+
"loss": 0.1019,
|
| 1784 |
+
"step": 11900
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 8.35,
|
| 1788 |
+
"eval_accuracy": 0.7379999756813049,
|
| 1789 |
+
"eval_loss": 1.287625789642334,
|
| 1790 |
+
"eval_runtime": 19.2034,
|
| 1791 |
+
"eval_samples_per_second": 104.148,
|
| 1792 |
+
"eval_steps_per_second": 6.509,
|
| 1793 |
+
"step": 11900
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 8.42,
|
| 1797 |
+
"learning_rate": 7.922535211267607e-07,
|
| 1798 |
+
"loss": 0.1142,
|
| 1799 |
+
"step": 12000
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 8.42,
|
| 1803 |
+
"eval_accuracy": 0.7384999990463257,
|
| 1804 |
+
"eval_loss": 1.2790753841400146,
|
| 1805 |
+
"eval_runtime": 12.6779,
|
| 1806 |
+
"eval_samples_per_second": 157.755,
|
| 1807 |
+
"eval_steps_per_second": 9.86,
|
| 1808 |
+
"step": 12000
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 8.49,
|
| 1812 |
+
"learning_rate": 7.570422535211268e-07,
|
| 1813 |
+
"loss": 0.1135,
|
| 1814 |
+
"step": 12100
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 8.49,
|
| 1818 |
+
"eval_accuracy": 0.7379999756813049,
|
| 1819 |
+
"eval_loss": 1.2882863283157349,
|
| 1820 |
+
"eval_runtime": 22.9048,
|
| 1821 |
+
"eval_samples_per_second": 87.318,
|
| 1822 |
+
"eval_steps_per_second": 5.457,
|
| 1823 |
+
"step": 12100
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 8.56,
|
| 1827 |
+
"learning_rate": 7.21830985915493e-07,
|
| 1828 |
+
"loss": 0.1139,
|
| 1829 |
+
"step": 12200
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 8.56,
|
| 1833 |
+
"eval_accuracy": 0.7360000014305115,
|
| 1834 |
+
"eval_loss": 1.2828530073165894,
|
| 1835 |
+
"eval_runtime": 12.6066,
|
| 1836 |
+
"eval_samples_per_second": 158.647,
|
| 1837 |
+
"eval_steps_per_second": 9.915,
|
| 1838 |
+
"step": 12200
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 8.63,
|
| 1842 |
+
"learning_rate": 6.866197183098592e-07,
|
| 1843 |
+
"loss": 0.1107,
|
| 1844 |
+
"step": 12300
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 8.63,
|
| 1848 |
+
"eval_accuracy": 0.7365000247955322,
|
| 1849 |
+
"eval_loss": 1.269805669784546,
|
| 1850 |
+
"eval_runtime": 18.0397,
|
| 1851 |
+
"eval_samples_per_second": 110.866,
|
| 1852 |
+
"eval_steps_per_second": 6.929,
|
| 1853 |
+
"step": 12300
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 8.7,
|
| 1857 |
+
"learning_rate": 6.514084507042254e-07,
|
| 1858 |
+
"loss": 0.1183,
|
| 1859 |
+
"step": 12400
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 8.7,
|
| 1863 |
+
"eval_accuracy": 0.734499990940094,
|
| 1864 |
+
"eval_loss": 1.266024112701416,
|
| 1865 |
+
"eval_runtime": 18.8559,
|
| 1866 |
+
"eval_samples_per_second": 106.068,
|
| 1867 |
+
"eval_steps_per_second": 6.629,
|
| 1868 |
+
"step": 12400
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 8.77,
|
| 1872 |
+
"learning_rate": 6.161971830985916e-07,
|
| 1873 |
+
"loss": 0.1064,
|
| 1874 |
+
"step": 12500
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 8.77,
|
| 1878 |
+
"eval_accuracy": 0.7365000247955322,
|
| 1879 |
+
"eval_loss": 1.288902759552002,
|
| 1880 |
+
"eval_runtime": 20.1463,
|
| 1881 |
+
"eval_samples_per_second": 99.274,
|
| 1882 |
+
"eval_steps_per_second": 6.205,
|
| 1883 |
+
"step": 12500
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 8.84,
|
| 1887 |
+
"learning_rate": 5.809859154929578e-07,
|
| 1888 |
+
"loss": 0.0895,
|
| 1889 |
+
"step": 12600
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 8.84,
|
| 1893 |
+
"eval_accuracy": 0.7329999804496765,
|
| 1894 |
+
"eval_loss": 1.3480335474014282,
|
| 1895 |
+
"eval_runtime": 19.9481,
|
| 1896 |
+
"eval_samples_per_second": 100.26,
|
| 1897 |
+
"eval_steps_per_second": 6.266,
|
| 1898 |
+
"step": 12600
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 8.91,
|
| 1902 |
+
"learning_rate": 5.457746478873239e-07,
|
| 1903 |
+
"loss": 0.1244,
|
| 1904 |
+
"step": 12700
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 8.91,
|
| 1908 |
+
"eval_accuracy": 0.7325000166893005,
|
| 1909 |
+
"eval_loss": 1.2872198820114136,
|
| 1910 |
+
"eval_runtime": 17.773,
|
| 1911 |
+
"eval_samples_per_second": 112.53,
|
| 1912 |
+
"eval_steps_per_second": 7.033,
|
| 1913 |
+
"step": 12700
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 8.98,
|
| 1917 |
+
"learning_rate": 5.105633802816902e-07,
|
| 1918 |
+
"loss": 0.1209,
|
| 1919 |
+
"step": 12800
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 8.98,
|
| 1923 |
+
"eval_accuracy": 0.737500011920929,
|
| 1924 |
+
"eval_loss": 1.2680846452713013,
|
| 1925 |
+
"eval_runtime": 22.2614,
|
| 1926 |
+
"eval_samples_per_second": 89.842,
|
| 1927 |
+
"eval_steps_per_second": 5.615,
|
| 1928 |
+
"step": 12800
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 9.05,
|
| 1932 |
+
"learning_rate": 4.7535211267605635e-07,
|
| 1933 |
+
"loss": 0.1144,
|
| 1934 |
+
"step": 12900
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 9.05,
|
| 1938 |
+
"eval_accuracy": 0.7369999885559082,
|
| 1939 |
+
"eval_loss": 1.2711447477340698,
|
| 1940 |
+
"eval_runtime": 18.1651,
|
| 1941 |
+
"eval_samples_per_second": 110.101,
|
| 1942 |
+
"eval_steps_per_second": 6.881,
|
| 1943 |
+
"step": 12900
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 9.12,
|
| 1947 |
+
"learning_rate": 4.4014084507042255e-07,
|
| 1948 |
+
"loss": 0.1034,
|
| 1949 |
+
"step": 13000
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 9.12,
|
| 1953 |
+
"eval_accuracy": 0.7360000014305115,
|
| 1954 |
+
"eval_loss": 1.2800805568695068,
|
| 1955 |
+
"eval_runtime": 20.275,
|
| 1956 |
+
"eval_samples_per_second": 98.644,
|
| 1957 |
+
"eval_steps_per_second": 6.165,
|
| 1958 |
+
"step": 13000
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 9.19,
|
| 1962 |
+
"learning_rate": 4.049295774647888e-07,
|
| 1963 |
+
"loss": 0.113,
|
| 1964 |
+
"step": 13100
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 9.19,
|
| 1968 |
+
"eval_accuracy": 0.7350000143051147,
|
| 1969 |
+
"eval_loss": 1.2801427841186523,
|
| 1970 |
+
"eval_runtime": 19.6919,
|
| 1971 |
+
"eval_samples_per_second": 101.565,
|
| 1972 |
+
"eval_steps_per_second": 6.348,
|
| 1973 |
+
"step": 13100
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 9.26,
|
| 1977 |
+
"learning_rate": 3.6971830985915495e-07,
|
| 1978 |
+
"loss": 0.0994,
|
| 1979 |
+
"step": 13200
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 9.26,
|
| 1983 |
+
"eval_accuracy": 0.7360000014305115,
|
| 1984 |
+
"eval_loss": 1.2920359373092651,
|
| 1985 |
+
"eval_runtime": 18.5273,
|
| 1986 |
+
"eval_samples_per_second": 107.949,
|
| 1987 |
+
"eval_steps_per_second": 6.747,
|
| 1988 |
+
"step": 13200
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 9.33,
|
| 1992 |
+
"learning_rate": 3.345070422535211e-07,
|
| 1993 |
+
"loss": 0.0966,
|
| 1994 |
+
"step": 13300
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 9.33,
|
| 1998 |
+
"eval_accuracy": 0.7335000038146973,
|
| 1999 |
+
"eval_loss": 1.2760682106018066,
|
| 2000 |
+
"eval_runtime": 21.2516,
|
| 2001 |
+
"eval_samples_per_second": 94.11,
|
| 2002 |
+
"eval_steps_per_second": 5.882,
|
| 2003 |
+
"step": 13300
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 9.4,
|
| 2007 |
+
"learning_rate": 2.992957746478873e-07,
|
| 2008 |
+
"loss": 0.0939,
|
| 2009 |
+
"step": 13400
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 9.4,
|
| 2013 |
+
"eval_accuracy": 0.7365000247955322,
|
| 2014 |
+
"eval_loss": 1.2908642292022705,
|
| 2015 |
+
"eval_runtime": 17.0257,
|
| 2016 |
+
"eval_samples_per_second": 117.47,
|
| 2017 |
+
"eval_steps_per_second": 7.342,
|
| 2018 |
+
"step": 13400
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 9.47,
|
| 2022 |
+
"learning_rate": 2.6408450704225356e-07,
|
| 2023 |
+
"loss": 0.0975,
|
| 2024 |
+
"step": 13500
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 9.47,
|
| 2028 |
+
"eval_accuracy": 0.7360000014305115,
|
| 2029 |
+
"eval_loss": 1.2952693700790405,
|
| 2030 |
+
"eval_runtime": 20.8537,
|
| 2031 |
+
"eval_samples_per_second": 95.906,
|
| 2032 |
+
"eval_steps_per_second": 5.994,
|
| 2033 |
+
"step": 13500
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 9.54,
|
| 2037 |
+
"learning_rate": 2.2887323943661974e-07,
|
| 2038 |
+
"loss": 0.0842,
|
| 2039 |
+
"step": 13600
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 9.54,
|
| 2043 |
+
"eval_accuracy": 0.7335000038146973,
|
| 2044 |
+
"eval_loss": 1.3179150819778442,
|
| 2045 |
+
"eval_runtime": 20.9509,
|
| 2046 |
+
"eval_samples_per_second": 95.461,
|
| 2047 |
+
"eval_steps_per_second": 5.966,
|
| 2048 |
+
"step": 13600
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 9.61,
|
| 2052 |
+
"learning_rate": 1.936619718309859e-07,
|
| 2053 |
+
"loss": 0.0871,
|
| 2054 |
+
"step": 13700
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 9.61,
|
| 2058 |
+
"eval_accuracy": 0.7384999990463257,
|
| 2059 |
+
"eval_loss": 1.314935564994812,
|
| 2060 |
+
"eval_runtime": 20.6989,
|
| 2061 |
+
"eval_samples_per_second": 96.623,
|
| 2062 |
+
"eval_steps_per_second": 6.039,
|
| 2063 |
+
"step": 13700
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 9.68,
|
| 2067 |
+
"learning_rate": 1.5845070422535212e-07,
|
| 2068 |
+
"loss": 0.1162,
|
| 2069 |
+
"step": 13800
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 9.68,
|
| 2073 |
+
"eval_accuracy": 0.7350000143051147,
|
| 2074 |
+
"eval_loss": 1.3124284744262695,
|
| 2075 |
+
"eval_runtime": 21.7736,
|
| 2076 |
+
"eval_samples_per_second": 91.854,
|
| 2077 |
+
"eval_steps_per_second": 5.741,
|
| 2078 |
+
"step": 13800
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 9.75,
|
| 2082 |
+
"learning_rate": 1.2323943661971832e-07,
|
| 2083 |
+
"loss": 0.085,
|
| 2084 |
+
"step": 13900
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 9.75,
|
| 2088 |
+
"eval_accuracy": 0.7354999780654907,
|
| 2089 |
+
"eval_loss": 1.3206626176834106,
|
| 2090 |
+
"eval_runtime": 18.1587,
|
| 2091 |
+
"eval_samples_per_second": 110.14,
|
| 2092 |
+
"eval_steps_per_second": 6.884,
|
| 2093 |
+
"step": 13900
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 9.82,
|
| 2097 |
+
"learning_rate": 8.802816901408452e-08,
|
| 2098 |
+
"loss": 0.0966,
|
| 2099 |
+
"step": 14000
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 9.82,
|
| 2103 |
+
"eval_accuracy": 0.7335000038146973,
|
| 2104 |
+
"eval_loss": 1.3247543573379517,
|
| 2105 |
+
"eval_runtime": 16.4512,
|
| 2106 |
+
"eval_samples_per_second": 121.572,
|
| 2107 |
+
"eval_steps_per_second": 7.598,
|
| 2108 |
+
"step": 14000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 9.89,
|
| 2112 |
+
"learning_rate": 5.281690140845071e-08,
|
| 2113 |
+
"loss": 0.1064,
|
| 2114 |
+
"step": 14100
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 9.89,
|
| 2118 |
+
"eval_accuracy": 0.7335000038146973,
|
| 2119 |
+
"eval_loss": 1.3260987997055054,
|
| 2120 |
+
"eval_runtime": 22.2976,
|
| 2121 |
+
"eval_samples_per_second": 89.696,
|
| 2122 |
+
"eval_steps_per_second": 5.606,
|
| 2123 |
+
"step": 14100
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 9.96,
|
| 2127 |
+
"learning_rate": 1.7605633802816902e-08,
|
| 2128 |
+
"loss": 0.1046,
|
| 2129 |
+
"step": 14200
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 9.96,
|
| 2133 |
+
"eval_accuracy": 0.7360000014305115,
|
| 2134 |
+
"eval_loss": 1.3255339860916138,
|
| 2135 |
+
"eval_runtime": 19.2834,
|
| 2136 |
+
"eval_samples_per_second": 103.716,
|
| 2137 |
+
"eval_steps_per_second": 6.482,
|
| 2138 |
+
"step": 14200
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 10.0,
|
| 2142 |
+
"step": 14250,
|
| 2143 |
+
"total_flos": 2.1254540922139392e+17,
|
| 2144 |
+
"train_loss": 0.2872312853629129,
|
| 2145 |
+
"train_runtime": 13159.309,
|
| 2146 |
+
"train_samples_per_second": 34.664,
|
| 2147 |
+
"train_steps_per_second": 1.083
|
| 2148 |
+
}
|
| 2149 |
+
],
|
| 2150 |
+
"max_steps": 14250,
|
| 2151 |
+
"num_train_epochs": 10,
|
| 2152 |
+
"total_flos": 2.1254540922139392e+17,
|
| 2153 |
+
"trial_name": null,
|
| 2154 |
+
"trial_params": null
|
| 2155 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f96f13160d8ffc1bca4aa21a830360cbd97bda3ce08b241fde8b2efb824992a9
|
| 3 |
+
size 3375
|