metadata
library_name: transformers
license: other
base_model: gpt2-medium
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: gpt2-medium-pt
results: []
gpt2-medium-pt
This model is a fine-tuned version of gpt2-medium on the dolma_v17 dataset. It achieves the following results on the evaluation set:
- Loss: 4.0213
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 2000
- training_steps: 480000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9406 | 0.0021 | 1000 | 4.2421 |
| 4.1862 | 0.0042 | 2000 | 4.3823 |
| 4.2825 | 0.0063 | 3000 | 4.3790 |
| 4.1645 | 0.0083 | 4000 | 4.3446 |
| 4.2677 | 0.0104 | 5000 | 4.3706 |
| 4.0537 | 0.0125 | 6000 | 4.3647 |
| 4.0605 | 0.0146 | 7000 | 4.3406 |
| 4.0504 | 0.0167 | 8000 | 4.3591 |
| 4.1096 | 0.0187 | 9000 | 4.3455 |
| 3.9671 | 0.0208 | 10000 | 4.3356 |
| 3.9795 | 0.0229 | 11000 | 4.3432 |
| 3.9739 | 0.025 | 12000 | 4.3560 |
| 4.0854 | 0.0271 | 13000 | 4.3599 |
| 3.9751 | 0.0292 | 14000 | 4.3569 |
| 4.178 | 0.0312 | 15000 | 4.3309 |
| 3.9919 | 0.0333 | 16000 | 4.3316 |
| 4.1456 | 0.0354 | 17000 | 4.3259 |
| 4.0668 | 0.0375 | 18000 | 4.3300 |
| 4.1336 | 0.0396 | 19000 | 4.3413 |
| 4.0671 | 0.0417 | 20000 | 4.3567 |
| 4.0745 | 0.0437 | 21000 | 4.3423 |
| 3.8593 | 0.0458 | 22000 | 4.3541 |
| 4.0354 | 0.0479 | 23000 | 4.3456 |
| 4.0783 | 0.05 | 24000 | 4.3473 |
| 4.0063 | 0.0521 | 25000 | 4.3363 |
| 4.0914 | 0.0542 | 26000 | 4.3279 |
| 4.1028 | 0.0563 | 27000 | 4.3403 |
| 3.9719 | 0.0583 | 28000 | 4.3337 |
| 3.9235 | 0.0604 | 29000 | 4.3229 |
| 4.0542 | 0.0625 | 30000 | 4.3088 |
| 3.995 | 0.0646 | 31000 | 4.3274 |
| 3.9575 | 0.0667 | 32000 | 4.3180 |
| 4.0015 | 0.0688 | 33000 | 4.3040 |
| 3.8917 | 0.0708 | 34000 | 4.3096 |
| 4.0533 | 0.0729 | 35000 | 4.3057 |
| 4.0497 | 0.075 | 36000 | 4.3005 |
| 3.9832 | 0.0771 | 37000 | 4.3032 |
| 3.9568 | 0.0792 | 38000 | 4.3099 |
| 3.8289 | 0.0813 | 39000 | 4.2920 |
| 3.8529 | 0.0833 | 40000 | 4.3161 |
| 3.8106 | 0.0854 | 41000 | 4.3104 |
| 3.969 | 0.0875 | 42000 | 4.3202 |
| 3.9867 | 0.0896 | 43000 | 4.3069 |
| 3.8601 | 0.0917 | 44000 | 4.3099 |
| 3.9873 | 0.0938 | 45000 | 4.2964 |
| 3.8743 | 0.0958 | 46000 | 4.2993 |
| 3.956 | 0.0979 | 47000 | 4.2866 |
| 4.0474 | 0.1 | 48000 | 4.2899 |
| 3.9868 | 0.1021 | 49000 | 4.2792 |
| 4.1809 | 0.1042 | 50000 | 4.2974 |
| 3.7905 | 0.1062 | 51000 | 4.2968 |
| 4.1425 | 0.1083 | 52000 | 4.2928 |
| 3.9946 | 0.1104 | 53000 | 4.2871 |
| 4.0914 | 0.1125 | 54000 | 4.2808 |
| 3.9746 | 0.1146 | 55000 | 4.2826 |
| 4.1812 | 0.1167 | 56000 | 4.2942 |
| 4.156 | 0.1187 | 57000 | 4.2894 |
| 3.9697 | 0.1208 | 58000 | 4.3088 |
| 3.8969 | 0.1229 | 59000 | 4.3043 |
| 3.9393 | 0.125 | 60000 | 4.2872 |
| 3.7209 | 0.1271 | 61000 | 4.2879 |
| 4.0016 | 0.1292 | 62000 | 4.2829 |
| 3.9925 | 0.1313 | 63000 | 4.2996 |
| 3.966 | 0.1333 | 64000 | 4.2836 |
| 4.162 | 0.1354 | 65000 | 4.2700 |
| 4.1639 | 0.1375 | 66000 | 4.2808 |
| 4.003 | 0.1396 | 67000 | 4.2764 |
| 3.9027 | 0.1417 | 68000 | 4.2868 |
| 4.0008 | 0.1437 | 69000 | 4.2744 |
| 3.9711 | 0.1458 | 70000 | 4.2691 |
| 4.0112 | 0.1479 | 71000 | 4.2842 |
| 4.0251 | 0.15 | 72000 | 4.2958 |
| 3.9756 | 0.1521 | 73000 | 4.2890 |
| 4.0327 | 0.1542 | 74000 | 4.2838 |
| 4.0919 | 0.1562 | 75000 | 4.2948 |
| 3.9199 | 0.1583 | 76000 | 4.2723 |
| 3.9125 | 0.1604 | 77000 | 4.2866 |
| 3.7808 | 0.1625 | 78000 | 4.2626 |
| 3.9531 | 0.1646 | 79000 | 4.2740 |
| 3.8218 | 0.1667 | 80000 | 4.2792 |
| 3.9225 | 0.1688 | 81000 | 4.2763 |
| 3.9183 | 0.1708 | 82000 | 4.2682 |
| 3.9687 | 0.1729 | 83000 | 4.2729 |
| 3.8568 | 0.175 | 84000 | 4.2648 |
| 4.0333 | 0.1771 | 85000 | 4.2709 |
| 4.0159 | 0.1792 | 86000 | 4.2644 |
| 3.9802 | 0.1812 | 87000 | 4.2762 |
| 3.9888 | 0.1833 | 88000 | 4.2907 |
| 3.9399 | 0.1854 | 89000 | 4.2989 |
| 3.8818 | 0.1875 | 90000 | 4.2921 |
| 3.8417 | 0.1896 | 91000 | 4.2766 |
| 3.9246 | 0.1917 | 92000 | 4.3040 |
| 4.0405 | 0.1938 | 93000 | 4.2696 |
| 4.0513 | 0.1958 | 94000 | 4.2859 |
| 3.9277 | 0.1979 | 95000 | 4.2711 |
| 3.8974 | 0.2 | 96000 | 4.2692 |
| 3.8104 | 0.2021 | 97000 | 4.2821 |
| 3.9236 | 0.2042 | 98000 | 4.2718 |
| 3.9511 | 0.2062 | 99000 | 4.2568 |
| 3.9057 | 0.2083 | 100000 | 4.2715 |
| 3.9731 | 0.2104 | 101000 | 4.2596 |
| 3.9541 | 0.2125 | 102000 | 4.2579 |
| 3.838 | 0.2146 | 103000 | 4.2609 |
| 3.8423 | 0.2167 | 104000 | 4.2744 |
| 3.7543 | 0.2188 | 105000 | 4.2600 |
| 3.897 | 0.2208 | 106000 | 4.2630 |
| 4.0565 | 0.2229 | 107000 | 4.2592 |
| 3.9413 | 0.225 | 108000 | 4.2702 |
| 3.923 | 0.2271 | 109000 | 4.2499 |
| 3.8697 | 0.2292 | 110000 | 4.2497 |
| 3.899 | 0.2313 | 111000 | 4.2592 |
| 3.7349 | 0.2333 | 112000 | 4.2554 |
| 3.9045 | 0.2354 | 113000 | 4.2610 |
| 3.8632 | 0.2375 | 114000 | 4.2747 |
| 3.8984 | 0.2396 | 115000 | 4.2779 |
| 3.93 | 0.2417 | 116000 | 4.2575 |
| 3.8582 | 0.2437 | 117000 | 4.2616 |
| 4.0219 | 0.2458 | 118000 | 4.2670 |
| 3.7756 | 0.2479 | 119000 | 4.2543 |
| 3.9143 | 0.25 | 120000 | 4.2616 |
| 3.6382 | 0.2521 | 121000 | 4.2462 |
| 3.8568 | 0.2542 | 122000 | 4.2457 |
| 3.9708 | 0.2562 | 123000 | 4.2640 |
| 4.0387 | 0.2583 | 124000 | 4.2511 |
| 3.8761 | 0.2604 | 125000 | 4.2514 |
| 3.9877 | 0.2625 | 126000 | 4.2384 |
| 4.1627 | 0.2646 | 127000 | 4.2349 |
| 3.9465 | 0.2667 | 128000 | 4.2322 |
| 4.022 | 0.2687 | 129000 | 4.2292 |
| 3.9426 | 0.2708 | 130000 | 4.2244 |
| 3.9976 | 0.2729 | 131000 | 4.2385 |
| 3.8491 | 0.275 | 132000 | 4.2288 |
| 3.7929 | 0.2771 | 133000 | 4.2520 |
| 3.9137 | 0.2792 | 134000 | 4.2459 |
| 4.0672 | 0.2812 | 135000 | 4.2212 |
| 3.949 | 0.2833 | 136000 | 4.2392 |
| 3.8779 | 0.2854 | 137000 | 4.2357 |
| 3.6715 | 0.2875 | 138000 | 4.2332 |
| 3.8978 | 0.2896 | 139000 | 4.2228 |
| 3.8223 | 0.2917 | 140000 | 4.2103 |
| 3.7498 | 0.2938 | 141000 | 4.2173 |
| 3.9105 | 0.2958 | 142000 | 4.2089 |
| 3.6953 | 0.2979 | 143000 | 4.2044 |
| 3.9106 | 0.3 | 144000 | 4.2080 |
| 3.926 | 0.3021 | 145000 | 4.1949 |
| 3.731 | 0.3042 | 146000 | 4.2039 |
| 3.8684 | 0.3063 | 147000 | 4.1905 |
| 3.8938 | 0.3083 | 148000 | 4.2073 |
| 4.0697 | 0.3104 | 149000 | 4.2016 |
| 3.9828 | 0.3125 | 150000 | 4.2087 |
| 3.8982 | 0.3146 | 151000 | 4.1983 |
| 3.8948 | 0.3167 | 152000 | 4.2070 |
| 3.7433 | 0.3187 | 153000 | 4.1971 |
| 3.9262 | 0.3208 | 154000 | 4.2023 |
| 3.8333 | 0.3229 | 155000 | 4.1901 |
| 3.7393 | 0.325 | 156000 | 4.1789 |
| 3.8245 | 0.3271 | 157000 | 4.1949 |
| 3.7302 | 0.3292 | 158000 | 4.2008 |
| 3.7852 | 0.3312 | 159000 | 4.2114 |
| 4.1717 | 0.3333 | 160000 | 4.2122 |
| 3.9231 | 0.3354 | 161000 | 4.2006 |
| 3.9928 | 0.3375 | 162000 | 4.2033 |
| 3.9021 | 0.3396 | 163000 | 4.1992 |
| 3.8111 | 0.3417 | 164000 | 4.1922 |
| 3.8097 | 0.3438 | 165000 | 4.1896 |
| 3.9761 | 0.3458 | 166000 | 4.1899 |
| 3.9246 | 0.3479 | 167000 | 4.1845 |
| 3.7704 | 0.35 | 168000 | 4.1973 |
| 3.848 | 0.3521 | 169000 | 4.1928 |
| 3.9466 | 0.3542 | 170000 | 4.1868 |
| 3.9217 | 0.3563 | 171000 | 4.1876 |
| 3.8834 | 0.3583 | 172000 | 4.1830 |
| 3.9101 | 0.3604 | 173000 | 4.1831 |
| 3.863 | 0.3625 | 174000 | 4.1878 |
| 3.7479 | 0.3646 | 175000 | 4.1790 |
| 3.9295 | 0.3667 | 176000 | 4.1882 |
| 3.9213 | 0.3688 | 177000 | 4.1748 |
| 3.9537 | 0.3708 | 178000 | 4.1818 |
| 3.8242 | 0.3729 | 179000 | 4.1876 |
| 3.8014 | 0.375 | 180000 | 4.1797 |
| 3.977 | 0.3771 | 181000 | 4.1774 |
| 3.8955 | 0.3792 | 182000 | 4.1732 |
| 3.6788 | 0.3812 | 183000 | 4.1850 |
| 3.7937 | 0.3833 | 184000 | 4.1899 |
| 3.7619 | 0.3854 | 185000 | 4.1798 |
| 3.6499 | 0.3875 | 186000 | 4.1672 |
| 3.88 | 0.3896 | 187000 | 4.1677 |
| 3.8804 | 0.3917 | 188000 | 4.1707 |
| 3.9147 | 0.3937 | 189000 | 4.1752 |
| 3.8926 | 0.3958 | 190000 | 4.1679 |
| 3.914 | 0.3979 | 191000 | 4.1687 |
| 3.8568 | 0.4 | 192000 | 4.1657 |
| 3.9354 | 0.4021 | 193000 | 4.1766 |
| 4.0083 | 0.4042 | 194000 | 4.1803 |
| 3.8001 | 0.4062 | 195000 | 4.1860 |
| 3.8921 | 0.4083 | 196000 | 4.1826 |
| 3.8765 | 0.4104 | 197000 | 4.1873 |
| 3.8115 | 0.4125 | 198000 | 4.1793 |
| 3.7874 | 0.4146 | 199000 | 4.1726 |
| 3.8914 | 0.4167 | 200000 | 4.1795 |
| 3.7419 | 0.4188 | 201000 | 4.1726 |
| 3.8238 | 0.4208 | 202000 | 4.1700 |
| 3.8894 | 0.4229 | 203000 | 4.1794 |
| 3.8286 | 0.425 | 204000 | 4.1889 |
| 3.8354 | 0.4271 | 205000 | 4.1837 |
| 3.7126 | 0.4292 | 206000 | 4.1815 |
| 3.9142 | 0.4313 | 207000 | 4.1855 |
| 3.7889 | 0.4333 | 208000 | 4.1708 |
| 3.8422 | 0.4354 | 209000 | 4.1663 |
| 3.672 | 0.4375 | 210000 | 4.1822 |
| 3.7588 | 0.4396 | 211000 | 4.1781 |
| 3.8026 | 0.4417 | 212000 | 4.1646 |
| 3.6782 | 0.4437 | 213000 | 4.1546 |
| 3.8097 | 0.4458 | 214000 | 4.1580 |
| 3.793 | 0.4479 | 215000 | 4.1565 |
| 3.747 | 0.45 | 216000 | 4.1563 |
| 3.717 | 0.4521 | 217000 | 4.1519 |
| 3.7103 | 0.4542 | 218000 | 4.1483 |
| 3.7573 | 0.4562 | 219000 | 4.1505 |
| 3.7231 | 0.4583 | 220000 | 4.1426 |
| 3.7455 | 0.4604 | 221000 | 4.1467 |
| 3.9432 | 0.4625 | 222000 | 4.1394 |
| 3.7637 | 0.4646 | 223000 | 4.1492 |
| 3.7523 | 0.4667 | 224000 | 4.1488 |
| 3.8442 | 0.4688 | 225000 | 4.1421 |
| 3.8075 | 0.4708 | 226000 | 4.1489 |
| 3.8635 | 0.4729 | 227000 | 4.1428 |
| 3.7968 | 0.475 | 228000 | 4.1277 |
| 4.0897 | 0.4771 | 229000 | 4.1367 |
| 3.7897 | 0.4792 | 230000 | 4.1387 |
| 3.8465 | 0.4813 | 231000 | 4.1335 |
| 3.7556 | 0.4833 | 232000 | 4.1389 |
| 3.7213 | 0.4854 | 233000 | 4.1405 |
| 3.8532 | 0.4875 | 234000 | 4.1432 |
| 3.8223 | 0.4896 | 235000 | 4.1326 |
| 3.7056 | 0.4917 | 236000 | 4.1450 |
| 3.8021 | 0.4938 | 237000 | 4.1437 |
| 3.6611 | 0.4958 | 238000 | 4.1558 |
| 3.6681 | 0.4979 | 239000 | 4.1495 |
| 3.7164 | 0.5 | 240000 | 4.1465 |
| 3.8413 | 0.5021 | 241000 | 4.1446 |
| 3.7366 | 0.5042 | 242000 | 4.1417 |
| 3.7334 | 0.5062 | 243000 | 4.1509 |
| 3.6592 | 0.5083 | 244000 | 4.1501 |
| 3.9593 | 0.5104 | 245000 | 4.1344 |
| 3.7163 | 0.5125 | 246000 | 4.1437 |
| 3.8853 | 0.5146 | 247000 | 4.1278 |
| 3.9094 | 0.5167 | 248000 | 4.1356 |
| 3.7408 | 0.5188 | 249000 | 4.1312 |
| 3.7387 | 0.5208 | 250000 | 4.1353 |
| 3.9224 | 0.5229 | 251000 | 4.1273 |
| 3.6346 | 0.525 | 252000 | 4.1171 |
| 3.7065 | 0.5271 | 253000 | 4.1247 |
| 3.7919 | 0.5292 | 254000 | 4.1224 |
| 3.6299 | 0.5312 | 255000 | 4.1313 |
| 3.808 | 0.5333 | 256000 | 4.1354 |
| 3.7369 | 0.5354 | 257000 | 4.1361 |
| 3.7384 | 0.5375 | 258000 | 4.1302 |
| 3.6545 | 0.5396 | 259000 | 4.1199 |
| 3.5952 | 0.5417 | 260000 | 4.1144 |
| 3.9045 | 0.5437 | 261000 | 4.1138 |
| 3.7152 | 0.5458 | 262000 | 4.1106 |
| 3.6045 | 0.5479 | 263000 | 4.1139 |
| 3.6828 | 0.55 | 264000 | 4.1062 |
| 3.6521 | 0.5521 | 265000 | 4.1086 |
| 3.7868 | 0.5542 | 266000 | 4.1060 |
| 3.6959 | 0.5563 | 267000 | 4.1037 |
| 3.7066 | 0.5583 | 268000 | 4.1052 |
| 3.4761 | 0.5604 | 269000 | 4.1036 |
| 3.8575 | 0.5625 | 270000 | 4.1076 |
| 3.8409 | 0.5646 | 271000 | 4.1045 |
| 3.6896 | 0.5667 | 272000 | 4.0957 |
| 3.6256 | 0.5687 | 273000 | 4.0979 |
| 3.7911 | 0.5708 | 274000 | 4.1005 |
| 3.7844 | 0.5729 | 275000 | 4.1017 |
| 3.7466 | 0.575 | 276000 | 4.0897 |
| 3.7865 | 0.5771 | 277000 | 4.0869 |
| 3.8352 | 0.5792 | 278000 | 4.0947 |
| 3.7003 | 0.5813 | 279000 | 4.0921 |
| 3.8638 | 0.5833 | 280000 | 4.0935 |
| 3.7721 | 0.5854 | 281000 | 4.0952 |
| 3.5453 | 0.5875 | 282000 | 4.0965 |
| 3.6949 | 0.5896 | 283000 | 4.1038 |
| 3.8031 | 0.5917 | 284000 | 4.0956 |
| 3.8408 | 0.5938 | 285000 | 4.0953 |
| 3.9591 | 0.5958 | 286000 | 4.0891 |
| 3.711 | 0.5979 | 287000 | 4.0869 |
| 3.7253 | 0.6 | 288000 | 4.0866 |
| 3.9207 | 0.6021 | 289000 | 4.0826 |
| 3.9178 | 0.6042 | 290000 | 4.0798 |
| 3.8347 | 0.6062 | 291000 | 4.0909 |
| 3.7539 | 0.6083 | 292000 | 4.0801 |
| 3.6809 | 0.6104 | 293000 | 4.0882 |
| 3.9774 | 0.6125 | 294000 | 4.0892 |
| 3.99 | 0.6146 | 295000 | 4.0904 |
| 3.8178 | 0.6167 | 296000 | 4.0853 |
| 3.8028 | 0.6188 | 297000 | 4.0819 |
| 3.7628 | 0.6208 | 298000 | 4.0846 |
| 3.8974 | 0.6229 | 299000 | 4.0858 |
| 3.8916 | 0.625 | 300000 | 4.0794 |
| 3.6816 | 0.6271 | 301000 | 4.0889 |
| 3.6983 | 0.6292 | 302000 | 4.0925 |
| 3.8691 | 0.6312 | 303000 | 4.0833 |
| 3.8447 | 0.6333 | 304000 | 4.0812 |
| 3.8257 | 0.6354 | 305000 | 4.0760 |
| 3.7056 | 0.6375 | 306000 | 4.0866 |
| 3.663 | 0.6396 | 307000 | 4.0830 |
| 3.8589 | 0.6417 | 308000 | 4.0789 |
| 3.6582 | 0.6438 | 309000 | 4.0806 |
| 3.7783 | 0.6458 | 310000 | 4.0789 |
| 3.5443 | 0.6479 | 311000 | 4.0866 |
| 3.8477 | 0.65 | 312000 | 4.0782 |
| 3.9814 | 0.6521 | 313000 | 4.0796 |
| 3.6754 | 0.6542 | 314000 | 4.0780 |
| 3.6139 | 0.6562 | 315000 | 4.0765 |
| 3.862 | 0.6583 | 316000 | 4.0782 |
| 3.7231 | 0.6604 | 317000 | 4.0777 |
| 3.9263 | 0.6625 | 318000 | 4.0740 |
| 3.6825 | 0.6646 | 319000 | 4.0617 |
| 3.8881 | 0.6667 | 320000 | 4.0692 |
| 3.8735 | 0.6687 | 321000 | 4.0639 |
| 4.0071 | 0.6708 | 322000 | 4.0702 |
| 3.9353 | 0.6729 | 323000 | 4.0590 |
| 3.8194 | 0.675 | 324000 | 4.0661 |
| 3.8207 | 0.6771 | 325000 | 4.0681 |
| 3.7925 | 0.6792 | 326000 | 4.0666 |
| 3.6689 | 0.6813 | 327000 | 4.0579 |
| 3.571 | 0.6833 | 328000 | 4.0545 |
| 3.7981 | 0.6854 | 329000 | 4.0564 |
| 3.5618 | 0.6875 | 330000 | 4.0552 |
| 3.6315 | 0.6896 | 331000 | 4.0509 |
| 3.6225 | 0.6917 | 332000 | 4.0490 |
| 3.391 | 0.6937 | 333000 | 4.0562 |
| 3.3154 | 0.6958 | 334000 | 4.0567 |
| 3.4765 | 0.6979 | 335000 | 4.0542 |
| 3.6147 | 0.7 | 336000 | 4.0432 |
| 3.3405 | 0.7021 | 337000 | 4.0461 |
| 3.4943 | 0.7042 | 338000 | 4.0509 |
| 3.4187 | 0.7063 | 339000 | 4.0499 |
| 3.3465 | 0.7083 | 340000 | 4.0498 |
| 3.4459 | 0.7104 | 341000 | 4.0488 |
| 3.2883 | 0.7125 | 342000 | 4.0545 |
| 3.4472 | 0.7146 | 343000 | 4.0549 |
| 3.3612 | 0.7167 | 344000 | 4.0524 |
| 3.5244 | 0.7188 | 345000 | 4.0501 |
| 3.265 | 0.7208 | 346000 | 4.0496 |
| 3.3411 | 0.7229 | 347000 | 4.0579 |
| 3.3817 | 0.725 | 348000 | 4.0592 |
| 3.2819 | 0.7271 | 349000 | 4.0600 |
| 3.427 | 0.7292 | 350000 | 4.0575 |
| 3.3368 | 0.7312 | 351000 | 4.0601 |
| 3.3201 | 0.7333 | 352000 | 4.0515 |
| 3.2364 | 0.7354 | 353000 | 4.0528 |
| 3.3919 | 0.7375 | 354000 | 4.0591 |
| 3.4735 | 0.7396 | 355000 | 4.0526 |
| 3.4194 | 0.7417 | 356000 | 4.0530 |
| 3.4013 | 0.7438 | 357000 | 4.0557 |
| 3.4342 | 0.7458 | 358000 | 4.0545 |
| 3.3518 | 0.7479 | 359000 | 4.0585 |
| 3.3723 | 0.75 | 360000 | 4.0546 |
| 3.2925 | 0.7521 | 361000 | 4.0522 |
| 3.2357 | 0.7542 | 362000 | 4.0526 |
| 3.3607 | 0.7562 | 363000 | 4.0535 |
| 3.3699 | 0.7583 | 364000 | 4.0549 |
| 3.3595 | 0.7604 | 365000 | 4.0536 |
| 3.247 | 0.7625 | 366000 | 4.0564 |
| 3.383 | 0.7646 | 367000 | 4.0516 |
| 3.2552 | 0.7667 | 368000 | 4.0509 |
| 3.2187 | 0.7688 | 369000 | 4.0511 |
| 3.3001 | 0.7708 | 370000 | 4.0524 |
| 3.227 | 0.7729 | 371000 | 4.0477 |
| 3.2463 | 0.775 | 372000 | 4.0482 |
| 3.2435 | 0.7771 | 373000 | 4.0481 |
| 3.3318 | 0.7792 | 374000 | 4.0482 |
| 3.4435 | 0.7812 | 375000 | 4.0465 |
| 3.2585 | 0.7833 | 376000 | 4.0413 |
| 3.3729 | 0.7854 | 377000 | 4.0385 |
| 3.2543 | 0.7875 | 378000 | 4.0430 |
| 3.3345 | 0.7896 | 379000 | 4.0438 |
| 3.3178 | 0.7917 | 380000 | 4.0443 |
| 3.2855 | 0.7937 | 381000 | 4.0426 |
| 3.3473 | 0.7958 | 382000 | 4.0372 |
| 3.2588 | 0.7979 | 383000 | 4.0413 |
| 3.3472 | 0.8 | 384000 | 4.0390 |
| 3.2474 | 0.8021 | 385000 | 4.0397 |
| 3.2547 | 0.8042 | 386000 | 4.0406 |
| 3.3257 | 0.8063 | 387000 | 4.0389 |
| 3.3034 | 0.8083 | 388000 | 4.0395 |
| 3.2571 | 0.8104 | 389000 | 4.0396 |
| 3.3638 | 0.8125 | 390000 | 4.0415 |
| 3.3034 | 0.8146 | 391000 | 4.0406 |
| 3.2749 | 0.8167 | 392000 | 4.0414 |
| 3.362 | 0.8187 | 393000 | 4.0383 |
| 3.329 | 0.8208 | 394000 | 4.0358 |
| 3.3517 | 0.8229 | 395000 | 4.0359 |
| 3.3818 | 0.825 | 396000 | 4.0355 |
| 3.4573 | 0.8271 | 397000 | 4.0342 |
| 3.4271 | 0.8292 | 398000 | 4.0367 |
| 3.3829 | 0.8313 | 399000 | 4.0316 |
| 3.3357 | 0.8333 | 400000 | 4.0337 |
| 3.2081 | 0.8354 | 401000 | 4.0346 |
| 3.3231 | 0.8375 | 402000 | 4.0315 |
| 3.3298 | 0.8396 | 403000 | 4.0338 |
| 3.3668 | 0.8417 | 404000 | 4.0367 |
| 3.4354 | 0.8438 | 405000 | 4.0350 |
| 3.2523 | 0.8458 | 406000 | 4.0339 |
| 3.3122 | 0.8479 | 407000 | 4.0335 |
| 3.394 | 0.85 | 408000 | 4.0304 |
| 3.3952 | 0.8521 | 409000 | 4.0309 |
| 3.2627 | 0.8542 | 410000 | 4.0303 |
| 3.3738 | 0.8562 | 411000 | 4.0293 |
| 3.2511 | 0.8583 | 412000 | 4.0313 |
| 3.2491 | 0.8604 | 413000 | 4.0282 |
| 3.3731 | 0.8625 | 414000 | 4.0288 |
| 3.2801 | 0.8646 | 415000 | 4.0294 |
| 3.4429 | 0.8667 | 416000 | 4.0298 |
| 3.4543 | 0.8688 | 417000 | 4.0262 |
| 3.3252 | 0.8708 | 418000 | 4.0266 |
| 3.3625 | 0.8729 | 419000 | 4.0246 |
| 3.2972 | 0.875 | 420000 | 4.0243 |
| 3.3973 | 0.8771 | 421000 | 4.0265 |
| 3.2867 | 0.8792 | 422000 | 4.0273 |
| 3.2743 | 0.8812 | 423000 | 4.0242 |
| 3.421 | 0.8833 | 424000 | 4.0249 |
| 3.253 | 0.8854 | 425000 | 4.0254 |
| 3.2381 | 0.8875 | 426000 | 4.0244 |
| 3.3784 | 0.8896 | 427000 | 4.0264 |
| 3.3259 | 0.8917 | 428000 | 4.0260 |
| 3.3907 | 0.8938 | 429000 | 4.0245 |
| 3.3264 | 0.8958 | 430000 | 4.0253 |
| 3.3454 | 0.8979 | 431000 | 4.0236 |
| 3.3574 | 0.9 | 432000 | 4.0245 |
| 3.2424 | 0.9021 | 433000 | 4.0241 |
| 3.2631 | 0.9042 | 434000 | 4.0220 |
| 3.2213 | 0.9062 | 435000 | 4.0215 |
| 3.4233 | 0.9083 | 436000 | 4.0215 |
| 3.2751 | 0.9104 | 437000 | 4.0216 |
| 3.2734 | 0.9125 | 438000 | 4.0238 |
| 3.2237 | 0.9146 | 439000 | 4.0246 |
| 3.2542 | 0.9167 | 440000 | 4.0227 |
| 3.3647 | 0.9187 | 441000 | 4.0240 |
| 3.3046 | 0.9208 | 442000 | 4.0235 |
| 3.3348 | 0.9229 | 443000 | 4.0245 |
| 3.3078 | 0.925 | 444000 | 4.0226 |
| 3.2955 | 0.9271 | 445000 | 4.0226 |
| 3.3743 | 0.9292 | 446000 | 4.0217 |
| 3.2428 | 0.9313 | 447000 | 4.0229 |
| 3.2628 | 0.9333 | 448000 | 4.0239 |
| 3.2181 | 0.9354 | 449000 | 4.0235 |
| 3.3325 | 0.9375 | 450000 | 4.0230 |
| 3.3257 | 0.9396 | 451000 | 4.0227 |
| 3.3099 | 0.9417 | 452000 | 4.0224 |
| 3.2589 | 0.9437 | 453000 | 4.0222 |
| 3.2739 | 0.9458 | 454000 | 4.0216 |
| 3.3549 | 0.9479 | 455000 | 4.0222 |
| 3.3398 | 0.95 | 456000 | 4.0222 |
| 3.3307 | 0.9521 | 457000 | 4.0221 |
| 3.3722 | 0.9542 | 458000 | 4.0211 |
| 3.3067 | 0.9563 | 459000 | 4.0213 |
| 3.3333 | 0.9583 | 460000 | 4.0219 |
| 3.3305 | 0.9604 | 461000 | 4.0218 |
| 3.3302 | 0.9625 | 462000 | 4.0221 |
| 3.3891 | 0.9646 | 463000 | 4.0223 |
| 3.4306 | 0.9667 | 464000 | 4.0220 |
| 3.3226 | 0.9688 | 465000 | 4.0229 |
| 3.326 | 0.9708 | 466000 | 4.0216 |
| 3.3749 | 0.9729 | 467000 | 4.0214 |
| 3.3369 | 0.975 | 468000 | 4.0216 |
| 3.3384 | 0.9771 | 469000 | 4.0215 |
| 3.3811 | 0.9792 | 470000 | 4.0214 |
| 3.2602 | 0.9812 | 471000 | 4.0217 |
| 3.4191 | 0.9833 | 472000 | 4.0221 |
| 3.3566 | 0.9854 | 473000 | 4.0221 |
| 3.1665 | 0.9875 | 474000 | 4.0221 |
| 3.2972 | 0.9896 | 475000 | 4.0218 |
| 3.3541 | 0.9917 | 476000 | 4.0218 |
| 3.4398 | 0.9938 | 477000 | 4.0217 |
| 3.3558 | 0.9958 | 478000 | 4.0217 |
| 3.2996 | 0.9979 | 479000 | 4.0221 |
| 3.3787 | 1.0 | 480000 | 4.0213 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 2.21.0
- Tokenizers 0.21.4