latin_gpt2
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.4614
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: 0.0005
- train_batch_size: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 3000
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.172 | 0.0057 | 500 | 7.1975 |
| 6.7223 | 0.0115 | 1000 | 6.9021 |
| 6.4626 | 0.0172 | 1500 | 6.6753 |
| 6.2743 | 0.0230 | 2000 | 6.5041 |
| 6.1669 | 0.0287 | 2500 | 6.3793 |
| 6.1212 | 0.0344 | 3000 | 6.3379 |
| 6.0511 | 0.0402 | 3500 | 6.3103 |
| 5.9919 | 0.0459 | 4000 | 6.2384 |
| 5.9364 | 0.0516 | 4500 | 6.2122 |
| 5.887 | 0.0574 | 5000 | 6.1205 |
| 5.8564 | 0.0631 | 5500 | 6.1243 |
| 5.8264 | 0.0689 | 6000 | 6.0895 |
| 5.7942 | 0.0746 | 6500 | 6.0713 |
| 5.7826 | 0.0803 | 7000 | 6.0359 |
| 5.7475 | 0.0861 | 7500 | 6.0351 |
| 5.7329 | 0.0918 | 8000 | 6.0039 |
| 5.7127 | 0.0975 | 8500 | 5.9915 |
| 5.6971 | 0.1033 | 9000 | 5.9835 |
| 5.6825 | 0.1090 | 9500 | 5.9810 |
| 5.6695 | 0.1148 | 10000 | 5.9542 |
| 5.6537 | 0.1205 | 10500 | 5.9367 |
| 5.6455 | 0.1262 | 11000 | 5.9178 |
| 5.6254 | 0.1320 | 11500 | 5.9097 |
| 5.62 | 0.1377 | 12000 | 5.9092 |
| 5.608 | 0.1434 | 12500 | 5.8881 |
| 5.5993 | 0.1492 | 13000 | 5.8807 |
| 5.5891 | 0.1549 | 13500 | 5.8707 |
| 5.5791 | 0.1607 | 14000 | 5.8809 |
| 5.5701 | 0.1664 | 14500 | 5.8585 |
| 5.5651 | 0.1721 | 15000 | 5.8436 |
| 5.5595 | 0.1779 | 15500 | 5.8607 |
| 5.5509 | 0.1836 | 16000 | 5.8308 |
| 5.5401 | 0.1894 | 16500 | 5.8381 |
| 5.535 | 0.1951 | 17000 | 5.8749 |
| 5.5281 | 0.2008 | 17500 | 5.8331 |
| 5.5231 | 0.2066 | 18000 | 5.8139 |
| 5.5148 | 0.2123 | 18500 | 5.8078 |
| 5.5112 | 0.2180 | 19000 | 5.8016 |
| 5.5049 | 0.2238 | 19500 | 5.8034 |
| 5.5006 | 0.2295 | 20000 | 5.8025 |
| 5.4909 | 0.2353 | 20500 | 5.8017 |
| 5.4835 | 0.2410 | 21000 | 5.7782 |
| 5.4841 | 0.2467 | 21500 | 5.7862 |
| 5.4794 | 0.2525 | 22000 | 5.7690 |
| 5.476 | 0.2582 | 22500 | 5.7689 |
| 5.4668 | 0.2639 | 23000 | 5.7806 |
| 5.4585 | 0.2697 | 23500 | 5.7678 |
| 5.4573 | 0.2754 | 24000 | 5.7499 |
| 5.4551 | 0.2812 | 24500 | 5.7696 |
| 5.451 | 0.2869 | 25000 | 5.7564 |
| 5.4465 | 0.2926 | 25500 | 5.7508 |
| 5.4396 | 0.2984 | 26000 | 5.7414 |
| 5.4356 | 0.3041 | 26500 | 5.7354 |
| 5.4321 | 0.3098 | 27000 | 5.7471 |
| 5.427 | 0.3156 | 27500 | 5.7296 |
| 5.4242 | 0.3213 | 28000 | 5.7294 |
| 5.4192 | 0.3271 | 28500 | 5.7252 |
| 5.4168 | 0.3328 | 29000 | 5.7183 |
| 5.4135 | 0.3385 | 29500 | 5.7241 |
| 5.4077 | 0.3443 | 30000 | 5.7148 |
| 5.4051 | 0.3500 | 30500 | 5.7215 |
| 5.3994 | 0.3557 | 31000 | 5.7140 |
| 5.3992 | 0.3615 | 31500 | 5.7079 |
| 5.3902 | 0.3672 | 32000 | 5.7057 |
| 5.3848 | 0.3730 | 32500 | 5.7047 |
| 5.3865 | 0.3787 | 33000 | 5.6973 |
| 5.3824 | 0.3844 | 33500 | 5.6938 |
| 5.3769 | 0.3902 | 34000 | 5.6950 |
| 5.3733 | 0.3959 | 34500 | 5.6885 |
| 5.3694 | 0.4017 | 35000 | 5.6819 |
| 5.3638 | 0.4074 | 35500 | 5.6770 |
| 5.3611 | 0.4131 | 36000 | 5.6819 |
| 5.3615 | 0.4189 | 36500 | 5.6705 |
| 5.354 | 0.4246 | 37000 | 5.6757 |
| 5.3522 | 0.4303 | 37500 | 5.6718 |
| 5.3422 | 0.4361 | 38000 | 5.6679 |
| 5.343 | 0.4418 | 38500 | 5.6655 |
| 5.3434 | 0.4476 | 39000 | 5.6591 |
| 5.3385 | 0.4533 | 39500 | 5.6608 |
| 5.3325 | 0.4590 | 40000 | 5.6629 |
| 5.3315 | 0.4648 | 40500 | 5.6581 |
| 5.3317 | 0.4705 | 41000 | 5.6534 |
| 5.3275 | 0.4762 | 41500 | 5.6447 |
| 5.3202 | 0.4820 | 42000 | 5.6451 |
| 5.3149 | 0.4877 | 42500 | 5.6348 |
| 5.313 | 0.4935 | 43000 | 5.6366 |
| 5.3122 | 0.4992 | 43500 | 5.6384 |
| 5.3065 | 0.5049 | 44000 | 5.6326 |
| 5.299 | 0.5107 | 44500 | 5.6226 |
| 5.2997 | 0.5164 | 45000 | 5.6301 |
| 5.2959 | 0.5221 | 45500 | 5.6172 |
| 5.2907 | 0.5279 | 46000 | 5.6232 |
| 5.2889 | 0.5336 | 46500 | 5.6239 |
| 5.288 | 0.5394 | 47000 | 5.6069 |
| 5.277 | 0.5451 | 47500 | 5.6154 |
| 5.2765 | 0.5508 | 48000 | 5.6157 |
| 5.2739 | 0.5566 | 48500 | 5.6035 |
| 5.2693 | 0.5623 | 49000 | 5.6009 |
| 5.2635 | 0.5681 | 49500 | 5.5978 |
| 5.2682 | 0.5738 | 50000 | 5.5987 |
| 5.258 | 0.5795 | 50500 | 5.5971 |
| 5.26 | 0.5853 | 51000 | 5.5994 |
| 5.2568 | 0.5910 | 51500 | 5.5873 |
| 5.2446 | 0.5967 | 52000 | 5.5771 |
| 5.2469 | 0.6025 | 52500 | 5.5824 |
| 5.2459 | 0.6082 | 53000 | 5.5853 |
| 5.239 | 0.6140 | 53500 | 5.5781 |
| 5.2355 | 0.6197 | 54000 | 5.5729 |
| 5.2296 | 0.6254 | 54500 | 5.5737 |
| 5.2301 | 0.6312 | 55000 | 5.5656 |
| 5.2277 | 0.6369 | 55500 | 5.5716 |
| 5.2197 | 0.6426 | 56000 | 5.5583 |
| 5.2131 | 0.6484 | 56500 | 5.5639 |
| 5.2132 | 0.6541 | 57000 | 5.5537 |
| 5.2103 | 0.6599 | 57500 | 5.5656 |
| 5.2078 | 0.6656 | 58000 | 5.5524 |
| 5.203 | 0.6713 | 58500 | 5.5470 |
| 5.2035 | 0.6771 | 59000 | 5.5454 |
| 5.1963 | 0.6828 | 59500 | 5.5428 |
| 5.1932 | 0.6885 | 60000 | 5.5355 |
| 5.1906 | 0.6943 | 60500 | 5.5338 |
| 5.1864 | 0.7000 | 61000 | 5.5352 |
| 5.1823 | 0.7058 | 61500 | 5.5295 |
| 5.179 | 0.7115 | 62000 | 5.5296 |
| 5.1752 | 0.7172 | 62500 | 5.5259 |
| 5.1726 | 0.7230 | 63000 | 5.5291 |
| 5.1692 | 0.7287 | 63500 | 5.5183 |
| 5.1694 | 0.7345 | 64000 | 5.5173 |
| 5.1624 | 0.7402 | 64500 | 5.5162 |
| 5.161 | 0.7459 | 65000 | 5.5104 |
| 5.1588 | 0.7517 | 65500 | 5.5145 |
| 5.156 | 0.7574 | 66000 | 5.5057 |
| 5.1539 | 0.7631 | 66500 | 5.5036 |
| 5.1474 | 0.7689 | 67000 | 5.5093 |
| 5.1457 | 0.7746 | 67500 | 5.5052 |
| 5.1444 | 0.7804 | 68000 | 5.4979 |
| 5.1437 | 0.7861 | 68500 | 5.4979 |
| 5.1402 | 0.7918 | 69000 | 5.5009 |
| 5.1346 | 0.7976 | 69500 | 5.4907 |
| 5.1308 | 0.8033 | 70000 | 5.4905 |
| 5.1325 | 0.8090 | 70500 | 5.4880 |
| 5.1297 | 0.8148 | 71000 | 5.4866 |
| 5.1246 | 0.8205 | 71500 | 5.4871 |
| 5.1232 | 0.8263 | 72000 | 5.4846 |
| 5.1232 | 0.8320 | 72500 | 5.4840 |
| 5.1219 | 0.8377 | 73000 | 5.4811 |
| 5.1126 | 0.8435 | 73500 | 5.4791 |
| 5.1168 | 0.8492 | 74000 | 5.4782 |
| 5.1175 | 0.8549 | 74500 | 5.4763 |
| 5.1108 | 0.8607 | 75000 | 5.4771 |
| 5.1082 | 0.8664 | 75500 | 5.4742 |
| 5.1053 | 0.8722 | 76000 | 5.4738 |
| 5.107 | 0.8779 | 76500 | 5.4718 |
| 5.1074 | 0.8836 | 77000 | 5.4694 |
| 5.1074 | 0.8894 | 77500 | 5.4692 |
| 5.1038 | 0.8951 | 78000 | 5.4697 |
| 5.105 | 0.9008 | 78500 | 5.4684 |
| 5.1019 | 0.9066 | 79000 | 5.4665 |
| 5.1015 | 0.9123 | 79500 | 5.4663 |
| 5.101 | 0.9181 | 80000 | 5.4672 |
| 5.1022 | 0.9238 | 80500 | 5.4654 |
| 5.1 | 0.9295 | 81000 | 5.4632 |
| 5.0981 | 0.9353 | 81500 | 5.4637 |
| 5.0981 | 0.9410 | 82000 | 5.4630 |
| 5.0951 | 0.9468 | 82500 | 5.4619 |
| 5.0941 | 0.9525 | 83000 | 5.4628 |
| 5.0947 | 0.9582 | 83500 | 5.4621 |
| 5.0949 | 0.9640 | 84000 | 5.4625 |
| 5.0971 | 0.9697 | 84500 | 5.4618 |
| 5.0895 | 0.9754 | 85000 | 5.4619 |
| 5.0937 | 0.9812 | 85500 | 5.4616 |
| 5.0978 | 0.9869 | 86000 | 5.4615 |
| 5.0958 | 0.9927 | 86500 | 5.4614 |
| 5.095 | 0.9984 | 87000 | 5.4614 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.0
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 29
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.