de_wiki_mlm_30
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.0055
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 30
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40000
- training_steps: 100000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0796 | 2000 | 8.1295 |
| 8.165 | 2.1592 | 4000 | 7.4511 |
| 8.165 | 3.2389 | 6000 | 7.3578 |
| 7.369 | 4.3185 | 8000 | 7.2654 |
| 7.369 | 5.3981 | 10000 | 7.1874 |
| 7.2089 | 6.4777 | 12000 | 7.1034 |
| 7.2089 | 7.5574 | 14000 | 7.0611 |
| 7.0701 | 8.6370 | 16000 | 6.9701 |
| 7.0701 | 9.7166 | 18000 | 6.9493 |
| 6.9567 | 10.7962 | 20000 | 6.8926 |
| 6.9567 | 11.8758 | 22000 | 6.8479 |
| 6.863 | 12.9555 | 24000 | 6.7844 |
| 6.863 | 14.0351 | 26000 | 6.7093 |
| 6.7236 | 15.1147 | 28000 | 6.5634 |
| 6.7236 | 16.1943 | 30000 | 6.4365 |
| 6.4847 | 17.2740 | 32000 | 6.1951 |
| 6.4847 | 18.3536 | 34000 | 5.8373 |
| 5.9256 | 19.4332 | 36000 | 5.2895 |
| 5.9256 | 20.5128 | 38000 | 4.9567 |
| 5.0992 | 21.5924 | 40000 | 4.6883 |
| 5.0992 | 22.6721 | 42000 | 4.4813 |
| 4.6231 | 23.7517 | 44000 | 4.3045 |
| 4.6231 | 24.8313 | 46000 | 4.1386 |
| 4.2683 | 25.9109 | 48000 | 4.0062 |
| 4.2683 | 26.9906 | 50000 | 3.8906 |
| 4.0096 | 28.0702 | 52000 | 3.7984 |
| 4.0096 | 29.1498 | 54000 | 3.7150 |
| 3.8199 | 30.2294 | 56000 | 3.6128 |
| 3.8199 | 31.3090 | 58000 | 3.5471 |
| 3.6694 | 32.3887 | 60000 | 3.4932 |
| 3.6694 | 33.4683 | 62000 | 3.4384 |
| 3.5482 | 34.5479 | 64000 | 3.4021 |
| 3.5482 | 35.6275 | 66000 | 3.3532 |
| 3.4458 | 36.7072 | 68000 | 3.3054 |
| 3.4458 | 37.7868 | 70000 | 3.2852 |
| 3.3631 | 38.8664 | 72000 | 3.2286 |
| 3.3631 | 39.9460 | 74000 | 3.1990 |
| 3.3013 | 41.0256 | 76000 | 3.1797 |
| 3.3013 | 42.1053 | 78000 | 3.1476 |
| 3.2413 | 43.1849 | 80000 | 3.1266 |
| 3.2413 | 44.2645 | 82000 | 3.1271 |
| 3.1916 | 45.3441 | 84000 | 3.0851 |
| 3.1916 | 46.4238 | 86000 | 3.0758 |
| 3.1512 | 47.5034 | 88000 | 3.0595 |
| 3.1512 | 48.5830 | 90000 | 3.0410 |
| 3.1197 | 49.6626 | 92000 | 3.0217 |
| 3.1197 | 50.7422 | 94000 | 3.0267 |
| 3.0925 | 51.8219 | 96000 | 3.0220 |
| 3.0925 | 52.9015 | 98000 | 3.0122 |
| 3.0794 | 53.9811 | 100000 | 3.0055 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- -