de_wiki_clm_13
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.0410
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: 13
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0796 | 2000 | 7.8049 |
| 7.9182 | 2.1592 | 4000 | 7.0934 |
| 7.9182 | 3.2389 | 6000 | 6.6438 |
| 6.6966 | 4.3185 | 8000 | 6.2800 |
| 6.6966 | 5.3981 | 10000 | 5.9653 |
| 6.0339 | 6.4777 | 12000 | 5.6957 |
| 6.0339 | 7.5574 | 14000 | 5.4541 |
| 5.528 | 8.6370 | 16000 | 5.2570 |
| 5.528 | 9.7166 | 18000 | 5.0856 |
| 5.1476 | 10.7962 | 20000 | 4.9407 |
| 5.1476 | 11.8758 | 22000 | 4.8186 |
| 4.8669 | 12.9555 | 24000 | 4.7103 |
| 4.8669 | 14.0351 | 26000 | 4.6188 |
| 4.6485 | 15.1147 | 28000 | 4.5406 |
| 4.6485 | 16.1943 | 30000 | 4.4777 |
| 4.4741 | 17.2740 | 32000 | 4.4203 |
| 4.4741 | 18.3536 | 34000 | 4.3693 |
| 4.333 | 19.4332 | 36000 | 4.3261 |
| 4.333 | 20.5128 | 38000 | 4.2889 |
| 4.2145 | 21.5924 | 40000 | 4.2505 |
| 4.2145 | 22.6721 | 42000 | 4.2194 |
| 4.1051 | 23.7517 | 44000 | 4.1901 |
| 4.1051 | 24.8313 | 46000 | 4.1683 |
| 4.0047 | 25.9109 | 48000 | 4.1445 |
| 4.0047 | 26.9906 | 50000 | 4.1277 |
| 3.9204 | 28.0702 | 52000 | 4.1219 |
| 3.9204 | 29.1498 | 54000 | 4.1097 |
| 3.8494 | 30.2294 | 56000 | 4.1006 |
| 3.8494 | 31.3090 | 58000 | 4.0901 |
| 3.791 | 32.3887 | 60000 | 4.0832 |
| 3.791 | 33.4683 | 62000 | 4.0762 |
| 3.7399 | 34.5479 | 64000 | 4.0722 |
| 3.7399 | 35.6275 | 66000 | 4.0661 |
| 3.695 | 36.7072 | 68000 | 4.0642 |
| 3.695 | 37.7868 | 70000 | 4.0604 |
| 3.6543 | 38.8664 | 72000 | 4.0546 |
| 3.6543 | 39.9460 | 74000 | 4.0523 |
| 3.6166 | 41.0256 | 76000 | 4.0533 |
| 3.6166 | 42.1053 | 78000 | 4.0529 |
| 3.5806 | 43.1849 | 80000 | 4.0531 |
| 3.5806 | 44.2645 | 82000 | 4.0514 |
| 3.5508 | 45.3441 | 84000 | 4.0521 |
| 3.5508 | 46.4238 | 86000 | 4.0497 |
| 3.5245 | 47.5034 | 88000 | 4.0466 |
| 3.5245 | 48.5830 | 90000 | 4.0466 |
| 3.4995 | 49.6626 | 92000 | 4.0458 |
| 3.4995 | 50.7422 | 94000 | 4.0434 |
| 3.4781 | 51.8219 | 96000 | 4.0429 |
| 3.4781 | 52.9015 | 98000 | 4.0413 |
| 3.4586 | 53.9811 | 100000 | 4.0410 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1