en_mlm_child_30_new
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1528
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 | 1.3952 | 2000 | 7.2962 |
| 7.2342 | 2.7904 | 4000 | 6.0346 |
| 7.2342 | 4.1856 | 6000 | 5.9052 |
| 5.7167 | 5.5807 | 8000 | 5.7987 |
| 5.7167 | 6.9759 | 10000 | 5.7122 |
| 5.5262 | 8.3711 | 12000 | 5.6412 |
| 5.5262 | 9.7663 | 14000 | 5.5936 |
| 5.3872 | 11.1615 | 16000 | 5.5304 |
| 5.3872 | 12.5567 | 18000 | 5.4717 |
| 5.2756 | 13.9519 | 20000 | 5.4238 |
| 5.2756 | 15.3471 | 22000 | 5.3846 |
| 5.154 | 16.7422 | 24000 | 5.2159 |
| 5.154 | 18.1374 | 26000 | 4.9780 |
| 4.7609 | 19.5326 | 28000 | 4.3088 |
| 4.7609 | 20.9278 | 30000 | 3.7411 |
| 3.6928 | 22.3230 | 32000 | 3.4477 |
| 3.6928 | 23.7182 | 34000 | 3.1948 |
| 3.0474 | 25.1134 | 36000 | 3.0640 |
| 3.0474 | 26.5085 | 38000 | 2.9524 |
| 2.7755 | 27.9037 | 40000 | 2.8535 |
| 2.7755 | 29.2989 | 42000 | 2.7650 |
| 2.5986 | 30.6941 | 44000 | 2.6769 |
| 2.5986 | 32.0893 | 46000 | 2.6227 |
| 2.4606 | 33.4845 | 48000 | 2.5682 |
| 2.4606 | 34.8797 | 50000 | 2.5149 |
| 2.3506 | 36.2749 | 52000 | 2.4691 |
| 2.3506 | 37.6700 | 54000 | 2.4395 |
| 2.2717 | 39.0652 | 56000 | 2.4192 |
| 2.2717 | 40.4604 | 58000 | 2.3797 |
| 2.2036 | 41.8556 | 60000 | 2.3556 |
| 2.2036 | 43.2508 | 62000 | 2.3366 |
| 2.1481 | 44.6460 | 64000 | 2.3093 |
| 2.1481 | 46.0412 | 66000 | 2.2859 |
| 2.1029 | 47.4363 | 68000 | 2.2736 |
| 2.1029 | 48.8315 | 70000 | 2.2488 |
| 2.0646 | 50.2267 | 72000 | 2.2464 |
| 2.0646 | 51.6219 | 74000 | 2.2329 |
| 2.0274 | 53.0171 | 76000 | 2.2133 |
| 2.0274 | 54.4123 | 78000 | 2.1916 |
| 1.999 | 55.8075 | 80000 | 2.1929 |
| 1.999 | 57.2027 | 82000 | 2.2003 |
| 1.9726 | 58.5978 | 84000 | 2.1797 |
| 1.9726 | 59.9930 | 86000 | 2.1607 |
| 1.9504 | 61.3882 | 88000 | 2.1396 |
| 1.9504 | 62.7834 | 90000 | 2.1378 |
| 1.9321 | 64.1786 | 92000 | 2.1362 |
| 1.9321 | 65.5738 | 94000 | 2.1394 |
| 1.9159 | 66.9690 | 96000 | 2.1435 |
| 1.9159 | 68.3641 | 98000 | 2.1298 |
| 1.9071 | 69.7593 | 100000 | 2.1528 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 14