en_clm_child_42_new
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.6177
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: 42
- 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 | 1.3952 | 2000 | 6.7895 |
| 6.707 | 2.7904 | 4000 | 5.2118 |
| 6.707 | 4.1856 | 6000 | 4.7848 |
| 4.6024 | 5.5807 | 8000 | 4.5102 |
| 4.6024 | 6.9759 | 10000 | 4.3292 |
| 4.1329 | 8.3711 | 12000 | 4.1850 |
| 4.1329 | 9.7663 | 14000 | 4.0620 |
| 3.856 | 11.1615 | 16000 | 3.9639 |
| 3.856 | 12.5567 | 18000 | 3.8726 |
| 3.6554 | 13.9519 | 20000 | 3.7965 |
| 3.6554 | 15.3471 | 22000 | 3.7222 |
| 3.4925 | 16.7422 | 24000 | 3.6700 |
| 3.4925 | 18.1374 | 26000 | 3.6203 |
| 3.3587 | 19.5326 | 28000 | 3.5773 |
| 3.3587 | 20.9278 | 30000 | 3.5367 |
| 3.2471 | 22.3230 | 32000 | 3.5141 |
| 3.2471 | 23.7182 | 34000 | 3.4847 |
| 3.1538 | 25.1134 | 36000 | 3.4676 |
| 3.1538 | 26.5085 | 38000 | 3.4517 |
| 3.0734 | 27.9037 | 40000 | 3.4406 |
| 3.0734 | 29.2989 | 42000 | 3.4351 |
| 2.9926 | 30.6941 | 44000 | 3.4226 |
| 2.9926 | 32.0893 | 46000 | 3.4355 |
| 2.9142 | 33.4845 | 48000 | 3.4269 |
| 2.9142 | 34.8797 | 50000 | 3.4246 |
| 2.8473 | 36.2749 | 52000 | 3.4378 |
| 2.8473 | 37.6700 | 54000 | 3.4406 |
| 2.7884 | 39.0652 | 56000 | 3.4472 |
| 2.7884 | 40.4604 | 58000 | 3.4580 |
| 2.7313 | 41.8556 | 60000 | 3.4623 |
| 2.7313 | 43.2508 | 62000 | 3.4835 |
| 2.68 | 44.6460 | 64000 | 3.4884 |
| 2.68 | 46.0412 | 66000 | 3.4953 |
| 2.6375 | 47.4363 | 68000 | 3.5087 |
| 2.6375 | 48.8315 | 70000 | 3.5093 |
| 2.597 | 50.2267 | 72000 | 3.5292 |
| 2.597 | 51.6219 | 74000 | 3.5357 |
| 2.5619 | 53.0171 | 76000 | 3.5439 |
| 2.5619 | 54.4123 | 78000 | 3.5563 |
| 2.5235 | 55.8075 | 80000 | 3.5586 |
| 2.5235 | 57.2027 | 82000 | 3.5730 |
| 2.4944 | 58.5978 | 84000 | 3.5791 |
| 2.4944 | 59.9930 | 86000 | 3.5846 |
| 2.4666 | 61.3882 | 88000 | 3.5987 |
| 2.4666 | 62.7834 | 90000 | 3.5998 |
| 2.4429 | 64.1786 | 92000 | 3.6077 |
| 2.4429 | 65.5738 | 94000 | 3.6094 |
| 2.4205 | 66.9690 | 96000 | 3.6123 |
| 2.4205 | 68.3641 | 98000 | 3.6164 |
| 2.4021 | 69.7593 | 100000 | 3.6177 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1