wikipedia
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7920
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: 5e-05
- 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: 100000
- training_steps: 400000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.0346 | 1.0160 | 2000 | 7.2841 |
| 7.2752 | 2.0320 | 4000 | 7.2837 |
| 7.2619 | 3.0480 | 6000 | 7.2576 |
| 7.2048 | 4.0640 | 8000 | 7.1034 |
| 6.9764 | 5.0800 | 10000 | 6.7982 |
| 6.4942 | 6.0960 | 12000 | 6.2032 |
| 5.9863 | 7.1120 | 14000 | 5.8090 |
| 5.6312 | 8.1280 | 16000 | 5.5046 |
| 5.3378 | 9.1440 | 18000 | 5.2551 |
| 5.0847 | 10.1600 | 20000 | 5.0341 |
| 4.8615 | 11.1760 | 22000 | 4.8711 |
| 4.6664 | 12.1920 | 24000 | 4.6536 |
| 4.496 | 13.2080 | 26000 | 4.5433 |
| 4.3435 | 14.2240 | 28000 | 4.3970 |
| 4.2129 | 15.2400 | 30000 | 4.2968 |
| 4.1048 | 16.2560 | 32000 | 4.2358 |
| 4.019 | 17.2720 | 34000 | 4.1681 |
| 3.9376 | 18.2880 | 36000 | 4.1167 |
| 3.8758 | 19.3040 | 38000 | 4.0411 |
| 3.8237 | 20.3200 | 40000 | 4.0252 |
| 3.782 | 21.3360 | 42000 | 4.0171 |
| 3.7474 | 22.3520 | 44000 | 3.9434 |
| 3.7152 | 23.3680 | 46000 | 3.9434 |
| 3.6944 | 24.3840 | 48000 | 3.9306 |
| 3.6642 | 25.4001 | 50000 | 3.9128 |
| 3.6556 | 26.4161 | 52000 | 3.8504 |
| 3.636 | 27.4321 | 54000 | 3.8669 |
| 3.6241 | 28.4481 | 56000 | 3.8512 |
| 3.6109 | 29.4641 | 58000 | 3.8412 |
| 3.5963 | 30.4801 | 60000 | 3.8352 |
| 3.5972 | 31.4961 | 62000 | 3.8418 |
| 3.5854 | 32.5121 | 64000 | 3.7850 |
| 3.5805 | 33.5281 | 66000 | 3.8185 |
| 3.5712 | 34.5441 | 68000 | 3.8206 |
| 3.5718 | 35.5601 | 70000 | 3.7920 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 7