wiki_w_42
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.4165
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: 256
- eval_batch_size: 256
- seed: 42
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.0611 | 1.0 | 400 | 6.1997 |
| 5.9588 | 2.0 | 800 | 5.8515 |
| 5.7334 | 3.0 | 1200 | 5.7185 |
| 5.6015 | 4.0 | 1600 | 5.6205 |
| 5.4947 | 5.0 | 2000 | 5.5516 |
| 5.4027 | 6.0 | 2400 | 5.4965 |
| 5.3214 | 7.0 | 2800 | 5.4555 |
| 5.2473 | 8.0 | 3200 | 5.4289 |
| 5.1798 | 9.0 | 3600 | 5.4064 |
| 5.1159 | 10.0 | 4000 | 5.3948 |
| 5.0562 | 11.0 | 4400 | 5.3875 |
| 4.9996 | 12.0 | 4800 | 5.3859 |
| 4.9462 | 13.0 | 5200 | 5.3856 |
| 4.8953 | 14.0 | 5600 | 5.3899 |
| 4.8497 | 15.0 | 6000 | 5.3935 |
| 4.8101 | 16.0 | 6400 | 5.3986 |
| 4.7757 | 17.0 | 6800 | 5.4051 |
| 4.7464 | 18.0 | 7200 | 5.4086 |
| 4.7222 | 19.0 | 7600 | 5.4147 |
| 4.7037 | 20.0 | 8000 | 5.4165 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0