metadata
tags:
- generated_from_trainer
model-index:
- name: model
results: []
model
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0360
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 500
- training_steps: 0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.1667 | 0.07 | 2000 | 3.1054 |
| 1.8298 | 0.14 | 4000 | 1.7209 |
| 1.4726 | 0.22 | 6000 | 1.4237 |
| 1.3446 | 0.29 | 8000 | 1.2875 |
| 1.2647 | 0.36 | 10000 | 1.2120 |
| 1.2023 | 0.43 | 12000 | 1.1621 |
| 1.185 | 0.51 | 14000 | 1.1240 |
| 1.1308 | 0.58 | 16000 | 1.0957 |
| 1.1057 | 0.65 | 18000 | 1.0736 |
| 1.0894 | 0.72 | 20000 | 1.0555 |
| 1.087 | 0.8 | 22000 | 1.0439 |
| 1.0829 | 0.87 | 24000 | 1.0372 |
| 1.0566 | 0.94 | 26000 | 1.0360 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1