metadata
tags:
- generated_from_trainer
model-index:
- name: myBit-Llama2-jp-127M-test-12
results: []
myBit-Llama2-jp-127M-test-12
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 6.3033
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: 0.00024
- train_batch_size: 96
- eval_batch_size: 96
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: polynomial
- lr_scheduler_warmup_steps: 50
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 10.0642 | 0.07 | 20 | 9.4022 |
| 9.0973 | 0.15 | 40 | 8.6900 |
| 8.3576 | 0.22 | 60 | 7.9690 |
| 7.7499 | 0.29 | 80 | 7.4678 |
| 7.3343 | 0.36 | 100 | 7.1266 |
| 7.0503 | 0.44 | 120 | 6.9132 |
| 6.9035 | 0.51 | 140 | 6.8141 |
| 6.8471 | 0.58 | 160 | 6.7611 |
| 6.8217 | 0.65 | 180 | 6.7305 |
| 6.7783 | 0.73 | 200 | 6.6345 |
| 6.6382 | 0.8 | 220 | 6.4734 |
| 6.5006 | 0.87 | 240 | 6.3855 |
| 6.4282 | 0.95 | 260 | 6.3033 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2