metadata
tags:
- generated_from_trainer
model-index:
- name: myBit-Llama2-jp-127M-test-21
results: []
myBit-Llama2-jp-127M-test-21
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4730
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: 0.0024
- 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: 500
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.8768 | 0.07 | 200 | 4.8775 |
| 4.6046 | 0.15 | 400 | 4.3967 |
| 4.3044 | 0.22 | 600 | 4.1899 |
| 4.1225 | 0.29 | 800 | 4.0563 |
| 4.0084 | 0.36 | 1000 | 3.9713 |
| 3.9223 | 0.44 | 1200 | 3.9033 |
| 3.8622 | 0.51 | 1400 | 3.8249 |
| 3.7846 | 0.58 | 1600 | 3.7565 |
| 3.7062 | 0.66 | 1800 | 3.6873 |
| 3.6472 | 0.73 | 2000 | 3.6323 |
| 3.5972 | 0.8 | 2200 | 3.5773 |
| 3.539 | 0.87 | 2400 | 3.5280 |
| 3.4795 | 0.95 | 2600 | 3.4730 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- mybitnet 0.3.0