metadata
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: myBit-Llama2-jp-127M-2B4TLike
results: []
myBit-Llama2-jp-127M-2B4TLike
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8431
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: 12
- eval_batch_size: 12
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 96
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 750
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.9846 | 0.0587 | 500 | 5.1982 |
| 3.7747 | 0.1175 | 1000 | 4.4941 |
| 3.5109 | 0.1762 | 1500 | 4.0737 |
| 3.3568 | 0.2350 | 2000 | 3.8909 |
| 3.276 | 0.2937 | 2500 | 3.7147 |
| 3.2203 | 0.3525 | 3000 | 3.5468 |
| 3.1626 | 0.4112 | 3500 | 3.4098 |
| 3.1272 | 0.4700 | 4000 | 3.3188 |
| 3.0925 | 0.5287 | 4500 | 3.2339 |
| 3.0693 | 0.5874 | 5000 | 3.1539 |
| 3.0412 | 0.6462 | 5500 | 3.0721 |
| 2.9981 | 0.7049 | 6000 | 3.0009 |
| 2.9881 | 0.7637 | 6500 | 2.9514 |
| 2.9871 | 0.8224 | 7000 | 2.9162 |
| 2.9796 | 0.8812 | 7500 | 2.8879 |
| 2.9914 | 0.9399 | 8000 | 2.8849 |
| 2.9649 | 0.9987 | 8500 | 2.8431 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1