83968dfb-1a36-4e0e-a54e-02723ea99cb1
This model is a fine-tuned version of elyza/Llama-3-ELYZA-JP-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2885
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: 0.00021
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0001 | 1 | 2.1965 |
| 1.6753 | 0.0069 | 50 | 1.5474 |
| 1.5619 | 0.0138 | 100 | 1.4791 |
| 1.5991 | 0.0207 | 150 | 1.4622 |
| 1.4688 | 0.0276 | 200 | 1.4420 |
| 1.6049 | 0.0345 | 250 | 1.4331 |
| 1.4969 | 0.0414 | 300 | 1.3716 |
| 1.4744 | 0.0483 | 350 | 1.3327 |
| 1.4701 | 0.0552 | 400 | 1.3042 |
| 1.4609 | 0.0621 | 450 | 1.2899 |
| 1.4306 | 0.0690 | 500 | 1.2885 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for lesso10/83968dfb-1a36-4e0e-a54e-02723ea99cb1
Base model
elyza/Llama-3-ELYZA-JP-8B