metadata
library_name: peft
license: llama3
base_model: unsloth/llama-3-8b
tags:
- axolotl
- generated_from_trainer
model-index:
- name: edaab7e5-3c78-476c-9252-265181f36c0f
results: []
edaab7e5-3c78-476c-9252-265181f36c0f
This model is a fine-tuned version of unsloth/llama-3-8b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4548
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: 0.000201
- 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 | 0.0002 | 1 | 1.8474 |
| 1.7866 | 0.0118 | 50 | 1.7584 |
| 1.8859 | 0.0235 | 100 | 1.7752 |
| 1.8239 | 0.0353 | 150 | 1.7706 |
| 1.7062 | 0.0470 | 200 | 1.6970 |
| 1.7411 | 0.0588 | 250 | 1.6723 |
| 1.6048 | 0.0705 | 300 | 1.5543 |
| 1.6202 | 0.0823 | 350 | 1.5112 |
| 1.7322 | 0.0941 | 400 | 1.4810 |
| 1.5949 | 0.1058 | 450 | 1.4706 |
| 1.5305 | 0.1176 | 500 | 1.4548 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1