metadata
library_name: peft
license: llama3
base_model: meta-llama/Meta-Llama-3-8B
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: fine_tune_output
results: []
fine_tune_output
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.2902
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.061 | 7.2727 | 10 | 3.1055 |
| 3.6905 | 14.5455 | 20 | 2.6699 |
| 2.4714 | 21.8182 | 30 | 1.8229 |
| 0.9142 | 29.0909 | 40 | 1.8090 |
| 0.0188 | 36.3636 | 50 | 3.1047 |
| 0.0544 | 43.6364 | 60 | 3.8352 |
| 0.0316 | 50.9091 | 70 | 3.7350 |
| 0.0116 | 58.1818 | 80 | 3.7428 |
| 0.0005 | 65.4545 | 90 | 4.4955 |
| 0.0001 | 72.7273 | 100 | 4.2902 |
Framework versions
- PEFT 0.10.0
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3