metadata
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
- GaetanMichelet/chat-60_ft_task-2
- GaetanMichelet/chat-120_ft_task-2
- GaetanMichelet/chat-180_ft_task-2
library_name: peft
license: llama3.1
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Llama-31-8B_task-2_180-samples_config-1_full
results: []
Llama-31-8B_task-2_180-samples_config-1_full
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the GaetanMichelet/chat-60_ft_task-2, the GaetanMichelet/chat-120_ft_task-2 and the GaetanMichelet/chat-180_ft_task-2 datasets. It achieves the following results on the evaluation set:
- Loss: 1.0345
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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.504 | 1.0 | 17 | 1.5036 |
| 1.3344 | 2.0 | 34 | 1.3101 |
| 1.0895 | 3.0 | 51 | 1.1146 |
| 0.9755 | 4.0 | 68 | 1.0741 |
| 0.9637 | 5.0 | 85 | 1.0524 |
| 0.9215 | 6.0 | 102 | 1.0349 |
| 0.8984 | 7.0 | 119 | 1.0345 |
| 0.7983 | 8.0 | 136 | 1.0459 |
| 0.711 | 9.0 | 153 | 1.0750 |
| 0.6725 | 10.0 | 170 | 1.1344 |
| 0.629 | 11.0 | 187 | 1.1630 |
| 0.4573 | 12.0 | 204 | 1.2680 |
| 0.4754 | 13.0 | 221 | 1.2757 |
| 0.4236 | 14.0 | 238 | 1.3371 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1