metadata
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
- GaetanMichelet/chat-60_ft_task-1
- GaetanMichelet/chat-120_ft_task-1
- GaetanMichelet/chat-180_ft_task-1
library_name: peft
license: llama3.1
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Llama-31-8B_task-1_180-samples_config-2
results: []
Llama-31-8B_task-1_180-samples_config-2
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the GaetanMichelet/chat-60_ft_task-1, the GaetanMichelet/chat-120_ft_task-1 and the GaetanMichelet/chat-180_ft_task-1 datasets. It achieves the following results on the evaluation set:
- Loss: 1.2262
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: 16
- total_train_batch_size: 16
- 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 |
|---|---|---|---|
| 2.0099 | 0.9412 | 8 | 1.9311 |
| 1.5434 | 2.0 | 17 | 1.5801 |
| 1.4423 | 2.9412 | 25 | 1.4170 |
| 1.2232 | 4.0 | 34 | 1.2908 |
| 1.0943 | 4.9412 | 42 | 1.2430 |
| 0.9751 | 6.0 | 51 | 1.2262 |
| 0.739 | 6.9412 | 59 | 1.3161 |
| 0.4877 | 8.0 | 68 | 1.5278 |
| 0.2813 | 8.9412 | 76 | 1.8161 |
| 0.1579 | 10.0 | 85 | 2.2197 |
| 0.0849 | 10.9412 | 93 | 2.5830 |
| 0.0474 | 12.0 | 102 | 2.6015 |
| 0.0374 | 12.9412 | 110 | 2.7205 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1