|
|
--- |
|
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct |
|
|
datasets: |
|
|
- GaetanMichelet/chat-60_ft_task-3_auto |
|
|
library_name: peft |
|
|
license: llama3.1 |
|
|
tags: |
|
|
- alignment-handbook |
|
|
- trl |
|
|
- sft |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: Llama-31-8B_task-3_60-samples_config-1_full_auto |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# Llama-31-8B_task-3_60-samples_config-1_full_auto |
|
|
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the GaetanMichelet/chat-60_ft_task-3_auto dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.1533 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-------:|:----:|:---------------:| |
|
|
| 1.6551 | 0.8696 | 5 | 1.6559 | |
|
|
| 1.627 | 1.9130 | 11 | 1.5675 | |
|
|
| 1.5266 | 2.9565 | 17 | 1.4605 | |
|
|
| 1.3591 | 4.0 | 23 | 1.3447 | |
|
|
| 1.2063 | 4.8696 | 28 | 1.2405 | |
|
|
| 1.1295 | 5.9130 | 34 | 1.1922 | |
|
|
| 1.0536 | 6.9565 | 40 | 1.1717 | |
|
|
| 1.0393 | 8.0 | 46 | 1.1585 | |
|
|
| 1.032 | 8.8696 | 51 | 1.1533 | |
|
|
| 1.0131 | 9.9130 | 57 | 1.1537 | |
|
|
| 0.9202 | 10.9565 | 63 | 1.1631 | |
|
|
| 0.8682 | 12.0 | 69 | 1.1720 | |
|
|
| 0.8608 | 12.8696 | 74 | 1.1812 | |
|
|
| 0.7371 | 13.9130 | 80 | 1.2313 | |
|
|
| 0.6739 | 14.9565 | 86 | 1.3223 | |
|
|
| 0.6784 | 16.0 | 92 | 1.2983 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.12.0 |
|
|
- Transformers 4.44.0 |
|
|
- Pytorch 2.1.2+cu121 |
|
|
- Datasets 2.20.0 |
|
|
- Tokenizers 0.19.1 |
