GaetanMichelet's picture
End of training
a8afeb9 verified
---
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
- GaetanMichelet/chat-60_ft_task-3
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
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
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 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4035
## 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 |
|:-------------:|:-------:|:----:|:---------------:|
| 2.4269 | 0.8696 | 5 | 2.3330 |
| 1.8916 | 1.9130 | 11 | 1.4686 |
| 0.8252 | 2.9565 | 17 | 0.6677 |
| 0.4209 | 4.0 | 23 | 0.4862 |
| 0.332 | 4.8696 | 28 | 0.4469 |
| 0.2549 | 5.9130 | 34 | 0.4227 |
| 0.2452 | 6.9565 | 40 | 0.4035 |
| 0.3307 | 8.0 | 46 | 0.4229 |
| 0.2278 | 8.8696 | 51 | 0.4286 |
| 0.1552 | 9.9130 | 57 | 0.5084 |
| 0.0554 | 10.9565 | 63 | 0.5310 |
| 0.0343 | 12.0 | 69 | 0.7842 |
| 0.0154 | 12.8696 | 74 | 0.7040 |
| 0.0048 | 13.9130 | 80 | 0.7500 |
### Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1