|
--- |
|
base_model: mistralai/Mistral-7B-Instruct-v0.3 |
|
datasets: |
|
- GaetanMichelet/chat-60_ft_task-2 |
|
- GaetanMichelet/chat-120_ft_task-2 |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- alignment-handbook |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: Mistral-7B_task-2_120-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. --> |
|
|
|
# Mistral-7B_task-2_120-samples_config-1 |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the GaetanMichelet/chat-60_ft_task-2 and the GaetanMichelet/chat-120_ft_task-2 datasets. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5406 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.8123 | 1.0 | 11 | 0.7915 | |
|
| 0.5536 | 2.0 | 22 | 0.6211 | |
|
| 0.5094 | 3.0 | 33 | 0.5669 | |
|
| 0.4475 | 4.0 | 44 | 0.5406 | |
|
| 0.392 | 5.0 | 55 | 0.5456 | |
|
| 0.25 | 6.0 | 66 | 0.6155 | |
|
| 0.1335 | 7.0 | 77 | 0.7172 | |
|
| 0.0743 | 8.0 | 88 | 0.7815 | |
|
| 0.0326 | 9.0 | 99 | 0.8637 | |
|
| 0.0175 | 10.0 | 110 | 0.9439 | |
|
| 0.0075 | 11.0 | 121 | 0.9338 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
