metadata
base_model: mistralai/Mistral-7B-Instruct-v0.3
datasets:
- GaetanMichelet/chat-60_ft_task-1
- GaetanMichelet/chat-120_ft_task-1
library_name: peft
license: apache-2.0
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Mistral-7B_task-1_120-samples_config-1_full
results: []
Mistral-7B_task-1_120-samples_config-1_full
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the GaetanMichelet/chat-60_ft_task-1 and the GaetanMichelet/chat-120_ft_task-1 datasets. It achieves the following results on the evaluation set:
- Loss: 0.9151
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 |
|---|---|---|---|
| 1.9008 | 1.0 | 11 | 1.7749 |
| 1.2368 | 2.0 | 22 | 1.2046 |
| 0.9597 | 3.0 | 33 | 0.9767 |
| 0.8364 | 4.0 | 44 | 0.9268 |
| 0.6751 | 5.0 | 55 | 0.9151 |
| 0.492 | 6.0 | 66 | 0.9614 |
| 0.3136 | 7.0 | 77 | 1.0794 |
| 0.2439 | 8.0 | 88 | 1.2906 |
| 0.1635 | 9.0 | 99 | 1.2869 |
| 0.1396 | 10.0 | 110 | 1.3567 |
| 0.116 | 11.0 | 121 | 1.3482 |
| 0.104 | 12.0 | 132 | 1.4277 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1