metadata
base_model: mistralai/Mistral-7B-Instruct-v0.3
datasets:
- GaetanMichelet/chat-60_ft_task-3
- GaetanMichelet/chat-120_ft_task-3
library_name: peft
license: apache-2.0
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Mistral-7B_task-3_120-samples_config-2
results: []
Mistral-7B_task-3_120-samples_config-2
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the GaetanMichelet/chat-60_ft_task-3 and the GaetanMichelet/chat-120_ft_task-3 datasets. It achieves the following results on the evaluation set:
- Loss: 0.3947
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 |
|---|---|---|---|
| 3.4696 | 0.9091 | 5 | 2.7714 |
| 1.5154 | 2.0 | 11 | 0.9233 |
| 0.4441 | 2.9091 | 16 | 0.5486 |
| 0.4453 | 4.0 | 22 | 0.4419 |
| 0.2943 | 4.9091 | 27 | 0.3947 |
| 0.209 | 6.0 | 33 | 0.3950 |
| 0.167 | 6.9091 | 38 | 0.4694 |
| 0.0931 | 8.0 | 44 | 0.5510 |
| 0.0271 | 8.9091 | 49 | 0.6278 |
| 0.0121 | 10.0 | 55 | 0.7051 |
| 0.0101 | 10.9091 | 60 | 0.7721 |
| 0.0546 | 12.0 | 66 | 0.7857 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1