metadata
base_model: mistralai/Mistral-7B-Instruct-v0.3
datasets:
- GaetanMichelet/chat-60_ft_task-2_auto
library_name: peft
license: apache-2.0
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Mistral-7B_task-2_60-samples_config-1_auto
results: []
Mistral-7B_task-2_60-samples_config-1_auto
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the GaetanMichelet/chat-60_ft_task-2_auto dataset. It achieves the following results on the evaluation set:
- Loss: 0.4861
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 |
|---|---|---|---|
| 0.7334 | 0.8696 | 5 | 0.7063 |
| 0.6319 | 1.9130 | 11 | 0.5730 |
| 0.5266 | 2.9565 | 17 | 0.5148 |
| 0.4086 | 4.0 | 23 | 0.4890 |
| 0.307 | 4.8696 | 28 | 0.4861 |
| 0.2061 | 5.9130 | 34 | 0.5480 |
| 0.1025 | 6.9565 | 40 | 0.6544 |
| 0.0474 | 8.0 | 46 | 0.7597 |
| 0.0255 | 8.8696 | 51 | 0.7984 |
| 0.0223 | 9.9130 | 57 | 0.7589 |
| 0.0134 | 10.9565 | 63 | 0.8149 |
| 0.0068 | 12.0 | 69 | 0.8507 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1