Mistral-7B-0.3_auto
Collection
36 items • Updated
Mistral-7B_task-2_60-samples_config-1_full_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: 0.7818
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 |
|---|---|---|---|
| 1.1106 | 0.8696 | 5 | 1.0845 |
| 1.0327 | 1.9130 | 11 | 0.9768 |
| 0.9473 | 2.9565 | 17 | 0.9031 |
| 0.8032 | 4.0 | 23 | 0.8144 |
| 0.7285 | 4.8696 | 28 | 0.7916 |
| 0.6954 | 5.9130 | 34 | 0.7828 |
| 0.6329 | 6.9565 | 40 | 0.7818 |
| 0.6007 | 8.0 | 46 | 0.7876 |
| 0.5438 | 8.8696 | 51 | 0.8092 |
| 0.4987 | 9.9130 | 57 | 0.8370 |
| 0.4104 | 10.9565 | 63 | 0.8623 |
| 0.3387 | 12.0 | 69 | 0.9043 |
| 0.3103 | 12.8696 | 74 | 0.9516 |
| 0.2409 | 13.9130 | 80 | 1.0892 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for GaetanMichelet/Mistral-7B_task-2_60-samples_config-1_full_auto
Base model
mistralai/Mistral-7B-v0.3 Finetuned
mistralai/Mistral-7B-Instruct-v0.3