Mistral-7b-ft
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8778
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.595 | 0.92 | 3 | 3.9725 |
| 4.0628 | 1.85 | 6 | 3.4618 |
| 3.49 | 2.77 | 9 | 3.0052 |
| 2.2748 | 4.0 | 13 | 2.5837 |
| 2.7034 | 4.92 | 16 | 2.3309 |
| 2.373 | 5.85 | 19 | 2.1371 |
| 2.1514 | 6.77 | 22 | 1.9951 |
| 1.5195 | 8.0 | 26 | 1.9252 |
| 1.9838 | 8.92 | 29 | 1.8884 |
| 1.3783 | 9.23 | 30 | 1.8778 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Downloads last month
- 0
Model tree for Gssmc/Mistral-7b-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ