ft-usermanual
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: 2.9086
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 |
|---|---|---|---|
| 6.1167 | 0.67 | 1 | 3.8820 |
| 3.004 | 2.0 | 3 | 3.6082 |
| 5.5234 | 2.67 | 4 | 3.4297 |
| 2.5899 | 4.0 | 6 | 3.1544 |
| 4.7867 | 4.67 | 7 | 3.0576 |
| 2.3257 | 6.0 | 9 | 2.9346 |
| 3.0372 | 6.67 | 10 | 2.9086 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1
Model tree for Farisya/ft-usermanual
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ