Configuration Parsing
Warning:
In adapter_config.json: "peft.base_model_name_or_path" must be a string
Mistral-7B-Instruct-v0.2_finetuned_40rows
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: 0.9862
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 |
|---|---|---|---|
| 2.1723 | 0.67 | 1 | 1.4223 |
| 1.0351 | 2.0 | 3 | 1.2149 |
| 1.7693 | 2.67 | 4 | 1.1417 |
| 0.7955 | 4.0 | 6 | 1.0425 |
| 1.4664 | 4.67 | 7 | 1.0168 |
| 0.6954 | 6.0 | 9 | 0.9917 |
| 0.8878 | 6.67 | 10 | 0.9862 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for mbona/Mistral-7B-Instruct-v0.2_finetuned_40rows
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ