Configuration Parsing
Warning:
In adapter_config.json: "peft.base_model_name_or_path" must be a string
recogs_mistral_ft
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.7522
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 |
|---|---|---|---|
| 7.1516 | 0.96 | 6 | 6.8988 |
| 6.5638 | 1.92 | 12 | 6.3491 |
| 6.0302 | 2.88 | 18 | 5.7975 |
| 4.7136 | 4.0 | 25 | 5.3152 |
| 5.0991 | 4.96 | 31 | 5.0892 |
| 4.7721 | 5.92 | 37 | 4.9895 |
| 4.6138 | 6.88 | 43 | 4.8591 |
| 3.7808 | 8.0 | 50 | 4.7853 |
| 4.3257 | 8.96 | 56 | 4.7611 |
| 3.6388 | 9.6 | 60 | 4.7522 |
Framework versions
- PEFT 0.9.0
- Transformers 4.37.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for justross50/recogs_mistral_ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ