XPFaculty-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: 1.2488
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: 2e-05
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 12
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|
| 10.017 | 1.0 | 25 | 2.1432 |
| 7.9205 | 2.0 | 50 | 1.7228 |
| 6.0142 | 3.0 | 75 | 1.3397 |
| 5.1375 | 4.0 | 100 | 1.2745 |
| 4.8759 | 5.0 | 125 | 1.2605 |
| 4.6752 | 6.0 | 150 | 1.2525 |
| 4.5039 | 7.0 | 175 | 1.2480 |
| 4.3596 | 8.0 | 200 | 1.2496 |
| 4.2584 | 9.0 | 225 | 1.2488 |
| 4.2064 | 10.0 | 250 | 1.2488 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 14
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for bala3040/XPFaculty-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ