AstroAI-ft
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.1-GPTQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9873
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: Use 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.5655 | 1.0 | 7 | 2.0467 |
| 6.4835 | 2.0 | 14 | 1.5206 |
| 4.7547 | 3.0 | 21 | 1.1481 |
| 3.705 | 4.0 | 28 | 0.9980 |
| 3.7889 | 4.32 | 30 | 0.9873 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 4
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 gomesadhikari1/AstroAI-ft
Base model
mistralai/Mistral-7B-v0.1
Finetuned
mistralai/Mistral-7B-Instruct-v0.1
Quantized
TheBloke/Mistral-7B-Instruct-v0.1-GPTQ