91710cf4-025e-40bb-8bde-2a68a7e95e09
This model is a fine-tuned version of unsloth/mistral-7b-instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5434
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: 0.000203
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0019 | 1 | 5.3737 |
| 7.4664 | 0.0935 | 50 | 5.3272 |
| 7.5024 | 0.1869 | 100 | 4.8616 |
| 7.1463 | 0.2804 | 150 | 4.3751 |
| 7.2262 | 0.3738 | 200 | 3.9955 |
| 7.022 | 0.4673 | 250 | 3.9549 |
| 6.9159 | 0.5607 | 300 | 3.8860 |
| 6.7775 | 0.6542 | 350 | 3.1104 |
| 7.234 | 0.7477 | 400 | 3.7883 |
| 7.4275 | 0.8411 | 450 | 2.5710 |
| 7.1904 | 0.9346 | 500 | 2.5434 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 0
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for lesso03/91710cf4-025e-40bb-8bde-2a68a7e95e09
Base model
unsloth/mistral-7b-instruct-v0.2