mistral_7b_samantha_
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the samantha-data dataset. It achieves the following results on the evaluation set:
- Loss: 1.2177
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8256 | 0.01 | 10 | 1.6091 |
| 1.1803 | 0.02 | 20 | 1.3865 |
| 1.0851 | 0.02 | 30 | 1.3218 |
| 1.061 | 0.03 | 40 | 1.2639 |
| 0.9776 | 0.04 | 50 | 1.2600 |
| 1.0178 | 0.05 | 60 | 1.2484 |
| 0.9253 | 0.05 | 70 | 1.2435 |
| 1.0814 | 0.06 | 80 | 1.2363 |
| 0.9787 | 0.07 | 90 | 1.2307 |
| 1.0406 | 0.08 | 100 | 1.2177 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 1
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 adarsh12x/mistral_7b_samantha_
Base model
mistralai/Mistral-7B-v0.1
Finetuned
mistralai/Mistral-7B-Instruct-v0.1