YT_Results
This model is a fine-tuned version of PrunaAI/mistralai-Mistral-7B-Instruct-v0.2-bnb-4bit-smashed on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4569
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 |
|---|---|---|---|
| 0.5678 | 1.0 | 1 | 2.5424 |
| 0.5678 | 2.0 | 2 | 2.5371 |
| 0.5533 | 3.0 | 3 | 2.5239 |
| 0.5226 | 4.0 | 4 | 2.5092 |
| 0.4941 | 5.0 | 5 | 2.4952 |
| 0.47 | 6.0 | 6 | 2.4823 |
| 0.4509 | 7.0 | 7 | 2.4720 |
| 0.4354 | 8.0 | 8 | 2.4639 |
| 0.424 | 9.0 | 9 | 2.4592 |
| 0.4162 | 10.0 | 10 | 2.4569 |
Framework versions
- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Downloads last month
- 4
Model tree for shouray/YT_Results
Base model
mistralai/Mistral-7B-Instruct-v0.2