ERC_SUMMARY_phi3_peft
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on the ArunaMak/ERC_summary dataset. It achieves the following results on the evaluation set:
- Loss: 1.3262
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4928 | 1.0 | 21 | 1.4815 |
| 1.3604 | 2.0 | 42 | 1.3828 |
| 1.3606 | 3.0 | 63 | 1.3482 |
| 1.3651 | 4.0 | 84 | 1.3323 |
| 1.3101 | 5.0 | 105 | 1.3271 |
| 1.2846 | 6.0 | 126 | 1.3262 |
Framework versions
- PEFT 0.12.0
- Transformers 4.43.0.dev0
- Pytorch 2.3.1+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for ArunaMak/phi3_fine_tuned
Base model
microsoft/Phi-3-mini-4k-instruct