metadata
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: phi_2_amazon
results: []
phi_2_amazon
This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6451
- Accuracy: 0.5659
- F1 Macro: 0.4655
- F1 Micro: 0.5659
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: 5e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
|---|---|---|---|---|---|---|
| 3.2062 | 0.13 | 50 | 3.1866 | 0.0922 | 0.0634 | 0.0922 |
| 2.9492 | 0.26 | 100 | 2.9088 | 0.1528 | 0.1081 | 0.1528 |
| 2.6945 | 0.39 | 150 | 2.6944 | 0.2286 | 0.1693 | 0.2286 |
| 2.457 | 0.53 | 200 | 2.4137 | 0.3373 | 0.2529 | 0.3373 |
| 2.0566 | 0.66 | 250 | 2.0552 | 0.4499 | 0.3541 | 0.4499 |
| 1.7723 | 0.79 | 300 | 1.7765 | 0.5264 | 0.4225 | 0.5264 |
| 1.7695 | 0.92 | 350 | 1.6451 | 0.5659 | 0.4655 | 0.5659 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2