|
--- |
|
license: mit |
|
base_model: microsoft/phi-2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: phi_2_scotus |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# phi_2_scotus |
|
|
|
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0717 |
|
- Accuracy: 0.3557 |
|
- F1 Macro: 0.1359 |
|
- F1 Micro: 0.3557 |
|
|
|
## 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: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 2.5187 | 0.32 | 50 | 2.4656 | 0.2171 | 0.0941 | 0.2171 | |
|
| 2.2348 | 0.64 | 100 | 2.3156 | 0.2579 | 0.0980 | 0.2579 | |
|
| 2.2023 | 0.96 | 150 | 2.2223 | 0.2914 | 0.1103 | 0.2914 | |
|
| 2.1145 | 1.27 | 200 | 2.1800 | 0.3064 | 0.1139 | 0.3064 | |
|
| 1.993 | 1.59 | 250 | 2.1359 | 0.3179 | 0.1254 | 0.3179 | |
|
| 1.9609 | 1.91 | 300 | 2.1034 | 0.3457 | 0.1345 | 0.3457 | |
|
| 2.0137 | 2.23 | 350 | 2.1008 | 0.3564 | 0.1382 | 0.3564 | |
|
| 1.9418 | 2.55 | 400 | 2.0717 | 0.3557 | 0.1359 | 0.3557 | |
|
| 1.8887 | 2.87 | 450 | 2.0744 | 0.3636 | 0.1442 | 0.3636 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
