|
|
--- |
|
|
license: mit |
|
|
base_model: microsoft/phi-2 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: phi_2_ledgar |
|
|
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_ledgar |
|
|
|
|
|
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: 0.6120 |
|
|
- Accuracy: 0.826 |
|
|
- F1 Macro: 0.7355 |
|
|
- F1 Micro: 0.826 |
|
|
|
|
|
## 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: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 2 |
|
|
- total_train_batch_size: 64 |
|
|
- total_eval_batch_size: 64 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
|
| 3.6034 | 0.11 | 100 | 3.2114 | 0.337 | 0.1236 | 0.337 | |
|
|
| 2.2678 | 0.21 | 200 | 1.9837 | 0.5623 | 0.3331 | 0.5623 | |
|
|
| 1.4927 | 0.32 | 300 | 1.3369 | 0.6712 | 0.4884 | 0.6712 | |
|
|
| 1.1518 | 0.43 | 400 | 1.0526 | 0.7243 | 0.5613 | 0.7243 | |
|
|
| 1.1041 | 0.53 | 500 | 0.9305 | 0.7521 | 0.6206 | 0.7521 | |
|
|
| 1.0144 | 0.64 | 600 | 0.9068 | 0.7574 | 0.6294 | 0.7574 | |
|
|
| 0.9892 | 0.75 | 700 | 0.8712 | 0.7669 | 0.6430 | 0.7669 | |
|
|
| 0.9972 | 0.85 | 800 | 0.8591 | 0.7675 | 0.6369 | 0.7675 | |
|
|
| 0.8439 | 0.96 | 900 | 0.7895 | 0.7848 | 0.6835 | 0.7848 | |
|
|
| 0.7409 | 1.07 | 1000 | 0.7614 | 0.7944 | 0.6809 | 0.7944 | |
|
|
| 0.7627 | 1.17 | 1100 | 0.7539 | 0.7946 | 0.6810 | 0.7946 | |
|
|
| 0.8065 | 1.28 | 1200 | 0.7289 | 0.8008 | 0.6945 | 0.8008 | |
|
|
| 0.7359 | 1.39 | 1300 | 0.7254 | 0.8034 | 0.6976 | 0.8034 | |
|
|
| 0.6525 | 1.49 | 1400 | 0.7073 | 0.8065 | 0.7050 | 0.8065 | |
|
|
| 0.7359 | 1.6 | 1500 | 0.7206 | 0.8033 | 0.6949 | 0.8033 | |
|
|
| 0.7291 | 1.71 | 1600 | 0.6924 | 0.8089 | 0.7066 | 0.8089 | |
|
|
| 0.7072 | 1.81 | 1700 | 0.6764 | 0.8102 | 0.7070 | 0.8102 | |
|
|
| 0.6688 | 1.92 | 1800 | 0.6546 | 0.814 | 0.7128 | 0.814 | |
|
|
| 0.6253 | 2.03 | 1900 | 0.6506 | 0.8158 | 0.7059 | 0.8158 | |
|
|
| 0.6044 | 2.13 | 2000 | 0.6603 | 0.8155 | 0.7165 | 0.8155 | |
|
|
| 0.6414 | 2.24 | 2100 | 0.6435 | 0.8138 | 0.7185 | 0.8138 | |
|
|
| 0.6115 | 2.35 | 2200 | 0.6368 | 0.8216 | 0.7280 | 0.8216 | |
|
|
| 0.6331 | 2.45 | 2300 | 0.6273 | 0.8208 | 0.7251 | 0.8208 | |
|
|
| 0.608 | 2.56 | 2400 | 0.6252 | 0.8232 | 0.7286 | 0.8232 | |
|
|
| 0.5879 | 2.67 | 2500 | 0.6172 | 0.8241 | 0.7308 | 0.8241 | |
|
|
| 0.6056 | 2.77 | 2600 | 0.6157 | 0.8257 | 0.7346 | 0.8257 | |
|
|
| 0.5711 | 2.88 | 2700 | 0.6129 | 0.8253 | 0.7341 | 0.8253 | |
|
|
| 0.5802 | 2.99 | 2800 | 0.6120 | 0.826 | 0.7355 | 0.826 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.39.0.dev0 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
