|
--- |
|
license: mit |
|
base_model: microsoft/phi-2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: V0328MP6 |
|
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. --> |
|
|
|
# V0328MP6 |
|
|
|
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: 2.0997 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine_with_restarts |
|
- lr_scheduler_warmup_steps: 20 |
|
- num_epochs: 1 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 5.1459 | 0.09 | 10 | 2.5412 | |
|
| 5.447 | 0.18 | 20 | 2.4861 | |
|
| 4.4839 | 0.27 | 30 | 2.3961 | |
|
| 4.023 | 0.36 | 40 | 2.3023 | |
|
| 3.4985 | 0.45 | 50 | 2.2335 | |
|
| 3.1396 | 0.54 | 60 | 2.1850 | |
|
| 2.8106 | 0.63 | 70 | 2.1461 | |
|
| 2.5426 | 0.73 | 80 | 2.1253 | |
|
| 2.6132 | 0.82 | 90 | 2.1091 | |
|
| 2.5482 | 0.91 | 100 | 2.1025 | |
|
| 2.5561 | 1.0 | 110 | 2.0997 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
