|
--- |
|
license: other |
|
base_model: microsoft/phi-1_5 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: phi-1_5-finetuned-model-15-10 |
|
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-1_5-finetuned-model-15-10 |
|
|
|
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.7222 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- training_steps: 1000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.7877 | 0.8 | 100 | 2.7425 | |
|
| 2.6025 | 1.6 | 200 | 2.6925 | |
|
| 2.5405 | 2.4 | 300 | 2.6806 | |
|
| 2.4735 | 3.2 | 400 | 2.6880 | |
|
| 2.4282 | 4.0 | 500 | 2.6807 | |
|
| 2.3467 | 4.8 | 600 | 2.6904 | |
|
| 2.2924 | 5.6 | 700 | 2.7146 | |
|
| 2.2779 | 6.4 | 800 | 2.7179 | |
|
| 2.249 | 7.2 | 900 | 2.7212 | |
|
| 2.2317 | 8.0 | 1000 | 2.7222 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
