|
--- |
|
license: mit |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: microsoft/phi-1_5 |
|
model-index: |
|
- name: phi-1_5-finetuned-addition-v2 |
|
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-addition-v2 |
|
|
|
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.9705 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 4.4643 | 0.03 | 100 | 4.1741 | |
|
| 4.1499 | 0.06 | 200 | 4.1183 | |
|
| 4.1148 | 0.09 | 300 | 4.1006 | |
|
| 4.0741 | 0.12 | 400 | 4.0455 | |
|
| 4.0357 | 0.15 | 500 | 4.0199 | |
|
| 4.0217 | 0.18 | 600 | 3.9980 | |
|
| 3.9901 | 0.21 | 700 | 3.9866 | |
|
| 3.9824 | 0.24 | 800 | 3.9775 | |
|
| 3.9837 | 0.27 | 900 | 3.9710 | |
|
| 3.9651 | 0.3 | 1000 | 3.9705 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
