|
--- |
|
license: mit |
|
base_model: microsoft/Phi-3-mini-128k-instruct |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: CodePhi-3-mini-128k-instruct-St |
|
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. --> |
|
|
|
# CodePhi-3-mini-128k-instruct-St |
|
|
|
This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8475 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 50 |
|
- training_steps: 450 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.7314 | 0.1111 | 50 | 1.0823 | |
|
| 0.6329 | 0.2222 | 100 | 0.9492 | |
|
| 0.4915 | 0.3333 | 150 | 0.8924 | |
|
| 0.4442 | 0.4444 | 200 | 0.8674 | |
|
| 0.4184 | 0.5556 | 250 | 0.8540 | |
|
| 0.4269 | 0.6667 | 300 | 0.8491 | |
|
| 0.3887 | 0.7778 | 350 | 0.8483 | |
|
| 0.3898 | 0.8889 | 400 | 0.8480 | |
|
| 0.3992 | 1.0 | 450 | 0.8475 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
