|
--- |
|
library_name: peft |
|
license: mit |
|
base_model: unsloth/Phi-3.5-mini-instruct |
|
tags: |
|
- trl |
|
- sft |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Phi-3.5-mini-instruct-2024-10-28_15-54-04 |
|
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-3.5-mini-instruct-2024-10-28_15-54-04 |
|
|
|
This model is a fine-tuned version of [unsloth/Phi-3.5-mini-instruct](https://huggingface.co/unsloth/Phi-3.5-mini-instruct) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6209 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.6797 | 0.2492 | 148 | 0.6636 | |
|
| 0.6457 | 0.4983 | 296 | 0.6456 | |
|
| 0.6394 | 0.7475 | 444 | 0.6378 | |
|
| 0.6539 | 0.9966 | 592 | 0.6329 | |
|
| 0.6116 | 1.2458 | 740 | 0.6299 | |
|
| 0.617 | 1.4949 | 888 | 0.6284 | |
|
| 0.5936 | 1.7441 | 1036 | 0.6254 | |
|
| 0.5994 | 1.9933 | 1184 | 0.6231 | |
|
| 0.6277 | 2.2424 | 1332 | 0.6226 | |
|
| 0.6123 | 2.4916 | 1480 | 0.6217 | |
|
| 0.6583 | 2.7407 | 1628 | 0.6210 | |
|
| 0.5918 | 2.9899 | 1776 | 0.6209 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.13.2 |
|
- Transformers 4.45.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.20.1 |
