|
--- |
|
base_model: microsoft/Phi-3.5-mini-instruct |
|
library_name: peft |
|
license: mit |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: Phi-3.5-MultiCap-mt-5 |
|
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-MultiCap-mt-5 |
|
|
|
This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6935 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.9814 | 0.5109 | 50 | 0.9569 | |
|
| 0.7431 | 1.0217 | 100 | 0.7821 | |
|
| 0.7487 | 1.5326 | 150 | 0.7389 | |
|
| 0.7355 | 2.0434 | 200 | 0.7197 | |
|
| 0.7317 | 2.5543 | 250 | 0.7090 | |
|
| 0.7308 | 3.0651 | 300 | 0.7025 | |
|
| 0.6926 | 3.5760 | 350 | 0.6978 | |
|
| 0.684 | 4.0868 | 400 | 0.6948 | |
|
| 0.6965 | 4.5977 | 450 | 0.6935 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
