---
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-ref-hybrid
  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-ref-hybrid

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: 0.5712

## 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: 2

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.1489        | 0.1354 | 30   | 1.1589          |
| 0.7977        | 0.2707 | 60   | 0.7714          |
| 0.671         | 0.4061 | 90   | 0.6689          |
| 0.6645        | 0.5415 | 120  | 0.6312          |
| 0.613         | 0.6768 | 150  | 0.6102          |
| 0.6147        | 0.8122 | 180  | 0.5977          |
| 0.6391        | 0.9475 | 210  | 0.5899          |
| 0.5892        | 1.0829 | 240  | 0.5844          |
| 0.6056        | 1.2183 | 270  | 0.5803          |
| 0.5662        | 1.3536 | 300  | 0.5770          |
| 0.574         | 1.4890 | 330  | 0.5747          |
| 0.5985        | 1.6244 | 360  | 0.5730          |
| 0.578         | 1.7597 | 390  | 0.5719          |
| 0.5541        | 1.8951 | 420  | 0.5712          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.0+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1