---
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: microsoft/Phi-3-mini-4k-instruct
model-index:
- name: phi3mini_4k_i_RE_QA_alpha16_r_16
  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. -->

# phi3mini_4k_i_RE_QA_alpha16_r_16

This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4520

## 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.8239        | 0.1187 | 100  | 0.5562          |
| 0.5517        | 0.2374 | 200  | 0.4838          |
| 0.522         | 0.3561 | 300  | 0.4682          |
| 0.5106        | 0.4748 | 400  | 0.4602          |
| 0.5055        | 0.5935 | 500  | 0.4563          |
| 0.4995        | 0.7122 | 600  | 0.4534          |
| 0.4966        | 0.8309 | 700  | 0.4525          |
| 0.4977        | 0.9496 | 800  | 0.4520          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.2.1
- Datasets 2.19.2
- Tokenizers 0.19.1