---
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: meta-llama/Llama-2-7b-hf
model-index:
- name: Llama2_AAID_new_mixed_train_final
  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. -->

# Llama2_AAID_new_mixed_train_final

This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the AAID_new_mixed dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5070

## 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: 0.0003
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.2211        | 0.0109 | 10   | 0.5508          |
| 0.446         | 0.0219 | 20   | 0.5180          |
| 0.3889        | 0.0328 | 30   | 0.5139          |
| 0.3757        | 0.0438 | 40   | 0.5758          |
| 0.3551        | 0.0547 | 50   | 0.5461          |
| 0.3351        | 0.0656 | 60   | 0.5407          |
| 0.3269        | 0.0766 | 70   | 0.5335          |
| 0.3231        | 0.0875 | 80   | 0.5121          |
| 0.3324        | 0.0984 | 90   | 0.5196          |
| 0.3039        | 0.1094 | 100  | 0.5252          |
| 0.3083        | 0.1203 | 110  | 0.5070          |
| 0.3034        | 0.1313 | 120  | 0.5375          |
| 0.3061        | 0.1422 | 130  | 0.5346          |
| 0.3021        | 0.1531 | 140  | 0.5112          |
| 0.3067        | 0.1641 | 150  | 0.5191          |
| 0.2958        | 0.1750 | 160  | 0.5278          |
| 0.3002        | 0.1859 | 170  | 0.5170          |
| 0.2896        | 0.1969 | 180  | 0.5086          |
| 0.2989        | 0.2078 | 190  | 0.5300          |
| 0.3012        | 0.2188 | 200  | 0.5137          |
| 0.2802        | 0.2297 | 210  | 0.5159          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1