---
library_name: peft
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
- llama-factory
- transformers
pipeline_tag: text-generation
model-index:
- name: train_sst2_101112_1760638079
  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. -->

# train_sst2_101112_1760638079

This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the sst2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0610
- Num Input Tokens Seen: 67752208

## 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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 101112
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20

### Training results

| Training Loss | Epoch | Step   | Validation Loss | Input Tokens Seen |
|:-------------:|:-----:|:------:|:---------------:|:-----------------:|
| 0.1208        | 1.0   | 15154  | 0.0875          | 3387376           |
| 0.0672        | 2.0   | 30308  | 0.0699          | 6776272           |
| 0.0929        | 3.0   | 45462  | 0.0665          | 10162816          |
| 0.0283        | 4.0   | 60616  | 0.0630          | 13553408          |
| 0.0132        | 5.0   | 75770  | 0.0642          | 16938528          |
| 0.0159        | 6.0   | 90924  | 0.0614          | 20326208          |
| 0.0907        | 7.0   | 106078 | 0.0610          | 23713072          |
| 0.0447        | 8.0   | 121232 | 0.0615          | 27100096          |
| 0.0372        | 9.0   | 136386 | 0.0612          | 30487024          |
| 0.0827        | 10.0  | 151540 | 0.0627          | 33871648          |
| 0.0091        | 11.0  | 166694 | 0.0625          | 37260608          |
| 0.0048        | 12.0  | 181848 | 0.0631          | 40646320          |
| 0.0093        | 13.0  | 197002 | 0.0629          | 44035072          |
| 0.0825        | 14.0  | 212156 | 0.0618          | 47423936          |
| 0.159         | 15.0  | 227310 | 0.0639          | 50810512          |
| 0.0099        | 16.0  | 242464 | 0.0650          | 54201824          |
| 0.0856        | 17.0  | 257618 | 0.0646          | 57588768          |
| 0.0038        | 18.0  | 272772 | 0.0649          | 60979040          |
| 0.0768        | 19.0  | 287926 | 0.0646          | 64364064          |
| 0.1332        | 20.0  | 303080 | 0.0646          | 67752208          |


### Framework versions

- PEFT 0.17.1
- Transformers 4.51.3
- Pytorch 2.9.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4