---
license: apache-2.0
base_model: JackFram/llama-160m
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: llama-160m-mnli
  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. -->

# llama-160m-mnli

This model is a fine-tuned version of [JackFram/llama-160m](https://huggingface.co/JackFram/llama-160m) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0860
- Accuracy: 0.4032

## 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: 16
- eval_batch_size: 32
- 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
- num_epochs: 4

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 1.1021        | 1.0   | 3068  | 1.0996          | 0.3860   |
| 1.0902        | 2.0   | 6136  | 1.0914          | 0.3947   |
| 1.0871        | 3.0   | 9204  | 1.0878          | 0.3980   |
| 1.0871        | 4.0   | 12272 | 1.0860          | 0.4032   |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.18.0
- Tokenizers 0.13.3