---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: feedback_model_e15
  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. -->

# feedback_model_e15

This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0258

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3.0

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 2.0708        | 0.0954 | 500   | 2.0258          |
| 1.7495        | 0.1908 | 1000  | 2.0441          |
| 1.4747        | 0.2862 | 1500  | 2.1073          |
| 1.1805        | 0.3815 | 2000  | 2.1233          |
| 0.963         | 0.4769 | 2500  | 2.2422          |
| 0.7523        | 0.5723 | 3000  | 2.3396          |
| 0.573         | 0.6677 | 3500  | 2.5663          |
| 0.4395        | 0.7631 | 4000  | 2.5910          |
| 0.3469        | 0.8585 | 4500  | 2.7149          |
| 0.2926        | 0.9538 | 5000  | 2.8265          |
| 0.2289        | 1.0492 | 5500  | 2.9349          |
| 0.1998        | 1.1446 | 6000  | 2.9571          |
| 0.1892        | 1.2400 | 6500  | 2.9969          |
| 0.1832        | 1.3354 | 7000  | 3.0586          |
| 0.1745        | 1.4308 | 7500  | 3.1055          |
| 0.164         | 1.5261 | 8000  | 3.1170          |
| 0.1546        | 1.6215 | 8500  | 3.1975          |
| 0.153         | 1.7169 | 9000  | 3.2386          |
| 0.147         | 1.8123 | 9500  | 3.2560          |
| 0.1385        | 1.9077 | 10000 | 3.2884          |
| 0.1344        | 2.0031 | 10500 | 3.3657          |
| 0.1071        | 2.0984 | 11000 | 3.4352          |
| 0.1027        | 2.1938 | 11500 | 3.4475          |
| 0.1012        | 2.2892 | 12000 | 3.4725          |
| 0.1015        | 2.3846 | 12500 | 3.5231          |
| 0.0997        | 2.4800 | 13000 | 3.5557          |
| 0.0953        | 2.5754 | 13500 | 3.5976          |
| 0.0932        | 2.6707 | 14000 | 3.6351          |
| 0.0904        | 2.7661 | 14500 | 3.6831          |
| 0.0869        | 2.8615 | 15000 | 3.7173          |
| 0.0856        | 2.9569 | 15500 | 3.7257          |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.3.0
- Datasets 2.14.4
- Tokenizers 0.20.3