---
license: other
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: google/gemma-2b-it
datasets:
- generator
model-index:
- name: logs
  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. -->

# logs

This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6382

## 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: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.7393        | 0.45  | 112  | 0.6998          |
| 0.6937        | 0.9   | 224  | 0.6506          |
| 0.6017        | 1.35  | 336  | 0.6331          |
| 0.6384        | 1.8   | 448  | 0.6193          |
| 0.5111        | 2.25  | 560  | 0.6176          |
| 0.523         | 2.7   | 672  | 0.6123          |
| 0.4642        | 3.15  | 784  | 0.6265          |
| 0.4888        | 3.6   | 896  | 0.6219          |
| 0.4547        | 4.05  | 1008 | 0.6330          |
| 0.4343        | 4.5   | 1120 | 0.6379          |
| 0.4664        | 4.96  | 1232 | 0.6382          |


### Framework versions

- PEFT 0.10.1.dev0
- Transformers 4.38.2
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2