---
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: eci-io/climategpt-7b
datasets:
- generator
model-index:
- name: climate-peft
  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. -->

# climate-peft

This model is a fine-tuned version of [eci-io/climategpt-7b](https://huggingface.co/eci-io/climategpt-7b) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2605

## 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: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 4

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.4821        | 1.0   | 18   | 1.3099          |
| 1.2442        | 2.0   | 36   | 1.2665          |
| 1.1787        | 3.0   | 54   | 1.2603          |
| 1.1356        | 4.0   | 72   | 1.2605          |


### Framework versions

- PEFT 0.7.2.dev0
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2