---
library_name: peft
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- ChenWu98/skills_metaphor_chat
base_model: merged_ckpts/skills_red_herring_chat-lora
model-index:
- name: skills_red_herring_chat-then-skills_metaphor_chat-lora
  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. -->

# skills_red_herring_chat-then-skills_metaphor_chat-lora

This model is a fine-tuned version of [merged_ckpts/skills_red_herring_chat-lora](https://huggingface.co/merged_ckpts/skills_red_herring_chat-lora) on the ChenWu98/skills_metaphor_chat dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2034

## 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: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.4913        | 0.96  | 9    | 0.2320          |
| 0.2051        | 1.92  | 18   | 0.2080          |
| 0.1665        | 2.99  | 28   | 0.2038          |
| 0.1519        | 3.84  | 36   | 0.2034          |


### Framework versions

- PEFT 0.7.1
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1