ChenWu98's picture
End of training
52f3a8f verified
metadata
license: mit
library_name: peft
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - ChenWu98/skills_metaphor_chat
base_model: HuggingFaceH4/zephyr-7b-beta
model-index:
  - name: skills_metaphor_chat-lora
    results: []

skills_metaphor_chat-lora

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the ChenWu98/skills_metaphor_chat dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2416

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: 2.0

Training results

Training Loss Epoch Step Validation Loss
1.5756 0.96 9 0.2956
0.2474 1.92 18 0.2416

Framework versions

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