DarshanDeshpande's picture
gemma_2b_oasst1_reward_model
738115b verified
metadata
license: other
library_name: peft
tags:
  - trl
  - reward-trainer
  - generated_from_trainer
base_model: google/gemma-2b
metrics:
  - accuracy
model-index:
  - name: gemma_2b_oasst1_reward_model
    results: []

gemma_2b_oasst1_reward_model

This model is a fine-tuned version of google/gemma-2b on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4345
  • Accuracy: 0.8051

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: 0.0005
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5106 1.0 100 0.5843 0.7203
0.4299 2.0 200 0.4418 0.7825
0.5035 2.99 300 0.4345 0.8051

Framework versions

  • PEFT 0.9.0
  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2