Hugging Face's logo

SiMajid
/
working

PEFT
TensorBoard
Safetensors
trl
reward-trainer
Generated from Trainer
Model card Files Metrics Community
working / README.md
SiMajid's picture
SiMajid
value-reward-model-opt-350m
cbc6b33 verified
preview code
|
raw
history blame contribute delete
No virus
1.1 kB
metadata
license: other
library_name: peft
tags:
  - trl
  - reward-trainer
  - generated_from_trainer
base_model: facebook/opt-350m
model-index:
  - name: facebook/opt-350m
    results: []

facebook/opt-350m

This model is a fine-tuned version of facebook/opt-350m on the None dataset.

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: 1.41e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 7

Training results

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.2
  • Pytorch 2.1.2
  • Datasets 2.19.2
  • Tokenizers 0.19.1