nizar-sayad's picture
Duplicate from lionelsh/opt-350m-HorrorCreepyPasta
bcda569
|
raw
history blame
1.42 kB
metadata
license: other
tags:
  - generated_from_trainer
model-index:
  - name: opt-350m-HorrorCreepyPasta
    results: []
duplicated_from: lionelsh/opt-350m-HorrorCreepyPasta

opt-350m-HorrorCreepyPasta

This model is a fine-tuned version of facebook/opt-350m on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.2370

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: 2e-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: 3.0

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 250 3.1713
2.8738 2.0 500 3.2044
2.8738 3.0 750 3.2370

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.11.0
  • Tokenizers 0.13.3