metadata

library_name: transformers
language:
  - en
license: mit
base_model: JeremiahZ/roberta-base-cola
tags:
  - generated_from_trainer
datasets:
  - glue
model-index:
  - name: roberta-base-relu-cola
    results: []

roberta-base-relu-cola

This model is a fine-tuned version of JeremiahZ/roberta-base-cola on the GLUE COLA dataset. It achieves the following results on the evaluation set:

eval_loss: 1.2395
eval_model_preparation_time: 0.0024
eval_matthews_correlation: 0.5652
eval_runtime: 9.4256
eval_samples_per_second: 110.656
eval_steps_per_second: 27.69
step: 0

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: 5e-05
train_batch_size: 8
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3.0
mixed_precision_training: Native AMP

Framework versions

Transformers 4.50.0.dev0
Pytorch 2.6.0+cu124
Datasets 3.3.2
Tokenizers 0.21.0