metadata
library_name: transformers
language:
- en
license: mit
base_model: JeremiahZ/roberta-base-rte
tags:
- generated_from_trainer
datasets:
- glue
model-index:
- name: roberta-base-relu-rte
results: []
roberta-base-relu-rte
This model is a fine-tuned version of JeremiahZ/roberta-base-rte on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.7095
- eval_model_preparation_time: 0.0023
- eval_accuracy: 0.5957
- eval_runtime: 2.7715
- eval_samples_per_second: 99.945
- eval_steps_per_second: 25.257
- step: 0
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-5, 2e-5, 3e-5
- train_batch_size: 16
- eval_batch_size: 4
- seed: 42
- num_epochs: 10
The best model was selected based on the highest accuracy, which is the key evaluation metric for this task.
Framework versions
- Transformers 4.50.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0