t5-gpt_par_bert_large_uncased_finetuned_v2

This model is a fine-tuned version of bert-large-uncased on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.0019
• eval_f1_micro: 0.9984
• eval_roc_auc_micro: 1.0000
• eval_accuracy: 0.9967
• eval_precision_micro: 0.9990
• eval_recall_micro: 0.9978
• eval_f1_macro: 0.9985
• eval_roc_auc_macro: 1.0000
• eval_accuracy1: 0.9967
• eval_precision_macro: 0.9992
• eval_recall_macro: 0.9978
• eval_pr_auc_micro: 1.0000
• eval_pr_auc_macro: 1.0000
• eval_runtime: 57.9074
• eval_samples_per_second: 41.929
• eval_steps_per_second: 5.25
• epoch: 3.4250
• step: 4158

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: 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: 5

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0