theharmonylab/implicit-motives-achievement-roberta-large

final

This model is a fine-tuned version of roberta-large on the GLUE SCHONE_ACH dataset. It achieves the following results on the evaluation set:

• Loss: 0.0846
• Roc Auc: 0.9888

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: 1e-05
• train_batch_size: 128
• eval_batch_size: 256
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Roc Auc
0.185	0.9985	332	0.1574	0.9583
0.1607	2.0	665	0.1283	0.9730
0.1357	2.9985	997	0.1071	0.9818
0.1214	4.0	1330	0.0978	0.9870
0.1011	4.9925	1660	0.0846	0.9888

Framework versions

• Transformers 4.44.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1