COPA_5_shot

This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6992
• F1: 0.514

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	2	0.6940	0.552
No log	2.0	4	0.6956	0.534
No log	3.0	6	0.6976	0.52
No log	4.0	8	0.6996	0.522
No log	5.0	10	0.7001	0.51
No log	6.0	12	0.6999	0.506
No log	7.0	14	0.7000	0.512
No log	8.0	16	0.6998	0.514
No log	9.0	18	0.6994	0.52
No log	10.0	20	0.6992	0.514

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3