COPA_Bert_Base_Uncased_Finetuned

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: 0.5670
• F1: 0.7384

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	63	0.6878	0.5954
No log	2.0	126	0.6608	0.6680
No log	3.0	189	0.6181	0.6887
No log	4.0	252	0.5839	0.7219
No log	5.0	315	0.5627	0.7219
No log	6.0	378	0.5537	0.7280
No log	7.0	441	0.5613	0.7319
0.5359	8.0	504	0.5636	0.7335
0.5359	9.0	567	0.5676	0.7326
0.5359	10.0	630	0.5670	0.7384

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1