bert_base_km_50_v1_cola

This model is a fine-tuned version of Hartunka/bert_base_km_50_v1 on the GLUE COLA dataset. It achieves the following results on the evaluation set:

• Loss: 0.6189
• Matthews Correlation: 0.0
• Accuracy: 0.6913

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: 5e-05
• train_batch_size: 256
• eval_batch_size: 256
• seed: 10
• 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation	Accuracy
0.617	1.0	34	0.6189	0.0	0.6913
0.5996	2.0	68	0.6232	0.0593	0.6932
0.5631	3.0	102	0.6375	-0.0024	0.6606
0.499	4.0	136	0.6979	0.0576	0.6711
0.4187	5.0	170	0.7206	0.1145	0.6558
0.3434	6.0	204	0.8469	0.0852	0.6424

Framework versions

• Transformers 4.50.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.21.1