bert_base_km_100_v1_cola

This model is a fine-tuned version of Hartunka/bert_base_km_100_v1 on the GLUE COLA dataset. It achieves the following results on the evaluation set:

• Loss: 0.6237
• 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
0.6167	1.0	34	0.6237	0.0	0.6913
0.5951	2.0	68	0.6253	0.0126	0.6894
0.5382	3.0	102	0.6292	0.1000	0.6711
0.456	4.0	136	0.6964	0.1330	0.6491
0.3717	5.0	170	0.7490	0.0652	0.6299
0.298	6.0	204	0.9227	0.0768	0.6424

Framework versions

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