czert_lr2e-05_bs4_train150

This model is a fine-tuned version of UWB-AIR/Czert-B-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2054
• Precision: 0.9023
• Recall: 0.9073
• F1: 0.9048
• Accuracy: 0.9463

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: 2e-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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	38	0.4712	0.7379	0.6987	0.7178	0.8556
No log	2.0	76	0.2761	0.8550	0.8455	0.8502	0.9201
No log	3.0	114	0.2196	0.8790	0.8841	0.8816	0.9353
No log	4.0	152	0.2077	0.8855	0.8889	0.8872	0.9404
No log	5.0	190	0.1977	0.8970	0.9000	0.8985	0.9447
No log	6.0	228	0.1957	0.9087	0.8938	0.9012	0.9468
No log	7.0	266	0.1952	0.9129	0.9054	0.9091	0.9514
No log	8.0	304	0.2117	0.9196	0.9005	0.9100	0.9500
No log	9.0	342	0.2235	0.9108	0.9073	0.9090	0.9508
No log	10.0	380	0.2222	0.9143	0.9068	0.9105	0.9514

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1