czert_lr2e-05_bs4_train287_cl_size2

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: 0.1715
• Precision: 0.9099
• Recall: 0.9222
• F1: 0.9160
• Accuracy: 0.9529

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	72	0.4681	0.7251	0.7489	0.7368	0.8673
No log	2.0	144	0.2397	0.8668	0.8860	0.8763	0.9332
No log	3.0	216	0.2036	0.9032	0.8875	0.8953	0.9429
No log	4.0	288	0.1787	0.9071	0.9150	0.9111	0.9508
No log	5.0	360	0.1585	0.9253	0.9213	0.9233	0.9586
No log	6.0	432	0.1683	0.9176	0.9194	0.9185	0.9567
0.2732	7.0	504	0.1641	0.9310	0.9189	0.9249	0.9588
0.2732	8.0	576	0.1746	0.9256	0.9256	0.9256	0.9596

Framework versions

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