czert_lr2e-05_bs4_train287_max_len256

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: 0.1677
• Precision: 0.9165
• Recall: 0.9328
• F1: 0.9246
• Accuracy: 0.9561

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: 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	Precision	Recall	F1	Accuracy
No log	1.0	72	0.2932	0.8413	0.8522	0.8467	0.9163
No log	2.0	144	0.1967	0.8936	0.8885	0.8910	0.9391
No log	3.0	216	0.1875	0.9168	0.8885	0.9024	0.9458
No log	4.0	288	0.1647	0.9079	0.9087	0.9083	0.9504
No log	5.0	360	0.1658	0.9298	0.9078	0.9186	0.9544
No log	6.0	432	0.1602	0.9258	0.9276	0.9267	0.9590
0.1926	7.0	504	0.1642	0.9209	0.9223	0.9216	0.9565
0.1926	8.0	576	0.1697	0.9298	0.9271	0.9284	0.9602
0.1926	9.0	648	0.1679	0.9287	0.9247	0.9267	0.9590

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+cu124
• Datasets 3.3.1
• Tokenizers 0.20.0