czert_lr2e-05_bs4_train287_max_len256_2layers

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: 0.1713
• Precision: 0.9107
• Recall: 0.9212
• F1: 0.9159
• Accuracy: 0.9513

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	0.5136	0.6578	0.6470	0.6524	0.8319
No log	2.0	144	0.2634	0.8669	0.8682	0.8676	0.9286
No log	3.0	216	0.2205	0.9024	0.8749	0.8885	0.9389
No log	4.0	288	0.1857	0.9059	0.8976	0.9018	0.9464
No log	5.0	360	0.1767	0.9111	0.9058	0.9085	0.9508
No log	6.0	432	0.1698	0.9216	0.9198	0.9207	0.9552
0.2996	7.0	504	0.1674	0.9266	0.9198	0.9232	0.9571

Framework versions

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