CNEC_2_0_Supertypes_robeczech-base

This model is a fine-tuned version of ufal/robeczech-base on the cnec dataset. It achieves the following results on the evaluation set:

• Loss: 0.2853
• Precision: 0.8543
• Recall: 0.9013
• F1: 0.8772
• Accuracy: 0.9623

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.065	17.78	4000	0.1785	0.8466	0.8893	0.8674	0.9608
0.0242	35.56	8000	0.2351	0.8534	0.8922	0.8724	0.9616
0.012	53.33	12000	0.2634	0.8537	0.8988	0.8757	0.9615
0.0075	71.11	16000	0.2730	0.8606	0.9050	0.8822	0.9641
0.0049	88.89	20000	0.2853	0.8543	0.9013	0.8772	0.9623

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0