lilt_robeczech_lr2e-05_bs4_train75

This model is a fine-tuned version of xkaska02/lilt-robeczech-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0695
• Precision: 0.5083
• Recall: 0.4047
• F1: 0.4506
• Accuracy: 0.5993

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.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	1.4687	0.9425	0.0417	0.0798	0.5545
No log	2.0	76	1.2490	0.5628	0.2140	0.3101	0.5819
No log	3.0	114	1.1380	0.5069	0.3569	0.4189	0.5880
No log	4.0	152	1.1092	0.5238	0.3528	0.4216	0.5972
No log	5.0	190	1.0809	0.5115	0.3721	0.4308	0.5960
No log	6.0	228	1.0695	0.5083	0.4047	0.4506	0.5993
No log	7.0	266	1.0940	0.5211	0.3386	0.4105	0.5982
No log	8.0	304	1.0792	0.5312	0.3640	0.4320	0.6043
No log	9.0	342	1.0899	0.5133	0.4016	0.4507	0.6010

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1