lbl-file16-fold4

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3406
• Accuracy: 0.5528
• F1: 0.5455
• Precision: 0.5517
• Recall: 0.5528
• Accuracy Label Label 0: 0.7686
• Accuracy Label Label 1: 0.5824
• Accuracy Label Label 2: 0.5063
• Accuracy Label Label 3: 0.7469
• Accuracy Label Label 4: 0.6877
• Accuracy Label Label 5: 0.4268
• Accuracy Label Label 6: 0.6691
• Accuracy Label Label 7: 0.1962
• Accuracy Label Label 8: 0.5622
• Accuracy Label Label 9: 0.3843

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-06
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Accuracy Label Label 0	Accuracy Label Label 1	Accuracy Label Label 2	Accuracy Label Label 3	Accuracy Label Label 4	Accuracy Label Label 5	Accuracy Label Label 6	Accuracy Label Label 7	Accuracy Label Label 8	Accuracy Label Label 9
No log	0.16	25	1.3593	0.546	0.5364	0.5424	0.546	0.7686	0.6044	0.4810	0.7469	0.6838	0.4228	0.6617	0.1615	0.5408	0.3884
No log	0.32	50	1.3547	0.5508	0.5414	0.5486	0.5508	0.7851	0.5934	0.4979	0.7469	0.6838	0.4228	0.6766	0.1654	0.5365	0.4008
No log	0.48	75	1.3491	0.5516	0.5424	0.5482	0.5516	0.7934	0.5934	0.5021	0.7469	0.6877	0.4268	0.6691	0.1769	0.5408	0.3802
No log	0.64	100	1.3446	0.5524	0.5438	0.5500	0.5524	0.7769	0.5824	0.5063	0.7469	0.6877	0.4268	0.6691	0.1808	0.5579	0.3926
No log	0.8	125	1.3417	0.5524	0.5448	0.5509	0.5524	0.7727	0.5824	0.5063	0.7469	0.6877	0.4268	0.6691	0.1885	0.5622	0.3843
No log	0.96	150	1.3406	0.5528	0.5455	0.5517	0.5528	0.7686	0.5824	0.5063	0.7469	0.6877	0.4268	0.6691	0.1962	0.5622	0.3843

Framework versions

• Transformers 4.30.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.13.3