lc_cate

This model is a fine-tuned version of microsoft/deberta-v3-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3148
• Accuracy: 0.7535
• F1: 0.7694
• Precision: 0.7812
• Recall: 0.7579

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: 64
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	32	0.2704	0.7415	0.7640	0.7874	0.7421
No log	2.0	64	0.2764	0.7275	0.7497	0.7726	0.7282
No log	3.0	96	0.2802	0.7495	0.7675	0.7859	0.75
No log	4.0	128	0.2915	0.7435	0.7614	0.7796	0.7440
No log	5.0	160	0.3044	0.7214	0.7472	0.7717	0.7242
No log	6.0	192	0.2972	0.7595	0.7737	0.7881	0.7599
No log	7.0	224	0.3061	0.7375	0.7626	0.7735	0.7520
No log	8.0	256	0.3049	0.7615	0.7759	0.7862	0.7659
No log	9.0	288	0.3073	0.7475	0.7657	0.7798	0.7520
No log	10.0	320	0.3067	0.7515	0.7705	0.7856	0.7560
No log	11.0	352	0.3187	0.7455	0.7647	0.7822	0.7480
No log	12.0	384	0.3148	0.7535	0.7694	0.7812	0.7579

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1