pd_cate

This model is a fine-tuned version of tangminhanh/pd_tg on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1397
• Accuracy: 0.5425
• F1: 0.6125
• Precision: 0.7033
• Recall: 0.5424

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: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	108	0.4029	0.2922	0.2948	0.2981	0.2915
No log	2.0	216	0.2405	0.0	0.0	0.0	0.0
No log	3.0	324	0.2119	0.0047	0.0092	1.0	0.0046
No log	4.0	432	0.1792	0.3516	0.4600	0.6681	0.3508
0.3163	5.0	540	0.1608	0.4179	0.5199	0.6904	0.4170
0.3163	6.0	648	0.1475	0.5099	0.5953	0.7083	0.5134
0.3163	7.0	756	0.1416	0.5180	0.6015	0.7170	0.5180
0.3163	8.0	864	0.1397	0.5425	0.6125	0.7033	0.5424

Framework versions

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