pd_subcate

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

• Loss: 0.1790
• Accuracy: 0.4074
• F1: 0.4502
• Precision: 0.4817
• Recall: 0.4227

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: 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	42	0.1567	0.4058	0.4567	0.4946	0.4242
No log	2.0	84	0.1583	0.3997	0.4503	0.4901	0.4165
No log	3.0	126	0.1599	0.4058	0.4613	0.5055	0.4242
No log	4.0	168	0.1636	0.4150	0.4596	0.4973	0.4273
No log	5.0	210	0.1670	0.3936	0.4474	0.4874	0.4135
No log	6.0	252	0.1682	0.4043	0.4507	0.4867	0.4196
No log	7.0	294	0.1739	0.4089	0.4594	0.4888	0.4334
No log	8.0	336	0.1790	0.4074	0.4502	0.4817	0.4227

Framework versions

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