results

This model is a fine-tuned version of dung6903/results on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.3588
• Accuracy: 0.5149
• F1: 0.5145
• Precision: 0.5180
• Recall: 0.5149

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• 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	142	2.3684	0.4612	0.4524	0.4814	0.4612
No log	2.0	284	2.3173	0.5149	0.5117	0.5226	0.5149
No log	3.0	426	2.3588	0.5149	0.5145	0.5180	0.5149
0.2514	4.0	568	2.5204	0.4950	0.4963	0.5052	0.4950
0.2514	5.0	710	2.8100	0.5050	0.5076	0.5255	0.5050
0.2514	6.0	852	2.9408	0.5089	0.5056	0.5262	0.5089
0.2514	7.0	994	3.0119	0.5129	0.5104	0.5245	0.5129
0.1376	8.0	1136	3.0821	0.4652	0.4594	0.4763	0.4652
0.1376	9.0	1278	3.2156	0.4911	0.4871	0.5028	0.4911
0.1376	10.0	1420	3.2285	0.4970	0.4969	0.5024	0.4970
0.0934	11.0	1562	3.1558	0.4970	0.4966	0.5030	0.4970
0.0934	12.0	1704	3.1808	0.5089	0.5078	0.5184	0.5089

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0