model_centroid_concat_DEFI

This model is a fine-tuned version of vinai/phobert-base-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0907
• Accuracy: 0.9698
• F1: 0.9649

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2645
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.1419	150	0.5116	0.7814	0.6661
No log	0.2838	300	0.2511	0.9442	0.9336
No log	0.4257	450	0.1793	0.9557	0.9484
No log	0.5676	600	0.1471	0.9609	0.9546
No log	0.7096	750	0.1278	0.9635	0.9576
No log	0.8515	900	0.1189	0.9646	0.9587
No log	0.9934	1050	0.1148	0.9670	0.9615
0.2587	1.1353	1200	0.1093	0.9670	0.9619
0.2587	1.2772	1350	0.0956	0.9683	0.9635
0.2587	1.4191	1500	0.0946	0.9672	0.9620
0.2587	1.5610	1650	0.1004	0.9687	0.9636
0.2587	1.7029	1800	0.0953	0.9691	0.9642
0.2587	1.8448	1950	0.0898	0.9707	0.9662
0.2587	1.9868	2100	0.0925	0.9687	0.9640
0.0938	2.1287	2250	0.1444	0.9593	0.9539
0.0938	2.2706	2400	0.1101	0.9668	0.9620
0.0938	2.4125	2550	0.0925	0.9640	0.9590
0.0938	2.5544	2700	0.0907	0.9698	0.9649

Framework versions

• Transformers 5.12.1
• Pytorch 2.7.1+cu118
• Datasets 5.0.0
• Tokenizers 0.22.2