metadata-cls-no-gov-8k-v2

This model is a fine-tuned version of vinai/phobert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3052
• Accuracy: 0.9447
• F1: 0.7927

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
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.5649	1.6260	200	0.2215	0.9455	0.7479
0.1634	3.2520	400	0.1869	0.9438	0.8204
0.1222	4.8780	600	0.2286	0.9370	0.7837
0.0808	6.5041	800	0.2174	0.9532	0.8263
0.0528	8.1301	1000	0.2440	0.9387	0.7862
0.046	9.7561	1200	0.2416	0.9472	0.8180
0.0329	11.3821	1400	0.2631	0.9464	0.7967
0.0271	13.0081	1600	0.2769	0.9481	0.8124
0.0179	14.6341	1800	0.2687	0.9506	0.8122
0.0185	16.2602	2000	0.2935	0.9438	0.7921
0.0153	17.8862	2200	0.2957	0.9455	0.7907
0.0146	19.5122	2400	0.3052	0.9447	0.7927

Framework versions

• Transformers 4.42.4
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1