metadata-cls-no-gov-8k-v3

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: 0.3064
• Accuracy: 0.9515
• F1: 0.8155

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
0.5565	1.6393	200	0.1942	0.9472	0.7911
0.1619	3.2787	400	0.1935	0.9404	0.7817
0.1275	4.9180	600	0.1903	0.9430	0.8019
0.0768	6.5574	800	0.2192	0.9489	0.8016
0.0579	8.1967	1000	0.2350	0.9455	0.7866
0.0477	9.8361	1200	0.2572	0.9498	0.7952
0.0358	11.4754	1400	0.2823	0.9413	0.7938
0.0277	13.1148	1600	0.2704	0.9464	0.8096
0.0233	14.7541	1800	0.2868	0.9481	0.7951
0.0139	16.3934	2000	0.3026	0.9438	0.7965
0.0125	18.0328	2200	0.3034	0.9489	0.8035
0.0085	19.6721	2400	0.3064	0.9515	0.8155

Framework versions

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