muhtasham/bert-small-finetuned-eoir_privacy-longer20

bert_uncased_L-4_H-512_A-8-finetuned-eoir_privacy-longer-finetuned-eoir_privacy-longer20

This model was trained from scratch on the eoir_privacy dataset. It achieves the following results on the evaluation set:

• Loss: 0.1994
• Accuracy: 0.9469
• F1: 0.8783

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	63	0.2134	0.9412	0.8581
No log	2.0	126	0.2083	0.9405	0.8610
No log	3.0	189	0.2108	0.9448	0.8702
No log	4.0	252	0.2281	0.9397	0.8537
No log	5.0	315	0.2034	0.9469	0.8783
No log	6.0	378	0.2133	0.9419	0.8629
No log	7.0	441	0.1971	0.9440	0.8746
0.0525	8.0	504	0.2013	0.9455	0.8778
0.0525	9.0	567	0.1987	0.9469	0.8787
0.0525	10.0	630	0.1994	0.9469	0.8783

Framework versions

• Transformers 4.21.1
• Pytorch 1.12.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1