baseline_BERT_50K_steps

This model is a fine-tuned version of bert-base-uncased on the arxiv_dataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.0192
• Accuracy: 0.9937
• Precision: 0.7968
• Recall: 0.4734
• F1: 0.5940
• Hamming: 0.0063

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: 6
• eval_batch_size: 6
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 50000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Hamming
0.0343	0.03	10000	0.0315	0.9912	0.7679	0.1370	0.2326	0.0088
0.0244	0.06	20000	0.0234	0.9925	0.7813	0.3262	0.4602	0.0075
0.0219	0.09	30000	0.0210	0.9931	0.7572	0.4320	0.5502	0.0069
0.0204	0.12	40000	0.0197	0.9935	0.7738	0.4711	0.5857	0.0065
0.0197	0.15	50000	0.0192	0.9937	0.7968	0.4734	0.5940	0.0063

Framework versions

• Transformers 4.37.2
• Pytorch 1.12.1+cu113
• Datasets 2.16.1
• Tokenizers 0.15.1