patentClassfication2

This model is a fine-tuned version of allenai/scibert_scivocab_uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6121
• Accuracy: 0.6746
• F1: 0.6765

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: 2.54241e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 41
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• lr_scheduler_warmup_steps: 24
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.6169	1.0	4438	0.6919	0.6121	0.6906
0.5475	2.0	8876	0.6121	0.6746	0.6765
0.4521	3.0	13314	0.7167	0.6706	0.6827

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.0
• Datasets 2.14.4
• Tokenizers 0.13.3