scibert-lm-v2-finetuned-20

This model is a fine-tuned version of allenai/scibert_scivocab_cased on the conll2003 dataset. It achieves the following results on the evaluation set:

• Loss: 15.7952

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.0211	1.0	878	15.1971
0.0001	2.0	1756	16.8774
0.0001	3.0	2634	15.7952

Framework versions

• Transformers 4.21.1
• Pytorch 1.12.0+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1