SciBERT_twowayloss_25K_bs64 – AI Model by bdpc | AlphaNeural AI

You can deploy this model and start earning money today!

bdpc/
SciBERT_twowayloss_25K_bs64

like

0

text-classification

generated_from_trainer

allenai/scibert_scivocab_uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

SciBERT_TwoWayLoss_25K_bs64

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: 5.7117
Accuracy: 0.7367
Precision: 0.0357
Recall: 0.9994
F1: 0.0689
Hamming: 0.2633

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: 192
eval_batch_size: 192
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: 25000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Hamming
6.7538	0.47	5000	6.4722	0.7208	0.0337	0.9987	0.0652	0.2792
6.1625	0.95	10000	6.0293	0.7311	0.0350	0.9991	0.0676	0.2689
5.7863	1.42	15000	5.8415	0.7362	0.0356	0.9992	0.0688	0.2638
5.6995	1.9	20000	5.7343	0.7366	0.0357	0.9994	0.0689	0.2634
5.4711	2.37	25000	5.7117	0.7367	0.0357	0.9994	0.0689	0.2633

Framework versions

Transformers 4.35.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.7.1
Tokenizers 0.14.1