metadata

base_model: allenai/scibert_scivocab_uncased
tags:
  - generated_from_trainer
datasets:
  - scicite
metrics:
  - accuracy
model-index:
  - name: Scicite_classification_model
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: scicite
          type: scicite
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8493449781659389

Scicite_classification_model

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

Loss: 1.2264
Accuracy: 0.8493

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: 16
eval_batch_size: 16
seed: 42
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
0.3988	1.0	513	0.4386	0.8428
0.2701	2.0	1026	0.5087	0.8504
0.1789	3.0	1539	0.6278	0.8526
0.1047	4.0	2052	0.8142	0.8548
0.0653	5.0	2565	1.0136	0.8461
0.0376	6.0	3078	1.1257	0.8417
0.0237	7.0	3591	1.1632	0.8341
0.0135	8.0	4104	1.2346	0.8493
0.0124	9.0	4617	1.2027	0.8483
0.0059	10.0	5130	1.2264	0.8493

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3