metadata
base_model: allenai/scibert_scivocab_uncased
tags:
- generated_from_trainer
datasets:
- scicite
metrics:
- accuracy
model-index:
- name: cite_classification
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: 0.9170305676855895
cite_classification
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: 0.6533
- Accuracy: 0.9170
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: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.4909 | 1.0 | 719 | 0.2266 | 0.9181 |
0.3215 | 2.0 | 1438 | 0.3707 | 0.9181 |
0.0825 | 3.0 | 2157 | 0.5539 | 0.9159 |
0.0539 | 4.0 | 2876 | 0.5117 | 0.9159 |
0.0245 | 5.0 | 3595 | 0.5720 | 0.9094 |
0.0209 | 6.0 | 4314 | 0.5710 | 0.9170 |
0.0104 | 7.0 | 5033 | 0.6443 | 0.9116 |
0.0059 | 8.0 | 5752 | 0.6533 | 0.9170 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1