metadata
base_model: allenai/scibert_scivocab_uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: patentClassfication2
results: []
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: 0.6329
- Accuracy: 0.6513
- F1: 0.6099
- Precision: 0.6941
- Recall: 0.5438
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 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.635 | 1.0 | 4438 | 0.6329 | 0.6513 | 0.6099 | 0.6941 | 0.5438 |
| 0.5772 | 2.0 | 8876 | 0.6393 | 0.6721 | 0.6831 | 0.6624 | 0.7050 |
| 0.5355 | 3.0 | 13314 | 0.6558 | 0.6683 | 0.6768 | 0.6613 | 0.6931 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3