metadata
license: apache-2.0
base_model: jonas-luehrs/bert-base-cased-MLM-chemistry
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-cased-MLM-chemistry-tokenCLS-BATTERY
results: []
bert-base-cased-MLM-chemistry-tokenCLS-BATTERY
This model is a fine-tuned version of jonas-luehrs/bert-base-cased-MLM-chemistry on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0704
- Precision: 0.7487
- Recall: 0.8681
- F1: 0.8040
- Accuracy: 0.9787
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 338 | 0.0852 | 0.6765 | 0.7699 | 0.7202 | 0.9719 |
| 0.1476 | 2.0 | 676 | 0.0677 | 0.7154 | 0.8252 | 0.7664 | 0.9773 |
| 0.0524 | 3.0 | 1014 | 0.0704 | 0.7487 | 0.8681 | 0.8040 | 0.9787 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3