metadata
license: apache-2.0
base_model: jonas-luehrs/bert-base-uncased-MLP-scirepeval-chemistry-LARGE
tags:
- generated_from_trainer
metrics:
- f1
- precision
- recall
- accuracy
model-index:
- name: >-
bert-base-uncased-MLP-scirepeval-chemistry-LARGE-textCLS-RHEOLOGY-20230913-3
results: []
datasets:
- bluesky333/chemical_language_understanding_benchmark
language:
- en
bert-base-uncased-MLP-scirepeval-chemistry-LARGE-textCLS-RHEOLOGY-20230913-3
This model is a fine-tuned version of jonas-luehrs/bert-base-uncased-MLP-scirepeval-chemistry-LARGE on the RHEOLOGY dataset of the blue333/chemical_language_understanding_benchmark. It achieves the following results on the evaluation set:
- Loss: 0.6836
- F1: 0.7805
- Precision: 0.7860
- Recall: 0.7840
- Accuracy: 0.7840
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.1777 | 1.0 | 46 | 0.8465 | 0.6593 | 0.6346 | 0.7037 | 0.7037 |
| 0.6923 | 2.0 | 92 | 0.7123 | 0.7491 | 0.7654 | 0.7593 | 0.7593 |
| 0.4974 | 3.0 | 138 | 0.6906 | 0.7563 | 0.7667 | 0.7593 | 0.7593 |
| 0.3789 | 4.0 | 184 | 0.6754 | 0.7645 | 0.7712 | 0.7716 | 0.7716 |
| 0.3053 | 5.0 | 230 | 0.6836 | 0.7805 | 0.7860 | 0.7840 | 0.7840 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3