metadata
license: mit
base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: MatSciBERT_BIOMAT_NER3
results: []
MatSciBERT_BIOMAT_NER3
This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3972
- Precision: 0.5228
- Recall: 0.7391
- F1: 0.6124
- Accuracy: 0.9437
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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 422 | 0.2590 | 0.4873 | 0.6950 | 0.5729 | 0.9387 |
| 0.2326 | 2.0 | 844 | 0.2598 | 0.5160 | 0.7084 | 0.5971 | 0.9428 |
| 0.0654 | 3.0 | 1266 | 0.3152 | 0.5105 | 0.6936 | 0.5881 | 0.9430 |
| 0.0342 | 4.0 | 1688 | 0.3075 | 0.5214 | 0.7208 | 0.6051 | 0.9432 |
| 0.0208 | 5.0 | 2110 | 0.3623 | 0.5109 | 0.7370 | 0.6034 | 0.9421 |
| 0.0126 | 6.0 | 2532 | 0.3504 | 0.5167 | 0.7139 | 0.5995 | 0.9428 |
| 0.0126 | 7.0 | 2954 | 0.3708 | 0.5260 | 0.7453 | 0.6167 | 0.9445 |
| 0.0073 | 8.0 | 3376 | 0.3898 | 0.5175 | 0.7294 | 0.6054 | 0.9432 |
| 0.0058 | 9.0 | 3798 | 0.3917 | 0.5185 | 0.7391 | 0.6094 | 0.9432 |
| 0.0039 | 10.0 | 4220 | 0.3972 | 0.5228 | 0.7391 | 0.6124 | 0.9437 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1