metadata
library_name: transformers
license: mit
base_model: Charangan/MedBERT
tags:
- generated_from_trainer
model-index:
- name: medbert-clinical-ner
results: []
medbert-clinical-ner
This model is a fine-tuned version of Charangan/MedBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3264
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.15
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 36 | 0.2732 |
| No log | 2.0 | 72 | 0.2875 |
| No log | 3.0 | 108 | 0.3106 |
| No log | 4.0 | 144 | 0.3228 |
| No log | 5.0 | 180 | 0.3264 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Tokenizers 0.19.1