metadata
library_name: transformers
license: apache-2.0
base_model: allenai/longformer-base-4096
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: uf_longformer_medical_model
results: []
uf_longformer_medical_model
This model is a fine-tuned version of allenai/longformer-base-4096 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4604
- Accuracy: 0.3996
- F1 Weighted: 0.2799
- F1 Macro: 0.0430
- Precision: 0.2229
- Recall: 0.3996
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Weighted | F1 Macro | Precision | Recall |
|---|---|---|---|---|---|---|---|---|
| 3.6859 | 1.0 | 147 | 3.4119 | 0.1142 | 0.0234 | 0.0031 | 0.0130 | 0.1142 |
| 3.5174 | 2.0 | 294 | 3.0762 | 0.3370 | 0.1754 | 0.0226 | 0.1188 | 0.3370 |
| 2.8324 | 3.0 | 441 | 2.4604 | 0.3996 | 0.2799 | 0.0430 | 0.2229 | 0.3996 |
Framework versions
- Transformers 4.56.2
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1