metadata
library_name: transformers
license: mit
base_model: deepset/gbert-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: flausch_span_gbert-large
results: []
flausch_span_gbert-large
This model is a fine-tuned version of deepset/gbert-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6725
- Model Preparation Time: 0.0057
- Precision: 0.5075
- Recall: 0.6548
- F1: 0.5718
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.5882 | 1.0 | 517 | 0.5842 | 0.0057 | 0.4539 | 0.6280 | 0.5270 |
| 0.3879 | 2.0 | 1034 | 0.5720 | 0.0057 | 0.5194 | 0.6646 | 0.5831 |
| 0.256 | 3.0 | 1551 | 0.6075 | 0.0057 | 0.4985 | 0.6445 | 0.5622 |
| 0.1477 | 4.0 | 2068 | 0.6725 | 0.0057 | 0.5075 | 0.6548 | 0.5718 |
Framework versions
- Transformers 4.52.2
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1