metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: Bert-RAdam-Large
results: []
datasets:
- surrey-nlp/PLOD-CW-25
- surrey-nlp/PLODv2-filtered
Bert-RAdam-Large
This model is a fine-tuned version of bert-base-cased on a subset of the PLODv2-filtered dataset. It achieves the following results on the evaluation set:
- Loss: 0.2110
- Precision: 0.7864
- Recall: 0.8598
- F1: 0.8215
- Accuracy: 0.9403
It achieves the following results on the test set:
- Loss: 0.1825
- Precision: 0.8017
- Recall: 0.8902
- F1: 0.8436
- Accuracy: 0.9500
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: 0.0001
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2244 | 1.0 | 500 | 0.1675 | 0.7653 | 0.8651 | 0.8121 | 0.9355 |
| 0.1231 | 2.0 | 1000 | 0.1673 | 0.7433 | 0.9011 | 0.8146 | 0.9375 |
| 0.0923 | 3.0 | 1500 | 0.1698 | 0.7867 | 0.8539 | 0.8189 | 0.9391 |
| 0.0657 | 4.0 | 2000 | 0.1865 | 0.7857 | 0.8405 | 0.8122 | 0.9394 |
| 0.0431 | 5.0 | 2500 | 0.2110 | 0.7864 | 0.8598 | 0.8215 | 0.9403 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1