metadata
license: mit
base_model: roberta-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta-large-ner-new
results: []
roberta-large-ner-new
This model is a fine-tuned version of roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1106
- Precision: 0.9670
- Recall: 0.9604
- F1: 0.9637
- Accuracy: 0.9600
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1241 | 0.71 | 5000 | 0.1161 | 0.9618 | 0.9505 | 0.9561 | 0.9521 |
| 0.0993 | 1.42 | 10000 | 0.1132 | 0.9633 | 0.9568 | 0.9600 | 0.9562 |
| 0.0812 | 2.13 | 15000 | 0.1223 | 0.9662 | 0.9574 | 0.9618 | 0.9580 |
| 0.074 | 2.84 | 20000 | 0.1118 | 0.9661 | 0.9607 | 0.9634 | 0.9598 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0