metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta_large-chunking_0715_v0
results: []
roberta_large-chunking_0715_v0
This model is a fine-tuned version of roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3602
- Precision: 0.3182
- Recall: 0.2213
- F1: 0.2610
- Accuracy: 0.8681
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 63 | 0.4019 | 0.5525 | 0.0824 | 0.1434 | 0.8748 |
| No log | 2.0 | 126 | 0.3614 | 0.4887 | 0.1517 | 0.2315 | 0.8747 |
| No log | 3.0 | 189 | 0.3569 | 0.4484 | 0.1638 | 0.2399 | 0.8744 |
| No log | 4.0 | 252 | 0.3581 | 0.3685 | 0.1909 | 0.2515 | 0.8719 |
| No log | 5.0 | 315 | 0.3602 | 0.3182 | 0.2213 | 0.2610 | 0.8681 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.3.2
- Tokenizers 0.12.1