metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: sentence-compression
results: []
sentence-compression
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4221
- Accuracy: 0.8121
- F1: 0.7275
- Precision: 0.7317
- Recall: 0.7233
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6263 | 1.0 | 50 | 0.6252 | 0.6549 | 0.0183 | 0.6667 | 0.0093 |
| 0.4727 | 2.0 | 100 | 0.4900 | 0.7805 | 0.6472 | 0.7309 | 0.5807 |
| 0.4053 | 3.0 | 150 | 0.4221 | 0.8121 | 0.7275 | 0.7317 | 0.7233 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.10.0+cu111
- Tokenizers 0.10.3