metadata
license: apache-2.0
base_model: cross-encoder/stsb-roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: ce-roberta-large
results: []
ce-roberta-large
This model is a fine-tuned version of cross-encoder/stsb-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1713
- Accuracy: 0.6869
- Precision: 0.8654
- Recall: 0.6522
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: 16
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall |
|---|---|---|---|---|---|---|
| 0.7081 | 1.0 | 56 | 0.6788 | 0.5960 | 0.8372 | 0.5217 |
| 0.2275 | 2.0 | 112 | 0.2457 | 0.6667 | 0.8333 | 0.6522 |
| 0.2263 | 3.0 | 168 | 0.1814 | 0.5455 | 0.9286 | 0.3768 |
| 0.2249 | 4.0 | 224 | 0.1833 | 0.5657 | 0.9062 | 0.4203 |
| 0.1803 | 5.0 | 280 | 0.1999 | 0.6768 | 0.7937 | 0.7246 |
| 0.1708 | 6.0 | 336 | 0.1956 | 0.6566 | 0.8302 | 0.6377 |
| 0.2091 | 7.0 | 392 | 0.1789 | 0.5556 | 0.9310 | 0.3913 |
| 0.186 | 8.0 | 448 | 0.1845 | 0.6364 | 0.9231 | 0.5217 |
| 0.2133 | 9.0 | 504 | 0.1755 | 0.6162 | 0.9189 | 0.4928 |
| 0.1982 | 10.0 | 560 | 0.1713 | 0.6869 | 0.8654 | 0.6522 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.1
- Datasets 2.14.6
- Tokenizers 0.15.1