metadata
license: mit
base_model: roberta-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: temp_model_outputdir
results: []
temp_model_outputdir
This model is a fine-tuned version of roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3571
- Precision: 0.9390
- Recall: 0.9355
- F1: 0.9315
- Accuracy: 0.9355
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: 2.2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.9118 | 1.0 | 1511 | 0.8173 | 0.8042 | 0.7125 | 0.8320 | 0.8173 |
| 0.6271 | 2.0 | 3022 | 0.8402 | 0.8360 | 0.6493 | 0.8535 | 0.8402 |
| 0.5214 | 3.0 | 4533 | 0.8342 | 0.8285 | 0.7902 | 0.8391 | 0.8342 |
| 0.7385 | 4.0 | 6044 | 0.8769 | 0.8724 | 0.5748 | 0.8879 | 0.8769 |
| 0.6674 | 5.0 | 7555 | 0.8640 | 0.8602 | 0.5157 | 0.8802 | 0.8640 |
| 0.4279 | 6.0 | 9066 | 0.9077 | 0.9029 | 0.4802 | 0.9148 | 0.9077 |
| 0.5507 | 7.0 | 10577 | 0.3693 | 0.9371 | 0.9332 | 0.9288 | 0.9332 |
| 0.2703 | 8.0 | 12088 | 0.3571 | 0.9390 | 0.9355 | 0.9315 | 0.9355 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0