metadata
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: ES_roberta_30_prepro
results: []
ES_roberta_30_prepro
This model is a fine-tuned version of klue/roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Exact Match: 26.25
- F1: 36.0319
- Loss: 1.2394
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Exact Match | F1 | Validation Loss |
|---|---|---|---|---|---|
| No log | 1.0 | 305 | 22.9167 | 34.1584 | 1.0608 |
| 0.7921 | 2.0 | 610 | 25.0 | 35.1179 | 1.0869 |
| 0.7921 | 3.0 | 915 | 26.25 | 36.0319 | 1.2394 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2