metadata
license: apache-2.0
base_model: google/electra-base-discriminator
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: electra-base-fp16
results: []
electra-base-fp16
This model is a fine-tuned version of google/electra-base-discriminator on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3364
- Accuracy: 0.8873
- Precision: 0.8903
- Recall: 0.8835
- F1: 0.8869
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3204 | 1.0 | 1074 | 0.2991 | 0.8777 | 0.8868 | 0.8660 | 0.8763 |
| 0.2293 | 2.0 | 2148 | 0.3006 | 0.8884 | 0.8926 | 0.8832 | 0.8879 |
| 0.1761 | 3.0 | 3222 | 0.3364 | 0.8873 | 0.8903 | 0.8835 | 0.8869 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0