electra-base-generator-Imdb-SeqClassification
This model is a fine-tuned version of google/electra-base-generator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2784
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: 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: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.2857 | 1.0 | 3125 | 0.2904 |
0.2805 | 2.0 | 6250 | 0.2843 |
0.316 | 3.0 | 9375 | 0.2784 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
Model tree for alitolga/electra-base-generator-Imdb-SeqClassification
Base model
google/electra-base-generator