metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: humor-no-humor
results: []
humor-no-humor
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1510
- Accuracy: 0.9814
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-06
- train_batch_size: 4
- eval_batch_size: 4
- 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 | Accuracy |
|---|---|---|---|---|
| 0.0066 | 1.0 | 6706 | 0.1510 | 0.9814 |
| 0.0014 | 2.0 | 13412 | 0.1526 | 0.9817 |
| 0.0 | 3.0 | 20118 | 0.1538 | 0.9820 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3