metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: output
results: []
output
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5751
- Accuracy: 0.0021
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: 0.0006058454513356471
- train_batch_size: 16
- eval_batch_size: 32
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2205 | 1.25 | 315 | 0.8209 | 0.0010 |
| 0.813 | 2.51 | 630 | 0.7684 | 0.0009 |
| 0.7645 | 3.76 | 945 | 0.7393 | 0.0008 |
| 0.7249 | 5.02 | 1260 | 0.6980 | 0.0007 |
| 0.6832 | 6.27 | 1575 | 0.6646 | 0.0003 |
| 0.6426 | 7.53 | 1890 | 0.6371 | 0.0019 |
| 0.6034 | 8.78 | 2205 | 0.6041 | 0.0020 |
| 0.564 | 10.04 | 2520 | 0.5897 | 0.0018 |
| 0.5253 | 11.29 | 2835 | 0.5857 | 0.0018 |
| 0.4961 | 12.55 | 3150 | 0.5771 | 0.0017 |
| 0.4752 | 13.8 | 3465 | 0.5751 | 0.0021 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3