gpt2_small_PL_unigram_8177_parallel10_42
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1523
- Accuracy: 0.4222
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|
| 5.4818 | 1.0 | 1746 | 4.0270 | 0.3242 |
| 3.8691 | 2.0 | 3492 | 3.6019 | 0.3681 |
| 3.5519 | 3.0 | 5238 | 3.4288 | 0.3873 |
| 3.4567 | 4.0 | 6984 | 3.3347 | 0.3992 |
| 3.3337 | 5.0 | 8730 | 3.2723 | 0.4067 |
| 3.2574 | 6.0 | 10476 | 3.2291 | 0.4112 |
| 3.2009 | 7.0 | 12222 | 3.1975 | 0.4155 |
| 3.1672 | 8.0 | 13968 | 3.1753 | 0.4194 |
| 3.1251 | 9.0 | 15714 | 3.1588 | 0.4212 |
| 3.0994 | 10.0 | 17460 | 3.1523 | 0.4222 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.19.1
