metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: GPT2_more_function_53
results: []
GPT2_more_function_53
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9183
- Accuracy: 0.5679
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: 0.0001
- train_batch_size: 128
- eval_batch_size: 128
- seed: 53
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.297 | 1.0 | 15568 | 2.2407 | 0.5113 |
| 2.1414 | 2.0 | 31136 | 2.1019 | 0.5349 |
| 2.0769 | 3.0 | 46704 | 2.0458 | 0.5440 |
| 2.0352 | 4.0 | 62272 | 2.0085 | 0.5512 |
| 2.0034 | 5.0 | 77840 | 1.9856 | 0.5555 |
| 1.9762 | 6.0 | 93408 | 1.9654 | 0.5584 |
| 1.9536 | 7.0 | 108976 | 1.9493 | 0.5618 |
| 1.9281 | 8.0 | 124544 | 1.9358 | 0.5642 |
| 1.9065 | 9.0 | 140112 | 1.9251 | 0.5664 |
| 1.8871 | 10.0 | 155680 | 1.9183 | 0.5679 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.1+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3