metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: GPT2_random_function_53
results: []
GPT2_random_function_53
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.8501
- Accuracy: 0.2494
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 |
|---|---|---|---|---|
| 5.9648 | 1.0 | 6426 | 5.7752 | 0.1790 |
| 5.4131 | 2.0 | 12852 | 5.2875 | 0.2089 |
| 5.1686 | 3.0 | 19278 | 5.1053 | 0.2241 |
| 5.0478 | 4.0 | 25704 | 5.0146 | 0.2328 |
| 4.9577 | 5.0 | 32130 | 4.9593 | 0.2377 |
| 4.8934 | 6.0 | 38556 | 4.9200 | 0.2411 |
| 4.8346 | 7.0 | 44982 | 4.8911 | 0.2447 |
| 4.7873 | 8.0 | 51408 | 4.8704 | 0.2465 |
| 4.7405 | 9.0 | 57834 | 4.8566 | 0.2485 |
| 4.7008 | 10.0 | 64260 | 4.8501 | 0.2494 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.1+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3