metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: GPT2_five_function_random_function_53
results: []
GPT2_five_function_random_function_53
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.0209
- Accuracy: 0.2681
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 |
|---|---|---|---|---|
| 5.114 | 1.0 | 6407 | 4.9375 | 0.1981 |
| 4.569 | 2.0 | 12814 | 4.4524 | 0.2293 |
| 4.3333 | 3.0 | 19221 | 4.2776 | 0.2426 |
| 4.2155 | 4.0 | 25628 | 4.1866 | 0.2511 |
| 4.1267 | 5.0 | 32035 | 4.1294 | 0.2558 |
| 4.0604 | 6.0 | 38442 | 4.0915 | 0.2598 |
| 4.0046 | 7.0 | 44849 | 4.0633 | 0.2623 |
| 3.9522 | 8.0 | 51256 | 4.0421 | 0.2650 |
| 3.9091 | 9.0 | 57663 | 4.0274 | 0.2675 |
| 3.8682 | 10.0 | 64070 | 4.0209 | 0.2681 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.11.0+cu126
- Datasets 4.1.1
- Tokenizers 0.13.3