metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: GPT2_five_function_67
results: []
GPT2_five_function_67
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.6032
- Accuracy: 0.4048
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: 67
- 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 |
|---|---|---|---|---|
| 4.7546 | 1.0 | 6408 | 4.5611 | 0.3264 |
| 4.1827 | 2.0 | 12816 | 4.0567 | 0.3615 |
| 3.9339 | 3.0 | 19224 | 3.8716 | 0.3765 |
| 3.8136 | 4.0 | 25632 | 3.7778 | 0.3857 |
| 3.72 | 5.0 | 32040 | 3.7189 | 0.3916 |
| 3.6514 | 6.0 | 38448 | 3.6762 | 0.3963 |
| 3.5942 | 7.0 | 44856 | 3.6475 | 0.3987 |
| 3.5418 | 8.0 | 51264 | 3.6251 | 0.4025 |
| 3.4961 | 9.0 | 57672 | 3.6103 | 0.4039 |
| 3.4556 | 10.0 | 64080 | 3.6032 | 0.4048 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.1+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3