metadata
license: mit
base_model: Aravindan/gpt2out
tags:
- generated_from_trainer
model-index:
- name: gpt2coder-8epochs
results: []
gpt2coder-8epochs
This model is a fine-tuned version of Aravindan/gpt2out on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9270
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 80
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.9810 | 31 | 3.2508 |
| No log | 1.9937 | 63 | 2.6920 |
| No log | 2.9747 | 94 | 2.3769 |
| No log | 3.9873 | 126 | 2.1444 |
| No log | 5.0 | 158 | 1.9673 |
| No log | 5.9810 | 189 | 1.8320 |
| No log | 6.9937 | 221 | 1.7097 |
| No log | 7.9747 | 252 | 1.6159 |
| No log | 8.9873 | 284 | 1.5231 |
| No log | 10.0 | 316 | 1.4535 |
| No log | 10.9810 | 347 | 1.3788 |
| No log | 11.9937 | 379 | 1.3109 |
| No log | 12.9747 | 410 | 1.2496 |
| No log | 13.9873 | 442 | 1.1989 |
| No log | 14.9810 | 465 | 1.1647 |
| No log | 15.9937 | 497 | 1.1208 |
| 1.3856 | 16.9747 | 528 | 1.0841 |
| 1.3856 | 17.9873 | 560 | 1.0464 |
| 1.3856 | 19.0 | 592 | 1.0180 |
| 1.3856 | 19.9810 | 623 | 0.9928 |
| 1.3856 | 20.9937 | 655 | 0.9689 |
| 1.3856 | 21.9747 | 686 | 0.9517 |
| 1.3856 | 22.9873 | 718 | 0.9390 |
| 1.3856 | 24.0 | 750 | 0.9298 |
| 1.3856 | 24.7911 | 775 | 0.9270 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1