|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: GPT2_more_function_53 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# GPT2_more_function_53 |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 4.3533 |
|
|
- Accuracy: 0.2671 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
|
| 5.6324 | 1.0 | 6417 | 5.4069 | 0.1901 | |
|
|
| 4.9863 | 2.0 | 12834 | 4.8399 | 0.2250 | |
|
|
| 4.7128 | 3.0 | 19251 | 4.6418 | 0.2408 | |
|
|
| 4.5849 | 4.0 | 25668 | 4.5399 | 0.2498 | |
|
|
| 4.485 | 5.0 | 32085 | 4.4786 | 0.2551 | |
|
|
| 4.4117 | 6.0 | 38502 | 4.4334 | 0.2588 | |
|
|
| 4.3507 | 7.0 | 44919 | 4.4014 | 0.2623 | |
|
|
| 4.2955 | 8.0 | 51336 | 4.3777 | 0.2646 | |
|
|
| 4.2474 | 9.0 | 57753 | 4.3611 | 0.2660 | |
|
|
| 4.2047 | 10.0 | 64170 | 4.3533 | 0.2671 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.30.2 |
|
|
- Pytorch 2.9.1+cu128 |
|
|
- Datasets 4.1.1 |
|
|
- Tokenizers 0.13.3 |
|
|
|
