|
--- |
|
license: mit |
|
base_model: gpt2-medium |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: gmra_model_gpt2-medium_14082023T134929 |
|
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. --> |
|
|
|
# gmra_model_gpt2-medium_14082023T134929 |
|
|
|
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3831 |
|
- Accuracy: 0.9438 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 284 | 0.2626 | 0.9069 | |
|
| 0.3464 | 2.0 | 568 | 0.2263 | 0.9262 | |
|
| 0.3464 | 3.0 | 852 | 0.2545 | 0.9394 | |
|
| 0.1022 | 4.0 | 1137 | 0.2577 | 0.9464 | |
|
| 0.1022 | 5.0 | 1421 | 0.3485 | 0.9420 | |
|
| 0.0292 | 6.0 | 1705 | 0.3445 | 0.9429 | |
|
| 0.0292 | 7.0 | 1989 | 0.3127 | 0.9464 | |
|
| 0.0125 | 8.0 | 2274 | 0.4068 | 0.9411 | |
|
| 0.0085 | 9.0 | 2558 | 0.3853 | 0.9438 | |
|
| 0.0085 | 9.99 | 2840 | 0.3831 | 0.9438 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
