|
--- |
|
license: mit |
|
base_model: gpt2-medium |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: results |
|
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. --> |
|
|
|
# results |
|
|
|
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: 0.5570 |
|
- Accuracy: 0.7508 |
|
|
|
## 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 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.6473 | 0.04 | 50 | 0.5683 | 0.7454 | |
|
| 0.6367 | 0.07 | 100 | 0.5670 | 0.7525 | |
|
| 0.6016 | 0.11 | 150 | 0.5676 | 0.7508 | |
|
| 0.6014 | 0.14 | 200 | 0.5498 | 0.75 | |
|
| 0.5801 | 0.18 | 250 | 0.5446 | 0.75 | |
|
| 0.4534 | 0.21 | 300 | 0.5383 | 0.7512 | |
|
| 0.669 | 0.25 | 350 | 0.5700 | 0.75 | |
|
| 0.5556 | 0.29 | 400 | 0.5536 | 0.7496 | |
|
| 0.5652 | 0.32 | 450 | 0.6341 | 0.75 | |
|
| 0.5801 | 0.36 | 500 | 0.5416 | 0.7454 | |
|
| 0.6476 | 0.39 | 550 | 0.5319 | 0.7508 | |
|
| 0.5473 | 0.43 | 600 | 0.5422 | 0.7492 | |
|
| 0.5094 | 0.46 | 650 | 0.5532 | 0.7504 | |
|
| 0.5656 | 0.5 | 700 | 0.5375 | 0.7504 | |
|
| 0.532 | 0.54 | 750 | 0.5617 | 0.7137 | |
|
| 0.5738 | 0.57 | 800 | 0.5501 | 0.7521 | |
|
| 0.544 | 0.61 | 850 | 0.5449 | 0.7538 | |
|
| 0.5271 | 0.64 | 900 | 0.5682 | 0.7496 | |
|
| 0.9725 | 0.68 | 950 | 0.7980 | 0.4921 | |
|
| 0.5955 | 0.71 | 1000 | 0.5220 | 0.7538 | |
|
| 0.5588 | 0.75 | 1050 | 0.5247 | 0.75 | |
|
| 0.612 | 0.79 | 1100 | 0.5183 | 0.7483 | |
|
| 0.6124 | 0.82 | 1150 | 0.5260 | 0.7542 | |
|
| 0.421 | 0.86 | 1200 | 0.5509 | 0.7508 | |
|
| 0.4582 | 0.89 | 1250 | 0.5249 | 0.75 | |
|
| 0.588 | 0.93 | 1300 | 0.5633 | 0.7267 | |
|
| 0.549 | 0.96 | 1350 | 0.5179 | 0.7492 | |
|
| 0.495 | 1.0 | 1400 | 0.5456 | 0.7512 | |
|
| 0.435 | 1.04 | 1450 | 0.5596 | 0.7504 | |
|
| 0.6061 | 1.07 | 1500 | 0.5421 | 0.7433 | |
|
| 0.5542 | 1.11 | 1550 | 0.5117 | 0.7554 | |
|
| 0.4277 | 1.14 | 1600 | 0.5291 | 0.7521 | |
|
| 0.4415 | 1.18 | 1650 | 0.5354 | 0.7538 | |
|
| 0.5029 | 1.21 | 1700 | 0.5084 | 0.7579 | |
|
| 0.6079 | 1.25 | 1750 | 0.5798 | 0.7554 | |
|
| 0.5692 | 1.29 | 1800 | 0.5003 | 0.755 | |
|
| 0.5297 | 1.32 | 1850 | 0.5563 | 0.7588 | |
|
| 0.6938 | 1.36 | 1900 | 0.5064 | 0.7529 | |
|
| 0.5679 | 1.39 | 1950 | 0.5505 | 0.7508 | |
|
| 0.4503 | 1.43 | 2000 | 0.5133 | 0.7554 | |
|
| 0.519 | 1.46 | 2050 | 0.4946 | 0.7525 | |
|
| 0.513 | 1.5 | 2100 | 0.5156 | 0.7283 | |
|
| 0.5393 | 1.54 | 2150 | 0.5003 | 0.7546 | |
|
| 0.6162 | 1.57 | 2200 | 0.4916 | 0.7625 | |
|
| 0.5526 | 1.61 | 2250 | 0.4980 | 0.755 | |
|
| 0.4472 | 1.64 | 2300 | 0.5001 | 0.76 | |
|
| 0.5678 | 1.68 | 2350 | 0.4958 | 0.7558 | |
|
| 0.3894 | 1.71 | 2400 | 0.4968 | 0.7646 | |
|
| 0.4086 | 1.75 | 2450 | 0.5065 | 0.7583 | |
|
| 0.4652 | 1.79 | 2500 | 0.5091 | 0.7567 | |
|
| 0.4837 | 1.82 | 2550 | 0.5190 | 0.7312 | |
|
| 0.4745 | 1.86 | 2600 | 0.4998 | 0.7567 | |
|
| 0.456 | 1.89 | 2650 | 0.5035 | 0.7558 | |
|
| 0.5784 | 1.93 | 2700 | 0.4997 | 0.7504 | |
|
| 0.452 | 1.96 | 2750 | 0.5315 | 0.7517 | |
|
| 0.5682 | 2.0 | 2800 | 0.5827 | 0.7521 | |
|
| 0.6134 | 2.04 | 2850 | 0.4944 | 0.7421 | |
|
| 0.3451 | 2.07 | 2900 | 0.5505 | 0.7575 | |
|
| 0.3682 | 2.11 | 2950 | 0.5122 | 0.7504 | |
|
| 0.3737 | 2.14 | 3000 | 0.8033 | 0.7546 | |
|
| 0.4899 | 2.18 | 3050 | 0.5645 | 0.7446 | |
|
| 0.4885 | 2.21 | 3100 | 0.5229 | 0.7554 | |
|
| 0.4121 | 2.25 | 3150 | 0.5172 | 0.7425 | |
|
| 0.3926 | 2.29 | 3200 | 0.5685 | 0.7512 | |
|
| 0.4242 | 2.32 | 3250 | 0.5380 | 0.7425 | |
|
| 0.4133 | 2.36 | 3300 | 0.5996 | 0.7488 | |
|
| 0.4322 | 2.39 | 3350 | 0.5769 | 0.7533 | |
|
| 0.4561 | 2.43 | 3400 | 0.5525 | 0.7583 | |
|
| 0.2765 | 2.46 | 3450 | 0.5399 | 0.7546 | |
|
| 0.4422 | 2.5 | 3500 | 0.5782 | 0.7554 | |
|
| 0.4343 | 2.54 | 3550 | 0.5325 | 0.7338 | |
|
| 0.3551 | 2.57 | 3600 | 0.5518 | 0.7504 | |
|
| 0.4058 | 2.61 | 3650 | 0.5585 | 0.7579 | |
|
| 0.4838 | 2.64 | 3700 | 0.5433 | 0.7379 | |
|
| 0.3821 | 2.68 | 3750 | 0.5244 | 0.7562 | |
|
| 0.4906 | 2.71 | 3800 | 0.5202 | 0.7525 | |
|
| 0.3046 | 2.75 | 3850 | 0.5430 | 0.7575 | |
|
| 0.4317 | 2.79 | 3900 | 0.5369 | 0.7546 | |
|
| 0.5641 | 2.82 | 3950 | 0.5406 | 0.7546 | |
|
| 0.4866 | 2.86 | 4000 | 0.5454 | 0.7546 | |
|
| 0.3687 | 2.89 | 4050 | 0.5450 | 0.7558 | |
|
| 0.484 | 2.93 | 4100 | 0.5456 | 0.7521 | |
|
| 0.2599 | 2.96 | 4150 | 0.5472 | 0.7533 | |
|
| 0.3381 | 3.0 | 4200 | 0.5461 | 0.7508 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|