|
--- |
|
license: apache-2.0 |
|
base_model: judy93536/distilroberta-rbm231k-ep20-op40 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilroberta-rbm231k-ep20-op40-phr2 |
|
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. --> |
|
|
|
# distilroberta-rbm231k-ep20-op40-phr2 |
|
|
|
This model is a fine-tuned version of [judy93536/distilroberta-rbm231k-ep20-op40](https://huggingface.co/judy93536/distilroberta-rbm231k-ep20-op40) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1783 |
|
- Accuracy: 0.9590 |
|
|
|
## 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: 1.153335054745316e-06 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.4 |
|
- num_epochs: 30 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 250 | 1.0615 | 0.6236 | |
|
| 1.0609 | 2.0 | 500 | 1.0082 | 0.6136 | |
|
| 1.0609 | 3.0 | 750 | 0.9017 | 0.6136 | |
|
| 0.9424 | 4.0 | 1000 | 0.8311 | 0.6136 | |
|
| 0.9424 | 5.0 | 1250 | 0.7762 | 0.6136 | |
|
| 0.807 | 6.0 | 1500 | 0.7233 | 0.6837 | |
|
| 0.807 | 7.0 | 1750 | 0.6546 | 0.7217 | |
|
| 0.676 | 8.0 | 2000 | 0.5831 | 0.7508 | |
|
| 0.676 | 9.0 | 2250 | 0.5061 | 0.7848 | |
|
| 0.5141 | 10.0 | 2500 | 0.4108 | 0.8509 | |
|
| 0.5141 | 11.0 | 2750 | 0.2958 | 0.9019 | |
|
| 0.3067 | 12.0 | 3000 | 0.2108 | 0.9309 | |
|
| 0.3067 | 13.0 | 3250 | 0.2005 | 0.9339 | |
|
| 0.1739 | 14.0 | 3500 | 0.1710 | 0.9409 | |
|
| 0.1739 | 15.0 | 3750 | 0.1635 | 0.9459 | |
|
| 0.1312 | 16.0 | 4000 | 0.1603 | 0.9510 | |
|
| 0.1312 | 17.0 | 4250 | 0.1713 | 0.9489 | |
|
| 0.1123 | 18.0 | 4500 | 0.1696 | 0.9550 | |
|
| 0.1123 | 19.0 | 4750 | 0.1658 | 0.9550 | |
|
| 0.1021 | 20.0 | 5000 | 0.1716 | 0.9560 | |
|
| 0.1021 | 21.0 | 5250 | 0.1601 | 0.9600 | |
|
| 0.0906 | 22.0 | 5500 | 0.1622 | 0.9590 | |
|
| 0.0906 | 23.0 | 5750 | 0.1742 | 0.9600 | |
|
| 0.0856 | 24.0 | 6000 | 0.1672 | 0.9600 | |
|
| 0.0856 | 25.0 | 6250 | 0.1773 | 0.9580 | |
|
| 0.0814 | 26.0 | 6500 | 0.1723 | 0.9610 | |
|
| 0.0814 | 27.0 | 6750 | 0.1766 | 0.9570 | |
|
| 0.077 | 28.0 | 7000 | 0.1793 | 0.9560 | |
|
| 0.077 | 29.0 | 7250 | 0.1782 | 0.9590 | |
|
| 0.0786 | 30.0 | 7500 | 0.1783 | 0.9590 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
