|
--- |
|
license: apache-2.0 |
|
base_model: judy93536/distilroberta-newsapi121k |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilroberta-newsapi121k-phrase5k |
|
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-newsapi121k-phrase5k |
|
|
|
This model is a fine-tuned version of [judy93536/distilroberta-newsapi121k](https://huggingface.co/judy93536/distilroberta-newsapi121k) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1848 |
|
- Accuracy: 0.9379 |
|
|
|
## 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: 8.103335054745316e-06 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.28 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 125 | 0.5800 | 0.7568 | |
|
| No log | 2.0 | 250 | 0.2335 | 0.9219 | |
|
| No log | 3.0 | 375 | 0.1848 | 0.9379 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
