# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("jonas/roberta-base-finetuned-sdg")
model = AutoModelForSequenceClassification.from_pretrained("jonas/roberta-base-finetuned-sdg")Quick Links
roberta-base-finetuned-sdg
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4993
- Acc: 0.9024
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: 64
- eval_batch_size: 64
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Acc |
|---|---|---|---|---|
| 0.4679 | 1.0 | 254 | 0.3660 | 0.8963 |
| 0.3578 | 2.0 | 508 | 0.3689 | 0.9019 |
| 0.2739 | 3.0 | 762 | 0.3284 | 0.9035 |
| 0.1841 | 4.0 | 1016 | 0.3763 | 0.9019 |
| 0.1127 | 5.0 | 1270 | 0.4174 | 0.9024 |
| 0.0822 | 6.0 | 1524 | 0.4523 | 0.9013 |
| 0.0329 | 7.0 | 1778 | 0.4829 | 0.9030 |
| 0.0157 | 8.0 | 2032 | 0.4993 | 0.9024 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.0a0+8a1a93a
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 182
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="jonas/roberta-base-finetuned-sdg")