# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("LorenzoAleCon29/roberta-base-ECB-dapt")
model = AutoModelForMaskedLM.from_pretrained("LorenzoAleCon29/roberta-base-ECB-dapt", device_map="auto")Quick Links
roberta-base-ECB-dapt
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9623
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 40.2248 | 0.2690 | 150 | 2.3196 |
| 38.1977 | 0.5381 | 300 | 2.1706 |
| 36.8653 | 0.8071 | 450 | 2.1671 |
| 35.4280 | 1.0753 | 600 | 2.1277 |
| 35.2623 | 1.3444 | 750 | 2.0359 |
| 35.0369 | 1.6134 | 900 | 2.0045 |
| 34.3773 | 1.8824 | 1050 | 2.0329 |
| 34.1305 | 2.1507 | 1200 | 1.9814 |
| 33.9732 | 2.4197 | 1350 | 1.9703 |
| 33.9225 | 2.6887 | 1500 | 1.9592 |
| 33.9132 | 2.9577 | 1650 | 1.9181 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2
- Downloads last month
- 47
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="LorenzoAleCon29/roberta-base-ECB-dapt")