bert2bert
This model is a fine-tuned version of mrm8488/bert-mini2bert-mini-finetuned-cnn_daily_mail-summarization on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1196
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1386 | 1.0 | 3677 | 0.1256 |
| 0.1294 | 2.0 | 7355 | 0.1227 |
| 0.1233 | 3.0 | 11032 | 0.1210 |
| 0.1204 | 4.0 | 14710 | 0.1200 |
| 0.1191 | 5.0 | 18385 | 0.1196 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Tokenizers 0.15.2
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.