Hierarchical BERT
Collection
Set of BERT models with Hierarchical attention pre-trained on conversational data to process multiple utterances at once
•
8 items
•
Updated
hat-tiny-cased-conversational-p2_1-grouped-128-v2
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5454
- Accuracy: 0.5161
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: 0.001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 30000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.3688 | 0.7422 | 7500 | 3.1865 | 0.4371 |
| 3.0558 | 1.4844 | 15000 | 2.9189 | 0.4672 |
| 2.8314 | 2.2266 | 22500 | 2.6859 | 0.4975 |
| 2.6241 | 2.9688 | 30000 | 2.5454 | 0.5161 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support