metadata
library_name: transformers
license: apache-2.0
base_model: uitnlp/CafeBERT
tags:
- generated_from_trainer
model-index:
- name: CafeBERT_massive
results: []
CafeBERT_massive
This model is a fine-tuned version of uitnlp/CafeBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8941
- Slot P: 0.0093
- Slot R: 0.0199
- Slot F1: 0.0127
- Slot Exact Match: 0.0679
- Intent Acc: 0.8756
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Slot P | Slot R | Slot F1 | Slot Exact Match | Intent Acc |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 45 | 2.2457 | 0.0123 | 0.0064 | 0.0085 | 0.3665 | 0.7201 |
| 10.82 | 2.0 | 90 | 1.1090 | 0.0111 | 0.0182 | 0.0138 | 0.1756 | 0.8598 |
| 2.7961 | 3.0 | 135 | 0.9549 | 0.0097 | 0.0176 | 0.0125 | 0.1604 | 0.8647 |
| 1.7004 | 4.0 | 180 | 0.9027 | 0.0098 | 0.0193 | 0.0130 | 0.1215 | 0.8726 |
| 1.2198 | 5.0 | 225 | 0.8941 | 0.0093 | 0.0199 | 0.0127 | 0.0679 | 0.8756 |
Framework versions
- Transformers 4.55.0
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.4