---
tags:
- generated_from_trainer
model-index:
- name: gttbsc_distilbert-freezed-best
  results: 
    - task:
        type: dialogue act classification
      dataset:
        name: asapp/slue-phase-2
        type: hvb
      metrics:
        - name: F1 macro E2E
          type: F1 macro
          value: 63.46
        - name: F1 macro GT
          type: F1 macro
          value: 69.82
datasets:
- asapp/slue-phase-2
language:
- en
metrics:
- f1-macro
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# gttbsc_distilbert-freezed-best

Ground truth text based multi-label DAC

## Model description

Backbone: [DistilBert uncased](https://huggingface.co/distilbert/distilbert-base-uncased)  
Pooling: Self attention  
Multi-label classification head: 2 dense layers with two dropouts 0.3 and Tanh activation inbetween  


## Training and evaluation data

Trained on ground truth [slue-phase-2 hvb](https://huggingface.co/datasets/asapp/slue-phase-2).  
Evaluated on ground truth (GT) and [Whisper small](https://huggingface.co/openai/whisper-small) transcripts (E2E).  

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.00043
- weight decay: 1.5e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20 (due to small patience stopped at around 3 epoch)


### Framework versions

- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1