<!-- 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. -->
model_broadclass_onSet0
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9207
- 0 Precision: 1.0
- 0 Recall: 1.0
- 0 F1-score: 1.0
- 0 Support: 31
- 1 Precision: 0.9615
- 1 Recall: 1.0
- 1 F1-score: 0.9804
- 1 Support: 25
- 2 Precision: 1.0
- 2 Recall: 0.9630
- 2 F1-score: 0.9811
- 2 Support: 27
- 3 Precision: 1.0
- 3 Recall: 1.0
- 3 F1-score: 1.0
- 3 Support: 15
- Accuracy: 0.9898
- Macro avg Precision: 0.9904
- Macro avg Recall: 0.9907
- Macro avg F1-score: 0.9904
- Macro avg Support: 98
- Weighted avg Precision: 0.9902
- Weighted avg Recall: 0.9898
- Weighted avg F1-score: 0.9898
- Weighted avg Support: 98
- Wer: 0.9344
- Mtrix: [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 1, 26, 0], [3, 0, 0, 0, 15]]
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | 0 Precision | 0 Recall | 0 F1-score | 0 Support | 1 Precision | 1 Recall | 1 F1-score | 1 Support | 2 Precision | 2 Recall | 2 F1-score | 2 Support | 3 Precision | 3 Recall | 3 F1-score | 3 Support | Accuracy | Macro avg Precision | Macro avg Recall | Macro avg F1-score | Macro avg Support | Weighted avg Precision | Weighted avg Recall | Weighted avg F1-score | Weighted avg Support | Wer | Mtrix |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2.3791 | 4.16 | 100 | 2.2297 | 0.3163 | 1.0 | 0.4806 | 31 | 0.0 | 0.0 | 0.0 | 25 | 0.0 | 0.0 | 0.0 | 27 | 0.0 | 0.0 | 0.0 | 15 | 0.3163 | 0.0791 | 0.25 | 0.1202 | 98 | 0.1001 | 0.3163 | 0.1520 | 98 | 0.9847 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]] |
2.276 | 8.33 | 200 | 2.1645 | 0.3163 | 1.0 | 0.4806 | 31 | 0.0 | 0.0 | 0.0 | 25 | 0.0 | 0.0 | 0.0 | 27 | 0.0 | 0.0 | 0.0 | 15 | 0.3163 | 0.0791 | 0.25 | 0.1202 | 98 | 0.1001 | 0.3163 | 0.1520 | 98 | 0.9847 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]] |
1.9646 | 12.49 | 300 | 1.9022 | 0.3163 | 1.0 | 0.4806 | 31 | 0.0 | 0.0 | 0.0 | 25 | 0.0 | 0.0 | 0.0 | 27 | 0.0 | 0.0 | 0.0 | 15 | 0.3163 | 0.0791 | 0.25 | 0.1202 | 98 | 0.1001 | 0.3163 | 0.1520 | 98 | 0.9847 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]] |
1.7089 | 16.65 | 400 | 1.6727 | 0.3163 | 1.0 | 0.4806 | 31 | 0.0 | 0.0 | 0.0 | 25 | 0.0 | 0.0 | 0.0 | 27 | 0.0 | 0.0 | 0.0 | 15 | 0.3163 | 0.0791 | 0.25 | 0.1202 | 98 | 0.1001 | 0.3163 | 0.1520 | 98 | 0.9847 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]] |
1.5546 | 20.82 | 500 | 1.5776 | 0.3163 | 1.0 | 0.4806 | 31 | 0.0 | 0.0 | 0.0 | 25 | 0.0 | 0.0 | 0.0 | 27 | 0.0 | 0.0 | 0.0 | 15 | 0.3163 | 0.0791 | 0.25 | 0.1202 | 98 | 0.1001 | 0.3163 | 0.1520 | 98 | 0.9847 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]] |
1.5671 | 24.98 | 600 | 1.5759 | 0.3163 | 1.0 | 0.4806 | 31 | 0.0 | 0.0 | 0.0 | 25 | 0.0 | 0.0 | 0.0 | 27 | 0.0 | 0.0 | 0.0 | 15 | 0.3163 | 0.0791 | 0.25 | 0.1202 | 98 | 0.1001 | 0.3163 | 0.1520 | 98 | 0.9847 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]] |
1.5548 | 29.16 | 700 | 1.5419 | 0.3163 | 1.0 | 0.4806 | 31 | 0.0 | 0.0 | 0.0 | 25 | 0.0 | 0.0 | 0.0 | 27 | 0.0 | 0.0 | 0.0 | 15 | 0.3163 | 0.0791 | 0.25 | 0.1202 | 98 | 0.1001 | 0.3163 | 0.1520 | 98 | 0.9847 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]] |
1.5148 | 33.33 | 800 | 1.4847 | 0.3263 | 1.0 | 0.4921 | 31 | 0.0 | 0.0 | 0.0 | 25 | 1.0 | 0.1111 | 0.2000 | 27 | 0.0 | 0.0 | 0.0 | 15 | 0.3469 | 0.3316 | 0.2778 | 0.1730 | 98 | 0.3787 | 0.3469 | 0.2108 | 98 | 0.9837 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 24, 0, 3, 0], [3, 15, 0, 0, 0]] |
1.4234 | 37.49 | 900 | 1.4497 | 0.4429 | 1.0 | 0.6139 | 31 | 1.0 | 0.28 | 0.4375 | 25 | 1.0 | 0.5556 | 0.7143 | 27 | 1.0 | 0.4 | 0.5714 | 15 | 0.6020 | 0.8607 | 0.5589 | 0.5843 | 98 | 0.8238 | 0.6020 | 0.5900 | 98 | 0.9975 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 18, 7, 0, 0], [2, 12, 0, 15, 0], [3, 9, 0, 0, 6]] |
1.3619 | 41.65 | 1000 | 1.3438 | 1.0 | 0.9677 | 0.9836 | 31 | 0.9259 | 1.0 | 0.9615 | 25 | 1.0 | 0.9630 | 0.9811 | 27 | 1.0 | 1.0 | 1.0 | 15 | 0.9796 | 0.9815 | 0.9827 | 0.9816 | 98 | 0.9811 | 0.9796 | 0.9798 | 98 | 0.9832 | [[0, 1, 2, 3], [0, 30, 1, 0, 0], [1, 0, 25, 0, 0], [2, 0, 1, 26, 0], [3, 0, 0, 0, 15]] |
0.9703 | 45.82 | 1100 | 0.9444 | 1.0 | 1.0 | 1.0 | 31 | 0.9615 | 1.0 | 0.9804 | 25 | 1.0 | 0.9630 | 0.9811 | 27 | 1.0 | 1.0 | 1.0 | 15 | 0.9898 | 0.9904 | 0.9907 | 0.9904 | 98 | 0.9902 | 0.9898 | 0.9898 | 98 | 0.9289 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 1, 26, 0], [3, 0, 0, 0, 15]] |
0.9299 | 49.98 | 1200 | 0.9207 | 1.0 | 1.0 | 1.0 | 31 | 0.9615 | 1.0 | 0.9804 | 25 | 1.0 | 0.9630 | 0.9811 | 27 | 1.0 | 1.0 | 1.0 | 15 | 0.9898 | 0.9904 | 0.9907 | 0.9904 | 98 | 0.9902 | 0.9898 | 0.9898 | 98 | 0.9344 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 1, 26, 0], [3, 0, 0, 0, 15]] |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2