song-artist-classifier-v3-roberta
This model is a fine-tuned version of distilbert/distilroberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0147
- F1: [0.8571428571428572, 0.5714285714285714, 0.888888888888889, 0.8181818181818182, 0.8571428571428571, 0.4, 0.8571428571428572, 0.7777777777777777, 0.5, 0.7, 0.5333333333333333, 0.6956521739130436, 0.7826086956521738, 0.8235294117647058, 0.5, 0.8000000000000002, 0.8181818181818182, 0.9, 0.47058823529411764, 0.608695652173913]
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 95 | 2.2772 | [0.15384615384615383, 0.41379310344827586, 0.0, 0.45454545454545453, 0.0, 0.16666666666666669, 0.14285714285714288, 0.3684210526315789, 0.0, 0.16666666666666669, 0.0, 0.0, 0.13333333333333333, 0.30769230769230765, 0.16666666666666666, 0.358974358974359, 0.4615384615384615, 0.3846153846153846, 0.16666666666666669, 0.15384615384615383] |
| No log | 2.0 | 190 | 1.7800 | [0.6666666666666665, 0.43478260869565216, 0.4347826086956522, 0.4000000000000001, 0.0, 0.0, 0.6451612903225806, 0.608695652173913, 0.3636363636363636, 0.18181818181818182, 0.22222222222222224, 0.125, 0.5555555555555556, 0.7368421052631577, 0.22222222222222224, 0.5217391304347826, 0.631578947368421, 0.8571428571428572, 0.37037037037037035, 0.28571428571428564] |
| No log | 3.0 | 285 | 1.4763 | [0.7777777777777777, 0.4761904761904762, 0.6, 0.588235294117647, 0.6666666666666666, 0.4285714285714285, 0.6451612903225806, 0.631578947368421, 0.33333333333333326, 0.631578947368421, 0.36363636363636365, 0.6363636363636364, 0.8421052631578948, 0.7058823529411764, 0.4, 0.6956521739130435, 0.64, 0.8571428571428572, 0.5, 0.5] |
| No log | 4.0 | 380 | 1.2157 | [0.8571428571428572, 0.4444444444444444, 0.7499999999999999, 0.5263157894736842, 0.6666666666666666, 0.37499999999999994, 0.8333333333333333, 0.7272727272727272, 0.26666666666666666, 0.6666666666666666, 0.4, 0.6399999999999999, 0.761904761904762, 0.8235294117647058, 0.5454545454545454, 0.7826086956521738, 0.8000000000000002, 0.9523809523809523, 0.47058823529411764, 0.6363636363636365] |
| No log | 5.0 | 475 | 1.1712 | [0.7826086956521738, 0.6086956521739131, 0.761904761904762, 0.5555555555555556, 0.8571428571428571, 0.37499999999999994, 0.8571428571428572, 0.7368421052631577, 0.4000000000000001, 0.7368421052631577, 0.4615384615384615, 0.7272727272727273, 0.9, 0.8235294117647058, 0.47619047619047616, 0.9, 0.8571428571428572, 0.9, 0.30769230769230765, 0.6363636363636365] |
| 1.6275 | 6.0 | 570 | 1.0779 | [0.8571428571428572, 0.46153846153846156, 0.888888888888889, 0.75, 0.8571428571428571, 0.37499999999999994, 0.9090909090909091, 0.7777777777777777, 0.4210526315789474, 0.7, 0.5714285714285714, 0.6956521739130436, 0.7826086956521738, 0.7499999999999999, 0.5263157894736842, 0.8000000000000002, 0.7272727272727272, 0.8571428571428572, 0.4444444444444445, 0.5454545454545454] |
| 1.6275 | 7.0 | 665 | 1.0801 | [0.8181818181818182, 0.5555555555555556, 0.8421052631578948, 0.7777777777777777, 0.8571428571428571, 0.4285714285714285, 0.8571428571428572, 0.7777777777777777, 0.5, 0.7777777777777777, 0.5333333333333333, 0.761904761904762, 0.75, 0.8235294117647058, 0.45454545454545453, 0.6666666666666665, 0.7826086956521738, 0.888888888888889, 0.5555555555555556, 0.5714285714285713] |
| 1.6275 | 8.0 | 760 | 1.0020 | [0.8571428571428572, 0.46153846153846156, 0.8421052631578948, 0.8181818181818182, 0.8571428571428571, 0.4, 0.9, 0.7777777777777777, 0.47619047619047616, 0.7, 0.5333333333333333, 0.7272727272727273, 0.7272727272727272, 0.8235294117647058, 0.5714285714285713, 0.7272727272727272, 0.7272727272727272, 0.9523809523809523, 0.4210526315789474, 0.5263157894736842] |
| 1.6275 | 9.0 | 855 | 1.0129 | [0.8571428571428572, 0.5714285714285714, 0.888888888888889, 0.8571428571428572, 0.8571428571428571, 0.4, 0.8571428571428572, 0.7777777777777777, 0.5714285714285713, 0.6666666666666666, 0.5333333333333333, 0.7272727272727273, 0.7826086956521738, 0.8235294117647058, 0.5263157894736842, 0.761904761904762, 0.7272727272727272, 0.9473684210526316, 0.5263157894736842, 0.5454545454545454] |
| 1.6275 | 10.0 | 950 | 1.0147 | [0.8571428571428572, 0.5714285714285714, 0.888888888888889, 0.8181818181818182, 0.8571428571428571, 0.4, 0.8571428571428572, 0.7777777777777777, 0.5, 0.7, 0.5333333333333333, 0.6956521739130436, 0.7826086956521738, 0.8235294117647058, 0.5, 0.8000000000000002, 0.8181818181818182, 0.9, 0.47058823529411764, 0.608695652173913] |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2