Hugging Face's logo

marcelovidigal
/
secoes_contrato_rotulos_classificacao_texto_v1

Safetensors
distilbert
Model card Files Community
secoes_contrato_rotulos_classificacao_texto_v1
File size: 12,171 Bytes 
28e186b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bf44cea
 
99549f6
57f5c8c
 
80073a7
 
72fd8e1
 
 
 
 
078cd08
65a461e
cd4afcf
 
52837df
55e7cff
7e97c8c
ef18aea
 
32d043e
b265de0
e8b9608
ea84d78
 
a46c7b5
ebaa724
5d52af7
 
 
67169d5
a5bfd59
861883a
cf5d08f
 
6efadbc
2684f03
89eff64
107a53b
 
 
1c36c56
80e2bec
bf6e71d
45f8e7d
 
dca6877
3c72947
44664b1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
712c11b
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
 
[]
[]
dados_tokenizados:
 DatasetDict({
    train: Dataset({
        features: ['rotulo', 'rotulo_simples', 'text', 'label', 'input_ids', 'attention_mask'],
        num_rows: 4000
    })
    validation: Dataset({
        features: ['rotulo', 'rotulo_simples', 'text', 'label', 'input_ids', 'attention_mask'],
        num_rows: 1000
    })
    test: Dataset({
        features: ['rotulo', 'rotulo_simples', 'text', 'label', 'input_ids', 'attention_mask'],
        num_rows: 1000
    })
})
/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884
  warnings.warn(
Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert/distilbert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight', 'pre_classifier.bias', 'pre_classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.21834564208984375, 'eval_accuracy': 0.938, 'eval_runtime': 30.3683, 'eval_samples_per_second': 32.929, 'eval_steps_per_second': 2.075, 'epoch': 1.0}
{'loss': 0.2031, 'grad_norm': 1.1480563879013062, 'learning_rate': 1.2e-05, 'epoch': 2.0}
{'eval_loss': 0.19427122175693512, 'eval_accuracy': 0.938, 'eval_runtime': 42.2287, 'eval_samples_per_second': 23.681, 'eval_steps_per_second': 1.492, 'epoch': 2.0}
{'eval_loss': 0.3195326626300812, 'eval_accuracy': 0.921, 'eval_runtime': 26.5577, 'eval_samples_per_second': 37.654, 'eval_steps_per_second': 2.372, 'epoch': 3.0}
{'loss': 0.0672, 'grad_norm': 1.1029362678527832, 'learning_rate': 4.000000000000001e-06, 'epoch': 4.0}
{'eval_loss': 0.36123067140579224, 'eval_accuracy': 0.925, 'eval_runtime': 26.675, 'eval_samples_per_second': 37.488, 'eval_steps_per_second': 2.362, 'epoch': 4.0}
{'eval_loss': 0.3963741362094879, 'eval_accuracy': 0.926, 'eval_runtime': 25.9784, 'eval_samples_per_second': 38.493, 'eval_steps_per_second': 2.425, 'epoch': 5.0}
{'train_runtime': 8026.8642, 'train_samples_per_second': 2.492, 'train_steps_per_second': 0.156, 'train_loss': 0.11480112991333008, 'epoch': 5.0}
Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert/distilbert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight', 'pre_classifier.bias', 'pre_classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert/distilbert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight', 'pre_classifier.bias', 'pre_classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
{'eval_loss': 0.17208045721054077, 'eval_accuracy': 0.939, 'eval_runtime': 40.1609, 'eval_samples_per_second': 24.9, 'eval_steps_per_second': 0.797, 'epoch': 1.0}
{'eval_loss': 0.24476991593837738, 'eval_accuracy': 0.926, 'eval_runtime': 38.171, 'eval_samples_per_second': 26.198, 'eval_steps_per_second': 0.838, 'epoch': 2.0}
{'eval_loss': 0.6838799715042114, 'eval_accuracy': 0.656, 'eval_runtime': 214.6826, 'eval_samples_per_second': 4.658, 'eval_steps_per_second': 0.149, 'epoch': 3.0}
{'loss': 0.2956, 'grad_norm': 2.695140838623047, 'learning_rate': 9.200000000000002e-06, 'epoch': 4.0}
{'eval_loss': 0.31772053241729736, 'eval_accuracy': 0.87, 'eval_runtime': 37.1806, 'eval_samples_per_second': 26.896, 'eval_steps_per_second': 0.861, 'epoch': 4.0}
{'eval_loss': 0.2808445990085602, 'eval_accuracy': 0.932, 'eval_runtime': 37.3397, 'eval_samples_per_second': 26.781, 'eval_steps_per_second': 0.857, 'epoch': 5.0}
{'eval_loss': 0.3926897644996643, 'eval_accuracy': 0.905, 'eval_runtime': 37.6368, 'eval_samples_per_second': 26.57, 'eval_steps_per_second': 0.85, 'epoch': 6.0}
{'eval_loss': 0.37185582518577576, 'eval_accuracy': 0.922, 'eval_runtime': 37.484, 'eval_samples_per_second': 26.678, 'eval_steps_per_second': 0.854, 'epoch': 7.0}
{'loss': 0.1013, 'grad_norm': 0.6478258371353149, 'learning_rate': 8.400000000000001e-06, 'epoch': 8.0}
{'eval_loss': 0.4580109715461731, 'eval_accuracy': 0.91, 'eval_runtime': 38.2702, 'eval_samples_per_second': 26.13, 'eval_steps_per_second': 0.836, 'epoch': 8.0}
{'eval_loss': 0.4977562129497528, 'eval_accuracy': 0.913, 'eval_runtime': 37.7002, 'eval_samples_per_second': 26.525, 'eval_steps_per_second': 0.849, 'epoch': 9.0}
{'eval_loss': 0.4662289023399353, 'eval_accuracy': 0.92, 'eval_runtime': 38.4422, 'eval_samples_per_second': 26.013, 'eval_steps_per_second': 0.832, 'epoch': 10.0}
{'eval_loss': 0.5506279468536377, 'eval_accuracy': 0.901, 'eval_runtime': 37.4907, 'eval_samples_per_second': 26.673, 'eval_steps_per_second': 0.854, 'epoch': 11.0}
{'loss': 0.0442, 'grad_norm': 0.6364777684211731, 'learning_rate': 7.600000000000001e-06, 'epoch': 12.0}
{'eval_loss': 0.578902006149292, 'eval_accuracy': 0.903, 'eval_runtime': 38.2969, 'eval_samples_per_second': 26.112, 'eval_steps_per_second': 0.836, 'epoch': 12.0}
{'eval_loss': 0.47741687297821045, 'eval_accuracy': 0.92, 'eval_runtime': 37.7268, 'eval_samples_per_second': 26.506, 'eval_steps_per_second': 0.848, 'epoch': 13.0}
{'eval_loss': 0.5484298467636108, 'eval_accuracy': 0.894, 'eval_runtime': 38.013, 'eval_samples_per_second': 26.307, 'eval_steps_per_second': 0.842, 'epoch': 14.0}
{'eval_loss': 0.538878321647644, 'eval_accuracy': 0.909, 'eval_runtime': 38.0368, 'eval_samples_per_second': 26.29, 'eval_steps_per_second': 0.841, 'epoch': 15.0}
{'loss': 0.0268, 'grad_norm': 20.58578109741211, 'learning_rate': 6.800000000000001e-06, 'epoch': 16.0}
{'eval_loss': 0.49775975942611694, 'eval_accuracy': 0.921, 'eval_runtime': 37.3442, 'eval_samples_per_second': 26.778, 'eval_steps_per_second': 0.857, 'epoch': 16.0}
{'eval_loss': 0.5782524347305298, 'eval_accuracy': 0.909, 'eval_runtime': 38.4136, 'eval_samples_per_second': 26.032, 'eval_steps_per_second': 0.833, 'epoch': 17.0}
{'eval_loss': 0.5907241106033325, 'eval_accuracy': 0.901, 'eval_runtime': 37.9133, 'eval_samples_per_second': 26.376, 'eval_steps_per_second': 0.844, 'epoch': 18.0}
{'eval_loss': 0.517770528793335, 'eval_accuracy': 0.917, 'eval_runtime': 37.8369, 'eval_samples_per_second': 26.429, 'eval_steps_per_second': 0.846, 'epoch': 19.0}
{'loss': 0.0187, 'grad_norm': 0.01947682909667492, 'learning_rate': 6e-06, 'epoch': 20.0}
{'eval_loss': 0.5195603966712952, 'eval_accuracy': 0.92, 'eval_runtime': 37.9909, 'eval_samples_per_second': 26.322, 'eval_steps_per_second': 0.842, 'epoch': 20.0}
{'eval_loss': 0.8739770650863647, 'eval_accuracy': 0.617, 'eval_runtime': 213.6265, 'eval_samples_per_second': 4.681, 'eval_steps_per_second': 0.15, 'epoch': 21.0}
{'eval_loss': 0.633865237236023, 'eval_accuracy': 0.901, 'eval_runtime': 38.1393, 'eval_samples_per_second': 26.22, 'eval_steps_per_second': 0.839, 'epoch': 22.0}
{'eval_loss': 0.5776236653327942, 'eval_accuracy': 0.92, 'eval_runtime': 38.5846, 'eval_samples_per_second': 25.917, 'eval_steps_per_second': 0.829, 'epoch': 23.0}
wandb: Network error (SSLError), entering retry loop.
{'loss': 0.0549, 'grad_norm': 0.032662052661180496, 'learning_rate': 5.2e-06, 'epoch': 24.0}
{'eval_loss': 0.6649676561355591, 'eval_accuracy': 0.907, 'eval_runtime': 38.4215, 'eval_samples_per_second': 26.027, 'eval_steps_per_second': 0.833, 'epoch': 24.0}
{'eval_loss': 0.6898632645606995, 'eval_accuracy': 0.9, 'eval_runtime': 38.2884, 'eval_samples_per_second': 26.118, 'eval_steps_per_second': 0.836, 'epoch': 25.0}
{'eval_loss': 0.7331468462944031, 'eval_accuracy': 0.9, 'eval_runtime': 37.8445, 'eval_samples_per_second': 26.424, 'eval_steps_per_second': 0.846, 'epoch': 26.0}
{'eval_loss': 0.8004008531570435, 'eval_accuracy': 0.891, 'eval_runtime': 37.8178, 'eval_samples_per_second': 26.443, 'eval_steps_per_second': 0.846, 'epoch': 27.0}
{'loss': 0.0101, 'grad_norm': 0.0740148276090622, 'learning_rate': 4.4e-06, 'epoch': 28.0}
{'eval_loss': 0.7997801303863525, 'eval_accuracy': 0.897, 'eval_runtime': 38.1717, 'eval_samples_per_second': 26.197, 'eval_steps_per_second': 0.838, 'epoch': 28.0}
{'eval_loss': 0.7122868895530701, 'eval_accuracy': 0.903, 'eval_runtime': 38.0461, 'eval_samples_per_second': 26.284, 'eval_steps_per_second': 0.841, 'epoch': 29.0}
{'eval_loss': 0.7891318798065186, 'eval_accuracy': 0.9, 'eval_runtime': 37.564, 'eval_samples_per_second': 26.621, 'eval_steps_per_second': 0.852, 'epoch': 30.0}
{'eval_loss': 0.6890597343444824, 'eval_accuracy': 0.903, 'eval_runtime': 51.1931, 'eval_samples_per_second': 19.534, 'eval_steps_per_second': 0.625, 'epoch': 31.0}
{'loss': 0.0089, 'grad_norm': 0.007422878406941891, 'learning_rate': 3.6000000000000003e-06, 'epoch': 32.0}
{'eval_loss': 0.6430081129074097, 'eval_accuracy': 0.912, 'eval_runtime': 38.3463, 'eval_samples_per_second': 26.078, 'eval_steps_per_second': 0.835, 'epoch': 32.0}
{'eval_loss': 0.6644126176834106, 'eval_accuracy': 0.912, 'eval_runtime': 37.0865, 'eval_samples_per_second': 26.964, 'eval_steps_per_second': 0.863, 'epoch': 33.0}
{'eval_loss': 0.6276940703392029, 'eval_accuracy': 0.914, 'eval_runtime': 37.8123, 'eval_samples_per_second': 26.446, 'eval_steps_per_second': 0.846, 'epoch': 34.0}
{'eval_loss': 0.6321740746498108, 'eval_accuracy': 0.917, 'eval_runtime': 50.725, 'eval_samples_per_second': 19.714, 'eval_steps_per_second': 0.631, 'epoch': 35.0}
{'loss': 0.0078, 'grad_norm': 0.00712945219129324, 'learning_rate': 2.8000000000000003e-06, 'epoch': 36.0}
{'eval_loss': 0.7095584869384766, 'eval_accuracy': 0.908, 'eval_runtime': 37.1239, 'eval_samples_per_second': 26.937, 'eval_steps_per_second': 0.862, 'epoch': 36.0}
{'eval_loss': 0.649186909198761, 'eval_accuracy': 0.911, 'eval_runtime': 37.5593, 'eval_samples_per_second': 26.625, 'eval_steps_per_second': 0.852, 'epoch': 37.0}
{'eval_loss': 0.6124615669250488, 'eval_accuracy': 0.915, 'eval_runtime': 41.4101, 'eval_samples_per_second': 24.149, 'eval_steps_per_second': 0.773, 'epoch': 38.0}
{'eval_loss': 0.7363823056221008, 'eval_accuracy': 0.904, 'eval_runtime': 47.3084, 'eval_samples_per_second': 21.138, 'eval_steps_per_second': 0.676, 'epoch': 39.0}
{'loss': 0.0054, 'grad_norm': 0.013953677378594875, 'learning_rate': 2.0000000000000003e-06, 'epoch': 40.0}
{'eval_loss': 0.6578059196472168, 'eval_accuracy': 0.913, 'eval_runtime': 37.731, 'eval_samples_per_second': 26.503, 'eval_steps_per_second': 0.848, 'epoch': 40.0}
{'eval_loss': 0.7589854598045349, 'eval_accuracy': 0.906, 'eval_runtime': 37.3152, 'eval_samples_per_second': 26.799, 'eval_steps_per_second': 0.858, 'epoch': 41.0}
{'eval_loss': 0.7142490744590759, 'eval_accuracy': 0.906, 'eval_runtime': 37.6936, 'eval_samples_per_second': 26.53, 'eval_steps_per_second': 0.849, 'epoch': 42.0}
{'eval_loss': 0.759125292301178, 'eval_accuracy': 0.903, 'eval_runtime': 37.463, 'eval_samples_per_second': 26.693, 'eval_steps_per_second': 0.854, 'epoch': 43.0}
{'loss': 0.0049, 'grad_norm': 0.007690785452723503, 'learning_rate': 1.2000000000000002e-06, 'epoch': 44.0}
{'eval_loss': 0.6526206731796265, 'eval_accuracy': 0.917, 'eval_runtime': 37.8543, 'eval_samples_per_second': 26.417, 'eval_steps_per_second': 0.845, 'epoch': 44.0}
{'eval_loss': 0.6948218941688538, 'eval_accuracy': 0.909, 'eval_runtime': 37.9107, 'eval_samples_per_second': 26.378, 'eval_steps_per_second': 0.844, 'epoch': 45.0}
{'eval_loss': 0.7213398218154907, 'eval_accuracy': 0.907, 'eval_runtime': 38.4455, 'eval_samples_per_second': 26.011, 'eval_steps_per_second': 0.832, 'epoch': 46.0}
{'eval_loss': 0.6751002669334412, 'eval_accuracy': 0.913, 'eval_runtime': 38.6152, 'eval_samples_per_second': 25.897, 'eval_steps_per_second': 0.829, 'epoch': 47.0}
{'loss': 0.0058, 'grad_norm': 0.0415799506008625, 'learning_rate': 4.0000000000000003e-07, 'epoch': 48.0}