Hugging Face's logo

wyluilipe
/
ggqqgqgqgb

Text Classification
Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
ggqqgqgqgb
File size: 3,914 Bytes 
aa3a886
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
 
{
  "best_metric": 0.9008125554721984,
  "best_model_checkpoint": "rubert_classification/checkpoint-3500",
  "epoch": 1.674641148325359,
  "eval_steps": 500,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24,
      "eval_accuracy": 0.7823053307284399,
      "eval_f1": 0.7752692727748154,
      "eval_loss": 0.6053181886672974,
      "eval_precision": 0.7849961270931392,
      "eval_recall": 0.7823053307284399,
      "eval_runtime": 38.9969,
      "eval_samples_per_second": 183.758,
      "eval_steps_per_second": 11.488,
      "step": 500
    },
    {
      "epoch": 0.29,
      "grad_norm": 22.682289123535156,
      "learning_rate": 4.975490196078432e-05,
      "loss": 0.9433,
      "step": 600
    },
    {
      "epoch": 0.48,
      "eval_accuracy": 0.8368685459112476,
      "eval_f1": 0.8330214371969107,
      "eval_loss": 0.46620890498161316,
      "eval_precision": 0.840415327990016,
      "eval_recall": 0.8368685459112476,
      "eval_runtime": 36.1817,
      "eval_samples_per_second": 198.056,
      "eval_steps_per_second": 12.382,
      "step": 1000
    },
    {
      "epoch": 0.57,
      "grad_norm": 12.139711380004883,
      "learning_rate": 4.82843137254902e-05,
      "loss": 0.5182,
      "step": 1200
    },
    {
      "epoch": 0.72,
      "eval_accuracy": 0.8428691041027072,
      "eval_f1": 0.8319455570081821,
      "eval_loss": 0.4372938573360443,
      "eval_precision": 0.8395761804457677,
      "eval_recall": 0.8428691041027072,
      "eval_runtime": 35.6356,
      "eval_samples_per_second": 201.091,
      "eval_steps_per_second": 12.572,
      "step": 1500
    },
    {
      "epoch": 0.86,
      "grad_norm": 37.54426574707031,
      "learning_rate": 4.681372549019608e-05,
      "loss": 0.4508,
      "step": 1800
    },
    {
      "epoch": 0.96,
      "eval_accuracy": 0.8644990231649455,
      "eval_f1": 0.8633019943338417,
      "eval_loss": 0.39909306168556213,
      "eval_precision": 0.8707480255460968,
      "eval_recall": 0.8644990231649455,
      "eval_runtime": 35.6445,
      "eval_samples_per_second": 201.041,
      "eval_steps_per_second": 12.569,
      "step": 2000
    },
    {
      "epoch": 1.15,
      "grad_norm": 3.496920108795166,
      "learning_rate": 4.5343137254901966e-05,
      "loss": 0.3875,
      "step": 2400
    },
    {
      "epoch": 1.2,
      "eval_accuracy": 0.8898967345799609,
      "eval_f1": 0.8875919037418019,
      "eval_loss": 0.33941856026649475,
      "eval_precision": 0.8906320921346105,
      "eval_recall": 0.8898967345799609,
      "eval_runtime": 35.5422,
      "eval_samples_per_second": 201.619,
      "eval_steps_per_second": 12.605,
      "step": 2500
    },
    {
      "epoch": 1.44,
      "grad_norm": 16.364843368530273,
      "learning_rate": 4.387254901960784e-05,
      "loss": 0.3401,
      "step": 3000
    },
    {
      "epoch": 1.44,
      "eval_accuracy": 0.8869662294166899,
      "eval_f1": 0.8851872123624062,
      "eval_loss": 0.3447243273258209,
      "eval_precision": 0.8869707495957468,
      "eval_recall": 0.8869662294166899,
      "eval_runtime": 35.7225,
      "eval_samples_per_second": 200.602,
      "eval_steps_per_second": 12.541,
      "step": 3000
    },
    {
      "epoch": 1.67,
      "eval_accuracy": 0.9016187552330449,
      "eval_f1": 0.9008125554721984,
      "eval_loss": 0.325568288564682,
      "eval_precision": 0.9021842242763984,
      "eval_recall": 0.9016187552330449,
      "eval_runtime": 35.7388,
      "eval_samples_per_second": 200.51,
      "eval_steps_per_second": 12.535,
      "step": 3500
    }
  ],
  "logging_steps": 600,
  "max_steps": 20900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1640277252096000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}