Hugging Face's logo

HikasaHana
/
BERT-WMM

Text Classification
Transformers
TensorBoard
Safetensors
Chinese
bert
Inference Endpoints
Model card Files Metrics Community
BERT-WMM
File size: 3,098 Bytes 
08db824
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.6369415521621704,
  "best_model_checkpoint": "BERT-WMM/run-0/checkpoint-533",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 3198,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.94,
      "grad_norm": 11.681629180908203,
      "learning_rate": 2.5842410540171958e-05,
      "loss": 0.7181,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7525821596244131,
      "eval_loss": 0.6369415521621704,
      "eval_runtime": 1.9836,
      "eval_samples_per_second": 1073.792,
      "eval_steps_per_second": 67.553,
      "step": 533
    },
    {
      "epoch": 1.88,
      "grad_norm": 6.492458820343018,
      "learning_rate": 2.1053231418568556e-05,
      "loss": 0.4571,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7497652582159624,
      "eval_loss": 0.6769182682037354,
      "eval_runtime": 2.0259,
      "eval_samples_per_second": 1051.385,
      "eval_steps_per_second": 66.144,
      "step": 1066
    },
    {
      "epoch": 2.81,
      "grad_norm": 13.743987083435059,
      "learning_rate": 1.626405229696515e-05,
      "loss": 0.2889,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7596244131455399,
      "eval_loss": 0.8726277351379395,
      "eval_runtime": 2.0636,
      "eval_samples_per_second": 1032.174,
      "eval_steps_per_second": 64.935,
      "step": 1599
    },
    {
      "epoch": 3.75,
      "grad_norm": 31.317466735839844,
      "learning_rate": 1.147487317536175e-05,
      "loss": 0.1815,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7572769953051643,
      "eval_loss": 1.311642050743103,
      "eval_runtime": 2.081,
      "eval_samples_per_second": 1023.549,
      "eval_steps_per_second": 64.392,
      "step": 2132
    },
    {
      "epoch": 4.69,
      "grad_norm": 0.05295910686254501,
      "learning_rate": 6.685694053758349e-06,
      "loss": 0.1073,
      "step": 2500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7610328638497652,
      "eval_loss": 1.4908134937286377,
      "eval_runtime": 2.0562,
      "eval_samples_per_second": 1035.88,
      "eval_steps_per_second": 65.168,
      "step": 2665
    },
    {
      "epoch": 5.63,
      "grad_norm": 0.06595510989427567,
      "learning_rate": 1.896514932154947e-06,
      "loss": 0.045,
      "step": 3000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7591549295774648,
      "eval_loss": 1.5977472066879272,
      "eval_runtime": 2.0716,
      "eval_samples_per_second": 1028.204,
      "eval_steps_per_second": 64.685,
      "step": 3198
    }
  ],
  "logging_steps": 500,
  "max_steps": 3198,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "total_flos": 1014949731017880.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 3.063158966177536e-05,
    "num_train_epochs": 6,
    "per_device_train_batch_size": 16,
    "weight_decay": 2.6426532465921284e-05
  }
}