Hugging Face's logo

joseph10
/
tinybert-toxigen-bothpretrained

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
tinybert-toxigen-bothpretrained
File size: 2,807 Bytes 
fa4b305
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.3621212121212121,
  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-2\\checkpoint-55",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 330,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 1.5441792724155395e-05,
      "loss": 0.036,
      "step": 55
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3621212121212121,
      "eval_loss": 0.035133831202983856,
      "eval_runtime": 3.3771,
      "eval_samples_per_second": 586.31,
      "eval_steps_per_second": 4.738,
      "step": 55
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.286816060346283e-05,
      "loss": 0.0354,
      "step": 110
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3621212121212121,
      "eval_loss": 0.0350903756916523,
      "eval_runtime": 3.3705,
      "eval_samples_per_second": 587.442,
      "eval_steps_per_second": 4.747,
      "step": 110
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.0294528482770263e-05,
      "loss": 0.0353,
      "step": 165
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3621212121212121,
      "eval_loss": 0.03502834588289261,
      "eval_runtime": 3.355,
      "eval_samples_per_second": 590.167,
      "eval_steps_per_second": 4.769,
      "step": 165
    },
    {
      "epoch": 4.0,
      "learning_rate": 7.720896362077698e-06,
      "loss": 0.0353,
      "step": 220
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3621212121212121,
      "eval_loss": 0.035031162202358246,
      "eval_runtime": 3.3196,
      "eval_samples_per_second": 596.459,
      "eval_steps_per_second": 4.82,
      "step": 220
    },
    {
      "epoch": 5.0,
      "learning_rate": 5.1472642413851315e-06,
      "loss": 0.0352,
      "step": 275
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3621212121212121,
      "eval_loss": 0.03497819975018501,
      "eval_runtime": 3.3426,
      "eval_samples_per_second": 592.36,
      "eval_steps_per_second": 4.787,
      "step": 275
    },
    {
      "epoch": 6.0,
      "learning_rate": 2.5736321206925658e-06,
      "loss": 0.0352,
      "step": 330
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3621212121212121,
      "eval_loss": 0.03496537730097771,
      "eval_runtime": 3.3354,
      "eval_samples_per_second": 593.638,
      "eval_steps_per_second": 4.797,
      "step": 330
    }
  ],
  "logging_steps": 500,
  "max_steps": 385,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 5049471335040.0,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.04724864888100444,
    "learning_rate": 1.801542484484796e-05,
    "num_train_epochs": 7,
    "temperature": 8
  }
}