Hugging Face's logo

gokuls
/
mobilebert_sa_GLUE_Experiment_wnli

Text Classification
Transformers
PyTorch
TensorBoard
English
mobilebert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mobilebert_sa_GLUE_Experiment_wnli
File size: 2,747 Bytes 
120e0d1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.6894944310188293,
  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_wnli/checkpoint-5",
  "epoch": 6.0,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.9e-05,
      "loss": 0.6956,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5633802816901409,
      "eval_loss": 0.6894944310188293,
      "eval_runtime": 0.1314,
      "eval_samples_per_second": 540.311,
      "eval_steps_per_second": 7.61,
      "step": 5
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.8e-05,
      "loss": 0.6944,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.43661971830985913,
      "eval_loss": 0.6944735050201416,
      "eval_runtime": 0.1308,
      "eval_samples_per_second": 542.667,
      "eval_steps_per_second": 7.643,
      "step": 10
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.7e-05,
      "loss": 0.6937,
      "step": 15
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.43661971830985913,
      "eval_loss": 0.6946936845779419,
      "eval_runtime": 0.1297,
      "eval_samples_per_second": 547.408,
      "eval_steps_per_second": 7.71,
      "step": 15
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.693,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5633802816901409,
      "eval_loss": 0.6914201378822327,
      "eval_runtime": 0.1315,
      "eval_samples_per_second": 540.072,
      "eval_steps_per_second": 7.607,
      "step": 20
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.5e-05,
      "loss": 0.693,
      "step": 25
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5633802816901409,
      "eval_loss": 0.6898038387298584,
      "eval_runtime": 0.1293,
      "eval_samples_per_second": 549.119,
      "eval_steps_per_second": 7.734,
      "step": 25
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6932,
      "step": 30
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5633802816901409,
      "eval_loss": 0.6900650858879089,
      "eval_runtime": 0.1293,
      "eval_samples_per_second": 549.18,
      "eval_steps_per_second": 7.735,
      "step": 30
    },
    {
      "epoch": 6.0,
      "step": 30,
      "total_flos": 119459738025984.0,
      "train_loss": 0.6938152154286702,
      "train_runtime": 47.698,
      "train_samples_per_second": 665.646,
      "train_steps_per_second": 5.241
    }
  ],
  "max_steps": 250,
  "num_train_epochs": 50,
  "total_flos": 119459738025984.0,
  "trial_name": null,
  "trial_params": null
}