Hugging Face's logo

gokuls
/
mobilebert_add_GLUE_Experiment_sst2_256

Text Classification
Transformers
PyTorch
TensorBoard
English
mobilebert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mobilebert_add_GLUE_Experiment_sst2_256
File size: 2,797 Bytes 
adf4e70
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.6813856959342957,
  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_sst2_256/checkpoint-527",
  "epoch": 6.0,
  "global_step": 3162,
  "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": 0.6662,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5561926605504587,
      "eval_loss": 0.6813856959342957,
      "eval_runtime": 1.5529,
      "eval_samples_per_second": 561.531,
      "eval_steps_per_second": 4.508,
      "step": 527
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.8e-05,
      "loss": 0.5954,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5493119266055045,
      "eval_loss": 0.7089729905128479,
      "eval_runtime": 1.5587,
      "eval_samples_per_second": 559.425,
      "eval_steps_per_second": 4.491,
      "step": 1054
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.7e-05,
      "loss": 0.5689,
      "step": 1581
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5596330275229358,
      "eval_loss": 0.715036153793335,
      "eval_runtime": 1.6372,
      "eval_samples_per_second": 532.618,
      "eval_steps_per_second": 4.276,
      "step": 1581
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.5546,
      "step": 2108
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5538990825688074,
      "eval_loss": 0.6892502307891846,
      "eval_runtime": 1.5477,
      "eval_samples_per_second": 563.399,
      "eval_steps_per_second": 4.523,
      "step": 2108
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.5e-05,
      "loss": 0.5473,
      "step": 2635
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5871559633027523,
      "eval_loss": 0.7050522565841675,
      "eval_runtime": 1.5988,
      "eval_samples_per_second": 545.394,
      "eval_steps_per_second": 4.378,
      "step": 2635
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.5421,
      "step": 3162
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5871559633027523,
      "eval_loss": 0.69826340675354,
      "eval_runtime": 1.5749,
      "eval_samples_per_second": 553.7,
      "eval_steps_per_second": 4.445,
      "step": 3162
    },
    {
      "epoch": 6.0,
      "step": 3162,
      "total_flos": 1.0415609493848064e+16,
      "train_loss": 0.5790761504876017,
      "train_runtime": 2176.4824,
      "train_samples_per_second": 1547.198,
      "train_steps_per_second": 12.107
    }
  ],
  "max_steps": 26350,
  "num_train_epochs": 50,
  "total_flos": 1.0415609493848064e+16,
  "trial_name": null,
  "trial_params": null
}