Hugging Face's logo

Hartunka
/
tiny_bert_km_20_v1_wnli

Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
Metrics Community
tiny_bert_km_20_v1_wnli
File size: 3,613 Bytes
a0e5c38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
142
143
144
145
146
147
148
149
 
{
  "best_global_step": 3,
  "best_metric": 0.7005943655967712,
  "best_model_checkpoint": "tiny_bert_km_20_v1_wnli/checkpoint-3",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.0073267221450806,
      "learning_rate": 4.9e-05,
      "loss": 0.7048,
      "step": 3
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.49295774647887325,
      "eval_loss": 0.7005943655967712,
      "eval_runtime": 0.0315,
      "eval_samples_per_second": 2256.386,
      "eval_steps_per_second": 31.78,
      "step": 3
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7369723320007324,
      "learning_rate": 4.8e-05,
      "loss": 0.6988,
      "step": 6
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5211267605633803,
      "eval_loss": 0.702409565448761,
      "eval_runtime": 0.0376,
      "eval_samples_per_second": 1889.338,
      "eval_steps_per_second": 26.61,
      "step": 6
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6635440587997437,
      "learning_rate": 4.7e-05,
      "loss": 0.6961,
      "step": 9
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.29577464788732394,
      "eval_loss": 0.7241968512535095,
      "eval_runtime": 0.0661,
      "eval_samples_per_second": 1074.38,
      "eval_steps_per_second": 15.132,
      "step": 9
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.6906999945640564,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.6903,
      "step": 12
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.30985915492957744,
      "eval_loss": 0.731184184551239,
      "eval_runtime": 0.0413,
      "eval_samples_per_second": 1720.884,
      "eval_steps_per_second": 24.238,
      "step": 12
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.9729248285293579,
      "learning_rate": 4.5e-05,
      "loss": 0.692,
      "step": 15
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3380281690140845,
      "eval_loss": 0.7305235266685486,
      "eval_runtime": 0.0312,
      "eval_samples_per_second": 2274.238,
      "eval_steps_per_second": 32.032,
      "step": 15
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7727306485176086,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6949,
      "step": 18
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.2676056338028169,
      "eval_loss": 0.7371810078620911,
      "eval_runtime": 0.0301,
      "eval_samples_per_second": 2357.955,
      "eval_steps_per_second": 33.211,
      "step": 18
    },
    {
      "epoch": 6.0,
      "step": 18,
      "total_flos": 99911832606720.0,
      "train_loss": 0.696158250172933,
      "train_runtime": 6.7636,
      "train_samples_per_second": 4694.268,
      "train_steps_per_second": 22.178
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 99911832606720.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}