Hugging Face's logo

Hartunka
/
tiny_bert_km_5_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_5_v1_wnli
File size: 3,615 Bytes
4e80cf8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.7231789231300354,
  "best_model_checkpoint": "tiny_bert_km_5_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": 0.9462671875953674,
      "learning_rate": 4.9e-05,
      "loss": 0.7063,
      "step": 3
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.39436619718309857,
      "eval_loss": 0.7231789231300354,
      "eval_runtime": 0.0292,
      "eval_samples_per_second": 2435.099,
      "eval_steps_per_second": 34.297,
      "step": 3
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.0501408576965332,
      "learning_rate": 4.8e-05,
      "loss": 0.702,
      "step": 6
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4647887323943662,
      "eval_loss": 0.7265077233314514,
      "eval_runtime": 0.0349,
      "eval_samples_per_second": 2033.067,
      "eval_steps_per_second": 28.635,
      "step": 6
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8395664095878601,
      "learning_rate": 4.7e-05,
      "loss": 0.6959,
      "step": 9
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.29577464788732394,
      "eval_loss": 0.7417474985122681,
      "eval_runtime": 0.0347,
      "eval_samples_per_second": 2048.268,
      "eval_steps_per_second": 28.849,
      "step": 9
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.6460738182067871,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.6927,
      "step": 12
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.2535211267605634,
      "eval_loss": 0.7537961006164551,
      "eval_runtime": 0.0325,
      "eval_samples_per_second": 2181.573,
      "eval_steps_per_second": 30.726,
      "step": 12
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.7992274761199951,
      "learning_rate": 4.5e-05,
      "loss": 0.6946,
      "step": 15
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.22535211267605634,
      "eval_loss": 0.760233461856842,
      "eval_runtime": 0.0292,
      "eval_samples_per_second": 2427.497,
      "eval_steps_per_second": 34.19,
      "step": 15
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7142523527145386,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6829,
      "step": 18
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.2112676056338028,
      "eval_loss": 0.7708516120910645,
      "eval_runtime": 0.0295,
      "eval_samples_per_second": 2410.285,
      "eval_steps_per_second": 33.948,
      "step": 18
    },
    {
      "epoch": 6.0,
      "step": 18,
      "total_flos": 99911832606720.0,
      "train_loss": 0.695737878481547,
      "train_runtime": 6.5593,
      "train_samples_per_second": 4840.435,
      "train_steps_per_second": 22.868
    }
  ],
  "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
}