Hugging Face's logo

Hartunka
/
bert_base_km_5_v2_cola

Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
Metrics Community
bert_base_km_5_v2_cola
File size: 4,388 Bytes
95ae23a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
 
{
  "best_global_step": 68,
  "best_metric": 0.610907256603241,
  "best_model_checkpoint": "bert_base_km_5_v2_cola/checkpoint-68",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 238,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.8859699964523315,
      "learning_rate": 4.9e-05,
      "loss": 0.6153,
      "step": 34
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 0.6196200251579285,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.6905,
      "eval_samples_per_second": 1510.588,
      "eval_steps_per_second": 7.242,
      "step": 34
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.576741099357605,
      "learning_rate": 4.8e-05,
      "loss": 0.5911,
      "step": 68
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6864812970161438,
      "eval_loss": 0.610907256603241,
      "eval_matthews_correlation": 0.006434621036303265,
      "eval_runtime": 0.707,
      "eval_samples_per_second": 1475.242,
      "eval_steps_per_second": 7.072,
      "step": 68
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.2591376304626465,
      "learning_rate": 4.7e-05,
      "loss": 0.5354,
      "step": 102
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6816874146461487,
      "eval_loss": 0.6186987161636353,
      "eval_matthews_correlation": 0.06958362417408409,
      "eval_runtime": 0.6766,
      "eval_samples_per_second": 1541.478,
      "eval_steps_per_second": 7.39,
      "step": 102
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.7871906757354736,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.4723,
      "step": 136
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6586769223213196,
      "eval_loss": 0.6894361972808838,
      "eval_matthews_correlation": 0.0819224208673349,
      "eval_runtime": 0.662,
      "eval_samples_per_second": 1575.441,
      "eval_steps_per_second": 7.552,
      "step": 136
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.169605016708374,
      "learning_rate": 4.5e-05,
      "loss": 0.4026,
      "step": 170
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6577181220054626,
      "eval_loss": 0.7197646498680115,
      "eval_matthews_correlation": 0.12428013934170246,
      "eval_runtime": 0.7117,
      "eval_samples_per_second": 1465.447,
      "eval_steps_per_second": 7.025,
      "step": 170
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.733868360519409,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.3374,
      "step": 204
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6347075700759888,
      "eval_loss": 0.7933048009872437,
      "eval_matthews_correlation": 0.1072591766108324,
      "eval_runtime": 0.6674,
      "eval_samples_per_second": 1562.878,
      "eval_steps_per_second": 7.492,
      "step": 204
    },
    {
      "epoch": 7.0,
      "grad_norm": 4.486270427703857,
      "learning_rate": 4.3e-05,
      "loss": 0.2903,
      "step": 238
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6366251111030579,
      "eval_loss": 0.9325408935546875,
      "eval_matthews_correlation": 0.09472138771242544,
      "eval_runtime": 0.6742,
      "eval_samples_per_second": 1547.052,
      "eval_steps_per_second": 7.416,
      "step": 238
    },
    {
      "epoch": 7.0,
      "step": 238,
      "total_flos": 7874519220341760.0,
      "train_loss": 0.4634779841959977,
      "train_runtime": 117.537,
      "train_samples_per_second": 3637.579,
      "train_steps_per_second": 14.464
    }
  ],
  "logging_steps": 1,
  "max_steps": 1700,
  "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": 7874519220341760.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}