Hugging Face's logo

Hartunka
/
tiny_bert_rand_50_v2_qqp

Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
Metrics Community
tiny_bert_rand_50_v2_qqp
File size: 4,668 Bytes
945dc34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
173
174
175
176
177
178
179
 
{
  "best_global_step": 2844,
  "best_metric": 0.42420217394828796,
  "best_model_checkpoint": "tiny_bert_rand_50_v2_qqp/checkpoint-2844",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 9954,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.624103307723999,
      "learning_rate": 4.9e-05,
      "loss": 0.4957,
      "step": 1422
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7809300024734108,
      "eval_combined_score": 0.7270215614876743,
      "eval_f1": 0.6731131205019376,
      "eval_loss": 0.4535508453845978,
      "eval_runtime": 11.7106,
      "eval_samples_per_second": 3452.424,
      "eval_steps_per_second": 13.492,
      "step": 1422
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.412515163421631,
      "learning_rate": 4.8e-05,
      "loss": 0.4098,
      "step": 2844
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8002226069750186,
      "eval_combined_score": 0.7547840157117707,
      "eval_f1": 0.7093454244485228,
      "eval_loss": 0.42420217394828796,
      "eval_runtime": 11.4883,
      "eval_samples_per_second": 3519.22,
      "eval_steps_per_second": 13.753,
      "step": 2844
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.119178533554077,
      "learning_rate": 4.7e-05,
      "loss": 0.3539,
      "step": 4266
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8104377937175364,
      "eval_combined_score": 0.7727062749623714,
      "eval_f1": 0.7349747562072065,
      "eval_loss": 0.4246242642402649,
      "eval_runtime": 11.8603,
      "eval_samples_per_second": 3408.855,
      "eval_steps_per_second": 13.322,
      "step": 4266
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.7941720485687256,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.3091,
      "step": 5688
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8165718525847143,
      "eval_combined_score": 0.7736160635771687,
      "eval_f1": 0.730660274569623,
      "eval_loss": 0.435099333524704,
      "eval_runtime": 11.4817,
      "eval_samples_per_second": 3521.267,
      "eval_steps_per_second": 13.761,
      "step": 5688
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.839110851287842,
      "learning_rate": 4.5e-05,
      "loss": 0.272,
      "step": 7110
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8204303734850359,
      "eval_combined_score": 0.7880094232089871,
      "eval_f1": 0.7555884729329383,
      "eval_loss": 0.43761980533599854,
      "eval_runtime": 11.4705,
      "eval_samples_per_second": 3524.709,
      "eval_steps_per_second": 13.775,
      "step": 7110
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.09541654586792,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.2409,
      "step": 8532
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8220133564185012,
      "eval_combined_score": 0.7904060212406911,
      "eval_f1": 0.7587986860628813,
      "eval_loss": 0.4505470395088196,
      "eval_runtime": 11.4624,
      "eval_samples_per_second": 3527.198,
      "eval_steps_per_second": 13.784,
      "step": 8532
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.9798851013183594,
      "learning_rate": 4.3e-05,
      "loss": 0.2152,
      "step": 9954
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8274795943606233,
      "eval_combined_score": 0.7946189856217504,
      "eval_f1": 0.7617583768828774,
      "eval_loss": 0.49352139234542847,
      "eval_runtime": 11.4875,
      "eval_samples_per_second": 3519.465,
      "eval_steps_per_second": 13.754,
      "step": 9954
    },
    {
      "epoch": 7.0,
      "step": 9954,
      "total_flos": 6.678940801217126e+16,
      "train_loss": 0.32807474441022455,
      "train_runtime": 1407.977,
      "train_samples_per_second": 12920.879,
      "train_steps_per_second": 50.498
    }
  ],
  "logging_steps": 1,
  "max_steps": 71100,
  "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": 6.678940801217126e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}