Hugging Face's logo

Hartunka
/
bert_base_rand_100_v1_stsb

Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
Metrics Community
bert_base_rand_100_v1_stsb
File size: 4,671 Bytes
23d8e6f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 46,
  "best_metric": 2.2721331119537354,
  "best_model_checkpoint": "bert_base_rand_100_v1_stsb/checkpoint-46",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 161,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.593254566192627,
      "learning_rate": 4.9e-05,
      "loss": 2.928,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.09373118085152038,
      "eval_loss": 2.4646432399749756,
      "eval_pearson": 0.09729602347430324,
      "eval_runtime": 1.0234,
      "eval_samples_per_second": 1465.672,
      "eval_spearmanr": 0.09016633822873751,
      "eval_steps_per_second": 5.863,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 9.706378936767578,
      "learning_rate": 4.8e-05,
      "loss": 1.9606,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.15897164929602992,
      "eval_loss": 2.2721331119537354,
      "eval_pearson": 0.1714444402412414,
      "eval_runtime": 0.9742,
      "eval_samples_per_second": 1539.784,
      "eval_spearmanr": 0.1464988583508184,
      "eval_steps_per_second": 6.159,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.275521278381348,
      "learning_rate": 4.7e-05,
      "loss": 1.6768,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.22735907820663778,
      "eval_loss": 2.3988537788391113,
      "eval_pearson": 0.22905661681057854,
      "eval_runtime": 0.9526,
      "eval_samples_per_second": 1574.702,
      "eval_spearmanr": 0.22566153960269703,
      "eval_steps_per_second": 6.299,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 15.667533874511719,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.3265,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.27087084601106837,
      "eval_loss": 2.473294496536255,
      "eval_pearson": 0.26928292870373316,
      "eval_runtime": 0.9818,
      "eval_samples_per_second": 1527.807,
      "eval_spearmanr": 0.27245876331840363,
      "eval_steps_per_second": 6.111,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 12.131975173950195,
      "learning_rate": 4.5e-05,
      "loss": 1.0076,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.24535384308215563,
      "eval_loss": 2.8601512908935547,
      "eval_pearson": 0.24502840732804015,
      "eval_runtime": 0.9804,
      "eval_samples_per_second": 1530.057,
      "eval_spearmanr": 0.2456792788362711,
      "eval_steps_per_second": 6.12,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 9.518048286437988,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.7949,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.2624430834646961,
      "eval_loss": 2.748502254486084,
      "eval_pearson": 0.2605689404882653,
      "eval_runtime": 1.0011,
      "eval_samples_per_second": 1498.382,
      "eval_spearmanr": 0.2643172264411269,
      "eval_steps_per_second": 5.994,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 10.415647506713867,
      "learning_rate": 4.3e-05,
      "loss": 0.626,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.2801360597793442,
      "eval_loss": 2.5590381622314453,
      "eval_pearson": 0.27921912329238546,
      "eval_runtime": 0.9848,
      "eval_samples_per_second": 1523.146,
      "eval_spearmanr": 0.28105299626630287,
      "eval_steps_per_second": 6.093,
      "step": 161
    },
    {
      "epoch": 7.0,
      "step": 161,
      "total_flos": 5294141566038528.0,
      "train_loss": 1.4743308843292804,
      "train_runtime": 87.3516,
      "train_samples_per_second": 3290.724,
      "train_steps_per_second": 13.165
    }
  ],
  "logging_steps": 1,
  "max_steps": 1150,
  "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": 5294141566038528.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}