Hugging Face's logo

Hartunka
/
bert_base_rand_5_v2_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_5_v2_stsb
File size: 4,667 Bytes
308dd43
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2.3162741661071777,
  "best_model_checkpoint": "bert_base_rand_5_v2_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": 4.672378063201904,
      "learning_rate": 4.9e-05,
      "loss": 2.6563,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.09050440946239476,
      "eval_loss": 2.468899726867676,
      "eval_pearson": 0.09885560057722062,
      "eval_runtime": 0.9893,
      "eval_samples_per_second": 1516.155,
      "eval_spearmanr": 0.08215321834756889,
      "eval_steps_per_second": 6.065,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 12.538728713989258,
      "learning_rate": 4.8e-05,
      "loss": 1.8843,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.17865816941006596,
      "eval_loss": 2.3162741661071777,
      "eval_pearson": 0.19542194735083257,
      "eval_runtime": 1.003,
      "eval_samples_per_second": 1495.455,
      "eval_spearmanr": 0.16189439146929932,
      "eval_steps_per_second": 5.982,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.898491859436035,
      "learning_rate": 4.7e-05,
      "loss": 1.6315,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.25567049594755953,
      "eval_loss": 2.365222930908203,
      "eval_pearson": 0.26043384251429863,
      "eval_runtime": 0.9606,
      "eval_samples_per_second": 1561.529,
      "eval_spearmanr": 0.25090714938082037,
      "eval_steps_per_second": 6.246,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.290682792663574,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.2245,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.28864361414381867,
      "eval_loss": 2.5701653957366943,
      "eval_pearson": 0.2910950881475413,
      "eval_runtime": 0.9942,
      "eval_samples_per_second": 1508.822,
      "eval_spearmanr": 0.286192140140096,
      "eval_steps_per_second": 6.035,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.64109992980957,
      "learning_rate": 4.5e-05,
      "loss": 0.8986,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.27109561622168327,
      "eval_loss": 2.6825172901153564,
      "eval_pearson": 0.27674054063954884,
      "eval_runtime": 0.9605,
      "eval_samples_per_second": 1561.745,
      "eval_spearmanr": 0.2654506918038177,
      "eval_steps_per_second": 6.247,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.450591564178467,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6617,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.30805346136071465,
      "eval_loss": 2.512233018875122,
      "eval_pearson": 0.3120714777686556,
      "eval_runtime": 1.0131,
      "eval_samples_per_second": 1480.655,
      "eval_spearmanr": 0.3040354449527736,
      "eval_steps_per_second": 5.923,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 12.366684913635254,
      "learning_rate": 4.3e-05,
      "loss": 0.5165,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.33508237397612906,
      "eval_loss": 2.374462127685547,
      "eval_pearson": 0.3379127982925731,
      "eval_runtime": 0.9637,
      "eval_samples_per_second": 1556.566,
      "eval_spearmanr": 0.332251949659685,
      "eval_steps_per_second": 6.226,
      "step": 161
    },
    {
      "epoch": 7.0,
      "step": 161,
      "total_flos": 5294141566038528.0,
      "train_loss": 1.3533399475287207,
      "train_runtime": 88.0763,
      "train_samples_per_second": 3263.646,
      "train_steps_per_second": 13.057
    }
  ],
  "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
}