Hugging Face's logo

Hartunka
/
bert_base_km_10_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_km_10_v2_stsb
File size: 4,657 Bytes
7643d84
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2.265411138534546,
  "best_model_checkpoint": "bert_base_km_10_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": 7.086790084838867,
      "learning_rate": 4.9e-05,
      "loss": 2.711,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.10658543423072875,
      "eval_loss": 2.354522943496704,
      "eval_pearson": 0.11120670304289051,
      "eval_runtime": 0.9923,
      "eval_samples_per_second": 1511.625,
      "eval_spearmanr": 0.10196416541856697,
      "eval_steps_per_second": 6.046,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.981199741363525,
      "learning_rate": 4.8e-05,
      "loss": 1.9988,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.2009889425479498,
      "eval_loss": 2.265411138534546,
      "eval_pearson": 0.2097104961123283,
      "eval_runtime": 0.9811,
      "eval_samples_per_second": 1528.952,
      "eval_spearmanr": 0.19226738898357132,
      "eval_steps_per_second": 6.116,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.845885276794434,
      "learning_rate": 4.7e-05,
      "loss": 1.8048,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.22149173965356517,
      "eval_loss": 2.294152021408081,
      "eval_pearson": 0.2305564079119015,
      "eval_runtime": 1.0134,
      "eval_samples_per_second": 1480.098,
      "eval_spearmanr": 0.21242707139522884,
      "eval_steps_per_second": 5.92,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.093894004821777,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.5374,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.2617844143516973,
      "eval_loss": 2.547459602355957,
      "eval_pearson": 0.2699579327432999,
      "eval_runtime": 0.9482,
      "eval_samples_per_second": 1581.894,
      "eval_spearmanr": 0.25361089596009473,
      "eval_steps_per_second": 6.328,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 7.534348964691162,
      "learning_rate": 4.5e-05,
      "loss": 1.2573,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.2667936066986546,
      "eval_loss": 2.6120412349700928,
      "eval_pearson": 0.26958414545814036,
      "eval_runtime": 0.9704,
      "eval_samples_per_second": 1545.769,
      "eval_spearmanr": 0.26400306793916883,
      "eval_steps_per_second": 6.183,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 8.248147964477539,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.9617,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.2914851323109282,
      "eval_loss": 2.569234609603882,
      "eval_pearson": 0.29488939547637344,
      "eval_runtime": 0.9467,
      "eval_samples_per_second": 1584.49,
      "eval_spearmanr": 0.28808086914548303,
      "eval_steps_per_second": 6.338,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 12.66100025177002,
      "learning_rate": 4.3e-05,
      "loss": 0.7474,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.30780744811664074,
      "eval_loss": 2.6657228469848633,
      "eval_pearson": 0.3060453241906782,
      "eval_runtime": 0.975,
      "eval_samples_per_second": 1538.411,
      "eval_spearmanr": 0.3095695720426032,
      "eval_steps_per_second": 6.154,
      "step": 161
    },
    {
      "epoch": 7.0,
      "step": 161,
      "total_flos": 5294141566038528.0,
      "train_loss": 1.574070948251286,
      "train_runtime": 86.1378,
      "train_samples_per_second": 3337.095,
      "train_steps_per_second": 13.351
    }
  ],
  "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
}