Hugging Face's logo

Seb0099
/
dataHub_autocomplete

Safetensors
t5
Model card Files
xet
Community
dataHub_autocomplete
File size: 3,891 Bytes 
ca62999
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 14.0,
  "eval_steps": 500,
  "global_step": 9296,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7530120481927711,
      "grad_norm": 0.2647170126438141,
      "learning_rate": 0.0004811746987951807,
      "loss": 0.3311,
      "step": 500
    },
    {
      "epoch": 1.5060240963855422,
      "grad_norm": 0.22880347073078156,
      "learning_rate": 0.00046234939759036143,
      "loss": 0.0907,
      "step": 1000
    },
    {
      "epoch": 2.2590361445783134,
      "grad_norm": 0.1677163541316986,
      "learning_rate": 0.00044352409638554217,
      "loss": 0.0568,
      "step": 1500
    },
    {
      "epoch": 3.0120481927710845,
      "grad_norm": 0.12338300049304962,
      "learning_rate": 0.0004246987951807229,
      "loss": 0.0451,
      "step": 2000
    },
    {
      "epoch": 3.765060240963855,
      "grad_norm": 0.08597979694604874,
      "learning_rate": 0.0004058734939759036,
      "loss": 0.0386,
      "step": 2500
    },
    {
      "epoch": 4.518072289156627,
      "grad_norm": 0.0988745242357254,
      "learning_rate": 0.00038704819277108433,
      "loss": 0.0352,
      "step": 3000
    },
    {
      "epoch": 5.271084337349397,
      "grad_norm": 0.11785969883203506,
      "learning_rate": 0.00036822289156626507,
      "loss": 0.0331,
      "step": 3500
    },
    {
      "epoch": 6.024096385542169,
      "grad_norm": 0.09906379133462906,
      "learning_rate": 0.0003493975903614458,
      "loss": 0.0315,
      "step": 4000
    },
    {
      "epoch": 6.77710843373494,
      "grad_norm": 0.1129639744758606,
      "learning_rate": 0.0003305722891566265,
      "loss": 0.0301,
      "step": 4500
    },
    {
      "epoch": 7.530120481927711,
      "grad_norm": 0.07321502268314362,
      "learning_rate": 0.00031174698795180723,
      "loss": 0.0292,
      "step": 5000
    },
    {
      "epoch": 8.283132530120483,
      "grad_norm": 0.05083702132105827,
      "learning_rate": 0.0002929216867469879,
      "loss": 0.028,
      "step": 5500
    },
    {
      "epoch": 9.036144578313253,
      "grad_norm": 0.073179692029953,
      "learning_rate": 0.0002740963855421687,
      "loss": 0.0275,
      "step": 6000
    },
    {
      "epoch": 9.789156626506024,
      "grad_norm": 0.060432616621255875,
      "learning_rate": 0.0002552710843373494,
      "loss": 0.0266,
      "step": 6500
    },
    {
      "epoch": 10.542168674698795,
      "grad_norm": 0.05641400068998337,
      "learning_rate": 0.00023644578313253013,
      "loss": 0.0265,
      "step": 7000
    },
    {
      "epoch": 11.295180722891565,
      "grad_norm": 0.055228352546691895,
      "learning_rate": 0.00021762048192771087,
      "loss": 0.0257,
      "step": 7500
    },
    {
      "epoch": 12.048192771084338,
      "grad_norm": 0.055986884981393814,
      "learning_rate": 0.00019879518072289158,
      "loss": 0.0254,
      "step": 8000
    },
    {
      "epoch": 12.801204819277109,
      "grad_norm": 0.06879087537527084,
      "learning_rate": 0.0001799698795180723,
      "loss": 0.025,
      "step": 8500
    },
    {
      "epoch": 13.55421686746988,
      "grad_norm": 0.08162941783666611,
      "learning_rate": 0.00016114457831325303,
      "loss": 0.0248,
      "step": 9000
    }
  ],
  "logging_steps": 500,
  "max_steps": 13280,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5026154645815296.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}