Hugging Face's logo

Kemasu
/
albert_sae

TensorBoard
Model card Files Metrics Community
albert_sae
File size: 3,764 Bytes 
46ad5eb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
180
181
182
183
184
185
186
187
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2184115523465704,
  "global_step": 13500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 1.969915764139591e-05,
      "loss": 3.07,
      "step": 500
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.939831528279182e-05,
      "loss": 0.0,
      "step": 1000
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9097472924187726e-05,
      "loss": 0.0,
      "step": 1500
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8796630565583636e-05,
      "loss": 0.0,
      "step": 2000
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.8495788206979545e-05,
      "loss": 0.0,
      "step": 2500
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.8194945848375454e-05,
      "loss": 0.0,
      "step": 3000
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.789410348977136e-05,
      "loss": 0.0,
      "step": 3500
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.759326113116727e-05,
      "loss": 0.0,
      "step": 4000
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.729241877256318e-05,
      "loss": 0.0,
      "step": 4500
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.699157641395909e-05,
      "loss": 0.0,
      "step": 5000
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.6690734055354995e-05,
      "loss": 0.0,
      "step": 5500
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.6389891696750904e-05,
      "loss": 0.0,
      "step": 6000
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.608904933814681e-05,
      "loss": 0.0,
      "step": 6500
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.5788206979542723e-05,
      "loss": 0.0,
      "step": 7000
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.548736462093863e-05,
      "loss": 0.0,
      "step": 7500
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.5186522262334538e-05,
      "loss": 0.0,
      "step": 8000
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.4885679903730446e-05,
      "loss": 0.0,
      "step": 8500
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.4584837545126355e-05,
      "loss": 0.0,
      "step": 9000
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.4283995186522264e-05,
      "loss": 0.0,
      "step": 9500
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.3983152827918172e-05,
      "loss": 0.0,
      "step": 10000
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.368231046931408e-05,
      "loss": 0.0,
      "step": 10500
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.338146811070999e-05,
      "loss": 0.0,
      "step": 11000
    },
    {
      "epoch": 1.0,
      "eval_loss": NaN,
      "eval_runtime": 72.3735,
      "eval_samples_per_second": 149.336,
      "eval_steps_per_second": 18.667,
      "step": 11080
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.3080625752105897e-05,
      "loss": 0.0,
      "step": 11500
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.2779783393501806e-05,
      "loss": 0.0,
      "step": 12000
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.2478941034897714e-05,
      "loss": 0.0,
      "step": 12500
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.2178098676293623e-05,
      "loss": 0.0,
      "step": 13000
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.1877256317689531e-05,
      "loss": 0.0,
      "step": 13500
    }
  ],
  "max_steps": 33240,
  "num_train_epochs": 3,
  "total_flos": 1788754928311296.0,
  "trial_name": null,
  "trial_params": null
}