Hugging Face's logo

trapoom555
/
MiniCPM-1-500-checkpoints-lr-5e-4

Safetensors
Model card Files Community
MiniCPM-1-500-checkpoints-lr-5e-4
File size: 4,098 Bytes 
ea96d68
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016689645163631087,
  "eval_steps": 500,
  "global_step": 230,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007256367462448298,
      "grad_norm": 12.0,
      "learning_rate": 5e-05,
      "loss": 3.0993,
      "step": 10
    },
    {
      "epoch": 0.0014512734924896596,
      "grad_norm": 10.4375,
      "learning_rate": 0.0001,
      "loss": 2.208,
      "step": 20
    },
    {
      "epoch": 0.0021769102387344894,
      "grad_norm": 6.5625,
      "learning_rate": 0.00015,
      "loss": 1.3285,
      "step": 30
    },
    {
      "epoch": 0.0029025469849793192,
      "grad_norm": 6.21875,
      "learning_rate": 0.0002,
      "loss": 0.6895,
      "step": 40
    },
    {
      "epoch": 0.003628183731224149,
      "grad_norm": 4.15625,
      "learning_rate": 0.00025,
      "loss": 0.714,
      "step": 50
    },
    {
      "epoch": 0.004353820477468979,
      "grad_norm": 4.71875,
      "learning_rate": 0.0003,
      "loss": 0.4849,
      "step": 60
    },
    {
      "epoch": 0.005079457223713809,
      "grad_norm": 3.828125,
      "learning_rate": 0.00035,
      "loss": 0.3671,
      "step": 70
    },
    {
      "epoch": 0.0058050939699586385,
      "grad_norm": 4.03125,
      "learning_rate": 0.0004,
      "loss": 0.5693,
      "step": 80
    },
    {
      "epoch": 0.006530730716203468,
      "grad_norm": 3.296875,
      "learning_rate": 0.00045000000000000004,
      "loss": 0.4133,
      "step": 90
    },
    {
      "epoch": 0.007256367462448298,
      "grad_norm": 2.640625,
      "learning_rate": 0.0005,
      "loss": 0.2668,
      "step": 100
    },
    {
      "epoch": 0.007982004208693128,
      "grad_norm": 1.5859375,
      "learning_rate": 0.000499999340865746,
      "loss": 0.2922,
      "step": 110
    },
    {
      "epoch": 0.008707640954937958,
      "grad_norm": 3.8125,
      "learning_rate": 0.0004999973634664594,
      "loss": 0.3996,
      "step": 120
    },
    {
      "epoch": 0.009433277701182788,
      "grad_norm": 2.0625,
      "learning_rate": 0.0004999940678125673,
      "loss": 0.2841,
      "step": 130
    },
    {
      "epoch": 0.010158914447427617,
      "grad_norm": 3.390625,
      "learning_rate": 0.000499989453921448,
      "loss": 0.3003,
      "step": 140
    },
    {
      "epoch": 0.010884551193672447,
      "grad_norm": 1.65625,
      "learning_rate": 0.0004999835218174307,
      "loss": 0.2747,
      "step": 150
    },
    {
      "epoch": 0.011610187939917277,
      "grad_norm": 1.671875,
      "learning_rate": 0.000499976271531796,
      "loss": 0.37,
      "step": 160
    },
    {
      "epoch": 0.012335824686162107,
      "grad_norm": 1.0390625,
      "learning_rate": 0.000499967703102775,
      "loss": 0.2163,
      "step": 170
    },
    {
      "epoch": 0.013061461432406937,
      "grad_norm": 2.546875,
      "learning_rate": 0.00049995781657555,
      "loss": 0.3652,
      "step": 180
    },
    {
      "epoch": 0.013787098178651766,
      "grad_norm": 3.71875,
      "learning_rate": 0.000499946612002253,
      "loss": 0.3177,
      "step": 190
    },
    {
      "epoch": 0.014512734924896596,
      "grad_norm": 2.6875,
      "learning_rate": 0.0004999340894419668,
      "loss": 0.2043,
      "step": 200
    },
    {
      "epoch": 0.015238371671141426,
      "grad_norm": 0.5,
      "learning_rate": 0.0004999202489607236,
      "loss": 0.2865,
      "step": 210
    },
    {
      "epoch": 0.015964008417386256,
      "grad_norm": 3.015625,
      "learning_rate": 0.0004999050906315055,
      "loss": 0.2039,
      "step": 220
    },
    {
      "epoch": 0.016689645163631087,
      "grad_norm": 0.99609375,
      "learning_rate": 0.0004998886145342434,
      "loss": 0.3509,
      "step": 230
    }
  ],
  "logging_steps": 10,
  "max_steps": 13781,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 0.0,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}