File size: 3,854 Bytes
cbfbd13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
188
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8072653884964682,
  "eval_steps": 500,
  "global_step": 10500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "ep_loss": 4.4238,
      "epoch": 0.04,
      "learning_rate": 2.5e-05,
      "loss": 11.1467,
      "mlm_loss": 6.7229,
      "step": 500
    },
    {
      "ep_loss": 0.4305,
      "epoch": 0.08,
      "learning_rate": 5e-05,
      "loss": 2.9841,
      "mlm_loss": 2.5537,
      "step": 1000
    },
    {
      "ep_loss": 0.3724,
      "epoch": 0.12,
      "learning_rate": 7.5e-05,
      "loss": 2.2371,
      "mlm_loss": 1.8647,
      "step": 1500
    },
    {
      "ep_loss": 0.364,
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 1.8477,
      "mlm_loss": 1.4837,
      "step": 2000
    },
    {
      "ep_loss": 0.3678,
      "epoch": 0.19,
      "learning_rate": 0.00012495,
      "loss": 1.5215,
      "mlm_loss": 1.1538,
      "step": 2500
    },
    {
      "ep_loss": 0.3617,
      "epoch": 0.23,
      "learning_rate": 0.00014995,
      "loss": 1.4119,
      "mlm_loss": 1.0501,
      "step": 3000
    },
    {
      "ep_loss": 0.3336,
      "epoch": 0.27,
      "learning_rate": 0.0001749,
      "loss": 1.3027,
      "mlm_loss": 0.9691,
      "step": 3500
    },
    {
      "ep_loss": 0.3348,
      "epoch": 0.31,
      "learning_rate": 0.0001999,
      "loss": 1.2441,
      "mlm_loss": 0.9093,
      "step": 4000
    },
    {
      "ep_loss": 0.3348,
      "epoch": 0.35,
      "learning_rate": 0.0002249,
      "loss": 1.1942,
      "mlm_loss": 0.8594,
      "step": 4500
    },
    {
      "ep_loss": 0.3331,
      "epoch": 0.38,
      "learning_rate": 0.0002499,
      "loss": 1.1466,
      "mlm_loss": 0.8135,
      "step": 5000
    },
    {
      "ep_loss": 0.3268,
      "epoch": 0.42,
      "learning_rate": 0.00027489999999999996,
      "loss": 1.1067,
      "mlm_loss": 0.7799,
      "step": 5500
    },
    {
      "ep_loss": 0.3378,
      "epoch": 0.46,
      "learning_rate": 0.00029985,
      "loss": 1.1007,
      "mlm_loss": 0.7629,
      "step": 6000
    },
    {
      "ep_loss": 0.3033,
      "epoch": 0.5,
      "learning_rate": 0.00032485,
      "loss": 1.028,
      "mlm_loss": 0.7246,
      "step": 6500
    },
    {
      "ep_loss": 0.2848,
      "epoch": 0.54,
      "learning_rate": 0.00034985,
      "loss": 0.9833,
      "mlm_loss": 0.6985,
      "step": 7000
    },
    {
      "ep_loss": 0.316,
      "epoch": 0.58,
      "learning_rate": 0.00037485000000000003,
      "loss": 1.0235,
      "mlm_loss": 0.7076,
      "step": 7500
    },
    {
      "ep_loss": 0.2885,
      "epoch": 0.62,
      "learning_rate": 0.00039975,
      "loss": 0.9673,
      "mlm_loss": 0.6789,
      "step": 8000
    },
    {
      "ep_loss": 0.274,
      "epoch": 0.65,
      "learning_rate": 0.00042475000000000005,
      "loss": 0.9266,
      "mlm_loss": 0.6525,
      "step": 8500
    },
    {
      "ep_loss": 0.3008,
      "epoch": 0.69,
      "learning_rate": 0.0004497,
      "loss": 0.9646,
      "mlm_loss": 0.6638,
      "step": 9000
    },
    {
      "ep_loss": 0.2843,
      "epoch": 0.73,
      "learning_rate": 0.00047470000000000005,
      "loss": 0.9349,
      "mlm_loss": 0.6506,
      "step": 9500
    },
    {
      "ep_loss": 0.2693,
      "epoch": 0.77,
      "learning_rate": 0.0004997,
      "loss": 0.8901,
      "mlm_loss": 0.6208,
      "step": 10000
    },
    {
      "ep_loss": 0.2655,
      "epoch": 0.81,
      "learning_rate": 0.0004995159140796489,
      "loss": 0.8783,
      "mlm_loss": 0.6128,
      "step": 10500
    }
  ],
  "logging_steps": 500,
  "max_steps": 520240,
  "num_train_epochs": 40,
  "save_steps": 500,
  "total_flos": 1.0025581355477238e+19,
  "trial_name": null,
  "trial_params": null
}