File size: 4,196 Bytes
46943f5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 11.991695501730105,
  "global_step": 4332,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.00027499999999999996,
      "loss": 2.3243,
      "step": 361
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.3360440731048584,
      "eval_runtime": 81.7171,
      "eval_samples_per_second": 457.077,
      "eval_steps_per_second": 57.136,
      "step": 361
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00025,
      "loss": 1.9943,
      "step": 722
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.3849265575408936,
      "eval_runtime": 80.8133,
      "eval_samples_per_second": 462.189,
      "eval_steps_per_second": 57.775,
      "step": 722
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.000225,
      "loss": 1.7331,
      "step": 1083
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.5010716915130615,
      "eval_runtime": 80.8638,
      "eval_samples_per_second": 461.9,
      "eval_steps_per_second": 57.739,
      "step": 1083
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00019993074792243765,
      "loss": 1.463,
      "step": 1445
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.7065136432647705,
      "eval_runtime": 80.5929,
      "eval_samples_per_second": 463.453,
      "eval_steps_per_second": 57.933,
      "step": 1445
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00017493074792243764,
      "loss": 1.1969,
      "step": 1806
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.9511666297912598,
      "eval_runtime": 80.4169,
      "eval_samples_per_second": 464.467,
      "eval_steps_per_second": 58.06,
      "step": 1806
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00014993074792243766,
      "loss": 0.9339,
      "step": 2167
    },
    {
      "epoch": 6.0,
      "eval_loss": 3.2412941455841064,
      "eval_runtime": 80.5491,
      "eval_samples_per_second": 463.705,
      "eval_steps_per_second": 57.965,
      "step": 2167
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.00012493074792243767,
      "loss": 0.6915,
      "step": 2528
    },
    {
      "epoch": 7.0,
      "eval_loss": 3.56394362449646,
      "eval_runtime": 79.8139,
      "eval_samples_per_second": 467.976,
      "eval_steps_per_second": 58.499,
      "step": 2528
    },
    {
      "epoch": 8.0,
      "learning_rate": 9.986149584487533e-05,
      "loss": 0.4811,
      "step": 2890
    },
    {
      "epoch": 8.0,
      "eval_loss": 3.897730827331543,
      "eval_runtime": 80.0943,
      "eval_samples_per_second": 466.338,
      "eval_steps_per_second": 58.294,
      "step": 2890
    },
    {
      "epoch": 9.0,
      "learning_rate": 7.486149584487535e-05,
      "loss": 0.3195,
      "step": 3251
    },
    {
      "epoch": 9.0,
      "eval_loss": 4.2111005783081055,
      "eval_runtime": 79.9229,
      "eval_samples_per_second": 467.338,
      "eval_steps_per_second": 58.419,
      "step": 3251
    },
    {
      "epoch": 10.0,
      "learning_rate": 4.986149584487534e-05,
      "loss": 0.211,
      "step": 3612
    },
    {
      "epoch": 10.0,
      "eval_loss": 4.46787166595459,
      "eval_runtime": 80.4105,
      "eval_samples_per_second": 464.504,
      "eval_steps_per_second": 58.065,
      "step": 3612
    },
    {
      "epoch": 11.0,
      "learning_rate": 2.4861495844875343e-05,
      "loss": 0.1515,
      "step": 3973
    },
    {
      "epoch": 11.0,
      "eval_loss": 4.6477370262146,
      "eval_runtime": 80.1153,
      "eval_samples_per_second": 466.216,
      "eval_steps_per_second": 58.279,
      "step": 3973
    },
    {
      "epoch": 11.99,
      "learning_rate": 0.0,
      "loss": 0.1233,
      "step": 4332
    },
    {
      "epoch": 11.99,
      "eval_loss": 4.7357659339904785,
      "eval_runtime": 80.0925,
      "eval_samples_per_second": 466.348,
      "eval_steps_per_second": 58.295,
      "step": 4332
    }
  ],
  "max_steps": 4332,
  "num_train_epochs": 12,
  "total_flos": 1.705389820458624e+17,
  "trial_name": null,
  "trial_params": null
}