File size: 3,681 Bytes
c879acf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.991150442477876,
  "global_step": 98,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 5e-05,
      "loss": 2.7205,
      "step": 3
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 2.7244,
      "step": 6
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 2.7638,
      "step": 9
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 2.7622,
      "step": 12
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 2.7498,
      "step": 15
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 2.7814,
      "step": 18
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 2.7404,
      "step": 21
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 2.8507,
      "step": 24
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 2.7969,
      "step": 27
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001,
      "loss": 2.7087,
      "step": 30
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 2.6703,
      "step": 33
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 2.7935,
      "step": 36
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001,
      "loss": 2.6768,
      "step": 39
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001,
      "loss": 2.7279,
      "step": 42
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001,
      "loss": 2.7542,
      "step": 45
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001,
      "loss": 2.7718,
      "step": 48
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001,
      "loss": 3.1325,
      "step": 51
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001,
      "loss": 2.6908,
      "step": 54
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001,
      "loss": 2.661,
      "step": 57
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001,
      "loss": 2.6744,
      "step": 60
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001,
      "loss": 2.7521,
      "step": 63
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001,
      "loss": 2.7165,
      "step": 66
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001,
      "loss": 2.752,
      "step": 69
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001,
      "loss": 2.7158,
      "step": 72
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001,
      "loss": 2.6624,
      "step": 75
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001,
      "loss": 2.7896,
      "step": 78
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0001,
      "loss": 2.706,
      "step": 81
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0001,
      "loss": 2.7365,
      "step": 84
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001,
      "loss": 2.7428,
      "step": 87
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001,
      "loss": 2.7072,
      "step": 90
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001,
      "loss": 2.7192,
      "step": 93
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001,
      "loss": 2.7297,
      "step": 96
    }
  ],
  "max_steps": 294,
  "num_train_epochs": 6,
  "total_flos": 4.665562387762381e+17,
  "trial_name": null,
  "trial_params": null
}