File size: 3,857 Bytes
2d3d730
2ce3056
 
 
2d3d730
2ce3056
2d3d730
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2a825d0
 
 
 
 
 
 
 
 
 
 
 
 
 
0e061f4
 
 
 
 
 
 
 
 
 
 
 
 
 
dcc7aba
 
 
 
 
 
 
 
 
 
 
 
 
 
775011e
 
 
 
 
 
 
 
 
 
 
 
 
 
3a26b3f
 
 
 
 
 
 
 
 
 
 
 
 
 
8823351
 
 
 
 
 
 
 
 
 
 
 
 
 
e629be4
 
 
 
 
 
 
 
 
 
 
 
 
 
f5ed411
 
 
 
 
 
 
 
 
 
 
 
 
 
d173f10
 
 
 
 
 
 
 
 
 
 
 
 
 
2ce3056
 
 
 
 
 
 
 
 
 
 
 
 
 
2d3d730
 
 
 
 
 
 
2ce3056
2d3d730
 
 
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
{
  "best_metric": 1.2266021966934204,
  "best_model_checkpoint": "./outputs/checkpoint-1100",
  "epoch": 1.4666666666666668,
  "eval_steps": 100,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.2648,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.3499459028244019,
      "eval_runtime": 466.0769,
      "eval_samples_per_second": 4.141,
      "eval_steps_per_second": 0.519,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.1034,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.3190627098083496,
      "eval_runtime": 466.6597,
      "eval_samples_per_second": 4.136,
      "eval_steps_per_second": 0.519,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.085,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.2993828058242798,
      "eval_runtime": 470.7014,
      "eval_samples_per_second": 4.1,
      "eval_steps_per_second": 0.514,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.0692,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.2881134748458862,
      "eval_runtime": 470.2444,
      "eval_samples_per_second": 4.104,
      "eval_steps_per_second": 0.515,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.0558,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.274288535118103,
      "eval_runtime": 467.1885,
      "eval_samples_per_second": 4.131,
      "eval_steps_per_second": 0.518,
      "step": 500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.0502,
      "step": 600
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.2627606391906738,
      "eval_runtime": 465.7624,
      "eval_samples_per_second": 4.144,
      "eval_steps_per_second": 0.52,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.0419,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.256902813911438,
      "eval_runtime": 459.9211,
      "eval_samples_per_second": 4.196,
      "eval_steps_per_second": 0.526,
      "step": 700
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.0301,
      "step": 800
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.2442457675933838,
      "eval_runtime": 457.8978,
      "eval_samples_per_second": 4.215,
      "eval_steps_per_second": 0.529,
      "step": 800
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.0199,
      "step": 900
    },
    {
      "epoch": 1.2,
      "eval_loss": 1.2393821477890015,
      "eval_runtime": 467.9251,
      "eval_samples_per_second": 4.125,
      "eval_steps_per_second": 0.517,
      "step": 900
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 1.0077,
      "step": 1000
    },
    {
      "epoch": 1.33,
      "eval_loss": 1.232779622077942,
      "eval_runtime": 473.1709,
      "eval_samples_per_second": 4.079,
      "eval_steps_per_second": 0.511,
      "step": 1000
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 1.0152,
      "step": 1100
    },
    {
      "epoch": 1.47,
      "eval_loss": 1.2266021966934204,
      "eval_runtime": 468.5166,
      "eval_samples_per_second": 4.119,
      "eval_steps_per_second": 0.517,
      "step": 1100
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 3.660881250995405e+16,
  "trial_name": null,
  "trial_params": null
}