File size: 3,839 Bytes
fb251b7
3872227
 
 
fb251b7
3872227
fb251b7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6c94f80
 
 
 
 
 
 
 
 
 
 
 
 
 
59abe4f
 
 
 
 
 
 
 
 
 
 
 
 
 
dcfc5bb
 
 
 
 
 
 
 
 
 
 
 
 
 
269425a
 
 
 
 
 
 
 
 
 
 
 
 
 
e7143f8
 
 
 
 
 
 
 
 
 
 
 
 
 
0d3f6ad
 
 
 
 
 
 
 
 
 
 
 
 
 
9c7a5c5
 
 
 
 
 
 
 
 
 
 
 
 
 
c3bd6b6
 
 
 
 
 
 
 
 
 
 
 
 
 
8e767ea
 
 
 
 
 
 
 
 
 
 
 
 
 
3872227
 
 
 
 
 
 
 
 
 
 
 
 
 
fb251b7
 
 
 
 
 
3872227
fb251b7
 
 
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
{
  "best_metric": 2.338806390762329,
  "best_model_checkpoint": "./outputs/checkpoint-1100",
  "epoch": 0.8014571948998178,
  "eval_steps": 100,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.7202,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.6173269748687744,
      "eval_runtime": 210.4944,
      "eval_samples_per_second": 29.806,
      "eval_steps_per_second": 3.729,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.5807,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.566875696182251,
      "eval_runtime": 206.05,
      "eval_samples_per_second": 30.449,
      "eval_steps_per_second": 3.81,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.5403,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.531456708908081,
      "eval_runtime": 205.7527,
      "eval_samples_per_second": 30.493,
      "eval_steps_per_second": 3.815,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5135,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.4987542629241943,
      "eval_runtime": 205.7584,
      "eval_samples_per_second": 30.492,
      "eval_steps_per_second": 3.815,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.4703,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 2.4730148315429688,
      "eval_runtime": 205.8153,
      "eval_samples_per_second": 30.484,
      "eval_steps_per_second": 3.814,
      "step": 500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.4449,
      "step": 600
    },
    {
      "epoch": 0.44,
      "eval_loss": 2.4445066452026367,
      "eval_runtime": 205.9496,
      "eval_samples_per_second": 30.464,
      "eval_steps_per_second": 3.812,
      "step": 600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.4265,
      "step": 700
    },
    {
      "epoch": 0.51,
      "eval_loss": 2.421610116958618,
      "eval_runtime": 206.1548,
      "eval_samples_per_second": 30.433,
      "eval_steps_per_second": 3.808,
      "step": 700
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.4059,
      "step": 800
    },
    {
      "epoch": 0.58,
      "eval_loss": 2.401268720626831,
      "eval_runtime": 206.1413,
      "eval_samples_per_second": 30.435,
      "eval_steps_per_second": 3.808,
      "step": 800
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 2.3694,
      "step": 900
    },
    {
      "epoch": 0.66,
      "eval_loss": 2.3795337677001953,
      "eval_runtime": 206.144,
      "eval_samples_per_second": 30.435,
      "eval_steps_per_second": 3.808,
      "step": 900
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 2.3664,
      "step": 1000
    },
    {
      "epoch": 0.73,
      "eval_loss": 2.3618950843811035,
      "eval_runtime": 205.9336,
      "eval_samples_per_second": 30.466,
      "eval_steps_per_second": 3.812,
      "step": 1000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.3599,
      "step": 1100
    },
    {
      "epoch": 0.8,
      "eval_loss": 2.338806390762329,
      "eval_runtime": 205.8736,
      "eval_samples_per_second": 30.475,
      "eval_steps_per_second": 3.813,
      "step": 1100
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 3.229353773162496e+16,
  "trial_name": null,
  "trial_params": null
}