File size: 3,840 Bytes
3a3b1b6
4d3928e
 
 
3a3b1b6
4d3928e
3a3b1b6
 
 
 
 
 
 
4d3928e
3a3b1b6
 
 
 
4d3928e
 
 
 
3a3b1b6
e5c5089
 
 
 
4d3928e
e5c5089
 
 
 
4d3928e
 
 
 
e5c5089
d68298f
 
 
 
4d3928e
d68298f
 
 
 
4d3928e
 
 
 
d68298f
d27a2cf
 
 
 
4d3928e
d27a2cf
 
 
 
4d3928e
 
 
 
d27a2cf
4d3928e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3a3b1b6
 
 
 
 
 
4d3928e
3a3b1b6
 
 
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": 2.360255479812622,
  "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": 2.7399,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.6418099403381348,
      "eval_runtime": 347.6157,
      "eval_samples_per_second": 18.049,
      "eval_steps_per_second": 2.258,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.6052,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.5918312072753906,
      "eval_runtime": 333.731,
      "eval_samples_per_second": 18.8,
      "eval_steps_per_second": 2.352,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.5622,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.551574468612671,
      "eval_runtime": 204.9306,
      "eval_samples_per_second": 30.615,
      "eval_steps_per_second": 3.831,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5366,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.517575263977051,
      "eval_runtime": 204.3925,
      "eval_samples_per_second": 30.696,
      "eval_steps_per_second": 3.841,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.4946,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 2.4924821853637695,
      "eval_runtime": 204.4035,
      "eval_samples_per_second": 30.694,
      "eval_steps_per_second": 3.84,
      "step": 500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.4686,
      "step": 600
    },
    {
      "epoch": 0.44,
      "eval_loss": 2.4666266441345215,
      "eval_runtime": 207.3453,
      "eval_samples_per_second": 30.259,
      "eval_steps_per_second": 3.786,
      "step": 600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.4503,
      "step": 700
    },
    {
      "epoch": 0.51,
      "eval_loss": 2.4440107345581055,
      "eval_runtime": 205.5485,
      "eval_samples_per_second": 30.523,
      "eval_steps_per_second": 3.819,
      "step": 700
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.4271,
      "step": 800
    },
    {
      "epoch": 0.58,
      "eval_loss": 2.4231719970703125,
      "eval_runtime": 204.3763,
      "eval_samples_per_second": 30.698,
      "eval_steps_per_second": 3.841,
      "step": 800
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 2.3911,
      "step": 900
    },
    {
      "epoch": 0.66,
      "eval_loss": 2.401764154434204,
      "eval_runtime": 204.7042,
      "eval_samples_per_second": 30.649,
      "eval_steps_per_second": 3.835,
      "step": 900
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 2.3881,
      "step": 1000
    },
    {
      "epoch": 0.73,
      "eval_loss": 2.3822004795074463,
      "eval_runtime": 204.6048,
      "eval_samples_per_second": 30.664,
      "eval_steps_per_second": 3.837,
      "step": 1000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.3811,
      "step": 1100
    },
    {
      "epoch": 0.8,
      "eval_loss": 2.360255479812622,
      "eval_runtime": 283.1616,
      "eval_samples_per_second": 22.157,
      "eval_steps_per_second": 2.772,
      "step": 1100
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 3.208363367473152e+16,
  "trial_name": null,
  "trial_params": null
}