File size: 2,958 Bytes
2bf41f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.9975144987572495,
  "global_step": 7540,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 0.7525,
      "step": 500
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 0.692,
      "step": 1000
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001,
      "loss": 0.6752,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6349760890007019,
      "eval_runtime": 199.764,
      "eval_samples_per_second": 16.084,
      "eval_steps_per_second": 1.006,
      "step": 1508
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001,
      "loss": 0.5067,
      "step": 2000
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001,
      "loss": 0.5211,
      "step": 2500
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0001,
      "loss": 0.5151,
      "step": 3000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5905311703681946,
      "eval_runtime": 198.2597,
      "eval_samples_per_second": 16.206,
      "eval_steps_per_second": 1.014,
      "step": 3017
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001,
      "loss": 0.3746,
      "step": 3500
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0001,
      "loss": 0.3784,
      "step": 4000
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0001,
      "loss": 0.3839,
      "step": 4500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6004335284233093,
      "eval_runtime": 198.543,
      "eval_samples_per_second": 16.183,
      "eval_steps_per_second": 1.012,
      "step": 4526
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0001,
      "loss": 0.2699,
      "step": 5000
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.0001,
      "loss": 0.2732,
      "step": 5500
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.0001,
      "loss": 0.2841,
      "step": 6000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6339293122291565,
      "eval_runtime": 198.2785,
      "eval_samples_per_second": 16.204,
      "eval_steps_per_second": 1.014,
      "step": 6035
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.0001,
      "loss": 0.1973,
      "step": 6500
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0001,
      "loss": 0.1981,
      "step": 7000
    },
    {
      "epoch": 4.97,
      "learning_rate": 0.0001,
      "loss": 0.2083,
      "step": 7500
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6874634027481079,
      "eval_runtime": 198.2649,
      "eval_samples_per_second": 16.206,
      "eval_steps_per_second": 1.014,
      "step": 7540
    }
  ],
  "max_steps": 7540,
  "num_train_epochs": 5,
  "total_flos": 31701581365248.0,
  "trial_name": null,
  "trial_params": null
}