File size: 3,126 Bytes
14f832b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15837402665962783,
  "eval_steps": 100,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.3109243697478994e-05,
      "loss": 1.3971,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.100840336134454e-05,
      "loss": 0.4632,
      "step": 100
    },
    {
      "epoch": 0.03,
      "eval_loss": 0.4099404215812683,
      "eval_runtime": 1367.0833,
      "eval_samples_per_second": 1.167,
      "eval_steps_per_second": 0.146,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.8907563025210083e-05,
      "loss": 0.382,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.6806722689075634e-05,
      "loss": 0.3659,
      "step": 200
    },
    {
      "epoch": 0.05,
      "eval_loss": 0.36828184127807617,
      "eval_runtime": 1367.1443,
      "eval_samples_per_second": 1.167,
      "eval_steps_per_second": 0.146,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 0.3167,
      "step": 250
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.2605042016806723e-05,
      "loss": 0.344,
      "step": 300
    },
    {
      "epoch": 0.08,
      "eval_loss": 0.3531185984611511,
      "eval_runtime": 1367.1817,
      "eval_samples_per_second": 1.167,
      "eval_steps_per_second": 0.146,
      "step": 300
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.050420168067227e-05,
      "loss": 0.3354,
      "step": 350
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.403361344537817e-06,
      "loss": 0.3324,
      "step": 400
    },
    {
      "epoch": 0.11,
      "eval_loss": 0.34376445412635803,
      "eval_runtime": 1367.1751,
      "eval_samples_per_second": 1.167,
      "eval_steps_per_second": 0.146,
      "step": 400
    },
    {
      "epoch": 0.12,
      "learning_rate": 6.3025210084033615e-06,
      "loss": 0.3198,
      "step": 450
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.2016806722689085e-06,
      "loss": 0.3228,
      "step": 500
    },
    {
      "epoch": 0.13,
      "eval_loss": 0.3370920419692993,
      "eval_runtime": 1367.1919,
      "eval_samples_per_second": 1.167,
      "eval_steps_per_second": 0.146,
      "step": 500
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.1008403361344543e-06,
      "loss": 0.3169,
      "step": 550
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0,
      "loss": 0.33,
      "step": 600
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.33460164070129395,
      "eval_runtime": 1367.2365,
      "eval_samples_per_second": 1.167,
      "eval_steps_per_second": 0.146,
      "step": 600
    }
  ],
  "logging_steps": 50,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 7.152722868436992e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}