File size: 3,181 Bytes
c9451c6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 300.0,
  "global_step": 6000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 50.0,
      "learning_rate": 2.4875e-05,
      "loss": 2.9129,
      "step": 1000
    },
    {
      "epoch": 50.0,
      "eval_bleu": 92.7571,
      "eval_em": 0.2302,
      "eval_gen_len": 79.2806,
      "eval_loss": 0.3861088156700134,
      "eval_rm": 0.2422,
      "eval_runtime": 119.9581,
      "eval_samples_per_second": 3.476,
      "eval_steps_per_second": 0.225,
      "step": 1000
    },
    {
      "epoch": 100.0,
      "learning_rate": 4.9875000000000006e-05,
      "loss": 0.052,
      "step": 2000
    },
    {
      "epoch": 100.0,
      "eval_bleu": 95.3257,
      "eval_em": 0.5156,
      "eval_gen_len": 80.6859,
      "eval_loss": 0.3531915545463562,
      "eval_rm": 0.5635,
      "eval_runtime": 114.8636,
      "eval_samples_per_second": 3.63,
      "eval_steps_per_second": 0.235,
      "step": 2000
    },
    {
      "epoch": 150.0,
      "learning_rate": 3.75625e-05,
      "loss": 0.0155,
      "step": 3000
    },
    {
      "epoch": 150.0,
      "eval_bleu": 94.8017,
      "eval_em": 0.5659,
      "eval_gen_len": 79.3165,
      "eval_loss": 0.4279763698577881,
      "eval_rm": 0.6355,
      "eval_runtime": 113.6979,
      "eval_samples_per_second": 3.668,
      "eval_steps_per_second": 0.237,
      "step": 3000
    },
    {
      "epoch": 200.0,
      "learning_rate": 2.50625e-05,
      "loss": 0.0086,
      "step": 4000
    },
    {
      "epoch": 200.0,
      "eval_bleu": 95.5885,
      "eval_em": 0.5803,
      "eval_gen_len": 80.6978,
      "eval_loss": 0.40772923827171326,
      "eval_rm": 0.6283,
      "eval_runtime": 118.0147,
      "eval_samples_per_second": 3.533,
      "eval_steps_per_second": 0.229,
      "step": 4000
    },
    {
      "epoch": 250.0,
      "learning_rate": 1.2562499999999999e-05,
      "loss": 0.0051,
      "step": 5000
    },
    {
      "epoch": 250.0,
      "eval_bleu": 95.5923,
      "eval_em": 0.6019,
      "eval_gen_len": 80.6523,
      "eval_loss": 0.41692906618118286,
      "eval_rm": 0.6523,
      "eval_runtime": 120.2437,
      "eval_samples_per_second": 3.468,
      "eval_steps_per_second": 0.225,
      "step": 5000
    },
    {
      "epoch": 300.0,
      "learning_rate": 6.250000000000001e-08,
      "loss": 0.0038,
      "step": 6000
    },
    {
      "epoch": 300.0,
      "eval_bleu": 95.481,
      "eval_em": 0.6019,
      "eval_gen_len": 80.4676,
      "eval_loss": 0.42530182003974915,
      "eval_rm": 0.6547,
      "eval_runtime": 133.449,
      "eval_samples_per_second": 3.125,
      "eval_steps_per_second": 0.202,
      "step": 6000
    },
    {
      "epoch": 300.0,
      "step": 6000,
      "total_flos": 1.014399554069376e+16,
      "train_loss": 0.49965806714693706,
      "train_runtime": 5702.8364,
      "train_samples_per_second": 64.494,
      "train_steps_per_second": 1.052
    }
  ],
  "max_steps": 6000,
  "num_train_epochs": 300,
  "total_flos": 1.014399554069376e+16,
  "trial_name": null,
  "trial_params": null
}