Hugging Face's logo

yesj1234
/
mbart-mmt_mid2_en-ko

Text2Text Generation
Transformers
PyTorch
English
Korean
mbart
Generated from Trainer
Inference Endpoints
Model card Files Community
mbart-mmt_mid2_en-ko
File size: 2,965 Bytes 
24a2797
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.523019790649414,
  "best_model_checkpoint": "./mbartLarge_mid_en-ko1/checkpoint-1500",
  "epoch": 4.487658937920718,
  "eval_steps": 1500,
  "global_step": 6000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.37,
      "learning_rate": 5e-05,
      "loss": 1.7061,
      "step": 500
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.952812382030955e-05,
      "loss": 1.619,
      "step": 1000
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.9056247640619104e-05,
      "loss": 1.4343,
      "step": 1500
    },
    {
      "epoch": 1.12,
      "eval_bleu": 11.2393,
      "eval_gen_len": 16.3612,
      "eval_loss": 1.523019790649414,
      "eval_runtime": 172.8656,
      "eval_samples_per_second": 15.457,
      "eval_steps_per_second": 0.966,
      "step": 1500
    },
    {
      "epoch": 1.5,
      "learning_rate": 4.8584371460928654e-05,
      "loss": 1.1601,
      "step": 2000
    },
    {
      "epoch": 1.87,
      "learning_rate": 4.8112495281238205e-05,
      "loss": 1.1956,
      "step": 2500
    },
    {
      "epoch": 2.24,
      "learning_rate": 4.7640619101547756e-05,
      "loss": 0.9153,
      "step": 3000
    },
    {
      "epoch": 2.24,
      "eval_bleu": 11.9955,
      "eval_gen_len": 16.2665,
      "eval_loss": 1.600303053855896,
      "eval_runtime": 166.8515,
      "eval_samples_per_second": 16.014,
      "eval_steps_per_second": 1.001,
      "step": 3000
    },
    {
      "epoch": 2.62,
      "learning_rate": 4.7168742921857306e-05,
      "loss": 0.79,
      "step": 3500
    },
    {
      "epoch": 2.99,
      "learning_rate": 4.669686674216686e-05,
      "loss": 0.8315,
      "step": 4000
    },
    {
      "epoch": 3.37,
      "learning_rate": 4.622499056247641e-05,
      "loss": 0.4823,
      "step": 4500
    },
    {
      "epoch": 3.37,
      "eval_bleu": 11.5074,
      "eval_gen_len": 16.1329,
      "eval_loss": 1.7483373880386353,
      "eval_runtime": 163.6405,
      "eval_samples_per_second": 16.328,
      "eval_steps_per_second": 1.021,
      "step": 4500
    },
    {
      "epoch": 3.74,
      "learning_rate": 4.575311438278596e-05,
      "loss": 0.5193,
      "step": 5000
    },
    {
      "epoch": 4.11,
      "learning_rate": 4.528123820309551e-05,
      "loss": 0.4565,
      "step": 5500
    },
    {
      "epoch": 4.49,
      "learning_rate": 4.480936202340506e-05,
      "loss": 0.3021,
      "step": 6000
    },
    {
      "epoch": 4.49,
      "eval_bleu": 11.452,
      "eval_gen_len": 16.2631,
      "eval_loss": 1.888548731803894,
      "eval_runtime": 159.6603,
      "eval_samples_per_second": 16.736,
      "eval_steps_per_second": 1.046,
      "step": 6000
    }
  ],
  "logging_steps": 500,
  "max_steps": 53480,
  "num_train_epochs": 40,
  "save_steps": 1500,
  "total_flos": 2.08044457721856e+17,
  "trial_name": null,
  "trial_params": null
}