Hugging Face's logo

smilemikan
/
nllb-finetuned-jpn-to-ain-2

Text2Text Generation
Transformers
PyTorch
m2m_100
Inference Endpoints
Model card Files Community
nllb-finetuned-jpn-to-ain-2
File size: 2,751 Bytes 
14d2d68
c608d35
 
 
14d2d68
c608d35
14d2d68
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c03f77a
 
 
 
 
 
 
 
 
 
 
 
 
 
a48dfeb
 
 
 
 
 
 
 
 
 
 
 
 
 
e4456fe
 
 
 
 
 
 
 
 
 
 
 
 
 
47afcf2
 
 
 
 
 
 
 
 
 
 
 
 
 
af03f50
 
 
 
 
 
 
 
 
 
 
 
 
 
c608d35
 
 
 
 
 
 
 
 
 
 
 
 
 
14d2d68
 
 
 
 
 
c608d35
14d2d68
 
 
 
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
 
{
  "best_metric": 2.30385422706604,
  "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-3500",
  "epoch": 0.771094954835867,
  "eval_steps": 500,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 1.9833333333333335e-05,
      "loss": 4.6196,
      "step": 500
    },
    {
      "epoch": 0.11,
      "eval_loss": 3.7452237606048584,
      "eval_runtime": 43.586,
      "eval_samples_per_second": 208.278,
      "eval_steps_per_second": 13.032,
      "step": 500
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9666666666666666e-05,
      "loss": 3.5915,
      "step": 1000
    },
    {
      "epoch": 0.22,
      "eval_loss": 3.2064383029937744,
      "eval_runtime": 43.0726,
      "eval_samples_per_second": 210.76,
      "eval_steps_per_second": 13.187,
      "step": 1000
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.95e-05,
      "loss": 3.1484,
      "step": 1500
    },
    {
      "epoch": 0.33,
      "eval_loss": 2.8919074535369873,
      "eval_runtime": 42.8255,
      "eval_samples_per_second": 211.977,
      "eval_steps_per_second": 13.263,
      "step": 1500
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.9333333333333333e-05,
      "loss": 2.902,
      "step": 2000
    },
    {
      "epoch": 0.44,
      "eval_loss": 2.679006338119507,
      "eval_runtime": 43.6162,
      "eval_samples_per_second": 208.134,
      "eval_steps_per_second": 13.023,
      "step": 2000
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.916666666666667e-05,
      "loss": 2.7296,
      "step": 2500
    },
    {
      "epoch": 0.55,
      "eval_loss": 2.5206823348999023,
      "eval_runtime": 42.8291,
      "eval_samples_per_second": 211.959,
      "eval_steps_per_second": 13.262,
      "step": 2500
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.9000333333333335e-05,
      "loss": 2.6105,
      "step": 3000
    },
    {
      "epoch": 0.66,
      "eval_loss": 2.394014835357666,
      "eval_runtime": 42.8022,
      "eval_samples_per_second": 212.092,
      "eval_steps_per_second": 13.27,
      "step": 3000
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.883366666666667e-05,
      "loss": 2.5068,
      "step": 3500
    },
    {
      "epoch": 0.77,
      "eval_loss": 2.30385422706604,
      "eval_runtime": 44.6981,
      "eval_samples_per_second": 203.096,
      "eval_steps_per_second": 12.707,
      "step": 3500
    }
  ],
  "logging_steps": 500,
  "max_steps": 60000,
  "num_train_epochs": 14,
  "save_steps": 500,
  "total_flos": 3540439421681664.0,
  "trial_name": null,
  "trial_params": null
}