Hugging Face's logo

anzorq
/
m2m100_418M_ft_ru-kbd_50K

Text2Text Generation
Transformers
PyTorch
Russian
Kabardian
m2m_100
Generated from Trainer
Inference Endpoints
Model card Files Community
m2m100_418M_ft_ru-kbd_50K
File size: 2,854 Bytes 
fb5797c
 
 
32be0c1
fb5797c
32be0c1
fb5797c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e9fbe8e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32be0c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fb5797c
 
 
32be0c1
 
fb5797c
32be0c1
fb5797c
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 9495,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.47,
      "learning_rate": 4.211690363349131e-05,
      "loss": 2.4319,
      "step": 500
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.4218009478672984e-05,
      "loss": 1.6405,
      "step": 1000
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.631911532385466e-05,
      "loss": 1.3383,
      "step": 1500
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.8420221169036335e-05,
      "loss": 1.2262,
      "step": 2000
    },
    {
      "epoch": 2.37,
      "learning_rate": 1.052132701421801e-05,
      "loss": 1.0607,
      "step": 2500
    },
    {
      "epoch": 2.84,
      "learning_rate": 2.622432859399684e-06,
      "loss": 0.9868,
      "step": 3000
    },
    {
      "epoch": 3.32,
      "learning_rate": 2.2361769352290678e-05,
      "loss": 0.9531,
      "step": 3500
    },
    {
      "epoch": 3.79,
      "learning_rate": 1.8412322274881517e-05,
      "loss": 0.9439,
      "step": 4000
    },
    {
      "epoch": 4.27,
      "learning_rate": 1.4462875197472355e-05,
      "loss": 0.8432,
      "step": 4500
    },
    {
      "epoch": 4.74,
      "learning_rate": 1.0513428120063192e-05,
      "loss": 0.7916,
      "step": 5000
    },
    {
      "epoch": 5.21,
      "learning_rate": 6.563981042654029e-06,
      "loss": 0.7389,
      "step": 5500
    },
    {
      "epoch": 5.69,
      "learning_rate": 2.6145339652448658e-06,
      "loss": 0.6903,
      "step": 6000
    },
    {
      "epoch": 6.16,
      "learning_rate": 1.577672459189047e-05,
      "loss": 0.6838,
      "step": 6500
    },
    {
      "epoch": 6.64,
      "learning_rate": 1.3143759873617695e-05,
      "loss": 0.675,
      "step": 7000
    },
    {
      "epoch": 7.11,
      "learning_rate": 1.0510795155344918e-05,
      "loss": 0.6546,
      "step": 7500
    },
    {
      "epoch": 7.58,
      "learning_rate": 7.877830437072143e-06,
      "loss": 0.5931,
      "step": 8000
    },
    {
      "epoch": 8.06,
      "learning_rate": 5.244865718799368e-06,
      "loss": 0.5853,
      "step": 8500
    },
    {
      "epoch": 8.53,
      "learning_rate": 2.611901000526593e-06,
      "loss": 0.5335,
      "step": 9000
    },
    {
      "epoch": 9.0,
      "step": 9495,
      "total_flos": 4.383681832019558e+16,
      "train_loss": 0.22391470878484565,
      "train_runtime": 758.6651,
      "train_samples_per_second": 600.467,
      "train_steps_per_second": 12.515
    }
  ],
  "logging_steps": 500,
  "max_steps": 9495,
  "num_train_epochs": 9,
  "save_steps": 500,
  "total_flos": 4.383681832019558e+16,
  "trial_name": null,
  "trial_params": null
}