Hugging Face's logo

anzorq
/
m2m100_1.2B_ft_kbd-ru_63K

Text2Text Generation
Transformers
PyTorch
Kabardian
Russian
m2m_100
Generated from Trainer
Inference Endpoints
Model card Files Community
1
m2m100_1.2B_ft_kbd-ru_63K
File size: 2,872 Bytes 
824dc30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2.271259147110775,
  "eval_steps": 500,
  "global_step": 9001,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "learning_rate": 4.8952813525107246e-05,
      "loss": 2.8381,
      "step": 500
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.790142148204223e-05,
      "loss": 2.3291,
      "step": 1000
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.7377273205087775e-05,
      "loss": 1.8496,
      "step": 1500
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.650303094011704e-05,
      "loss": 2.0352,
      "step": 2000
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.650096728067962e-05,
      "loss": 1.2524,
      "step": 2500
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.580003925196961e-05,
      "loss": 1.9539,
      "step": 3000
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.510051307931702e-05,
      "loss": 1.8607,
      "step": 3500
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.4399585050607007e-05,
      "loss": 1.7809,
      "step": 4000
    },
    {
      "epoch": 1.14,
      "learning_rate": 4.369865702189699e-05,
      "loss": 1.297,
      "step": 4500
    },
    {
      "epoch": 1.26,
      "learning_rate": 4.299772899318698e-05,
      "loss": 1.3119,
      "step": 5000
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.229820282053439e-05,
      "loss": 1.343,
      "step": 5500
    },
    {
      "epoch": 1.51,
      "learning_rate": 4.1597274791824374e-05,
      "loss": 1.2962,
      "step": 6000
    },
    {
      "epoch": 1.64,
      "learning_rate": 4.0897748619171785e-05,
      "loss": 1.2929,
      "step": 6500
    },
    {
      "epoch": 1.77,
      "learning_rate": 4.019682059046178e-05,
      "loss": 1.2726,
      "step": 7000
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.949589256175176e-05,
      "loss": 1.2686,
      "step": 7500
    },
    {
      "epoch": 2.02,
      "learning_rate": 3.879496453304175e-05,
      "loss": 1.1702,
      "step": 8000
    },
    {
      "epoch": 2.14,
      "learning_rate": 3.8094036504331735e-05,
      "loss": 0.8145,
      "step": 8500
    },
    {
      "epoch": 2.27,
      "learning_rate": 3.739310847562173e-05,
      "loss": 0.8225,
      "step": 9000
    },
    {
      "epoch": 2.27,
      "step": 9001,
      "total_flos": 5.460691370980147e+16,
      "train_loss": 5.4469778463318936e-05,
      "train_runtime": 1.6018,
      "train_samples_per_second": 89898.478,
      "train_steps_per_second": 5618.655
    }
  ],
  "logging_steps": 500,
  "max_steps": 9000,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "total_flos": 5.460691370980147e+16,
  "trial_name": null,
  "trial_params": null
}