Hugging Face's logo

masakhane
/
m2m100_418M_fr_fon_rel

Text2Text Generation
Transformers
PyTorch
French
Fon
m2m_100
Inference Endpoints
Model card Files Community
2
m2m100_418M_fr_fon_rel
File size: 2,909 Bytes 
fc9ba13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
138
139
140
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 9657,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "learning_rate": 4.7411204307756033e-05,
      "loss": 2.4532,
      "step": 500
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.482240861551207e-05,
      "loss": 1.6939,
      "step": 1000
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.2233612923268096e-05,
      "loss": 1.4835,
      "step": 1500
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.964481723102413e-05,
      "loss": 1.3597,
      "step": 2000
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.7056021538780165e-05,
      "loss": 1.2939,
      "step": 2500
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.4467225846536196e-05,
      "loss": 1.2304,
      "step": 3000
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.187843015429223e-05,
      "loss": 1.1246,
      "step": 3500
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.9289634462048254e-05,
      "loss": 1.0545,
      "step": 4000
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.670083876980429e-05,
      "loss": 1.0199,
      "step": 4500
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.411204307756032e-05,
      "loss": 1.0216,
      "step": 5000
    },
    {
      "epoch": 1.71,
      "learning_rate": 2.1523247385316354e-05,
      "loss": 0.9894,
      "step": 5500
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.8934451693072382e-05,
      "loss": 0.9787,
      "step": 6000
    },
    {
      "epoch": 2.02,
      "learning_rate": 1.6345656000828417e-05,
      "loss": 0.9494,
      "step": 6500
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.3756860308584446e-05,
      "loss": 0.8392,
      "step": 7000
    },
    {
      "epoch": 2.33,
      "learning_rate": 1.1168064616340479e-05,
      "loss": 0.8201,
      "step": 7500
    },
    {
      "epoch": 2.49,
      "learning_rate": 8.57926892409651e-06,
      "loss": 0.8225,
      "step": 8000
    },
    {
      "epoch": 2.64,
      "learning_rate": 5.9904732318525425e-06,
      "loss": 0.8176,
      "step": 8500
    },
    {
      "epoch": 2.8,
      "learning_rate": 3.401677539608574e-06,
      "loss": 0.8109,
      "step": 9000
    },
    {
      "epoch": 2.95,
      "learning_rate": 8.12881847364606e-07,
      "loss": 0.7971,
      "step": 9500
    },
    {
      "epoch": 3.0,
      "step": 9657,
      "total_flos": 1.0817124216717312e+16,
      "train_loss": 1.1291042611109392,
      "train_runtime": 3221.1049,
      "train_samples_per_second": 29.974,
      "train_steps_per_second": 2.998
    }
  ],
  "max_steps": 9657,
  "num_train_epochs": 3,
  "total_flos": 1.0817124216717312e+16,
  "trial_name": null,
  "trial_params": null
}