Hugging Face's logo

TuhinColumbia
/
germanpoetrymany

Text2Text Generation
Transformers
PyTorch
mbart
Inference Endpoints
Model card Files Community
1
germanpoetrymany
File size: 2,953 Bytes 
c1597f6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 8340,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18,
      "learning_rate": 4.8501199040767384e-05,
      "loss": 2.0957,
      "step": 500
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.700239808153478e-05,
      "loss": 2.022,
      "step": 1000
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.550359712230216e-05,
      "loss": 1.9842,
      "step": 1500
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.400479616306955e-05,
      "loss": 1.9624,
      "step": 2000
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.2505995203836936e-05,
      "loss": 1.9237,
      "step": 2500
    },
    {
      "epoch": 1.0,
      "eval_bleu": 25.317,
      "eval_gen_len": 11.9956,
      "eval_loss": 1.8112746477127075,
      "eval_runtime": 164.477,
      "eval_samples_per_second": 12.518,
      "step": 2780
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.100719424460432e-05,
      "loss": 1.7808,
      "step": 3000
    },
    {
      "epoch": 1.26,
      "learning_rate": 3.9508393285371705e-05,
      "loss": 1.6002,
      "step": 3500
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.8009592326139094e-05,
      "loss": 1.6191,
      "step": 4000
    },
    {
      "epoch": 1.62,
      "learning_rate": 3.6510791366906475e-05,
      "loss": 1.6215,
      "step": 4500
    },
    {
      "epoch": 1.8,
      "learning_rate": 3.501199040767386e-05,
      "loss": 1.6134,
      "step": 5000
    },
    {
      "epoch": 1.98,
      "learning_rate": 3.351318944844125e-05,
      "loss": 1.6013,
      "step": 5500
    },
    {
      "epoch": 2.0,
      "eval_bleu": 25.523,
      "eval_gen_len": 12.0345,
      "eval_loss": 1.8125885725021362,
      "eval_runtime": 182.336,
      "eval_samples_per_second": 11.292,
      "step": 5560
    },
    {
      "epoch": 2.16,
      "learning_rate": 3.201438848920863e-05,
      "loss": 1.3405,
      "step": 6000
    },
    {
      "epoch": 2.34,
      "learning_rate": 3.051558752997602e-05,
      "loss": 1.3232,
      "step": 6500
    },
    {
      "epoch": 2.52,
      "learning_rate": 2.9016786570743405e-05,
      "loss": 1.3278,
      "step": 7000
    },
    {
      "epoch": 2.7,
      "learning_rate": 2.7517985611510793e-05,
      "loss": 1.3295,
      "step": 7500
    },
    {
      "epoch": 2.88,
      "learning_rate": 2.6019184652278178e-05,
      "loss": 1.335,
      "step": 8000
    },
    {
      "epoch": 3.0,
      "eval_bleu": 25.7471,
      "eval_gen_len": 11.8786,
      "eval_loss": 1.90364408493042,
      "eval_runtime": 179.3491,
      "eval_samples_per_second": 11.48,
      "step": 8340
    }
  ],
  "max_steps": 16680,
  "num_train_epochs": 6,
  "total_flos": 9.179024483690496e+16,
  "trial_name": null,
  "trial_params": null
}