Hugging Face's logo

xihajun
/
cnn_dailymail_long_training

PEFT
PyTorch
Model card Files Community
cnn_dailymail_long_training
File size: 3,140 Bytes 
40749d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 23061,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 0.003427580225498699,
      "loss": 5.0966,
      "step": 1000
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.006896790980052038,
      "loss": 9.0282,
      "step": 2000
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.01020294882914137,
      "loss": 9.2789,
      "step": 3000
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.010206418039895923,
      "loss": 812422.208,
      "step": 4000
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 5000
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 6000
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 7000
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 8000
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 9000
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 10000
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 11000
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 12000
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 13000
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 14000
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 15000
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 16000
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 17000
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 18000
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 19000
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 20000
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 21000
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 22000
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.010206418039895923,
      "loss": 0.0,
      "step": 23000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 57650,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 5.243846810778206e+19,
  "trial_name": null,
  "trial_params": null
}