Hugging Face's logo

kcarnold
/
inquisitive-full

Text2Text Generation
Transformers
PyTorch
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
inquisitive-full
File size: 2,307 Bytes 
98d6cee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 15.0,
  "global_step": 7470,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.6653279785809906e-05,
      "loss": 2.185,
      "step": 500
    },
    {
      "epoch": 2.01,
      "learning_rate": 4.3306559571619816e-05,
      "loss": 1.8076,
      "step": 1000
    },
    {
      "epoch": 3.01,
      "learning_rate": 3.995983935742972e-05,
      "loss": 1.5817,
      "step": 1500
    },
    {
      "epoch": 4.02,
      "learning_rate": 3.661311914323963e-05,
      "loss": 1.3979,
      "step": 2000
    },
    {
      "epoch": 5.02,
      "learning_rate": 3.326639892904953e-05,
      "loss": 1.2541,
      "step": 2500
    },
    {
      "epoch": 6.02,
      "learning_rate": 2.991967871485944e-05,
      "loss": 1.127,
      "step": 3000
    },
    {
      "epoch": 7.03,
      "learning_rate": 2.6572958500669343e-05,
      "loss": 1.0202,
      "step": 3500
    },
    {
      "epoch": 8.03,
      "learning_rate": 2.322623828647925e-05,
      "loss": 0.9236,
      "step": 4000
    },
    {
      "epoch": 9.04,
      "learning_rate": 1.9879518072289157e-05,
      "loss": 0.8492,
      "step": 4500
    },
    {
      "epoch": 10.04,
      "learning_rate": 1.6532797858099064e-05,
      "loss": 0.7856,
      "step": 5000
    },
    {
      "epoch": 11.04,
      "learning_rate": 1.318607764390897e-05,
      "loss": 0.7317,
      "step": 5500
    },
    {
      "epoch": 12.05,
      "learning_rate": 9.839357429718876e-06,
      "loss": 0.6839,
      "step": 6000
    },
    {
      "epoch": 13.05,
      "learning_rate": 6.492637215528783e-06,
      "loss": 0.6487,
      "step": 6500
    },
    {
      "epoch": 14.06,
      "learning_rate": 3.1459170013386886e-06,
      "loss": 0.6207,
      "step": 7000
    },
    {
      "epoch": 15.0,
      "step": 7470,
      "total_flos": 2.979518169858048e+16,
      "train_loss": 1.0831103017212078,
      "train_runtime": 1681.1253,
      "train_samples_per_second": 142.146,
      "train_steps_per_second": 4.443
    }
  ],
  "max_steps": 7470,
  "num_train_epochs": 15,
  "total_flos": 2.979518169858048e+16,
  "trial_name": null,
  "trial_params": null
}