Hugging Face's logo

osazuwa
/
causalLLM-kingdom

Text2Text Generation
Transformers
PyTorch
bart
Inference Endpoints
Model card Files Community
1
causalLLM-kingdom
File size: 2,051 Bytes 
f98b171
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.998773507767784,
  "global_step": 7335,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 3e-05,
      "loss": 0.1737,
      "step": 500
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.8384317104696252e-05,
      "loss": 0.067,
      "step": 1000
    },
    {
      "epoch": 0.61,
      "learning_rate": 2.6768634209392504e-05,
      "loss": 0.063,
      "step": 1500
    },
    {
      "epoch": 0.82,
      "learning_rate": 2.5152951314088755e-05,
      "loss": 0.0614,
      "step": 2000
    },
    {
      "epoch": 1.02,
      "learning_rate": 2.3537268418785007e-05,
      "loss": 0.0592,
      "step": 2500
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.1921585523481258e-05,
      "loss": 0.0563,
      "step": 3000
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.030590262817751e-05,
      "loss": 0.0543,
      "step": 3500
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.8690219732873765e-05,
      "loss": 0.0545,
      "step": 4000
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.7074536837570013e-05,
      "loss": 0.0546,
      "step": 4500
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.5458853942266264e-05,
      "loss": 0.0536,
      "step": 5000
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.3843171046962518e-05,
      "loss": 0.0512,
      "step": 5500
    },
    {
      "epoch": 2.45,
      "learning_rate": 1.2227488151658767e-05,
      "loss": 0.0506,
      "step": 6000
    },
    {
      "epoch": 2.66,
      "learning_rate": 1.0611805256355019e-05,
      "loss": 0.0498,
      "step": 6500
    },
    {
      "epoch": 2.86,
      "learning_rate": 8.996122361051272e-06,
      "loss": 0.0496,
      "step": 7000
    }
  ],
  "max_steps": 9784,
  "num_train_epochs": 4,
  "total_flos": 6.357201350295552e+16,
  "trial_name": null,
  "trial_params": null
}