Hugging Face's logo

Mestopholis
/
test-train

Text Generation
TensorBoard
Safetensors
Trained with AutoTrain
Model card Files
xet
Metrics Community
test-train
File size: 2,742 Bytes 
4c2b43e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 39.25,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.25,
      "learning_rate": 2.5e-05,
      "loss": 1.305,
      "step": 2
    },
    {
      "epoch": 3.25,
      "learning_rate": 5e-05,
      "loss": 1.2911,
      "step": 4
    },
    {
      "epoch": 5.25,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2513,
      "step": 6
    },
    {
      "epoch": 7.25,
      "learning_rate": 0.0001,
      "loss": 1.1854,
      "step": 8
    },
    {
      "epoch": 9.25,
      "learning_rate": 0.000125,
      "loss": 1.09,
      "step": 10
    },
    {
      "epoch": 11.25,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.9929,
      "step": 12
    },
    {
      "epoch": 13.25,
      "learning_rate": 0.000175,
      "loss": 0.9166,
      "step": 14
    },
    {
      "epoch": 15.25,
      "learning_rate": 0.0002,
      "loss": 0.8551,
      "step": 16
    },
    {
      "epoch": 17.25,
      "learning_rate": 0.00019722222222222225,
      "loss": 0.7925,
      "step": 18
    },
    {
      "epoch": 19.25,
      "learning_rate": 0.00019444444444444446,
      "loss": 0.7263,
      "step": 20
    },
    {
      "epoch": 21.25,
      "learning_rate": 0.00019166666666666667,
      "loss": 0.6448,
      "step": 22
    },
    {
      "epoch": 23.25,
      "learning_rate": 0.00018888888888888888,
      "loss": 0.5356,
      "step": 24
    },
    {
      "epoch": 25.25,
      "learning_rate": 0.00018611111111111112,
      "loss": 0.4362,
      "step": 26
    },
    {
      "epoch": 27.25,
      "learning_rate": 0.00018333333333333334,
      "loss": 0.3425,
      "step": 28
    },
    {
      "epoch": 29.25,
      "learning_rate": 0.00018055555555555557,
      "loss": 0.2636,
      "step": 30
    },
    {
      "epoch": 31.25,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.1984,
      "step": 32
    },
    {
      "epoch": 33.25,
      "learning_rate": 0.000175,
      "loss": 0.1303,
      "step": 34
    },
    {
      "epoch": 35.25,
      "learning_rate": 0.00017222222222222224,
      "loss": 0.081,
      "step": 36
    },
    {
      "epoch": 37.25,
      "learning_rate": 0.00016944444444444445,
      "loss": 0.0457,
      "step": 38
    },
    {
      "epoch": 39.25,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.0268,
      "step": 40
    }
  ],
  "logging_steps": 2,
  "max_steps": 160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 500,
  "total_flos": 3251764702740480.0,
  "trial_name": null,
  "trial_params": null
}