Hugging Face's logo

sqllama
/
lora-wikisql-dono

Model card Files Community
lora-wikisql-dono
File size: 2,960 Bytes 
7a5e46a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.6641973853111267,
  "best_model_checkpoint": "./lora-alpaca/checkpoint-200",
  "epoch": 0.47058823529411764,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 2.0163,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.9284,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.77,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.3452,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00015,
      "loss": 0.9243,
      "step": 50
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.8385,
      "step": 60
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.7986,
      "step": 70
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.7786,
      "step": 80
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00027,
      "loss": 0.75,
      "step": 90
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.7389,
      "step": 100
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00029076923076923073,
      "loss": 0.7248,
      "step": 110
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002815384615384615,
      "loss": 0.7199,
      "step": 120
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002723076923076923,
      "loss": 0.7159,
      "step": 130
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00026307692307692306,
      "loss": 0.7029,
      "step": 140
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002538461538461538,
      "loss": 0.6851,
      "step": 150
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002446153846153846,
      "loss": 0.6935,
      "step": 160
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00023538461538461536,
      "loss": 0.6737,
      "step": 170
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00022615384615384614,
      "loss": 0.682,
      "step": 180
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002169230769230769,
      "loss": 0.667,
      "step": 190
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00020769230769230766,
      "loss": 0.6731,
      "step": 200
    },
    {
      "epoch": 0.47,
      "eval_loss": 0.6641973853111267,
      "eval_runtime": 178.902,
      "eval_samples_per_second": 11.179,
      "eval_steps_per_second": 0.699,
      "step": 200
    }
  ],
  "max_steps": 425,
  "num_train_epochs": 1,
  "total_flos": 2.5997626021249024e+17,
  "trial_name": null,
  "trial_params": null
}