Hugging Face's logo

tmnam20
/
codellama_instruct_pt_text2sql

Generated from Trainer
Model card Files Community
codellama_instruct_pt_text2sql
File size: 4,665 Bytes 
71a2e5f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
 
{
  "best_metric": 0.01821763999760151,
  "best_model_checkpoint": "./text2sql/codellama_instruct_pt_text2sql/checkpoint-18000",
  "epoch": 2.005152126992968,
  "eval_steps": 2000,
  "global_step": 18000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.1139992573338283e-07,
      "loss": 1.2191,
      "step": 1
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00011139992573338284,
      "loss": 0.2684,
      "step": 1000
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00022279985146676567,
      "loss": 0.0693,
      "step": 2000
    },
    {
      "epoch": 0.22,
      "eval_loss": 0.05887996032834053,
      "eval_runtime": 171.127,
      "eval_samples_per_second": 11.687,
      "eval_steps_per_second": 1.461,
      "step": 2000
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00029781686301467276,
      "loss": 0.0565,
      "step": 3000
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002907056676227274,
      "loss": 0.047,
      "step": 4000
    },
    {
      "epoch": 0.45,
      "eval_loss": 0.03957173973321915,
      "eval_runtime": 171.3682,
      "eval_samples_per_second": 11.671,
      "eval_steps_per_second": 1.459,
      "step": 4000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00028359447223078195,
      "loss": 0.0403,
      "step": 5000
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002764832768388366,
      "loss": 0.0364,
      "step": 6000
    },
    {
      "epoch": 0.67,
      "eval_loss": 0.030724667012691498,
      "eval_runtime": 170.9405,
      "eval_samples_per_second": 11.7,
      "eval_steps_per_second": 1.462,
      "step": 6000
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002693720814468912,
      "loss": 0.0341,
      "step": 7000
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00026226088605494583,
      "loss": 0.0311,
      "step": 8000
    },
    {
      "epoch": 0.89,
      "eval_loss": 0.027806701138615608,
      "eval_runtime": 171.064,
      "eval_samples_per_second": 11.692,
      "eval_steps_per_second": 1.461,
      "step": 8000
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00025514969066300046,
      "loss": 0.0289,
      "step": 9000
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00024803849527105503,
      "loss": 0.0251,
      "step": 10000
    },
    {
      "epoch": 1.11,
      "eval_loss": 0.024082325398921967,
      "eval_runtime": 171.4689,
      "eval_samples_per_second": 11.664,
      "eval_steps_per_second": 1.458,
      "step": 10000
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00024092729987910966,
      "loss": 0.0242,
      "step": 11000
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00023381610448716428,
      "loss": 0.0243,
      "step": 12000
    },
    {
      "epoch": 1.34,
      "eval_loss": 0.02279273048043251,
      "eval_runtime": 171.2147,
      "eval_samples_per_second": 11.681,
      "eval_steps_per_second": 1.46,
      "step": 12000
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00022670490909521888,
      "loss": 0.0219,
      "step": 13000
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002195937137032735,
      "loss": 0.0227,
      "step": 14000
    },
    {
      "epoch": 1.56,
      "eval_loss": 0.022252563387155533,
      "eval_runtime": 171.1834,
      "eval_samples_per_second": 11.683,
      "eval_steps_per_second": 1.46,
      "step": 14000
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00021248251831132813,
      "loss": 0.0218,
      "step": 15000
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00020537132291938273,
      "loss": 0.0212,
      "step": 16000
    },
    {
      "epoch": 1.78,
      "eval_loss": 0.020056582987308502,
      "eval_runtime": 170.9191,
      "eval_samples_per_second": 11.701,
      "eval_steps_per_second": 1.463,
      "step": 16000
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00019826012752743733,
      "loss": 0.0208,
      "step": 17000
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00019114893213549196,
      "loss": 0.0202,
      "step": 18000
    },
    {
      "epoch": 2.01,
      "eval_loss": 0.01821763999760151,
      "eval_runtime": 171.4736,
      "eval_samples_per_second": 11.664,
      "eval_steps_per_second": 1.458,
      "step": 18000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 44880,
  "num_train_epochs": 5,
  "save_steps": 2000,
  "total_flos": 8.764643133510451e+18,
  "trial_name": null,
  "trial_params": null
}