Hugging Face's logo

lleticiasilvaa
/
StableCode-text2SQL-withoutquantization

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
sft
Model card Files Metrics Community
StableCode-text2SQL-withoutquantization
File size: 4,637 Bytes 
07494b2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9335978527249388,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09335978527249388,
      "grad_norm": 5.347364902496338,
      "learning_rate": 9.897551417342852e-05,
      "loss": 4.6888,
      "step": 100
    },
    {
      "epoch": 0.09335978527249388,
      "eval_loss": 0.3825870752334595,
      "eval_runtime": 23.2535,
      "eval_samples_per_second": 3.741,
      "eval_steps_per_second": 3.741,
      "step": 100
    },
    {
      "epoch": 0.18671957054498775,
      "grad_norm": 5.412732124328613,
      "learning_rate": 9.374809314115647e-05,
      "loss": 2.3316,
      "step": 200
    },
    {
      "epoch": 0.18671957054498775,
      "eval_loss": 0.25006037950515747,
      "eval_runtime": 23.4002,
      "eval_samples_per_second": 3.718,
      "eval_steps_per_second": 3.718,
      "step": 200
    },
    {
      "epoch": 0.2800793558174816,
      "grad_norm": 2.9451260566711426,
      "learning_rate": 8.454375586546417e-05,
      "loss": 1.5881,
      "step": 300
    },
    {
      "epoch": 0.2800793558174816,
      "eval_loss": 0.1890459656715393,
      "eval_runtime": 23.2549,
      "eval_samples_per_second": 3.741,
      "eval_steps_per_second": 3.741,
      "step": 300
    },
    {
      "epoch": 0.3734391410899755,
      "grad_norm": 5.892703533172607,
      "learning_rate": 7.219922175040683e-05,
      "loss": 1.2221,
      "step": 400
    },
    {
      "epoch": 0.3734391410899755,
      "eval_loss": 0.14931949973106384,
      "eval_runtime": 23.3305,
      "eval_samples_per_second": 3.729,
      "eval_steps_per_second": 3.729,
      "step": 400
    },
    {
      "epoch": 0.4667989263624694,
      "grad_norm": 3.341991424560547,
      "learning_rate": 5.783666949486448e-05,
      "loss": 1.038,
      "step": 500
    },
    {
      "epoch": 0.4667989263624694,
      "eval_loss": 0.13619396090507507,
      "eval_runtime": 23.3865,
      "eval_samples_per_second": 3.72,
      "eval_steps_per_second": 3.72,
      "step": 500
    },
    {
      "epoch": 0.5601587116349632,
      "grad_norm": 2.6955649852752686,
      "learning_rate": 4.276172554471998e-05,
      "loss": 0.9644,
      "step": 600
    },
    {
      "epoch": 0.5601587116349632,
      "eval_loss": 0.1279439479112625,
      "eval_runtime": 23.3534,
      "eval_samples_per_second": 3.725,
      "eval_steps_per_second": 3.725,
      "step": 600
    },
    {
      "epoch": 0.6535184969074571,
      "grad_norm": 3.1168127059936523,
      "learning_rate": 2.834477624505443e-05,
      "loss": 0.8806,
      "step": 700
    },
    {
      "epoch": 0.6535184969074571,
      "eval_loss": 0.12419606000185013,
      "eval_runtime": 23.2939,
      "eval_samples_per_second": 3.735,
      "eval_steps_per_second": 3.735,
      "step": 700
    },
    {
      "epoch": 0.746878282179951,
      "grad_norm": 2.7166848182678223,
      "learning_rate": 1.5896392999869652e-05,
      "loss": 0.8333,
      "step": 800
    },
    {
      "epoch": 0.746878282179951,
      "eval_loss": 0.1232759952545166,
      "eval_runtime": 23.4216,
      "eval_samples_per_second": 3.715,
      "eval_steps_per_second": 3.715,
      "step": 800
    },
    {
      "epoch": 0.8402380674524449,
      "grad_norm": 2.7149593830108643,
      "learning_rate": 6.548194903336408e-06,
      "loss": 0.8307,
      "step": 900
    },
    {
      "epoch": 0.8402380674524449,
      "eval_loss": 0.12131741642951965,
      "eval_runtime": 23.2806,
      "eval_samples_per_second": 3.737,
      "eval_steps_per_second": 3.737,
      "step": 900
    },
    {
      "epoch": 0.9335978527249388,
      "grad_norm": 2.5703158378601074,
      "learning_rate": 1.149979013737007e-06,
      "loss": 0.8138,
      "step": 1000
    },
    {
      "epoch": 0.9335978527249388,
      "eval_loss": 0.12097638100385666,
      "eval_runtime": 23.3058,
      "eval_samples_per_second": 3.733,
      "eval_steps_per_second": 3.733,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 1071,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.858832364327936e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}