Hugging Face's logo

lleticiasilvaa
/
StableCode-text2SQL-withoutquantization2

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
sft
Inference Endpoints
Model card Files Metrics Community
StableCode-text2SQL-withoutquantization2
File size: 3,867 Bytes 
faeb0e1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.737456242707118,
  "eval_steps": 250,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.46674445740956827,
      "grad_norm": 6.355308532714844,
      "learning_rate": 9.899294610497411e-05,
      "loss": 3.4363,
      "step": 250
    },
    {
      "epoch": 0.46674445740956827,
      "eval_loss": 0.2021917849779129,
      "eval_runtime": 11.2146,
      "eval_samples_per_second": 7.758,
      "eval_steps_per_second": 7.758,
      "step": 250
    },
    {
      "epoch": 0.9334889148191365,
      "grad_norm": 2.1196815967559814,
      "learning_rate": 9.378729871108362e-05,
      "loss": 1.1086,
      "step": 500
    },
    {
      "epoch": 0.9334889148191365,
      "eval_loss": 0.13436643779277802,
      "eval_runtime": 11.2216,
      "eval_samples_per_second": 7.753,
      "eval_steps_per_second": 7.753,
      "step": 500
    },
    {
      "epoch": 1.4014002333722286,
      "grad_norm": 0.9552448391914368,
      "learning_rate": 8.459812499901582e-05,
      "loss": 0.817,
      "step": 750
    },
    {
      "epoch": 1.4014002333722286,
      "eval_loss": 0.12236687541007996,
      "eval_runtime": 11.2082,
      "eval_samples_per_second": 7.762,
      "eval_steps_per_second": 7.762,
      "step": 750
    },
    {
      "epoch": 1.8681446907817971,
      "grad_norm": 0.8024685978889465,
      "learning_rate": 7.226140518225348e-05,
      "loss": 0.7757,
      "step": 1000
    },
    {
      "epoch": 1.8681446907817971,
      "eval_loss": 0.11266180872917175,
      "eval_runtime": 11.2333,
      "eval_samples_per_second": 7.745,
      "eval_steps_per_second": 7.745,
      "step": 1000
    },
    {
      "epoch": 2.336056009334889,
      "grad_norm": 1.2465705871582031,
      "learning_rate": 5.7899465814766306e-05,
      "loss": 0.6768,
      "step": 1250
    },
    {
      "epoch": 2.336056009334889,
      "eval_loss": 0.11375312507152557,
      "eval_runtime": 11.2449,
      "eval_samples_per_second": 7.737,
      "eval_steps_per_second": 7.737,
      "step": 1250
    },
    {
      "epoch": 2.8028004667444573,
      "grad_norm": 1.350077748298645,
      "learning_rate": 4.281887672695056e-05,
      "loss": 0.6549,
      "step": 1500
    },
    {
      "epoch": 2.8028004667444573,
      "eval_loss": 0.10809295624494553,
      "eval_runtime": 11.217,
      "eval_samples_per_second": 7.756,
      "eval_steps_per_second": 7.756,
      "step": 1500
    },
    {
      "epoch": 3.2707117852975496,
      "grad_norm": 1.6034570932388306,
      "learning_rate": 2.8391586527038743e-05,
      "loss": 0.627,
      "step": 1750
    },
    {
      "epoch": 3.2707117852975496,
      "eval_loss": 0.10999161005020142,
      "eval_runtime": 11.2004,
      "eval_samples_per_second": 7.768,
      "eval_steps_per_second": 7.768,
      "step": 1750
    },
    {
      "epoch": 3.737456242707118,
      "grad_norm": 1.894575595855713,
      "learning_rate": 1.5930110302808637e-05,
      "loss": 0.5768,
      "step": 2000
    },
    {
      "epoch": 3.737456242707118,
      "eval_loss": 0.10841962695121765,
      "eval_runtime": 11.2,
      "eval_samples_per_second": 7.768,
      "eval_steps_per_second": 7.768,
      "step": 2000
    }
  ],
  "logging_steps": 250,
  "max_steps": 2675,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.153354536978227e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}