Hugging Face's logo

lamahugface
/
sqlcoder-stackexchange

Text Generation
PEFT
Safetensors
Transformers
lora
Model card Files
xet
 Community
sqlcoder-stackexchange
File size: 3,015 Bytes
19eca80
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": 58,
  "best_metric": 0.08409731090068817,
  "best_model_checkpoint": "finetune/sqlcoder-finetuned\\checkpoint-58",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 87,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 1.021061897277832,
      "learning_rate": 0.00019882804237803488,
      "loss": 0.21164827346801757,
      "step": 10
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.6921543478965759,
      "learning_rate": 0.00018595696069872013,
      "loss": 0.06274759769439697,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.09725816547870636,
      "eval_runtime": 6.4034,
      "eval_samples_per_second": 3.904,
      "eval_steps_per_second": 2.03,
      "step": 29
    },
    {
      "epoch": 1.0353982300884956,
      "grad_norm": 0.7166405320167542,
      "learning_rate": 0.0001606225410966638,
      "loss": 0.05296058654785156,
      "step": 30
    },
    {
      "epoch": 1.3893805309734513,
      "grad_norm": 0.9153704643249512,
      "learning_rate": 0.0001264981502196662,
      "loss": 0.034215536713600156,
      "step": 40
    },
    {
      "epoch": 1.7433628318584071,
      "grad_norm": 0.3629709482192993,
      "learning_rate": 8.853165746015997e-05,
      "loss": 0.029726356267929077,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.08409731090068817,
      "eval_runtime": 6.3711,
      "eval_samples_per_second": 3.924,
      "eval_steps_per_second": 2.04,
      "step": 58
    },
    {
      "epoch": 2.0707964601769913,
      "grad_norm": 0.333617627620697,
      "learning_rate": 5.222801814877369e-05,
      "loss": 0.021506759524345397,
      "step": 60
    },
    {
      "epoch": 2.4247787610619467,
      "grad_norm": 0.31595540046691895,
      "learning_rate": 2.2851082017805703e-05,
      "loss": 0.014973489940166474,
      "step": 70
    },
    {
      "epoch": 2.7787610619469025,
      "grad_norm": 0.37690794467926025,
      "learning_rate": 4.660360794506946e-06,
      "loss": 0.008486340939998626,
      "step": 80
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.08731406927108765,
      "eval_runtime": 6.5254,
      "eval_samples_per_second": 3.831,
      "eval_steps_per_second": 1.992,
      "step": 87
    }
  ],
  "logging_steps": 10,
  "max_steps": 87,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9027218363252736.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}