Hugging Face's logo

SujanKarki
/
Qwen2.5-3B-Instruct_text_to_sql_qlora

PEFT
TensorBoard
Safetensors
Model card Files Metrics Community
Qwen2.5-3B-Instruct_text_to_sql_qlora
File size: 2,595 Bytes 
bd9e1a3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7886435331230284,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07886435331230283,
      "grad_norm": 0.04835394397377968,
      "learning_rate": 0.0002,
      "loss": 0.66,
      "step": 50
    },
    {
      "epoch": 0.15772870662460567,
      "grad_norm": 0.0558183453977108,
      "learning_rate": 0.0001996405260481014,
      "loss": 0.4766,
      "step": 100
    },
    {
      "epoch": 0.23659305993690852,
      "grad_norm": 0.049051981419324875,
      "learning_rate": 0.00019856468862284752,
      "loss": 0.4494,
      "step": 150
    },
    {
      "epoch": 0.31545741324921134,
      "grad_norm": 0.05015840008854866,
      "learning_rate": 0.00019678022243485544,
      "loss": 0.4443,
      "step": 200
    },
    {
      "epoch": 0.3943217665615142,
      "grad_norm": 0.04640612378716469,
      "learning_rate": 0.0001942999568663777,
      "loss": 0.4342,
      "step": 250
    },
    {
      "epoch": 0.47318611987381703,
      "grad_norm": 0.046447452157735825,
      "learning_rate": 0.00019114172373472754,
      "loss": 0.4287,
      "step": 300
    },
    {
      "epoch": 0.5520504731861199,
      "grad_norm": 0.0452335923910141,
      "learning_rate": 0.0001873282290908019,
      "loss": 0.4267,
      "step": 350
    },
    {
      "epoch": 0.6309148264984227,
      "grad_norm": 0.046432506293058395,
      "learning_rate": 0.00018288688997440474,
      "loss": 0.4235,
      "step": 400
    },
    {
      "epoch": 0.7097791798107256,
      "grad_norm": 0.5536419749259949,
      "learning_rate": 0.00017784963730001395,
      "loss": 0.4187,
      "step": 450
    },
    {
      "epoch": 0.7886435331230284,
      "grad_norm": 0.05094370245933533,
      "learning_rate": 0.00017225268629014097,
      "loss": 0.4134,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 1902,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4218388570112e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}