Hugging Face's logo

paulo037
/
Llama-3.2-1B-Instruct-CoT-SQL

TensorBoard
Safetensors
Model card Files Metrics Community
Llama-3.2-1B-Instruct-CoT-SQL
File size: 2,702 Bytes 
b909362
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8936550491510277,
  "eval_steps": 200,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17873100983020554,
      "grad_norm": 0.5410762429237366,
      "learning_rate": 9.999142157322298e-05,
      "loss": 0.5394,
      "step": 200
    },
    {
      "epoch": 0.17873100983020554,
      "eval_loss": 0.2514195740222931,
      "eval_runtime": 56.7459,
      "eval_samples_per_second": 3.19,
      "eval_steps_per_second": 1.604,
      "step": 200
    },
    {
      "epoch": 0.3574620196604111,
      "grad_norm": 0.3244825303554535,
      "learning_rate": 9.95497608932715e-05,
      "loss": 0.2114,
      "step": 400
    },
    {
      "epoch": 0.3574620196604111,
      "eval_loss": 0.19941778481006622,
      "eval_runtime": 56.7365,
      "eval_samples_per_second": 3.19,
      "eval_steps_per_second": 1.604,
      "step": 400
    },
    {
      "epoch": 0.5361930294906166,
      "grad_norm": 0.23322512209415436,
      "learning_rate": 9.844466810070319e-05,
      "loss": 0.184,
      "step": 600
    },
    {
      "epoch": 0.5361930294906166,
      "eval_loss": 0.1872645616531372,
      "eval_runtime": 56.8389,
      "eval_samples_per_second": 3.184,
      "eval_steps_per_second": 1.601,
      "step": 600
    },
    {
      "epoch": 0.7149240393208222,
      "grad_norm": 0.20280934870243073,
      "learning_rate": 9.669093951406317e-05,
      "loss": 0.1797,
      "step": 800
    },
    {
      "epoch": 0.7149240393208222,
      "eval_loss": 0.18097320199012756,
      "eval_runtime": 56.861,
      "eval_samples_per_second": 3.183,
      "eval_steps_per_second": 1.6,
      "step": 800
    },
    {
      "epoch": 0.8936550491510277,
      "grad_norm": 0.18255303800106049,
      "learning_rate": 9.431205617221452e-05,
      "loss": 0.1719,
      "step": 1000
    },
    {
      "epoch": 0.8936550491510277,
      "eval_loss": 0.17648382484912872,
      "eval_runtime": 58.6626,
      "eval_samples_per_second": 3.085,
      "eval_steps_per_second": 1.551,
      "step": 1000
    }
  ],
  "logging_steps": 200,
  "max_steps": 5595,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1132992026783744e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}