Hugging Face's logo

cosail-knu
/
pythia-12b-draft-1b-mathReasoning

Safetensors
gpt_neox
Model card Files
xet
 Community
pythia-12b-draft-1b-mathReasoning
File size: 2,822 Bytes
b70380e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 111,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 83519.3984375,
      "learning_rate": 2.976784795504466e-05,
      "loss": 0.4468,
      "step": 10
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 65933.90625,
      "learning_rate": 2.8375080559518636e-05,
      "loss": 0.4158,
      "step": 20
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 70156.265625,
      "learning_rate": 2.5837574131992033e-05,
      "loss": 0.4158,
      "step": 30
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 58326.26953125,
      "learning_rate": 2.2372507375697017e-05,
      "loss": 0.3315,
      "step": 40
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 71025.0,
      "learning_rate": 1.8276446516666194e-05,
      "loss": 0.2244,
      "step": 50
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 70432.6796875,
      "learning_rate": 1.3899962956837443e-05,
      "loss": 0.2253,
      "step": 60
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 66741.46875,
      "learning_rate": 9.617628761892964e-06,
      "loss": 0.2252,
      "step": 70
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 54901.2890625,
      "learning_rate": 5.795957993502093e-06,
      "loss": 0.1684,
      "step": 80
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 70116.1796875,
      "learning_rate": 2.7620377055756426e-06,
      "loss": 0.111,
      "step": 90
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 50857.875,
      "learning_rate": 7.755333975558704e-07,
      "loss": 0.1102,
      "step": 100
    },
    {
      "epoch": 2.972972972972973,
      "grad_norm": 54652.5546875,
      "learning_rate": 6.464906595023967e-09,
      "loss": 0.1247,
      "step": 110
    },
    {
      "epoch": 3.0,
      "step": 111,
      "total_flos": 1.969709143346381e+16,
      "train_loss": 0.2534091994837598,
      "train_runtime": 84.269,
      "train_samples_per_second": 41.866,
      "train_steps_per_second": 1.317
    }
  ],
  "logging_steps": 10,
  "max_steps": 111,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.969709143346381e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}