Hugging Face's logo

aixk
/
fasthypernet118

Safetensors
Model card Files
xet
 Community
fasthypernet118
File size: 2,463 Bytes
cc08567
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005289256198347108,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005289256198347108,
      "grad_norm": 854.5975952148438,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 8.0868,
      "step": 10
    },
    {
      "epoch": 0.0010578512396694215,
      "grad_norm": 138.97642517089844,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 7.9821,
      "step": 20
    },
    {
      "epoch": 0.0015867768595041322,
      "grad_norm": 94.62591552734375,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 7.834,
      "step": 30
    },
    {
      "epoch": 0.002115702479338843,
      "grad_norm": 60.26542663574219,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 7.7639,
      "step": 40
    },
    {
      "epoch": 0.002644628099173554,
      "grad_norm": 42.77493667602539,
      "learning_rate": 3.6e-06,
      "loss": 7.8094,
      "step": 50
    },
    {
      "epoch": 0.0031735537190082643,
      "grad_norm": 95.4593505859375,
      "learning_rate": 4.4e-06,
      "loss": 7.6688,
      "step": 60
    },
    {
      "epoch": 0.0037024793388429752,
      "grad_norm": 136.63748168945312,
      "learning_rate": 5.2e-06,
      "loss": 7.8215,
      "step": 70
    },
    {
      "epoch": 0.004231404958677686,
      "grad_norm": 85.70698547363281,
      "learning_rate": 6e-06,
      "loss": 7.6843,
      "step": 80
    },
    {
      "epoch": 0.004760330578512397,
      "grad_norm": 212.5619659423828,
      "learning_rate": 6.800000000000001e-06,
      "loss": 7.7493,
      "step": 90
    },
    {
      "epoch": 0.005289256198347108,
      "grad_norm": 134.31051635742188,
      "learning_rate": 7.6e-06,
      "loss": 7.5662,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 529,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1740714979737600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}