Hugging Face's logo

Elkelouizajo
/
bert_mixed

Safetensors
bert
Generated from Trainer
Model card Files Community
bert_mixed
File size: 2,573 Bytes 
3403fcb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.251625812906453,
  "eval_steps": 500,
  "global_step": 6500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 40.72060012817383,
      "learning_rate": 1.8999499749874938e-05,
      "loss": 0.416,
      "step": 500
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.45640167593955994,
      "learning_rate": 1.7998999499749875e-05,
      "loss": 0.259,
      "step": 1000
    },
    {
      "epoch": 0.75,
      "grad_norm": 24.118961334228516,
      "learning_rate": 1.6998499249624815e-05,
      "loss": 0.2726,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "grad_norm": 43.76200485229492,
      "learning_rate": 1.599799899949975e-05,
      "loss": 0.2471,
      "step": 2000
    },
    {
      "epoch": 1.25,
      "grad_norm": 31.93831443786621,
      "learning_rate": 1.4997498749374688e-05,
      "loss": 0.1518,
      "step": 2500
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.02012985199689865,
      "learning_rate": 1.3996998499249626e-05,
      "loss": 0.1421,
      "step": 3000
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.22942015528678894,
      "learning_rate": 1.2996498249124563e-05,
      "loss": 0.1463,
      "step": 3500
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.18562756478786469,
      "learning_rate": 1.19959979989995e-05,
      "loss": 0.1512,
      "step": 4000
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.14861415326595306,
      "learning_rate": 1.0995497748874438e-05,
      "loss": 0.0811,
      "step": 4500
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.19507120549678802,
      "learning_rate": 9.994997498749376e-06,
      "loss": 0.0634,
      "step": 5000
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.011564640328288078,
      "learning_rate": 8.994497248624313e-06,
      "loss": 0.0776,
      "step": 5500
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.1320619136095047,
      "learning_rate": 7.993996998499251e-06,
      "loss": 0.0583,
      "step": 6000
    },
    {
      "epoch": 3.25,
      "grad_norm": 0.002501310082152486,
      "learning_rate": 6.9934967483741875e-06,
      "loss": 0.0283,
      "step": 6500
    }
  ],
  "logging_steps": 500,
  "max_steps": 9995,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.2113709826219008e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}