Hugging Face's logo

phi0108
/
np_en

Safetensors
bert
Model card Files
xet
Community
np_en
File size: 3,209 Bytes 
f24be38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
121
122
123
124
125
126
127
128
129
130
 
{
  "best_metric": 0.3673701882362366,
  "best_model_checkpoint": "/content/drive/MyDrive/BERT/np_model_en/checkpoint-1281",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 5124,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.39,
      "learning_rate": 5.60967993754879e-06,
      "loss": 0.017,
      "step": 500
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.2193598750975805e-06,
      "loss": 0.0185,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9556333917104495,
      "eval_f1": 0.8681155105686216,
      "eval_loss": 0.3673701882362366,
      "eval_precision": 0.8556338028169014,
      "eval_recall": 0.8809667673716012,
      "eval_runtime": 12.6723,
      "eval_samples_per_second": 50.583,
      "eval_steps_per_second": 25.331,
      "step": 1281
    },
    {
      "epoch": 1.17,
      "learning_rate": 4.82903981264637e-06,
      "loss": 0.0171,
      "step": 1500
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.43871975019516e-06,
      "loss": 0.026,
      "step": 2000
    },
    {
      "epoch": 1.95,
      "learning_rate": 4.04839968774395e-06,
      "loss": 0.0147,
      "step": 2500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9529334500875657,
      "eval_f1": 0.8568033273915627,
      "eval_loss": 0.3900972008705139,
      "eval_precision": 0.842781998831093,
      "eval_recall": 0.8712990936555891,
      "eval_runtime": 12.7155,
      "eval_samples_per_second": 50.411,
      "eval_steps_per_second": 25.245,
      "step": 2562
    },
    {
      "epoch": 2.34,
      "learning_rate": 3.6580796252927404e-06,
      "loss": 0.0165,
      "step": 3000
    },
    {
      "epoch": 2.73,
      "learning_rate": 3.26775956284153e-06,
      "loss": 0.0157,
      "step": 3500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9541009924109749,
      "eval_f1": 0.8641901931649331,
      "eval_loss": 0.39443621039390564,
      "eval_precision": 0.8502923976608188,
      "eval_recall": 0.8785498489425981,
      "eval_runtime": 12.2687,
      "eval_samples_per_second": 52.247,
      "eval_steps_per_second": 26.164,
      "step": 3843
    },
    {
      "epoch": 3.12,
      "learning_rate": 2.8774395003903203e-06,
      "loss": 0.0099,
      "step": 4000
    },
    {
      "epoch": 3.51,
      "learning_rate": 2.48711943793911e-06,
      "loss": 0.0088,
      "step": 4500
    },
    {
      "epoch": 3.9,
      "learning_rate": 2.0967993754879002e-06,
      "loss": 0.0137,
      "step": 5000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9572387624051372,
      "eval_f1": 0.8727598566308244,
      "eval_loss": 0.37448590993881226,
      "eval_precision": 0.8629651506202008,
      "eval_recall": 0.8827794561933535,
      "eval_runtime": 13.0619,
      "eval_samples_per_second": 49.074,
      "eval_steps_per_second": 24.575,
      "step": 5124
    }
  ],
  "logging_steps": 500,
  "max_steps": 7686,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "total_flos": 193986016343568.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}