Hugging Face's logo

seanfarrell
/
bert_v2_test

Safetensors
bert
Model card Files
xet
 Community
bert_v2_test
File size: 3,405 Bytes
544ce42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": 1488,
  "best_metric": 0.7845666705758181,
  "best_model_checkpoint": "/home/users/seanfarr/PetBERT/projects/PetBERT_disease/model/checkpoint-1488",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1488,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_f1": 0.7454965357967668,
      "eval_loss": 0.020537996664643288,
      "eval_precision": 0.7096065069245988,
      "eval_recall": 0.7852104110921917,
      "eval_runtime": 23.7231,
      "eval_samples_per_second": 210.639,
      "eval_steps_per_second": 6.618,
      "step": 248
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.7633587786259544,
      "eval_loss": 0.02155238576233387,
      "eval_precision": 0.71795970852979,
      "eval_recall": 0.8148868888348334,
      "eval_runtime": 23.8598,
      "eval_samples_per_second": 209.432,
      "eval_steps_per_second": 6.58,
      "step": 496
    },
    {
      "epoch": 2.0161290322580645,
      "grad_norm": 0.2515815198421478,
      "learning_rate": 4.9899395161290325e-05,
      "loss": 0.06134441375732422,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.7608919382504288,
      "eval_loss": 0.02318727970123291,
      "eval_precision": 0.7179542511868796,
      "eval_recall": 0.8092921430308927,
      "eval_runtime": 23.871,
      "eval_samples_per_second": 209.333,
      "eval_steps_per_second": 6.577,
      "step": 744
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.7779738792799152,
      "eval_loss": 0.024106163531541824,
      "eval_precision": 0.7534184138559709,
      "eval_recall": 0.8041838968620774,
      "eval_runtime": 23.6471,
      "eval_samples_per_second": 211.315,
      "eval_steps_per_second": 6.639,
      "step": 992
    },
    {
      "epoch": 4.032258064516129,
      "grad_norm": 0.13704919815063477,
      "learning_rate": 4.979858870967742e-05,
      "loss": 0.013821365356445313,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_f1": 0.7597054886211513,
      "eval_loss": 0.02818991430103779,
      "eval_precision": 0.7016278590562539,
      "eval_recall": 0.8282656288007784,
      "eval_runtime": 23.8709,
      "eval_samples_per_second": 209.335,
      "eval_steps_per_second": 6.577,
      "step": 1240
    },
    {
      "epoch": 6.0,
      "eval_f1": 0.7845666705758181,
      "eval_loss": 0.02867285907268524,
      "eval_precision": 0.7574728260869565,
      "eval_recall": 0.8136706397470201,
      "eval_runtime": 23.8825,
      "eval_samples_per_second": 209.233,
      "eval_steps_per_second": 6.574,
      "step": 1488
    }
  ],
  "logging_steps": 500,
  "max_steps": 248000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1000,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2405959576819712e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}