Hugging Face's logo

xshubhamx
/
InLegalBERT-lora-no-grad

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
InLegalBERT-lora-no-grad
File size: 5,524 Bytes 
6197a72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
 
{
  "best_metric": 0.7571266313428899,
  "best_model_checkpoint": "legal-bert-lora-no-grad/checkpoint-3215",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 3215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.78,
      "learning_rate": 4.870399170554692e-05,
      "loss": 1.6412,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7513555383423702,
      "eval_f1_macro": 0.4277259717095209,
      "eval_f1_micro": 0.7513555383423703,
      "eval_f1_weighted": 0.7282568827191913,
      "eval_loss": 0.7924586534500122,
      "eval_macro_fpr": 0.023743972756733803,
      "eval_macro_sensitivity": 0.47068996339347813,
      "eval_macro_specificity": 0.9814182576870886,
      "eval_precision": 0.7190272898782211,
      "eval_precision_macro": 0.4122596954919311,
      "eval_recall": 0.7513555383423702,
      "eval_recall_macro": 0.47068996339347813,
      "eval_runtime": 31.9941,
      "eval_samples_per_second": 40.351,
      "eval_steps_per_second": 5.063,
      "eval_weighted_fpr": 0.023091863894683835,
      "eval_weighted_sensitivity": 0.7513555383423702,
      "eval_weighted_specificity": 0.9699183269639584,
      "step": 643
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.740798341109383e-05,
      "loss": 0.7481,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7900852052672347,
      "eval_f1_macro": 0.5997806825026601,
      "eval_f1_micro": 0.7900852052672347,
      "eval_f1_weighted": 0.7768800571423996,
      "eval_loss": 0.6771801710128784,
      "eval_macro_fpr": 0.019203116699768798,
      "eval_macro_sensitivity": 0.6251797015497511,
      "eval_macro_specificity": 0.9842820395671547,
      "eval_precision": 0.7726267649469656,
      "eval_precision_macro": 0.595773614705663,
      "eval_recall": 0.7900852052672347,
      "eval_recall_macro": 0.6251797015497511,
      "eval_runtime": 33.2196,
      "eval_samples_per_second": 38.863,
      "eval_steps_per_second": 4.877,
      "eval_weighted_fpr": 0.018624149542986735,
      "eval_weighted_sensitivity": 0.7900852052672347,
      "eval_weighted_specificity": 0.9741453882400846,
      "step": 1286
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.6111975116640746e-05,
      "loss": 0.6465,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8048024786986832,
      "eval_f1_macro": 0.610991978534836,
      "eval_f1_micro": 0.804802478698683,
      "eval_f1_weighted": 0.7903758160570191,
      "eval_loss": 0.64998859167099,
      "eval_macro_fpr": 0.017565196384739988,
      "eval_macro_sensitivity": 0.6414017118652243,
      "eval_macro_specificity": 0.9854108558122262,
      "eval_precision": 0.7930969709541013,
      "eval_precision_macro": 0.6215844916422869,
      "eval_recall": 0.8048024786986832,
      "eval_recall_macro": 0.6414017118652243,
      "eval_runtime": 33.2556,
      "eval_samples_per_second": 38.821,
      "eval_steps_per_second": 4.871,
      "eval_weighted_fpr": 0.017029328287606435,
      "eval_weighted_sensitivity": 0.8048024786986832,
      "eval_weighted_specificity": 0.9763603584847095,
      "step": 1929
    },
    {
      "epoch": 3.11,
      "learning_rate": 4.481596682218767e-05,
      "loss": 0.5559,
      "step": 2000
    },
    {
      "epoch": 3.89,
      "learning_rate": 4.3519958527734576e-05,
      "loss": 0.4707,
      "step": 2500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8094500387296669,
      "eval_f1_macro": 0.6424924237429005,
      "eval_f1_micro": 0.8094500387296669,
      "eval_f1_weighted": 0.801786166531795,
      "eval_loss": 0.6704407930374146,
      "eval_macro_fpr": 0.017261054466023888,
      "eval_macro_sensitivity": 0.6689319587406968,
      "eval_macro_specificity": 0.9855970345792379,
      "eval_precision": 0.8007850899141215,
      "eval_precision_macro": 0.6321597811403302,
      "eval_recall": 0.8094500387296669,
      "eval_recall_macro": 0.6689319587406968,
      "eval_runtime": 32.7354,
      "eval_samples_per_second": 39.437,
      "eval_steps_per_second": 4.949,
      "eval_weighted_fpr": 0.016536703414896478,
      "eval_weighted_sensitivity": 0.8094500387296669,
      "eval_weighted_specificity": 0.9745054799589014,
      "step": 2572
    },
    {
      "epoch": 4.67,
      "learning_rate": 4.22239502332815e-05,
      "loss": 0.4021,
      "step": 3000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8280402788536019,
      "eval_f1_macro": 0.7571266313428899,
      "eval_f1_micro": 0.8280402788536019,
      "eval_f1_weighted": 0.8219004240794867,
      "eval_loss": 0.7320332527160645,
      "eval_macro_fpr": 0.015397351101601975,
      "eval_macro_sensitivity": 0.7573467308503988,
      "eval_macro_specificity": 0.9869691873059906,
      "eval_precision": 0.8268949272272527,
      "eval_precision_macro": 0.7782079900717894,
      "eval_recall": 0.8280402788536019,
      "eval_recall_macro": 0.7573467308503988,
      "eval_runtime": 33.3254,
      "eval_samples_per_second": 38.739,
      "eval_steps_per_second": 4.861,
      "eval_weighted_fpr": 0.014616802739004477,
      "eval_weighted_sensitivity": 0.8280402788536019,
      "eval_weighted_specificity": 0.9764975307362563,
      "step": 3215
    }
  ],
  "logging_steps": 500,
  "max_steps": 19290,
  "num_train_epochs": 30,
  "save_steps": 500,
  "total_flos": 6972431086817280.0,
  "trial_name": null,
  "trial_params": null
}