Hugging Face's logo

xshubhamx
/
InLegalBERT

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
InLegalBERT
File size: 7,992 Bytes 
f8d5e20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
 
{
  "best_metric": 0.7985673319510695,
  "best_model_checkpoint": "InLegalBERT/checkpoint-3215",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 4501,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.78,
      "grad_norm": 6.225058078765869,
      "learning_rate": 4.742871954380509e-05,
      "loss": 1.065,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7993803253292022,
      "eval_f1_macro": 0.6028764374506596,
      "eval_f1_micro": 0.7993803253292022,
      "eval_f1_weighted": 0.780434475079005,
      "eval_loss": 0.6395189166069031,
      "eval_macro_fpr": 0.01853296480715729,
      "eval_macro_sensitivity": 0.6307714529979154,
      "eval_macro_specificity": 0.9847175193097543,
      "eval_precision": 0.7817573111259606,
      "eval_precision_macro": 0.6194286814679265,
      "eval_recall": 0.7993803253292022,
      "eval_recall_macro": 0.6307714529979154,
      "eval_runtime": 29.4696,
      "eval_samples_per_second": 43.808,
      "eval_steps_per_second": 5.497,
      "eval_weighted_fpr": 0.017610661589719183,
      "eval_weighted_sensitivity": 0.7993803253292022,
      "eval_weighted_specificity": 0.9713824643171124,
      "step": 643
    },
    {
      "epoch": 1.56,
      "grad_norm": 8.756747245788574,
      "learning_rate": 4.483670295489891e-05,
      "loss": 0.5866,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8187451587916343,
      "eval_f1_macro": 0.7276084501581802,
      "eval_f1_micro": 0.8187451587916342,
      "eval_f1_weighted": 0.8152450677099363,
      "eval_loss": 0.6906521916389465,
      "eval_macro_fpr": 0.01610571025604924,
      "eval_macro_sensitivity": 0.7365748487318147,
      "eval_macro_specificity": 0.9863504064994671,
      "eval_precision": 0.8198905458065566,
      "eval_precision_macro": 0.7284980957351811,
      "eval_recall": 0.8187451587916343,
      "eval_recall_macro": 0.7365748487318147,
      "eval_runtime": 57.1075,
      "eval_samples_per_second": 22.606,
      "eval_steps_per_second": 2.837,
      "eval_weighted_fpr": 0.015566790846194785,
      "eval_weighted_sensitivity": 0.8187451587916343,
      "eval_weighted_specificity": 0.976510938700373,
      "step": 1286
    },
    {
      "epoch": 2.33,
      "grad_norm": 8.241662979125977,
      "learning_rate": 4.224468636599274e-05,
      "loss": 0.4622,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8179705654531371,
      "eval_f1_macro": 0.7282676953256336,
      "eval_f1_micro": 0.817970565453137,
      "eval_f1_weighted": 0.8150036178041801,
      "eval_loss": 0.8055915236473083,
      "eval_macro_fpr": 0.016168738933500626,
      "eval_macro_sensitivity": 0.737597935006265,
      "eval_macro_specificity": 0.9862931306285473,
      "eval_precision": 0.8137371356291269,
      "eval_precision_macro": 0.7226669118270935,
      "eval_recall": 0.8179705654531371,
      "eval_recall_macro": 0.737597935006265,
      "eval_runtime": 56.5581,
      "eval_samples_per_second": 22.826,
      "eval_steps_per_second": 2.864,
      "eval_weighted_fpr": 0.01564684732671949,
      "eval_weighted_sensitivity": 0.8179705654531371,
      "eval_weighted_specificity": 0.9764263939750704,
      "step": 1929
    },
    {
      "epoch": 3.11,
      "grad_norm": 5.718050003051758,
      "learning_rate": 3.9652669777086575e-05,
      "loss": 0.346,
      "step": 2000
    },
    {
      "epoch": 3.89,
      "grad_norm": 28.698440551757812,
      "learning_rate": 3.7060653188180404e-05,
      "loss": 0.2398,
      "step": 2500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8171959721146398,
      "eval_f1_macro": 0.7407336443567221,
      "eval_f1_micro": 0.8171959721146398,
      "eval_f1_weighted": 0.8160506897887181,
      "eval_loss": 0.9310164451599121,
      "eval_macro_fpr": 0.016134598971936556,
      "eval_macro_sensitivity": 0.7424877811517157,
      "eval_macro_specificity": 0.9862275325034797,
      "eval_precision": 0.8234764041889034,
      "eval_precision_macro": 0.7660803499273104,
      "eval_recall": 0.8171959721146398,
      "eval_recall_macro": 0.7424877811517157,
      "eval_runtime": 58.71,
      "eval_samples_per_second": 21.989,
      "eval_steps_per_second": 2.759,
      "eval_weighted_fpr": 0.015727042516326804,
      "eval_weighted_sensitivity": 0.8171959721146398,
      "eval_weighted_specificity": 0.9762170154375561,
      "step": 2572
    },
    {
      "epoch": 4.67,
      "grad_norm": 8.432526588439941,
      "learning_rate": 3.447382063245205e-05,
      "loss": 0.1611,
      "step": 3000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8303640588690937,
      "eval_f1_macro": 0.7985673319510695,
      "eval_f1_micro": 0.8303640588690937,
      "eval_f1_weighted": 0.8304130023375266,
      "eval_loss": 1.0763046741485596,
      "eval_macro_fpr": 0.014791024663918677,
      "eval_macro_sensitivity": 0.7918299512118986,
      "eval_macro_specificity": 0.9872504344639083,
      "eval_precision": 0.8362631231068205,
      "eval_precision_macro": 0.8174407838611729,
      "eval_recall": 0.8303640588690937,
      "eval_recall_macro": 0.7918299512118986,
      "eval_runtime": 71.8128,
      "eval_samples_per_second": 17.977,
      "eval_steps_per_second": 2.256,
      "eval_weighted_fpr": 0.014382347146516056,
      "eval_weighted_sensitivity": 0.8303640588690937,
      "eval_weighted_specificity": 0.978392458089531,
      "step": 3215
    },
    {
      "epoch": 5.44,
      "grad_norm": 0.10359270125627518,
      "learning_rate": 3.1881804043545884e-05,
      "loss": 0.1055,
      "step": 3500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.82571649883811,
      "eval_f1_macro": 0.786305894104014,
      "eval_f1_micro": 0.82571649883811,
      "eval_f1_weighted": 0.824551084474796,
      "eval_loss": 1.1377127170562744,
      "eval_macro_fpr": 0.015367631824352218,
      "eval_macro_sensitivity": 0.7810139173900718,
      "eval_macro_specificity": 0.9868830526127108,
      "eval_precision": 0.8275394319817495,
      "eval_precision_macro": 0.8039087862954798,
      "eval_recall": 0.82571649883811,
      "eval_recall_macro": 0.7810139173900718,
      "eval_runtime": 64.6694,
      "eval_samples_per_second": 19.963,
      "eval_steps_per_second": 2.505,
      "eval_weighted_fpr": 0.01485246550927454,
      "eval_weighted_sensitivity": 0.82571649883811,
      "eval_weighted_specificity": 0.9775292903525532,
      "step": 3858
    },
    {
      "epoch": 6.22,
      "grad_norm": 0.07212593406438828,
      "learning_rate": 2.928978745463971e-05,
      "loss": 0.1152,
      "step": 4000
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.15883693099021912,
      "learning_rate": 2.669777086573354e-05,
      "loss": 0.0463,
      "step": 4500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8071262587141751,
      "eval_f1_macro": 0.7661147949067431,
      "eval_f1_micro": 0.8071262587141751,
      "eval_f1_weighted": 0.8078396785965507,
      "eval_loss": 1.321502447128296,
      "eval_macro_fpr": 0.017229971151571283,
      "eval_macro_sensitivity": 0.7688718615633127,
      "eval_macro_specificity": 0.9855509290260365,
      "eval_precision": 0.8111033305830805,
      "eval_precision_macro": 0.7691608912363075,
      "eval_recall": 0.8071262587141751,
      "eval_recall_macro": 0.7688718615633127,
      "eval_runtime": 77.5552,
      "eval_samples_per_second": 16.646,
      "eval_steps_per_second": 2.089,
      "eval_weighted_fpr": 0.016782368403316036,
      "eval_weighted_sensitivity": 0.8071262587141751,
      "eval_weighted_specificity": 0.9761376766763701,
      "step": 4501
    }
  ],
  "logging_steps": 500,
  "max_steps": 9645,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "total_flos": 9464156761135104.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}