Harshkmr commited on
Commit
0f5ffb9
1 Parent(s): 41422b3

Model save

Browse files
Files changed (5) hide show
  1. README.md +83 -0
  2. all_results.json +37 -0
  3. eval_results.json +31 -0
  4. train_results.json +9 -0
  5. trainer_state.json +838 -0
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/deberta-v3-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: deberta-v3-base_finetuned_bluegennx_run2.21_3e
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # deberta-v3-base_finetuned_bluegennx_run2.21_3e
15
+
16
+ This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0168
19
+ - Overall Precision: 0.9773
20
+ - Overall Recall: 0.9878
21
+ - Overall F1: 0.9825
22
+ - Overall Accuracy: 0.9959
23
+ - Aadhar Card F1: 0.9866
24
+ - Age F1: 0.9707
25
+ - City F1: 0.9868
26
+ - Country F1: 0.9865
27
+ - Creditcardcvv F1: 0.9888
28
+ - Creditcardnumber F1: 0.9587
29
+ - Date F1: 0.9643
30
+ - Dateofbirth F1: 0.9165
31
+ - Email F1: 0.9894
32
+ - Expirydate F1: 0.9921
33
+ - Organization F1: 0.9917
34
+ - Pan Card F1: 0.9856
35
+ - Person F1: 0.9883
36
+ - Phonenumber F1: 0.9868
37
+ - Pincode F1: 0.9936
38
+ - Secondaryaddress F1: 0.9861
39
+ - State F1: 0.9901
40
+ - Time F1: 0.9821
41
+ - Url F1: 0.9949
42
+
43
+ ## Model description
44
+
45
+ More information needed
46
+
47
+ ## Intended uses & limitations
48
+
49
+ More information needed
50
+
51
+ ## Training and evaluation data
52
+
53
+ More information needed
54
+
55
+ ## Training procedure
56
+
57
+ ### Training hyperparameters
58
+
59
+ The following hyperparameters were used during training:
60
+ - learning_rate: 5e-05
61
+ - train_batch_size: 4
62
+ - eval_batch_size: 4
63
+ - seed: 42
64
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
+ - lr_scheduler_type: cosine_with_restarts
66
+ - lr_scheduler_warmup_ratio: 0.2
67
+ - num_epochs: 3
68
+
69
+ ### Training results
70
+
71
+ | Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Aadhar Card F1 | Age F1 | City F1 | Country F1 | Creditcardcvv F1 | Creditcardnumber F1 | Date F1 | Dateofbirth F1 | Email F1 | Expirydate F1 | Organization F1 | Pan Card F1 | Person F1 | Phonenumber F1 | Pincode F1 | Secondaryaddress F1 | State F1 | Time F1 | Url F1 |
72
+ |:-------------:|:-----:|:-----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|:--------------:|:------:|:-------:|:----------:|:----------------:|:-------------------:|:-------:|:--------------:|:--------:|:-------------:|:---------------:|:-----------:|:---------:|:--------------:|:----------:|:-------------------:|:--------:|:-------:|:------:|
73
+ | 0.0308 | 1.0 | 16005 | 0.0359 | 0.9500 | 0.9755 | 0.9626 | 0.9920 | 0.9350 | 0.9315 | 0.9658 | 0.9706 | 0.9631 | 0.9282 | 0.9251 | 0.8430 | 0.9719 | 0.9842 | 0.9866 | 0.9696 | 0.9772 | 0.9503 | 0.9835 | 0.9680 | 0.9815 | 0.9739 | 0.9845 |
74
+ | 0.0202 | 2.0 | 32010 | 0.0195 | 0.9737 | 0.9836 | 0.9786 | 0.9950 | 0.9756 | 0.9586 | 0.9790 | 0.9826 | 0.9866 | 0.9497 | 0.9593 | 0.9060 | 0.9893 | 0.9872 | 0.9902 | 0.9716 | 0.9875 | 0.9830 | 0.9939 | 0.9831 | 0.9871 | 0.9799 | 0.9927 |
75
+ | 0.0107 | 3.0 | 48015 | 0.0168 | 0.9773 | 0.9878 | 0.9825 | 0.9959 | 0.9866 | 0.9707 | 0.9868 | 0.9865 | 0.9888 | 0.9587 | 0.9643 | 0.9165 | 0.9894 | 0.9921 | 0.9917 | 0.9856 | 0.9883 | 0.9868 | 0.9936 | 0.9861 | 0.9901 | 0.9821 | 0.9949 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.41.2
81
+ - Pytorch 2.1.2
82
+ - Datasets 2.19.2
83
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_AADHAR_CARD_f1": 0.9865537848605577,
4
+ "eval_AGE_f1": 0.9707006369426752,
5
+ "eval_CITY_f1": 0.9867601246105918,
6
+ "eval_COUNTRY_f1": 0.9864864864864865,
7
+ "eval_CREDITCARDCVV_f1": 0.9887830687830689,
8
+ "eval_CREDITCARDNUMBER_f1": 0.9587166255328696,
9
+ "eval_DATEOFBIRTH_f1": 0.9165348101265822,
10
+ "eval_DATE_f1": 0.9642906194204092,
11
+ "eval_EMAIL_f1": 0.9894194498113901,
12
+ "eval_EXPIRYDATE_f1": 0.9921259842519685,
13
+ "eval_ORGANIZATION_f1": 0.9917026219714571,
14
+ "eval_PAN_CARD_f1": 0.9855999999999999,
15
+ "eval_PERSON_f1": 0.9883056021325078,
16
+ "eval_PHONENUMBER_f1": 0.9868345735546651,
17
+ "eval_PINCODE_f1": 0.9936386768447837,
18
+ "eval_SECONDARYADDRESS_f1": 0.9860662358642972,
19
+ "eval_STATE_f1": 0.9901351845085861,
20
+ "eval_TIME_f1": 0.9821322719959352,
21
+ "eval_URL_f1": 0.994939493949395,
22
+ "eval_loss": 0.016786308959126472,
23
+ "eval_overall_accuracy": 0.9958519111859447,
24
+ "eval_overall_f1": 0.9824886126865787,
25
+ "eval_overall_precision": 0.9772792726075866,
26
+ "eval_overall_recall": 0.9877537866580728,
27
+ "eval_runtime": 267.5949,
28
+ "eval_samples": 16005,
29
+ "eval_samples_per_second": 59.811,
30
+ "eval_steps_per_second": 14.955,
31
+ "total_flos": 1.8885846596837596e+16,
32
+ "train_loss": 0.0555913904110963,
33
+ "train_runtime": 9844.7347,
34
+ "train_samples": 64019,
35
+ "train_samples_per_second": 19.509,
36
+ "train_steps_per_second": 4.877
37
+ }
eval_results.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_AADHAR_CARD_f1": 0.9865537848605577,
4
+ "eval_AGE_f1": 0.9707006369426752,
5
+ "eval_CITY_f1": 0.9867601246105918,
6
+ "eval_COUNTRY_f1": 0.9864864864864865,
7
+ "eval_CREDITCARDCVV_f1": 0.9887830687830689,
8
+ "eval_CREDITCARDNUMBER_f1": 0.9587166255328696,
9
+ "eval_DATEOFBIRTH_f1": 0.9165348101265822,
10
+ "eval_DATE_f1": 0.9642906194204092,
11
+ "eval_EMAIL_f1": 0.9894194498113901,
12
+ "eval_EXPIRYDATE_f1": 0.9921259842519685,
13
+ "eval_ORGANIZATION_f1": 0.9917026219714571,
14
+ "eval_PAN_CARD_f1": 0.9855999999999999,
15
+ "eval_PERSON_f1": 0.9883056021325078,
16
+ "eval_PHONENUMBER_f1": 0.9868345735546651,
17
+ "eval_PINCODE_f1": 0.9936386768447837,
18
+ "eval_SECONDARYADDRESS_f1": 0.9860662358642972,
19
+ "eval_STATE_f1": 0.9901351845085861,
20
+ "eval_TIME_f1": 0.9821322719959352,
21
+ "eval_URL_f1": 0.994939493949395,
22
+ "eval_loss": 0.016786308959126472,
23
+ "eval_overall_accuracy": 0.9958519111859447,
24
+ "eval_overall_f1": 0.9824886126865787,
25
+ "eval_overall_precision": 0.9772792726075866,
26
+ "eval_overall_recall": 0.9877537866580728,
27
+ "eval_runtime": 267.5949,
28
+ "eval_samples": 16005,
29
+ "eval_samples_per_second": 59.811,
30
+ "eval_steps_per_second": 14.955
31
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.8885846596837596e+16,
4
+ "train_loss": 0.0555913904110963,
5
+ "train_runtime": 9844.7347,
6
+ "train_samples": 64019,
7
+ "train_samples_per_second": 19.509,
8
+ "train_steps_per_second": 4.877
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,838 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.016786308959126472,
3
+ "best_model_checkpoint": "./deberta-v3-base_finetuned_bluegennx_run2.21_3e/checkpoint-48015",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 48015,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.031240237425804437,
13
+ "grad_norm": 1.9453787803649902,
14
+ "learning_rate": 2.6033531188170364e-06,
15
+ "loss": 2.1742,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.062480474851608875,
20
+ "grad_norm": 2.207657814025879,
21
+ "learning_rate": 5.206706237634073e-06,
22
+ "loss": 0.3611,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.09372071227741331,
27
+ "grad_norm": 3.9118669033050537,
28
+ "learning_rate": 7.81005935645111e-06,
29
+ "loss": 0.1781,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.12496094970321775,
34
+ "grad_norm": 1.7872343063354492,
35
+ "learning_rate": 1.0413412475268146e-05,
36
+ "loss": 0.1175,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.15620118712902217,
41
+ "grad_norm": 0.5929828882217407,
42
+ "learning_rate": 1.3016765594085182e-05,
43
+ "loss": 0.0815,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.18744142455482662,
48
+ "grad_norm": 0.8290306925773621,
49
+ "learning_rate": 1.562011871290222e-05,
50
+ "loss": 0.0766,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.21868166198063105,
55
+ "grad_norm": 0.4442843198776245,
56
+ "learning_rate": 1.8223471831719256e-05,
57
+ "loss": 0.0637,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.2499218994064355,
62
+ "grad_norm": 5.056885719299316,
63
+ "learning_rate": 2.082682495053629e-05,
64
+ "loss": 0.0588,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.28116213683223995,
69
+ "grad_norm": 2.825920820236206,
70
+ "learning_rate": 2.3430178069353328e-05,
71
+ "loss": 0.0525,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.31240237425804435,
76
+ "grad_norm": 1.8231415748596191,
77
+ "learning_rate": 2.6033531188170364e-05,
78
+ "loss": 0.0533,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.3436426116838488,
83
+ "grad_norm": 0.9496334195137024,
84
+ "learning_rate": 2.86368843069874e-05,
85
+ "loss": 0.06,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.37488284910965325,
90
+ "grad_norm": 0.6990556716918945,
91
+ "learning_rate": 3.124023742580444e-05,
92
+ "loss": 0.059,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.40612308653545764,
97
+ "grad_norm": 1.7713068723678589,
98
+ "learning_rate": 3.384359054462147e-05,
99
+ "loss": 0.0465,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.4373633239612621,
104
+ "grad_norm": 0.48251184821128845,
105
+ "learning_rate": 3.644694366343851e-05,
106
+ "loss": 0.0508,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.46860356138706655,
111
+ "grad_norm": 0.4298129379749298,
112
+ "learning_rate": 3.9050296782255544e-05,
113
+ "loss": 0.0531,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.499843798812871,
118
+ "grad_norm": 0.6740893125534058,
119
+ "learning_rate": 4.165364990107258e-05,
120
+ "loss": 0.0443,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.5310840362386754,
125
+ "grad_norm": 0.515224277973175,
126
+ "learning_rate": 4.425700301988962e-05,
127
+ "loss": 0.0442,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.5623242736644799,
132
+ "grad_norm": 0.07582231611013412,
133
+ "learning_rate": 4.6860356138706655e-05,
134
+ "loss": 0.0455,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 0.5935645110902843,
139
+ "grad_norm": 0.13481149077415466,
140
+ "learning_rate": 4.9463709257523695e-05,
141
+ "loss": 0.0502,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 0.6248047485160887,
146
+ "grad_norm": 0.06367824971675873,
147
+ "learning_rate": 4.998682293232702e-05,
148
+ "loss": 0.0497,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.6560449859418932,
153
+ "grad_norm": 0.107658751308918,
154
+ "learning_rate": 4.993275406892816e-05,
155
+ "loss": 0.0429,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 0.6872852233676976,
160
+ "grad_norm": 0.1800769716501236,
161
+ "learning_rate": 4.9836996765456125e-05,
162
+ "loss": 0.0425,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 0.718525460793502,
167
+ "grad_norm": 0.3818538784980774,
168
+ "learning_rate": 4.969971113148389e-05,
169
+ "loss": 0.035,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 0.7497656982193065,
174
+ "grad_norm": 0.8075230717658997,
175
+ "learning_rate": 4.952112671341091e-05,
176
+ "loss": 0.0378,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 0.7810059356451109,
181
+ "grad_norm": 1.5522449016571045,
182
+ "learning_rate": 4.9301542110653454e-05,
183
+ "loss": 0.0434,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 0.8122461730709153,
188
+ "grad_norm": 0.18798592686653137,
189
+ "learning_rate": 4.904132447637588e-05,
190
+ "loss": 0.0377,
191
+ "step": 13000
192
+ },
193
+ {
194
+ "epoch": 0.8434864104967198,
195
+ "grad_norm": 0.46252405643463135,
196
+ "learning_rate": 4.8740908903597714e-05,
197
+ "loss": 0.0386,
198
+ "step": 13500
199
+ },
200
+ {
201
+ "epoch": 0.8747266479225242,
202
+ "grad_norm": 1.5039823055267334,
203
+ "learning_rate": 4.8400797697702785e-05,
204
+ "loss": 0.036,
205
+ "step": 14000
206
+ },
207
+ {
208
+ "epoch": 0.9059668853483287,
209
+ "grad_norm": 4.865286350250244,
210
+ "learning_rate": 4.802155953656704e-05,
211
+ "loss": 0.0332,
212
+ "step": 14500
213
+ },
214
+ {
215
+ "epoch": 0.9372071227741331,
216
+ "grad_norm": 1.6047935485839844,
217
+ "learning_rate": 4.760382851970915e-05,
218
+ "loss": 0.0358,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 0.9684473601999375,
223
+ "grad_norm": 0.28227582573890686,
224
+ "learning_rate": 4.714830310805381e-05,
225
+ "loss": 0.0338,
226
+ "step": 15500
227
+ },
228
+ {
229
+ "epoch": 0.999687597625742,
230
+ "grad_norm": 1.1359831094741821,
231
+ "learning_rate": 4.6655744956080655e-05,
232
+ "loss": 0.0308,
233
+ "step": 16000
234
+ },
235
+ {
236
+ "epoch": 1.0,
237
+ "eval_AADHAR_CARD_f1": 0.935032483758121,
238
+ "eval_AGE_f1": 0.9315192743764172,
239
+ "eval_CITY_f1": 0.965787821720025,
240
+ "eval_COUNTRY_f1": 0.9705882352941178,
241
+ "eval_CREDITCARDCVV_f1": 0.9630872483221476,
242
+ "eval_CREDITCARDNUMBER_f1": 0.9281792224906655,
243
+ "eval_DATEOFBIRTH_f1": 0.8429846212265047,
244
+ "eval_DATE_f1": 0.9250582271544047,
245
+ "eval_EMAIL_f1": 0.9719218537028623,
246
+ "eval_EXPIRYDATE_f1": 0.9841930116472545,
247
+ "eval_ORGANIZATION_f1": 0.9866225478610258,
248
+ "eval_PAN_CARD_f1": 0.9696224758560141,
249
+ "eval_PERSON_f1": 0.9771855010660981,
250
+ "eval_PHONENUMBER_f1": 0.9502501389660922,
251
+ "eval_PINCODE_f1": 0.9834710743801652,
252
+ "eval_SECONDARYADDRESS_f1": 0.968014484007242,
253
+ "eval_STATE_f1": 0.9814928300036769,
254
+ "eval_TIME_f1": 0.9739364385404405,
255
+ "eval_URL_f1": 0.9844536895117144,
256
+ "eval_loss": 0.03587241843342781,
257
+ "eval_overall_accuracy": 0.9919974872098162,
258
+ "eval_overall_f1": 0.96261001579714,
259
+ "eval_overall_precision": 0.9500096174288057,
260
+ "eval_overall_recall": 0.9755491563835206,
261
+ "eval_runtime": 307.0183,
262
+ "eval_samples_per_second": 52.13,
263
+ "eval_steps_per_second": 13.035,
264
+ "step": 16005
265
+ },
266
+ {
267
+ "epoch": 1.0309278350515463,
268
+ "grad_norm": 2.9516384601593018,
269
+ "learning_rate": 4.6126977638311145e-05,
270
+ "loss": 0.0315,
271
+ "step": 16500
272
+ },
273
+ {
274
+ "epoch": 1.0621680724773508,
275
+ "grad_norm": 0.9985421299934387,
276
+ "learning_rate": 4.556288527226308e-05,
277
+ "loss": 0.0258,
278
+ "step": 17000
279
+ },
280
+ {
281
+ "epoch": 1.0934083099031553,
282
+ "grad_norm": 0.09413296729326248,
283
+ "learning_rate": 4.496441104017508e-05,
284
+ "loss": 0.0251,
285
+ "step": 17500
286
+ },
287
+ {
288
+ "epoch": 1.1246485473289598,
289
+ "grad_norm": 0.5080928802490234,
290
+ "learning_rate": 4.433255561197277e-05,
291
+ "loss": 0.0375,
292
+ "step": 18000
293
+ },
294
+ {
295
+ "epoch": 1.155888784754764,
296
+ "grad_norm": 0.6283013224601746,
297
+ "learning_rate": 4.366837547211354e-05,
298
+ "loss": 0.0238,
299
+ "step": 18500
300
+ },
301
+ {
302
+ "epoch": 1.1871290221805686,
303
+ "grad_norm": 0.09778323024511337,
304
+ "learning_rate": 4.297298115310743e-05,
305
+ "loss": 0.0258,
306
+ "step": 19000
307
+ },
308
+ {
309
+ "epoch": 1.218369259606373,
310
+ "grad_norm": 0.5504295825958252,
311
+ "learning_rate": 4.224753537866777e-05,
312
+ "loss": 0.0337,
313
+ "step": 19500
314
+ },
315
+ {
316
+ "epoch": 1.2496094970321774,
317
+ "grad_norm": 0.045782480388879776,
318
+ "learning_rate": 4.1493251119596374e-05,
319
+ "loss": 0.0299,
320
+ "step": 20000
321
+ },
322
+ {
323
+ "epoch": 1.280849734457982,
324
+ "grad_norm": 0.31934645771980286,
325
+ "learning_rate": 4.071138956565373e-05,
326
+ "loss": 0.0264,
327
+ "step": 20500
328
+ },
329
+ {
330
+ "epoch": 1.3120899718837864,
331
+ "grad_norm": 0.09766834229230881,
332
+ "learning_rate": 3.990325801680546e-05,
333
+ "loss": 0.0247,
334
+ "step": 21000
335
+ },
336
+ {
337
+ "epoch": 1.3433302093095907,
338
+ "grad_norm": 1.4730592966079712,
339
+ "learning_rate": 3.907020769737086e-05,
340
+ "loss": 0.024,
341
+ "step": 21500
342
+ },
343
+ {
344
+ "epoch": 1.3745704467353952,
345
+ "grad_norm": 0.22080545127391815,
346
+ "learning_rate": 3.8213631496728466e-05,
347
+ "loss": 0.0263,
348
+ "step": 22000
349
+ },
350
+ {
351
+ "epoch": 1.4058106841611997,
352
+ "grad_norm": 1.110324501991272,
353
+ "learning_rate": 3.733496164035603e-05,
354
+ "loss": 0.0232,
355
+ "step": 22500
356
+ },
357
+ {
358
+ "epoch": 1.437050921587004,
359
+ "grad_norm": 0.38805103302001953,
360
+ "learning_rate": 3.643566729509932e-05,
361
+ "loss": 0.0277,
362
+ "step": 23000
363
+ },
364
+ {
365
+ "epoch": 1.4682911590128085,
366
+ "grad_norm": 0.02454444207251072,
367
+ "learning_rate": 3.551725211267354e-05,
368
+ "loss": 0.0227,
369
+ "step": 23500
370
+ },
371
+ {
372
+ "epoch": 1.499531396438613,
373
+ "grad_norm": 1.0061655044555664,
374
+ "learning_rate": 3.458125171550487e-05,
375
+ "loss": 0.0258,
376
+ "step": 24000
377
+ },
378
+ {
379
+ "epoch": 1.5307716338644175,
380
+ "grad_norm": 0.09139035642147064,
381
+ "learning_rate": 3.362923112911588e-05,
382
+ "loss": 0.0238,
383
+ "step": 24500
384
+ },
385
+ {
386
+ "epoch": 1.5620118712902218,
387
+ "grad_norm": 1.6061333417892456,
388
+ "learning_rate": 3.266278216534792e-05,
389
+ "loss": 0.0228,
390
+ "step": 25000
391
+ },
392
+ {
393
+ "epoch": 1.5932521087160263,
394
+ "grad_norm": 0.014178004115819931,
395
+ "learning_rate": 3.1683520760795795e-05,
396
+ "loss": 0.0253,
397
+ "step": 25500
398
+ },
399
+ {
400
+ "epoch": 1.6244923461418308,
401
+ "grad_norm": 0.1629280000925064,
402
+ "learning_rate": 3.069308427490513e-05,
403
+ "loss": 0.0226,
404
+ "step": 26000
405
+ },
406
+ {
407
+ "epoch": 1.655732583567635,
408
+ "grad_norm": 0.6675782203674316,
409
+ "learning_rate": 2.969312875224981e-05,
410
+ "loss": 0.0209,
411
+ "step": 26500
412
+ },
413
+ {
414
+ "epoch": 1.6869728209934396,
415
+ "grad_norm": 0.20190191268920898,
416
+ "learning_rate": 2.8685326153567404e-05,
417
+ "loss": 0.0232,
418
+ "step": 27000
419
+ },
420
+ {
421
+ "epoch": 1.718213058419244,
422
+ "grad_norm": 0.22869578003883362,
423
+ "learning_rate": 2.7671361560182018e-05,
424
+ "loss": 0.0205,
425
+ "step": 27500
426
+ },
427
+ {
428
+ "epoch": 1.7494532958450484,
429
+ "grad_norm": 0.4046876132488251,
430
+ "learning_rate": 2.6652930356489275e-05,
431
+ "loss": 0.0235,
432
+ "step": 28000
433
+ },
434
+ {
435
+ "epoch": 1.780693533270853,
436
+ "grad_norm": 0.08248839527368546,
437
+ "learning_rate": 2.563173539521398e-05,
438
+ "loss": 0.0212,
439
+ "step": 28500
440
+ },
441
+ {
442
+ "epoch": 1.8119337706966574,
443
+ "grad_norm": 0.14581803977489471,
444
+ "learning_rate": 2.460948415018067e-05,
445
+ "loss": 0.022,
446
+ "step": 29000
447
+ },
448
+ {
449
+ "epoch": 1.8431740081224617,
450
+ "grad_norm": 0.07922026515007019,
451
+ "learning_rate": 2.3587885861357417e-05,
452
+ "loss": 0.0201,
453
+ "step": 29500
454
+ },
455
+ {
456
+ "epoch": 1.8744142455482662,
457
+ "grad_norm": 0.12380392849445343,
458
+ "learning_rate": 2.256864867694655e-05,
459
+ "loss": 0.0222,
460
+ "step": 30000
461
+ },
462
+ {
463
+ "epoch": 1.9056544829740707,
464
+ "grad_norm": 0.01387234590947628,
465
+ "learning_rate": 2.1553476797300967e-05,
466
+ "loss": 0.0172,
467
+ "step": 30500
468
+ },
469
+ {
470
+ "epoch": 1.936894720399875,
471
+ "grad_norm": 0.7150996923446655,
472
+ "learning_rate": 2.054406762544126e-05,
473
+ "loss": 0.0193,
474
+ "step": 31000
475
+ },
476
+ {
477
+ "epoch": 1.9681349578256795,
478
+ "grad_norm": 0.12249834090471268,
479
+ "learning_rate": 1.954210892893833e-05,
480
+ "loss": 0.0162,
481
+ "step": 31500
482
+ },
483
+ {
484
+ "epoch": 1.999375195251484,
485
+ "grad_norm": 0.20916196703910828,
486
+ "learning_rate": 1.8549276017906707e-05,
487
+ "loss": 0.0202,
488
+ "step": 32000
489
+ },
490
+ {
491
+ "epoch": 2.0,
492
+ "eval_AADHAR_CARD_f1": 0.975609756097561,
493
+ "eval_AGE_f1": 0.9585812623964532,
494
+ "eval_CITY_f1": 0.9789817842129845,
495
+ "eval_COUNTRY_f1": 0.9825646794150731,
496
+ "eval_CREDITCARDCVV_f1": 0.9866327180140038,
497
+ "eval_CREDITCARDNUMBER_f1": 0.9497256746165043,
498
+ "eval_DATEOFBIRTH_f1": 0.9060173073052928,
499
+ "eval_DATE_f1": 0.9592630501535313,
500
+ "eval_EMAIL_f1": 0.9893244984354868,
501
+ "eval_EXPIRYDATE_f1": 0.9871847871021083,
502
+ "eval_ORGANIZATION_f1": 0.9902360413309318,
503
+ "eval_PAN_CARD_f1": 0.9716031631919482,
504
+ "eval_PERSON_f1": 0.9874935533780299,
505
+ "eval_PHONENUMBER_f1": 0.9829537315570835,
506
+ "eval_PINCODE_f1": 0.9939471169162153,
507
+ "eval_SECONDARYADDRESS_f1": 0.9831296090514193,
508
+ "eval_STATE_f1": 0.9871265484576147,
509
+ "eval_TIME_f1": 0.9798612286342867,
510
+ "eval_URL_f1": 0.9927456583864586,
511
+ "eval_loss": 0.019483117386698723,
512
+ "eval_overall_accuracy": 0.9950012756613735,
513
+ "eval_overall_f1": 0.9786100681623069,
514
+ "eval_overall_precision": 0.9736953143492266,
515
+ "eval_overall_recall": 0.9835746883868889,
516
+ "eval_runtime": 307.7213,
517
+ "eval_samples_per_second": 52.011,
518
+ "eval_steps_per_second": 13.005,
519
+ "step": 32010
520
+ },
521
+ {
522
+ "epoch": 2.0306154326772883,
523
+ "grad_norm": 0.4832023084163666,
524
+ "learning_rate": 1.7567228943827265e-05,
525
+ "loss": 0.0189,
526
+ "step": 32500
527
+ },
528
+ {
529
+ "epoch": 2.0618556701030926,
530
+ "grad_norm": 0.07361295074224472,
531
+ "learning_rate": 1.6597609723882834e-05,
532
+ "loss": 0.0177,
533
+ "step": 33000
534
+ },
535
+ {
536
+ "epoch": 2.0930959075288973,
537
+ "grad_norm": 0.5370087623596191,
538
+ "learning_rate": 1.5642039595447862e-05,
539
+ "loss": 0.0108,
540
+ "step": 33500
541
+ },
542
+ {
543
+ "epoch": 2.1243361449547016,
544
+ "grad_norm": 0.2966110408306122,
545
+ "learning_rate": 1.4702116305322614e-05,
546
+ "loss": 0.0122,
547
+ "step": 34000
548
+ },
549
+ {
550
+ "epoch": 2.155576382380506,
551
+ "grad_norm": 0.25330406427383423,
552
+ "learning_rate": 1.3779411438244385e-05,
553
+ "loss": 0.0126,
554
+ "step": 34500
555
+ },
556
+ {
557
+ "epoch": 2.1868166198063106,
558
+ "grad_norm": 0.023234376683831215,
559
+ "learning_rate": 1.2875467789142694e-05,
560
+ "loss": 0.0149,
561
+ "step": 35000
562
+ },
563
+ {
564
+ "epoch": 2.218056857232115,
565
+ "grad_norm": 0.15632040798664093,
566
+ "learning_rate": 1.1991796783531975e-05,
567
+ "loss": 0.0118,
568
+ "step": 35500
569
+ },
570
+ {
571
+ "epoch": 2.2492970946579196,
572
+ "grad_norm": 2.662566900253296,
573
+ "learning_rate": 1.1129875950355095e-05,
574
+ "loss": 0.0147,
575
+ "step": 36000
576
+ },
577
+ {
578
+ "epoch": 2.280537332083724,
579
+ "grad_norm": 0.07179576903581619,
580
+ "learning_rate": 1.0291146451503033e-05,
581
+ "loss": 0.013,
582
+ "step": 36500
583
+ },
584
+ {
585
+ "epoch": 2.311777569509528,
586
+ "grad_norm": 1.6363691091537476,
587
+ "learning_rate": 9.477010672141675e-06,
588
+ "loss": 0.0101,
589
+ "step": 37000
590
+ },
591
+ {
592
+ "epoch": 2.3430178069353325,
593
+ "grad_norm": 0.0774739608168602,
594
+ "learning_rate": 8.688829875874516e-06,
595
+ "loss": 0.0175,
596
+ "step": 37500
597
+ },
598
+ {
599
+ "epoch": 2.374258044361137,
600
+ "grad_norm": 0.07443530112504959,
601
+ "learning_rate": 7.927921928662193e-06,
602
+ "loss": 0.0104,
603
+ "step": 38000
604
+ },
605
+ {
606
+ "epoch": 2.4054982817869415,
607
+ "grad_norm": 0.021464819088578224,
608
+ "learning_rate": 7.195559095304283e-06,
609
+ "loss": 0.0118,
610
+ "step": 38500
611
+ },
612
+ {
613
+ "epoch": 2.436738519212746,
614
+ "grad_norm": 0.9025238752365112,
615
+ "learning_rate": 6.492965912167923e-06,
616
+ "loss": 0.0122,
617
+ "step": 39000
618
+ },
619
+ {
620
+ "epoch": 2.4679787566385505,
621
+ "grad_norm": 0.19682565331459045,
622
+ "learning_rate": 5.821317139720001e-06,
623
+ "loss": 0.0118,
624
+ "step": 39500
625
+ },
626
+ {
627
+ "epoch": 2.4992189940643548,
628
+ "grad_norm": 0.056999098509550095,
629
+ "learning_rate": 5.1817357982864415e-06,
630
+ "loss": 0.0113,
631
+ "step": 40000
632
+ },
633
+ {
634
+ "epoch": 2.530459231490159,
635
+ "grad_norm": 0.016481826081871986,
636
+ "learning_rate": 4.575291290322764e-06,
637
+ "loss": 0.011,
638
+ "step": 40500
639
+ },
640
+ {
641
+ "epoch": 2.561699468915964,
642
+ "grad_norm": 0.011844165623188019,
643
+ "learning_rate": 4.0029976123356544e-06,
644
+ "loss": 0.0108,
645
+ "step": 41000
646
+ },
647
+ {
648
+ "epoch": 2.592939706341768,
649
+ "grad_norm": 0.02857145480811596,
650
+ "learning_rate": 3.465811659445206e-06,
651
+ "loss": 0.0134,
652
+ "step": 41500
653
+ },
654
+ {
655
+ "epoch": 2.624179943767573,
656
+ "grad_norm": 0.03046867437660694,
657
+ "learning_rate": 2.9646316254226786e-06,
658
+ "loss": 0.0126,
659
+ "step": 42000
660
+ },
661
+ {
662
+ "epoch": 2.655420181193377,
663
+ "grad_norm": 0.0065807169303298,
664
+ "learning_rate": 2.5002955008790074e-06,
665
+ "loss": 0.0089,
666
+ "step": 42500
667
+ },
668
+ {
669
+ "epoch": 2.6866604186191814,
670
+ "grad_norm": 0.16103477776050568,
671
+ "learning_rate": 2.0735796721150447e-06,
672
+ "loss": 0.0154,
673
+ "step": 43000
674
+ },
675
+ {
676
+ "epoch": 2.717900656044986,
677
+ "grad_norm": 0.08998264372348785,
678
+ "learning_rate": 1.6851976229764393e-06,
679
+ "loss": 0.0123,
680
+ "step": 43500
681
+ },
682
+ {
683
+ "epoch": 2.7491408934707904,
684
+ "grad_norm": 0.04546121135354042,
685
+ "learning_rate": 1.3357987418835955e-06,
686
+ "loss": 0.0092,
687
+ "step": 44000
688
+ },
689
+ {
690
+ "epoch": 2.7803811308965947,
691
+ "grad_norm": 0.6218581199645996,
692
+ "learning_rate": 1.0259672360314221e-06,
693
+ "loss": 0.0101,
694
+ "step": 44500
695
+ },
696
+ {
697
+ "epoch": 2.8116213683223994,
698
+ "grad_norm": 0.2742210030555725,
699
+ "learning_rate": 7.562211545744102e-07,
700
+ "loss": 0.009,
701
+ "step": 45000
702
+ },
703
+ {
704
+ "epoch": 2.8428616057482037,
705
+ "grad_norm": 0.0064840721897780895,
706
+ "learning_rate": 5.270115224302541e-07,
707
+ "loss": 0.0109,
708
+ "step": 45500
709
+ },
710
+ {
711
+ "epoch": 2.874101843174008,
712
+ "grad_norm": 0.033717311918735504,
713
+ "learning_rate": 3.3872158615035067e-07,
714
+ "loss": 0.0136,
715
+ "step": 46000
716
+ },
717
+ {
718
+ "epoch": 2.9053420805998127,
719
+ "grad_norm": 0.08778509497642517,
720
+ "learning_rate": 1.9166617311812407e-07,
721
+ "loss": 0.0122,
722
+ "step": 46500
723
+ },
724
+ {
725
+ "epoch": 2.936582318025617,
726
+ "grad_norm": 4.181912422180176,
727
+ "learning_rate": 8.609116514657622e-08,
728
+ "loss": 0.0105,
729
+ "step": 47000
730
+ },
731
+ {
732
+ "epoch": 2.9678225554514217,
733
+ "grad_norm": 0.6781991124153137,
734
+ "learning_rate": 2.2173087355270573e-08,
735
+ "loss": 0.0129,
736
+ "step": 47500
737
+ },
738
+ {
739
+ "epoch": 2.999062792877226,
740
+ "grad_norm": 0.332028865814209,
741
+ "learning_rate": 1.8813014129870354e-11,
742
+ "loss": 0.0107,
743
+ "step": 48000
744
+ },
745
+ {
746
+ "epoch": 3.0,
747
+ "eval_AADHAR_CARD_f1": 0.9865537848605577,
748
+ "eval_AGE_f1": 0.9707006369426752,
749
+ "eval_CITY_f1": 0.9867601246105918,
750
+ "eval_COUNTRY_f1": 0.9864864864864865,
751
+ "eval_CREDITCARDCVV_f1": 0.9887830687830689,
752
+ "eval_CREDITCARDNUMBER_f1": 0.9587166255328696,
753
+ "eval_DATEOFBIRTH_f1": 0.9165348101265822,
754
+ "eval_DATE_f1": 0.9642906194204092,
755
+ "eval_EMAIL_f1": 0.9894194498113901,
756
+ "eval_EXPIRYDATE_f1": 0.9921259842519685,
757
+ "eval_ORGANIZATION_f1": 0.9917026219714571,
758
+ "eval_PAN_CARD_f1": 0.9855999999999999,
759
+ "eval_PERSON_f1": 0.9883056021325078,
760
+ "eval_PHONENUMBER_f1": 0.9868345735546651,
761
+ "eval_PINCODE_f1": 0.9936386768447837,
762
+ "eval_SECONDARYADDRESS_f1": 0.9860662358642972,
763
+ "eval_STATE_f1": 0.9901351845085861,
764
+ "eval_TIME_f1": 0.9821322719959352,
765
+ "eval_URL_f1": 0.994939493949395,
766
+ "eval_loss": 0.016786308959126472,
767
+ "eval_overall_accuracy": 0.9958519111859447,
768
+ "eval_overall_f1": 0.9824886126865787,
769
+ "eval_overall_precision": 0.9772792726075866,
770
+ "eval_overall_recall": 0.9877537866580728,
771
+ "eval_runtime": 309.3329,
772
+ "eval_samples_per_second": 51.74,
773
+ "eval_steps_per_second": 12.938,
774
+ "step": 48015
775
+ },
776
+ {
777
+ "epoch": 3.0,
778
+ "step": 48015,
779
+ "total_flos": 1.8885846596837596e+16,
780
+ "train_loss": 0.0555913904110963,
781
+ "train_runtime": 9844.7347,
782
+ "train_samples_per_second": 19.509,
783
+ "train_steps_per_second": 4.877
784
+ },
785
+ {
786
+ "epoch": 3.0,
787
+ "eval_AADHAR_CARD_f1": 0.9865537848605577,
788
+ "eval_AGE_f1": 0.9707006369426752,
789
+ "eval_CITY_f1": 0.9867601246105918,
790
+ "eval_COUNTRY_f1": 0.9864864864864865,
791
+ "eval_CREDITCARDCVV_f1": 0.9887830687830689,
792
+ "eval_CREDITCARDNUMBER_f1": 0.9587166255328696,
793
+ "eval_DATEOFBIRTH_f1": 0.9165348101265822,
794
+ "eval_DATE_f1": 0.9642906194204092,
795
+ "eval_EMAIL_f1": 0.9894194498113901,
796
+ "eval_EXPIRYDATE_f1": 0.9921259842519685,
797
+ "eval_ORGANIZATION_f1": 0.9917026219714571,
798
+ "eval_PAN_CARD_f1": 0.9855999999999999,
799
+ "eval_PERSON_f1": 0.9883056021325078,
800
+ "eval_PHONENUMBER_f1": 0.9868345735546651,
801
+ "eval_PINCODE_f1": 0.9936386768447837,
802
+ "eval_SECONDARYADDRESS_f1": 0.9860662358642972,
803
+ "eval_STATE_f1": 0.9901351845085861,
804
+ "eval_TIME_f1": 0.9821322719959352,
805
+ "eval_URL_f1": 0.994939493949395,
806
+ "eval_loss": 0.016786308959126472,
807
+ "eval_overall_accuracy": 0.9958519111859447,
808
+ "eval_overall_f1": 0.9824886126865787,
809
+ "eval_overall_precision": 0.9772792726075866,
810
+ "eval_overall_recall": 0.9877537866580728,
811
+ "eval_runtime": 267.5949,
812
+ "eval_samples_per_second": 59.811,
813
+ "eval_steps_per_second": 14.955,
814
+ "step": 48015
815
+ }
816
+ ],
817
+ "logging_steps": 500,
818
+ "max_steps": 48015,
819
+ "num_input_tokens_seen": 0,
820
+ "num_train_epochs": 3,
821
+ "save_steps": 500,
822
+ "stateful_callbacks": {
823
+ "TrainerControl": {
824
+ "args": {
825
+ "should_epoch_stop": false,
826
+ "should_evaluate": false,
827
+ "should_log": false,
828
+ "should_save": true,
829
+ "should_training_stop": true
830
+ },
831
+ "attributes": {}
832
+ }
833
+ },
834
+ "total_flos": 1.8885846596837596e+16,
835
+ "train_batch_size": 4,
836
+ "trial_name": null,
837
+ "trial_params": null
838
+ }