CordwainerSmith commited on
Commit
9882178
1 Parent(s): ce268dc

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-6092/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-7615/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-6092/config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B-BANK_ACCOUNT_NUM",
15
+ "1": "B-CC_NUM",
16
+ "2": "B-CC_PROVIDER",
17
+ "3": "B-CITY",
18
+ "4": "B-DATE",
19
+ "5": "B-EMAIL",
20
+ "6": "B-FIRST_NAME",
21
+ "7": "B-ID_NUM",
22
+ "8": "B-LAST_NAME",
23
+ "9": "B-PHONE_NUM",
24
+ "10": "B-POSTAL_CODE",
25
+ "11": "B-STREET",
26
+ "12": "I-BANK_ACCOUNT_NUM",
27
+ "13": "I-CC_NUM",
28
+ "14": "I-CC_PROVIDER",
29
+ "15": "I-CITY",
30
+ "16": "I-DATE",
31
+ "17": "I-EMAIL",
32
+ "18": "I-FIRST_NAME",
33
+ "19": "I-ID_NUM",
34
+ "20": "I-LAST_NAME",
35
+ "21": "I-PHONE_NUM",
36
+ "22": "I-POSTAL_CODE",
37
+ "23": "I-STREET",
38
+ "24": "O"
39
+ },
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 3072,
42
+ "label2id": {
43
+ "B-BANK_ACCOUNT_NUM": 0,
44
+ "B-CC_NUM": 1,
45
+ "B-CC_PROVIDER": 2,
46
+ "B-CITY": 3,
47
+ "B-DATE": 4,
48
+ "B-EMAIL": 5,
49
+ "B-FIRST_NAME": 6,
50
+ "B-ID_NUM": 7,
51
+ "B-LAST_NAME": 8,
52
+ "B-PHONE_NUM": 9,
53
+ "B-POSTAL_CODE": 10,
54
+ "B-STREET": 11,
55
+ "I-BANK_ACCOUNT_NUM": 12,
56
+ "I-CC_NUM": 13,
57
+ "I-CC_PROVIDER": 14,
58
+ "I-CITY": 15,
59
+ "I-DATE": 16,
60
+ "I-EMAIL": 17,
61
+ "I-FIRST_NAME": 18,
62
+ "I-ID_NUM": 19,
63
+ "I-LAST_NAME": 20,
64
+ "I-PHONE_NUM": 21,
65
+ "I-POSTAL_CODE": 22,
66
+ "I-STREET": 23,
67
+ "O": 24
68
+ },
69
+ "layer_norm_eps": 1e-05,
70
+ "max_position_embeddings": 514,
71
+ "model_type": "xlm-roberta",
72
+ "num_attention_heads": 12,
73
+ "num_hidden_layers": 12,
74
+ "output_past": true,
75
+ "pad_token_id": 1,
76
+ "position_embedding_type": "absolute",
77
+ "torch_dtype": "float32",
78
+ "transformers_version": "4.44.2",
79
+ "type_vocab_size": 1,
80
+ "use_cache": true,
81
+ "vocab_size": 250002
82
+ }
checkpoint-6092/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c66b7cff987c01f5c0228bd9aa9a1effa78f81d3b3807f49110c614932f921a5
3
+ size 1109913172
checkpoint-6092/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa34aa36acd6fe306a8c1b1a27e2b5c97b9be5ca72bcf7c45e571026b74156b
3
+ size 2219944634
checkpoint-6092/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e411b02601fbfa14272097e8a1b924c7589a1fcadc45e9c5832a14d8180167b
3
+ size 14244
checkpoint-6092/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8023cb1a907042e11636158736ea7995792a9239adb25662fbb007702279897
3
+ size 1064
checkpoint-6092/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-6092/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-6092/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
3
+ size 17082999
checkpoint-6092/tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
checkpoint-6092/trainer_state.json ADDED
@@ -0,0 +1,928 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9977469995625562,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/GolemPII/GolemPII-xlm-roberta-v1/checkpoint-6092",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6092,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03282994090610637,
13
+ "grad_norm": 10.239672660827637,
14
+ "learning_rate": 6.036745406824147e-06,
15
+ "loss": 3.0294,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.06565988181221274,
20
+ "grad_norm": 1.969146966934204,
21
+ "learning_rate": 1.2598425196850394e-05,
22
+ "loss": 1.5238,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.0984898227183191,
27
+ "grad_norm": 0.7575042843818665,
28
+ "learning_rate": 1.916010498687664e-05,
29
+ "loss": 0.2974,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.1313197636244255,
34
+ "grad_norm": 0.6243991851806641,
35
+ "learning_rate": 2.572178477690289e-05,
36
+ "loss": 0.0568,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.16414970453053185,
41
+ "grad_norm": 0.35771840810775757,
42
+ "learning_rate": 3.228346456692913e-05,
43
+ "loss": 0.031,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.1969796454366382,
48
+ "grad_norm": 0.7596266865730286,
49
+ "learning_rate": 3.8845144356955383e-05,
50
+ "loss": 0.0205,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.2298095863427446,
55
+ "grad_norm": 0.4744904339313507,
56
+ "learning_rate": 4.540682414698163e-05,
57
+ "loss": 0.0189,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.262639527248851,
62
+ "grad_norm": 1.39719557762146,
63
+ "learning_rate": 4.989632291954659e-05,
64
+ "loss": 0.0138,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.29546946815495734,
69
+ "grad_norm": 0.29437175393104553,
70
+ "learning_rate": 4.955073265136854e-05,
71
+ "loss": 0.0125,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.3282994090610637,
76
+ "grad_norm": 0.19857335090637207,
77
+ "learning_rate": 4.920514238319049e-05,
78
+ "loss": 0.0107,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.36112934996717005,
83
+ "grad_norm": 0.34563446044921875,
84
+ "learning_rate": 4.885955211501244e-05,
85
+ "loss": 0.0106,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.3939592908732764,
90
+ "grad_norm": 0.3963533639907837,
91
+ "learning_rate": 4.851396184683439e-05,
92
+ "loss": 0.0122,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.42678923177938277,
97
+ "grad_norm": 0.37360525131225586,
98
+ "learning_rate": 4.816837157865634e-05,
99
+ "loss": 0.009,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.4596191726854892,
104
+ "grad_norm": 0.2154053896665573,
105
+ "learning_rate": 4.78227813104783e-05,
106
+ "loss": 0.0083,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.49244911359159554,
111
+ "grad_norm": 0.33652621507644653,
112
+ "learning_rate": 4.747719104230025e-05,
113
+ "loss": 0.0078,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.525279054497702,
118
+ "grad_norm": 0.5589196085929871,
119
+ "learning_rate": 4.71316007741222e-05,
120
+ "loss": 0.0088,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.5581089954038083,
125
+ "grad_norm": 0.33235111832618713,
126
+ "learning_rate": 4.678601050594415e-05,
127
+ "loss": 0.0064,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.5909389363099147,
132
+ "grad_norm": 0.36602529883384705,
133
+ "learning_rate": 4.644042023776611e-05,
134
+ "loss": 0.0068,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.623768877216021,
139
+ "grad_norm": 1.011355996131897,
140
+ "learning_rate": 4.609482996958806e-05,
141
+ "loss": 0.0059,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.6565988181221274,
146
+ "grad_norm": 0.5964003205299377,
147
+ "learning_rate": 4.574923970141001e-05,
148
+ "loss": 0.0051,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.6894287590282338,
153
+ "grad_norm": 0.21312755346298218,
154
+ "learning_rate": 4.540364943323196e-05,
155
+ "loss": 0.0058,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.7222586999343401,
160
+ "grad_norm": 0.19403104484081268,
161
+ "learning_rate": 4.5058059165053913e-05,
162
+ "loss": 0.0058,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.7550886408404465,
167
+ "grad_norm": 0.15370243787765503,
168
+ "learning_rate": 4.4712468896875864e-05,
169
+ "loss": 0.0051,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.7879185817465528,
174
+ "grad_norm": 0.3946862518787384,
175
+ "learning_rate": 4.4366878628697815e-05,
176
+ "loss": 0.0054,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.8207485226526592,
181
+ "grad_norm": 0.23363596200942993,
182
+ "learning_rate": 4.402128836051977e-05,
183
+ "loss": 0.0048,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.8535784635587655,
188
+ "grad_norm": 0.25897666811943054,
189
+ "learning_rate": 4.367569809234172e-05,
190
+ "loss": 0.007,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.886408404464872,
195
+ "grad_norm": 0.15858227014541626,
196
+ "learning_rate": 4.3330107824163674e-05,
197
+ "loss": 0.0042,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.9192383453709784,
202
+ "grad_norm": 0.13322387635707855,
203
+ "learning_rate": 4.2984517555985625e-05,
204
+ "loss": 0.005,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.9520682862770847,
209
+ "grad_norm": 0.16873428225517273,
210
+ "learning_rate": 4.2638927287807575e-05,
211
+ "loss": 0.0046,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.9848982271831911,
216
+ "grad_norm": 0.18423955142498016,
217
+ "learning_rate": 4.229333701962953e-05,
218
+ "loss": 0.0058,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 1.0,
223
+ "eval_accuracy": 0.9993276594535457,
224
+ "eval_f1": 0.9933933815429036,
225
+ "eval_loss": 0.0024869011249393225,
226
+ "eval_precision": 0.9931092525380043,
227
+ "eval_recall": 0.9936776731732028,
228
+ "eval_runtime": 76.0097,
229
+ "eval_samples_per_second": 236.812,
230
+ "eval_steps_per_second": 3.71,
231
+ "step": 1523
232
+ },
233
+ {
234
+ "epoch": 1.0177281680892973,
235
+ "grad_norm": 0.29311779141426086,
236
+ "learning_rate": 4.1947746751451484e-05,
237
+ "loss": 0.0041,
238
+ "step": 1550
239
+ },
240
+ {
241
+ "epoch": 1.050558108995404,
242
+ "grad_norm": 0.10629381239414215,
243
+ "learning_rate": 4.1602156483273434e-05,
244
+ "loss": 0.0037,
245
+ "step": 1600
246
+ },
247
+ {
248
+ "epoch": 1.0833880499015103,
249
+ "grad_norm": 0.18275995552539825,
250
+ "learning_rate": 4.1256566215095385e-05,
251
+ "loss": 0.0043,
252
+ "step": 1650
253
+ },
254
+ {
255
+ "epoch": 1.1162179908076166,
256
+ "grad_norm": 0.06012125313282013,
257
+ "learning_rate": 4.0910975946917336e-05,
258
+ "loss": 0.0062,
259
+ "step": 1700
260
+ },
261
+ {
262
+ "epoch": 1.149047931713723,
263
+ "grad_norm": 7.185174942016602,
264
+ "learning_rate": 4.0565385678739286e-05,
265
+ "loss": 0.0085,
266
+ "step": 1750
267
+ },
268
+ {
269
+ "epoch": 1.1818778726198294,
270
+ "grad_norm": 0.07045840471982956,
271
+ "learning_rate": 4.021979541056124e-05,
272
+ "loss": 0.0031,
273
+ "step": 1800
274
+ },
275
+ {
276
+ "epoch": 1.2147078135259357,
277
+ "grad_norm": 0.23435795307159424,
278
+ "learning_rate": 3.9874205142383195e-05,
279
+ "loss": 0.0026,
280
+ "step": 1850
281
+ },
282
+ {
283
+ "epoch": 1.247537754432042,
284
+ "grad_norm": 0.046855829656124115,
285
+ "learning_rate": 3.9528614874205145e-05,
286
+ "loss": 0.0031,
287
+ "step": 1900
288
+ },
289
+ {
290
+ "epoch": 1.2803676953381484,
291
+ "grad_norm": 0.3116040527820587,
292
+ "learning_rate": 3.9183024606027096e-05,
293
+ "loss": 0.0032,
294
+ "step": 1950
295
+ },
296
+ {
297
+ "epoch": 1.3131976362442548,
298
+ "grad_norm": 0.10148299485445023,
299
+ "learning_rate": 3.883743433784905e-05,
300
+ "loss": 0.0026,
301
+ "step": 2000
302
+ },
303
+ {
304
+ "epoch": 1.3460275771503611,
305
+ "grad_norm": 0.06928931921720505,
306
+ "learning_rate": 3.8491844069671004e-05,
307
+ "loss": 0.0028,
308
+ "step": 2050
309
+ },
310
+ {
311
+ "epoch": 1.3788575180564675,
312
+ "grad_norm": 0.09313840419054031,
313
+ "learning_rate": 3.8146253801492955e-05,
314
+ "loss": 0.0027,
315
+ "step": 2100
316
+ },
317
+ {
318
+ "epoch": 1.4116874589625739,
319
+ "grad_norm": 0.28150513768196106,
320
+ "learning_rate": 3.7800663533314906e-05,
321
+ "loss": 0.0032,
322
+ "step": 2150
323
+ },
324
+ {
325
+ "epoch": 1.4445173998686802,
326
+ "grad_norm": 0.4722907841205597,
327
+ "learning_rate": 3.745507326513685e-05,
328
+ "loss": 0.0037,
329
+ "step": 2200
330
+ },
331
+ {
332
+ "epoch": 1.4773473407747866,
333
+ "grad_norm": 0.5664809346199036,
334
+ "learning_rate": 3.710948299695881e-05,
335
+ "loss": 0.0026,
336
+ "step": 2250
337
+ },
338
+ {
339
+ "epoch": 1.510177281680893,
340
+ "grad_norm": 0.03828972578048706,
341
+ "learning_rate": 3.676389272878076e-05,
342
+ "loss": 0.0022,
343
+ "step": 2300
344
+ },
345
+ {
346
+ "epoch": 1.5430072225869993,
347
+ "grad_norm": 0.5701923370361328,
348
+ "learning_rate": 3.641830246060271e-05,
349
+ "loss": 0.0022,
350
+ "step": 2350
351
+ },
352
+ {
353
+ "epoch": 1.5758371634931057,
354
+ "grad_norm": 0.15145182609558105,
355
+ "learning_rate": 3.607271219242466e-05,
356
+ "loss": 0.0029,
357
+ "step": 2400
358
+ },
359
+ {
360
+ "epoch": 1.608667104399212,
361
+ "grad_norm": 0.055488649755716324,
362
+ "learning_rate": 3.572712192424662e-05,
363
+ "loss": 0.002,
364
+ "step": 2450
365
+ },
366
+ {
367
+ "epoch": 1.6414970453053184,
368
+ "grad_norm": 0.2535063624382019,
369
+ "learning_rate": 3.538153165606857e-05,
370
+ "loss": 0.0024,
371
+ "step": 2500
372
+ },
373
+ {
374
+ "epoch": 1.6743269862114247,
375
+ "grad_norm": 0.09548994898796082,
376
+ "learning_rate": 3.503594138789052e-05,
377
+ "loss": 0.0024,
378
+ "step": 2550
379
+ },
380
+ {
381
+ "epoch": 1.707156927117531,
382
+ "grad_norm": 0.04930610582232475,
383
+ "learning_rate": 3.469035111971247e-05,
384
+ "loss": 0.0021,
385
+ "step": 2600
386
+ },
387
+ {
388
+ "epoch": 1.7399868680236374,
389
+ "grad_norm": 0.12071087211370468,
390
+ "learning_rate": 3.434476085153443e-05,
391
+ "loss": 0.0023,
392
+ "step": 2650
393
+ },
394
+ {
395
+ "epoch": 1.7728168089297438,
396
+ "grad_norm": 0.038167692720890045,
397
+ "learning_rate": 3.399917058335638e-05,
398
+ "loss": 0.0027,
399
+ "step": 2700
400
+ },
401
+ {
402
+ "epoch": 1.8056467498358502,
403
+ "grad_norm": 0.016604498028755188,
404
+ "learning_rate": 3.365358031517832e-05,
405
+ "loss": 0.0025,
406
+ "step": 2750
407
+ },
408
+ {
409
+ "epoch": 1.8384766907419565,
410
+ "grad_norm": 0.10711315274238586,
411
+ "learning_rate": 3.330799004700028e-05,
412
+ "loss": 0.0021,
413
+ "step": 2800
414
+ },
415
+ {
416
+ "epoch": 1.8713066316480629,
417
+ "grad_norm": 0.10547716170549393,
418
+ "learning_rate": 3.296239977882223e-05,
419
+ "loss": 0.0029,
420
+ "step": 2850
421
+ },
422
+ {
423
+ "epoch": 1.9041365725541692,
424
+ "grad_norm": 0.12901557981967926,
425
+ "learning_rate": 3.261680951064418e-05,
426
+ "loss": 0.0026,
427
+ "step": 2900
428
+ },
429
+ {
430
+ "epoch": 1.9369665134602758,
431
+ "grad_norm": 0.16034963726997375,
432
+ "learning_rate": 3.227121924246613e-05,
433
+ "loss": 0.0031,
434
+ "step": 2950
435
+ },
436
+ {
437
+ "epoch": 1.9697964543663822,
438
+ "grad_norm": 0.060961514711380005,
439
+ "learning_rate": 3.192562897428809e-05,
440
+ "loss": 0.0017,
441
+ "step": 3000
442
+ },
443
+ {
444
+ "epoch": 2.0,
445
+ "eval_accuracy": 0.9995754536025347,
446
+ "eval_f1": 0.995708295650744,
447
+ "eval_loss": 0.0013849161332473159,
448
+ "eval_precision": 0.9954693109933322,
449
+ "eval_recall": 0.9959473950829271,
450
+ "eval_runtime": 75.6987,
451
+ "eval_samples_per_second": 237.785,
452
+ "eval_steps_per_second": 3.725,
453
+ "step": 3046
454
+ },
455
+ {
456
+ "epoch": 2.0026263952724883,
457
+ "grad_norm": 0.08297313749790192,
458
+ "learning_rate": 3.158003870611004e-05,
459
+ "loss": 0.0026,
460
+ "step": 3050
461
+ },
462
+ {
463
+ "epoch": 2.0354563361785947,
464
+ "grad_norm": 0.19145315885543823,
465
+ "learning_rate": 3.123444843793199e-05,
466
+ "loss": 0.0014,
467
+ "step": 3100
468
+ },
469
+ {
470
+ "epoch": 2.0682862770847015,
471
+ "grad_norm": 0.08754308521747589,
472
+ "learning_rate": 3.088885816975394e-05,
473
+ "loss": 0.0014,
474
+ "step": 3150
475
+ },
476
+ {
477
+ "epoch": 2.101116217990808,
478
+ "grad_norm": 0.1580217033624649,
479
+ "learning_rate": 3.054326790157589e-05,
480
+ "loss": 0.0016,
481
+ "step": 3200
482
+ },
483
+ {
484
+ "epoch": 2.133946158896914,
485
+ "grad_norm": 0.022689586505293846,
486
+ "learning_rate": 3.0197677633397846e-05,
487
+ "loss": 0.0016,
488
+ "step": 3250
489
+ },
490
+ {
491
+ "epoch": 2.1667760998030205,
492
+ "grad_norm": 0.10402818024158478,
493
+ "learning_rate": 2.9852087365219793e-05,
494
+ "loss": 0.0015,
495
+ "step": 3300
496
+ },
497
+ {
498
+ "epoch": 2.199606040709127,
499
+ "grad_norm": 0.11667637526988983,
500
+ "learning_rate": 2.9506497097041747e-05,
501
+ "loss": 0.002,
502
+ "step": 3350
503
+ },
504
+ {
505
+ "epoch": 2.2324359816152333,
506
+ "grad_norm": 0.24381309747695923,
507
+ "learning_rate": 2.9160906828863698e-05,
508
+ "loss": 0.0039,
509
+ "step": 3400
510
+ },
511
+ {
512
+ "epoch": 2.2652659225213396,
513
+ "grad_norm": 0.03473767638206482,
514
+ "learning_rate": 2.8815316560685652e-05,
515
+ "loss": 0.0016,
516
+ "step": 3450
517
+ },
518
+ {
519
+ "epoch": 2.298095863427446,
520
+ "grad_norm": 1.3230725526809692,
521
+ "learning_rate": 2.8469726292507603e-05,
522
+ "loss": 0.0016,
523
+ "step": 3500
524
+ },
525
+ {
526
+ "epoch": 2.3309258043335523,
527
+ "grad_norm": 0.1341700553894043,
528
+ "learning_rate": 2.8124136024329557e-05,
529
+ "loss": 0.0047,
530
+ "step": 3550
531
+ },
532
+ {
533
+ "epoch": 2.3637557452396587,
534
+ "grad_norm": 0.13513527810573578,
535
+ "learning_rate": 2.7778545756151508e-05,
536
+ "loss": 0.0018,
537
+ "step": 3600
538
+ },
539
+ {
540
+ "epoch": 2.396585686145765,
541
+ "grad_norm": 0.0577649362385273,
542
+ "learning_rate": 2.743295548797346e-05,
543
+ "loss": 0.0014,
544
+ "step": 3650
545
+ },
546
+ {
547
+ "epoch": 2.4294156270518714,
548
+ "grad_norm": 0.1941065490245819,
549
+ "learning_rate": 2.7087365219795412e-05,
550
+ "loss": 0.0011,
551
+ "step": 3700
552
+ },
553
+ {
554
+ "epoch": 2.4622455679579778,
555
+ "grad_norm": 0.15985670685768127,
556
+ "learning_rate": 2.6741774951617367e-05,
557
+ "loss": 0.0016,
558
+ "step": 3750
559
+ },
560
+ {
561
+ "epoch": 2.495075508864084,
562
+ "grad_norm": 0.08614476025104523,
563
+ "learning_rate": 2.6396184683439317e-05,
564
+ "loss": 0.0016,
565
+ "step": 3800
566
+ },
567
+ {
568
+ "epoch": 2.5279054497701905,
569
+ "grad_norm": 0.15596601366996765,
570
+ "learning_rate": 2.605059441526127e-05,
571
+ "loss": 0.0016,
572
+ "step": 3850
573
+ },
574
+ {
575
+ "epoch": 2.560735390676297,
576
+ "grad_norm": 0.12409207224845886,
577
+ "learning_rate": 2.5705004147083215e-05,
578
+ "loss": 0.0015,
579
+ "step": 3900
580
+ },
581
+ {
582
+ "epoch": 2.593565331582403,
583
+ "grad_norm": 0.189951092004776,
584
+ "learning_rate": 2.535941387890517e-05,
585
+ "loss": 0.0015,
586
+ "step": 3950
587
+ },
588
+ {
589
+ "epoch": 2.6263952724885096,
590
+ "grad_norm": 0.059304554015398026,
591
+ "learning_rate": 2.501382361072712e-05,
592
+ "loss": 0.0014,
593
+ "step": 4000
594
+ },
595
+ {
596
+ "epoch": 2.659225213394616,
597
+ "grad_norm": 0.24233925342559814,
598
+ "learning_rate": 2.4668233342549074e-05,
599
+ "loss": 0.0013,
600
+ "step": 4050
601
+ },
602
+ {
603
+ "epoch": 2.6920551543007223,
604
+ "grad_norm": 0.2739645838737488,
605
+ "learning_rate": 2.4322643074371025e-05,
606
+ "loss": 0.0012,
607
+ "step": 4100
608
+ },
609
+ {
610
+ "epoch": 2.7248850952068286,
611
+ "grad_norm": 0.11855873465538025,
612
+ "learning_rate": 2.397705280619298e-05,
613
+ "loss": 0.0019,
614
+ "step": 4150
615
+ },
616
+ {
617
+ "epoch": 2.757715036112935,
618
+ "grad_norm": 0.05818852037191391,
619
+ "learning_rate": 2.363146253801493e-05,
620
+ "loss": 0.0027,
621
+ "step": 4200
622
+ },
623
+ {
624
+ "epoch": 2.7905449770190414,
625
+ "grad_norm": 0.06046278029680252,
626
+ "learning_rate": 2.3285872269836884e-05,
627
+ "loss": 0.0014,
628
+ "step": 4250
629
+ },
630
+ {
631
+ "epoch": 2.8233749179251477,
632
+ "grad_norm": 0.04216454550623894,
633
+ "learning_rate": 2.2940282001658835e-05,
634
+ "loss": 0.0011,
635
+ "step": 4300
636
+ },
637
+ {
638
+ "epoch": 2.856204858831254,
639
+ "grad_norm": 0.0564955435693264,
640
+ "learning_rate": 2.2594691733480785e-05,
641
+ "loss": 0.0015,
642
+ "step": 4350
643
+ },
644
+ {
645
+ "epoch": 2.8890347997373604,
646
+ "grad_norm": 0.10374019294977188,
647
+ "learning_rate": 2.224910146530274e-05,
648
+ "loss": 0.0013,
649
+ "step": 4400
650
+ },
651
+ {
652
+ "epoch": 2.921864740643467,
653
+ "grad_norm": 0.2742884159088135,
654
+ "learning_rate": 2.190351119712469e-05,
655
+ "loss": 0.0014,
656
+ "step": 4450
657
+ },
658
+ {
659
+ "epoch": 2.954694681549573,
660
+ "grad_norm": 0.02845386229455471,
661
+ "learning_rate": 2.155792092894664e-05,
662
+ "loss": 0.0013,
663
+ "step": 4500
664
+ },
665
+ {
666
+ "epoch": 2.9875246224556795,
667
+ "grad_norm": 0.10036207735538483,
668
+ "learning_rate": 2.1212330660768595e-05,
669
+ "loss": 0.0012,
670
+ "step": 4550
671
+ },
672
+ {
673
+ "epoch": 3.0,
674
+ "eval_accuracy": 0.9997391341413165,
675
+ "eval_f1": 0.9973228263586491,
676
+ "eval_loss": 0.0009462219895794988,
677
+ "eval_precision": 0.9971588480180992,
678
+ "eval_recall": 0.9974868586390879,
679
+ "eval_runtime": 75.644,
680
+ "eval_samples_per_second": 237.957,
681
+ "eval_steps_per_second": 3.728,
682
+ "step": 4569
683
+ },
684
+ {
685
+ "epoch": 3.020354563361786,
686
+ "grad_norm": 0.08079813420772552,
687
+ "learning_rate": 2.0866740392590546e-05,
688
+ "loss": 0.0011,
689
+ "step": 4600
690
+ },
691
+ {
692
+ "epoch": 3.0531845042678922,
693
+ "grad_norm": 0.09932583570480347,
694
+ "learning_rate": 2.0521150124412497e-05,
695
+ "loss": 0.0023,
696
+ "step": 4650
697
+ },
698
+ {
699
+ "epoch": 3.0860144451739986,
700
+ "grad_norm": 0.05140871927142143,
701
+ "learning_rate": 2.017555985623445e-05,
702
+ "loss": 0.001,
703
+ "step": 4700
704
+ },
705
+ {
706
+ "epoch": 3.118844386080105,
707
+ "grad_norm": 0.19095173478126526,
708
+ "learning_rate": 1.98299695880564e-05,
709
+ "loss": 0.001,
710
+ "step": 4750
711
+ },
712
+ {
713
+ "epoch": 3.1516743269862113,
714
+ "grad_norm": 0.041814982891082764,
715
+ "learning_rate": 1.9484379319878356e-05,
716
+ "loss": 0.0018,
717
+ "step": 4800
718
+ },
719
+ {
720
+ "epoch": 3.1845042678923177,
721
+ "grad_norm": 0.025649981573224068,
722
+ "learning_rate": 1.9138789051700303e-05,
723
+ "loss": 0.0008,
724
+ "step": 4850
725
+ },
726
+ {
727
+ "epoch": 3.217334208798424,
728
+ "grad_norm": 0.12662899494171143,
729
+ "learning_rate": 1.8793198783522257e-05,
730
+ "loss": 0.0009,
731
+ "step": 4900
732
+ },
733
+ {
734
+ "epoch": 3.2501641497045304,
735
+ "grad_norm": 0.10787362605333328,
736
+ "learning_rate": 1.8447608515344208e-05,
737
+ "loss": 0.0008,
738
+ "step": 4950
739
+ },
740
+ {
741
+ "epoch": 3.2829940906106367,
742
+ "grad_norm": 0.03877755254507065,
743
+ "learning_rate": 1.8102018247166162e-05,
744
+ "loss": 0.0008,
745
+ "step": 5000
746
+ },
747
+ {
748
+ "epoch": 3.315824031516743,
749
+ "grad_norm": 0.11100368201732635,
750
+ "learning_rate": 1.7756427978988113e-05,
751
+ "loss": 0.0007,
752
+ "step": 5050
753
+ },
754
+ {
755
+ "epoch": 3.3486539724228495,
756
+ "grad_norm": 0.027431080117821693,
757
+ "learning_rate": 1.7410837710810067e-05,
758
+ "loss": 0.0008,
759
+ "step": 5100
760
+ },
761
+ {
762
+ "epoch": 3.381483913328956,
763
+ "grad_norm": 0.013812090270221233,
764
+ "learning_rate": 1.7065247442632014e-05,
765
+ "loss": 0.0008,
766
+ "step": 5150
767
+ },
768
+ {
769
+ "epoch": 3.414313854235062,
770
+ "grad_norm": 0.1110658347606659,
771
+ "learning_rate": 1.6719657174453968e-05,
772
+ "loss": 0.0022,
773
+ "step": 5200
774
+ },
775
+ {
776
+ "epoch": 3.4471437951411685,
777
+ "grad_norm": 0.11397113651037216,
778
+ "learning_rate": 1.637406690627592e-05,
779
+ "loss": 0.0009,
780
+ "step": 5250
781
+ },
782
+ {
783
+ "epoch": 3.479973736047275,
784
+ "grad_norm": 0.2407987117767334,
785
+ "learning_rate": 1.6028476638097873e-05,
786
+ "loss": 0.0008,
787
+ "step": 5300
788
+ },
789
+ {
790
+ "epoch": 3.5128036769533812,
791
+ "grad_norm": 0.06540926545858383,
792
+ "learning_rate": 1.5682886369919824e-05,
793
+ "loss": 0.001,
794
+ "step": 5350
795
+ },
796
+ {
797
+ "epoch": 3.5456336178594876,
798
+ "grad_norm": 0.08520480245351791,
799
+ "learning_rate": 1.5337296101741775e-05,
800
+ "loss": 0.0007,
801
+ "step": 5400
802
+ },
803
+ {
804
+ "epoch": 3.578463558765594,
805
+ "grad_norm": 0.091216079890728,
806
+ "learning_rate": 1.4991705833563727e-05,
807
+ "loss": 0.0011,
808
+ "step": 5450
809
+ },
810
+ {
811
+ "epoch": 3.6112934996717003,
812
+ "grad_norm": 0.1052037924528122,
813
+ "learning_rate": 1.464611556538568e-05,
814
+ "loss": 0.0008,
815
+ "step": 5500
816
+ },
817
+ {
818
+ "epoch": 3.6441234405778067,
819
+ "grad_norm": 0.30819040536880493,
820
+ "learning_rate": 1.4300525297207632e-05,
821
+ "loss": 0.0007,
822
+ "step": 5550
823
+ },
824
+ {
825
+ "epoch": 3.6769533814839135,
826
+ "grad_norm": 0.06232546642422676,
827
+ "learning_rate": 1.3954935029029584e-05,
828
+ "loss": 0.0005,
829
+ "step": 5600
830
+ },
831
+ {
832
+ "epoch": 3.70978332239002,
833
+ "grad_norm": 0.08547823131084442,
834
+ "learning_rate": 1.3609344760851537e-05,
835
+ "loss": 0.0006,
836
+ "step": 5650
837
+ },
838
+ {
839
+ "epoch": 3.742613263296126,
840
+ "grad_norm": 0.12835901975631714,
841
+ "learning_rate": 1.3263754492673486e-05,
842
+ "loss": 0.0028,
843
+ "step": 5700
844
+ },
845
+ {
846
+ "epoch": 3.7754432042022326,
847
+ "grad_norm": 0.07907555252313614,
848
+ "learning_rate": 1.2918164224495438e-05,
849
+ "loss": 0.001,
850
+ "step": 5750
851
+ },
852
+ {
853
+ "epoch": 3.808273145108339,
854
+ "grad_norm": 0.03760789334774017,
855
+ "learning_rate": 1.257257395631739e-05,
856
+ "loss": 0.0008,
857
+ "step": 5800
858
+ },
859
+ {
860
+ "epoch": 3.8411030860144453,
861
+ "grad_norm": 0.008074942976236343,
862
+ "learning_rate": 1.2226983688139343e-05,
863
+ "loss": 0.0007,
864
+ "step": 5850
865
+ },
866
+ {
867
+ "epoch": 3.8739330269205516,
868
+ "grad_norm": 0.039751049131155014,
869
+ "learning_rate": 1.1881393419961294e-05,
870
+ "loss": 0.0008,
871
+ "step": 5900
872
+ },
873
+ {
874
+ "epoch": 3.906762967826658,
875
+ "grad_norm": 0.1129092127084732,
876
+ "learning_rate": 1.1535803151783246e-05,
877
+ "loss": 0.0009,
878
+ "step": 5950
879
+ },
880
+ {
881
+ "epoch": 3.9395929087327644,
882
+ "grad_norm": 0.030842676758766174,
883
+ "learning_rate": 1.1190212883605199e-05,
884
+ "loss": 0.0006,
885
+ "step": 6000
886
+ },
887
+ {
888
+ "epoch": 3.9724228496388707,
889
+ "grad_norm": 0.24821631610393524,
890
+ "learning_rate": 1.084462261542715e-05,
891
+ "loss": 0.0009,
892
+ "step": 6050
893
+ },
894
+ {
895
+ "epoch": 4.0,
896
+ "eval_accuracy": 0.9997499325101945,
897
+ "eval_f1": 0.9977469995625562,
898
+ "eval_loss": 0.0008962151478044689,
899
+ "eval_precision": 0.9976255936015996,
900
+ "eval_recall": 0.997868435076085,
901
+ "eval_runtime": 75.9398,
902
+ "eval_samples_per_second": 237.03,
903
+ "eval_steps_per_second": 3.713,
904
+ "step": 6092
905
+ }
906
+ ],
907
+ "logging_steps": 50,
908
+ "max_steps": 7615,
909
+ "num_input_tokens_seen": 0,
910
+ "num_train_epochs": 5,
911
+ "save_steps": 500,
912
+ "stateful_callbacks": {
913
+ "TrainerControl": {
914
+ "args": {
915
+ "should_epoch_stop": false,
916
+ "should_evaluate": false,
917
+ "should_log": false,
918
+ "should_save": true,
919
+ "should_training_stop": false
920
+ },
921
+ "attributes": {}
922
+ }
923
+ },
924
+ "total_flos": 1.018777915628544e+17,
925
+ "train_batch_size": 64,
926
+ "trial_name": null,
927
+ "trial_params": null
928
+ }
checkpoint-6092/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff86125497f499c04776e35f8f3ab0d025d38457377342b96f30a71196a241e2
3
+ size 5240
checkpoint-7615/config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B-BANK_ACCOUNT_NUM",
15
+ "1": "B-CC_NUM",
16
+ "2": "B-CC_PROVIDER",
17
+ "3": "B-CITY",
18
+ "4": "B-DATE",
19
+ "5": "B-EMAIL",
20
+ "6": "B-FIRST_NAME",
21
+ "7": "B-ID_NUM",
22
+ "8": "B-LAST_NAME",
23
+ "9": "B-PHONE_NUM",
24
+ "10": "B-POSTAL_CODE",
25
+ "11": "B-STREET",
26
+ "12": "I-BANK_ACCOUNT_NUM",
27
+ "13": "I-CC_NUM",
28
+ "14": "I-CC_PROVIDER",
29
+ "15": "I-CITY",
30
+ "16": "I-DATE",
31
+ "17": "I-EMAIL",
32
+ "18": "I-FIRST_NAME",
33
+ "19": "I-ID_NUM",
34
+ "20": "I-LAST_NAME",
35
+ "21": "I-PHONE_NUM",
36
+ "22": "I-POSTAL_CODE",
37
+ "23": "I-STREET",
38
+ "24": "O"
39
+ },
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 3072,
42
+ "label2id": {
43
+ "B-BANK_ACCOUNT_NUM": 0,
44
+ "B-CC_NUM": 1,
45
+ "B-CC_PROVIDER": 2,
46
+ "B-CITY": 3,
47
+ "B-DATE": 4,
48
+ "B-EMAIL": 5,
49
+ "B-FIRST_NAME": 6,
50
+ "B-ID_NUM": 7,
51
+ "B-LAST_NAME": 8,
52
+ "B-PHONE_NUM": 9,
53
+ "B-POSTAL_CODE": 10,
54
+ "B-STREET": 11,
55
+ "I-BANK_ACCOUNT_NUM": 12,
56
+ "I-CC_NUM": 13,
57
+ "I-CC_PROVIDER": 14,
58
+ "I-CITY": 15,
59
+ "I-DATE": 16,
60
+ "I-EMAIL": 17,
61
+ "I-FIRST_NAME": 18,
62
+ "I-ID_NUM": 19,
63
+ "I-LAST_NAME": 20,
64
+ "I-PHONE_NUM": 21,
65
+ "I-POSTAL_CODE": 22,
66
+ "I-STREET": 23,
67
+ "O": 24
68
+ },
69
+ "layer_norm_eps": 1e-05,
70
+ "max_position_embeddings": 514,
71
+ "model_type": "xlm-roberta",
72
+ "num_attention_heads": 12,
73
+ "num_hidden_layers": 12,
74
+ "output_past": true,
75
+ "pad_token_id": 1,
76
+ "position_embedding_type": "absolute",
77
+ "torch_dtype": "float32",
78
+ "transformers_version": "4.44.2",
79
+ "type_vocab_size": 1,
80
+ "use_cache": true,
81
+ "vocab_size": 250002
82
+ }
checkpoint-7615/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb60e772f76b4f658de8a682f5851cb8fd5c2479f313f5ba3537e2eee07af663
3
+ size 1109913172
checkpoint-7615/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54daf99ea6d92157fee688327ff4e170cca1ac08bb95ba9f82508ac18db322b6
3
+ size 2219944634
checkpoint-7615/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf61d2d43a2a1d3499c22d3bc2cbce30d7aaf9b1950fa18402026d7149849c91
3
+ size 14244
checkpoint-7615/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12b4cb0cfb4aa16cd6ebae55dc0b3ffe98a32cabe91abc81d611021578868c9b
3
+ size 1064
checkpoint-7615/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-7615/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-7615/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
3
+ size 17082999
checkpoint-7615/tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
checkpoint-7615/trainer_state.json ADDED
@@ -0,0 +1,1157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.998085740410612,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/GolemPII/GolemPII-xlm-roberta-v1/checkpoint-7615",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7615,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03282994090610637,
13
+ "grad_norm": 10.239672660827637,
14
+ "learning_rate": 6.036745406824147e-06,
15
+ "loss": 3.0294,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.06565988181221274,
20
+ "grad_norm": 1.969146966934204,
21
+ "learning_rate": 1.2598425196850394e-05,
22
+ "loss": 1.5238,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.0984898227183191,
27
+ "grad_norm": 0.7575042843818665,
28
+ "learning_rate": 1.916010498687664e-05,
29
+ "loss": 0.2974,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.1313197636244255,
34
+ "grad_norm": 0.6243991851806641,
35
+ "learning_rate": 2.572178477690289e-05,
36
+ "loss": 0.0568,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.16414970453053185,
41
+ "grad_norm": 0.35771840810775757,
42
+ "learning_rate": 3.228346456692913e-05,
43
+ "loss": 0.031,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.1969796454366382,
48
+ "grad_norm": 0.7596266865730286,
49
+ "learning_rate": 3.8845144356955383e-05,
50
+ "loss": 0.0205,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.2298095863427446,
55
+ "grad_norm": 0.4744904339313507,
56
+ "learning_rate": 4.540682414698163e-05,
57
+ "loss": 0.0189,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.262639527248851,
62
+ "grad_norm": 1.39719557762146,
63
+ "learning_rate": 4.989632291954659e-05,
64
+ "loss": 0.0138,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.29546946815495734,
69
+ "grad_norm": 0.29437175393104553,
70
+ "learning_rate": 4.955073265136854e-05,
71
+ "loss": 0.0125,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.3282994090610637,
76
+ "grad_norm": 0.19857335090637207,
77
+ "learning_rate": 4.920514238319049e-05,
78
+ "loss": 0.0107,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.36112934996717005,
83
+ "grad_norm": 0.34563446044921875,
84
+ "learning_rate": 4.885955211501244e-05,
85
+ "loss": 0.0106,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.3939592908732764,
90
+ "grad_norm": 0.3963533639907837,
91
+ "learning_rate": 4.851396184683439e-05,
92
+ "loss": 0.0122,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.42678923177938277,
97
+ "grad_norm": 0.37360525131225586,
98
+ "learning_rate": 4.816837157865634e-05,
99
+ "loss": 0.009,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.4596191726854892,
104
+ "grad_norm": 0.2154053896665573,
105
+ "learning_rate": 4.78227813104783e-05,
106
+ "loss": 0.0083,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.49244911359159554,
111
+ "grad_norm": 0.33652621507644653,
112
+ "learning_rate": 4.747719104230025e-05,
113
+ "loss": 0.0078,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.525279054497702,
118
+ "grad_norm": 0.5589196085929871,
119
+ "learning_rate": 4.71316007741222e-05,
120
+ "loss": 0.0088,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.5581089954038083,
125
+ "grad_norm": 0.33235111832618713,
126
+ "learning_rate": 4.678601050594415e-05,
127
+ "loss": 0.0064,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.5909389363099147,
132
+ "grad_norm": 0.36602529883384705,
133
+ "learning_rate": 4.644042023776611e-05,
134
+ "loss": 0.0068,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.623768877216021,
139
+ "grad_norm": 1.011355996131897,
140
+ "learning_rate": 4.609482996958806e-05,
141
+ "loss": 0.0059,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.6565988181221274,
146
+ "grad_norm": 0.5964003205299377,
147
+ "learning_rate": 4.574923970141001e-05,
148
+ "loss": 0.0051,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.6894287590282338,
153
+ "grad_norm": 0.21312755346298218,
154
+ "learning_rate": 4.540364943323196e-05,
155
+ "loss": 0.0058,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.7222586999343401,
160
+ "grad_norm": 0.19403104484081268,
161
+ "learning_rate": 4.5058059165053913e-05,
162
+ "loss": 0.0058,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.7550886408404465,
167
+ "grad_norm": 0.15370243787765503,
168
+ "learning_rate": 4.4712468896875864e-05,
169
+ "loss": 0.0051,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.7879185817465528,
174
+ "grad_norm": 0.3946862518787384,
175
+ "learning_rate": 4.4366878628697815e-05,
176
+ "loss": 0.0054,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.8207485226526592,
181
+ "grad_norm": 0.23363596200942993,
182
+ "learning_rate": 4.402128836051977e-05,
183
+ "loss": 0.0048,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.8535784635587655,
188
+ "grad_norm": 0.25897666811943054,
189
+ "learning_rate": 4.367569809234172e-05,
190
+ "loss": 0.007,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.886408404464872,
195
+ "grad_norm": 0.15858227014541626,
196
+ "learning_rate": 4.3330107824163674e-05,
197
+ "loss": 0.0042,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.9192383453709784,
202
+ "grad_norm": 0.13322387635707855,
203
+ "learning_rate": 4.2984517555985625e-05,
204
+ "loss": 0.005,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.9520682862770847,
209
+ "grad_norm": 0.16873428225517273,
210
+ "learning_rate": 4.2638927287807575e-05,
211
+ "loss": 0.0046,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.9848982271831911,
216
+ "grad_norm": 0.18423955142498016,
217
+ "learning_rate": 4.229333701962953e-05,
218
+ "loss": 0.0058,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 1.0,
223
+ "eval_accuracy": 0.9993276594535457,
224
+ "eval_f1": 0.9933933815429036,
225
+ "eval_loss": 0.0024869011249393225,
226
+ "eval_precision": 0.9931092525380043,
227
+ "eval_recall": 0.9936776731732028,
228
+ "eval_runtime": 76.0097,
229
+ "eval_samples_per_second": 236.812,
230
+ "eval_steps_per_second": 3.71,
231
+ "step": 1523
232
+ },
233
+ {
234
+ "epoch": 1.0177281680892973,
235
+ "grad_norm": 0.29311779141426086,
236
+ "learning_rate": 4.1947746751451484e-05,
237
+ "loss": 0.0041,
238
+ "step": 1550
239
+ },
240
+ {
241
+ "epoch": 1.050558108995404,
242
+ "grad_norm": 0.10629381239414215,
243
+ "learning_rate": 4.1602156483273434e-05,
244
+ "loss": 0.0037,
245
+ "step": 1600
246
+ },
247
+ {
248
+ "epoch": 1.0833880499015103,
249
+ "grad_norm": 0.18275995552539825,
250
+ "learning_rate": 4.1256566215095385e-05,
251
+ "loss": 0.0043,
252
+ "step": 1650
253
+ },
254
+ {
255
+ "epoch": 1.1162179908076166,
256
+ "grad_norm": 0.06012125313282013,
257
+ "learning_rate": 4.0910975946917336e-05,
258
+ "loss": 0.0062,
259
+ "step": 1700
260
+ },
261
+ {
262
+ "epoch": 1.149047931713723,
263
+ "grad_norm": 7.185174942016602,
264
+ "learning_rate": 4.0565385678739286e-05,
265
+ "loss": 0.0085,
266
+ "step": 1750
267
+ },
268
+ {
269
+ "epoch": 1.1818778726198294,
270
+ "grad_norm": 0.07045840471982956,
271
+ "learning_rate": 4.021979541056124e-05,
272
+ "loss": 0.0031,
273
+ "step": 1800
274
+ },
275
+ {
276
+ "epoch": 1.2147078135259357,
277
+ "grad_norm": 0.23435795307159424,
278
+ "learning_rate": 3.9874205142383195e-05,
279
+ "loss": 0.0026,
280
+ "step": 1850
281
+ },
282
+ {
283
+ "epoch": 1.247537754432042,
284
+ "grad_norm": 0.046855829656124115,
285
+ "learning_rate": 3.9528614874205145e-05,
286
+ "loss": 0.0031,
287
+ "step": 1900
288
+ },
289
+ {
290
+ "epoch": 1.2803676953381484,
291
+ "grad_norm": 0.3116040527820587,
292
+ "learning_rate": 3.9183024606027096e-05,
293
+ "loss": 0.0032,
294
+ "step": 1950
295
+ },
296
+ {
297
+ "epoch": 1.3131976362442548,
298
+ "grad_norm": 0.10148299485445023,
299
+ "learning_rate": 3.883743433784905e-05,
300
+ "loss": 0.0026,
301
+ "step": 2000
302
+ },
303
+ {
304
+ "epoch": 1.3460275771503611,
305
+ "grad_norm": 0.06928931921720505,
306
+ "learning_rate": 3.8491844069671004e-05,
307
+ "loss": 0.0028,
308
+ "step": 2050
309
+ },
310
+ {
311
+ "epoch": 1.3788575180564675,
312
+ "grad_norm": 0.09313840419054031,
313
+ "learning_rate": 3.8146253801492955e-05,
314
+ "loss": 0.0027,
315
+ "step": 2100
316
+ },
317
+ {
318
+ "epoch": 1.4116874589625739,
319
+ "grad_norm": 0.28150513768196106,
320
+ "learning_rate": 3.7800663533314906e-05,
321
+ "loss": 0.0032,
322
+ "step": 2150
323
+ },
324
+ {
325
+ "epoch": 1.4445173998686802,
326
+ "grad_norm": 0.4722907841205597,
327
+ "learning_rate": 3.745507326513685e-05,
328
+ "loss": 0.0037,
329
+ "step": 2200
330
+ },
331
+ {
332
+ "epoch": 1.4773473407747866,
333
+ "grad_norm": 0.5664809346199036,
334
+ "learning_rate": 3.710948299695881e-05,
335
+ "loss": 0.0026,
336
+ "step": 2250
337
+ },
338
+ {
339
+ "epoch": 1.510177281680893,
340
+ "grad_norm": 0.03828972578048706,
341
+ "learning_rate": 3.676389272878076e-05,
342
+ "loss": 0.0022,
343
+ "step": 2300
344
+ },
345
+ {
346
+ "epoch": 1.5430072225869993,
347
+ "grad_norm": 0.5701923370361328,
348
+ "learning_rate": 3.641830246060271e-05,
349
+ "loss": 0.0022,
350
+ "step": 2350
351
+ },
352
+ {
353
+ "epoch": 1.5758371634931057,
354
+ "grad_norm": 0.15145182609558105,
355
+ "learning_rate": 3.607271219242466e-05,
356
+ "loss": 0.0029,
357
+ "step": 2400
358
+ },
359
+ {
360
+ "epoch": 1.608667104399212,
361
+ "grad_norm": 0.055488649755716324,
362
+ "learning_rate": 3.572712192424662e-05,
363
+ "loss": 0.002,
364
+ "step": 2450
365
+ },
366
+ {
367
+ "epoch": 1.6414970453053184,
368
+ "grad_norm": 0.2535063624382019,
369
+ "learning_rate": 3.538153165606857e-05,
370
+ "loss": 0.0024,
371
+ "step": 2500
372
+ },
373
+ {
374
+ "epoch": 1.6743269862114247,
375
+ "grad_norm": 0.09548994898796082,
376
+ "learning_rate": 3.503594138789052e-05,
377
+ "loss": 0.0024,
378
+ "step": 2550
379
+ },
380
+ {
381
+ "epoch": 1.707156927117531,
382
+ "grad_norm": 0.04930610582232475,
383
+ "learning_rate": 3.469035111971247e-05,
384
+ "loss": 0.0021,
385
+ "step": 2600
386
+ },
387
+ {
388
+ "epoch": 1.7399868680236374,
389
+ "grad_norm": 0.12071087211370468,
390
+ "learning_rate": 3.434476085153443e-05,
391
+ "loss": 0.0023,
392
+ "step": 2650
393
+ },
394
+ {
395
+ "epoch": 1.7728168089297438,
396
+ "grad_norm": 0.038167692720890045,
397
+ "learning_rate": 3.399917058335638e-05,
398
+ "loss": 0.0027,
399
+ "step": 2700
400
+ },
401
+ {
402
+ "epoch": 1.8056467498358502,
403
+ "grad_norm": 0.016604498028755188,
404
+ "learning_rate": 3.365358031517832e-05,
405
+ "loss": 0.0025,
406
+ "step": 2750
407
+ },
408
+ {
409
+ "epoch": 1.8384766907419565,
410
+ "grad_norm": 0.10711315274238586,
411
+ "learning_rate": 3.330799004700028e-05,
412
+ "loss": 0.0021,
413
+ "step": 2800
414
+ },
415
+ {
416
+ "epoch": 1.8713066316480629,
417
+ "grad_norm": 0.10547716170549393,
418
+ "learning_rate": 3.296239977882223e-05,
419
+ "loss": 0.0029,
420
+ "step": 2850
421
+ },
422
+ {
423
+ "epoch": 1.9041365725541692,
424
+ "grad_norm": 0.12901557981967926,
425
+ "learning_rate": 3.261680951064418e-05,
426
+ "loss": 0.0026,
427
+ "step": 2900
428
+ },
429
+ {
430
+ "epoch": 1.9369665134602758,
431
+ "grad_norm": 0.16034963726997375,
432
+ "learning_rate": 3.227121924246613e-05,
433
+ "loss": 0.0031,
434
+ "step": 2950
435
+ },
436
+ {
437
+ "epoch": 1.9697964543663822,
438
+ "grad_norm": 0.060961514711380005,
439
+ "learning_rate": 3.192562897428809e-05,
440
+ "loss": 0.0017,
441
+ "step": 3000
442
+ },
443
+ {
444
+ "epoch": 2.0,
445
+ "eval_accuracy": 0.9995754536025347,
446
+ "eval_f1": 0.995708295650744,
447
+ "eval_loss": 0.0013849161332473159,
448
+ "eval_precision": 0.9954693109933322,
449
+ "eval_recall": 0.9959473950829271,
450
+ "eval_runtime": 75.6987,
451
+ "eval_samples_per_second": 237.785,
452
+ "eval_steps_per_second": 3.725,
453
+ "step": 3046
454
+ },
455
+ {
456
+ "epoch": 2.0026263952724883,
457
+ "grad_norm": 0.08297313749790192,
458
+ "learning_rate": 3.158003870611004e-05,
459
+ "loss": 0.0026,
460
+ "step": 3050
461
+ },
462
+ {
463
+ "epoch": 2.0354563361785947,
464
+ "grad_norm": 0.19145315885543823,
465
+ "learning_rate": 3.123444843793199e-05,
466
+ "loss": 0.0014,
467
+ "step": 3100
468
+ },
469
+ {
470
+ "epoch": 2.0682862770847015,
471
+ "grad_norm": 0.08754308521747589,
472
+ "learning_rate": 3.088885816975394e-05,
473
+ "loss": 0.0014,
474
+ "step": 3150
475
+ },
476
+ {
477
+ "epoch": 2.101116217990808,
478
+ "grad_norm": 0.1580217033624649,
479
+ "learning_rate": 3.054326790157589e-05,
480
+ "loss": 0.0016,
481
+ "step": 3200
482
+ },
483
+ {
484
+ "epoch": 2.133946158896914,
485
+ "grad_norm": 0.022689586505293846,
486
+ "learning_rate": 3.0197677633397846e-05,
487
+ "loss": 0.0016,
488
+ "step": 3250
489
+ },
490
+ {
491
+ "epoch": 2.1667760998030205,
492
+ "grad_norm": 0.10402818024158478,
493
+ "learning_rate": 2.9852087365219793e-05,
494
+ "loss": 0.0015,
495
+ "step": 3300
496
+ },
497
+ {
498
+ "epoch": 2.199606040709127,
499
+ "grad_norm": 0.11667637526988983,
500
+ "learning_rate": 2.9506497097041747e-05,
501
+ "loss": 0.002,
502
+ "step": 3350
503
+ },
504
+ {
505
+ "epoch": 2.2324359816152333,
506
+ "grad_norm": 0.24381309747695923,
507
+ "learning_rate": 2.9160906828863698e-05,
508
+ "loss": 0.0039,
509
+ "step": 3400
510
+ },
511
+ {
512
+ "epoch": 2.2652659225213396,
513
+ "grad_norm": 0.03473767638206482,
514
+ "learning_rate": 2.8815316560685652e-05,
515
+ "loss": 0.0016,
516
+ "step": 3450
517
+ },
518
+ {
519
+ "epoch": 2.298095863427446,
520
+ "grad_norm": 1.3230725526809692,
521
+ "learning_rate": 2.8469726292507603e-05,
522
+ "loss": 0.0016,
523
+ "step": 3500
524
+ },
525
+ {
526
+ "epoch": 2.3309258043335523,
527
+ "grad_norm": 0.1341700553894043,
528
+ "learning_rate": 2.8124136024329557e-05,
529
+ "loss": 0.0047,
530
+ "step": 3550
531
+ },
532
+ {
533
+ "epoch": 2.3637557452396587,
534
+ "grad_norm": 0.13513527810573578,
535
+ "learning_rate": 2.7778545756151508e-05,
536
+ "loss": 0.0018,
537
+ "step": 3600
538
+ },
539
+ {
540
+ "epoch": 2.396585686145765,
541
+ "grad_norm": 0.0577649362385273,
542
+ "learning_rate": 2.743295548797346e-05,
543
+ "loss": 0.0014,
544
+ "step": 3650
545
+ },
546
+ {
547
+ "epoch": 2.4294156270518714,
548
+ "grad_norm": 0.1941065490245819,
549
+ "learning_rate": 2.7087365219795412e-05,
550
+ "loss": 0.0011,
551
+ "step": 3700
552
+ },
553
+ {
554
+ "epoch": 2.4622455679579778,
555
+ "grad_norm": 0.15985670685768127,
556
+ "learning_rate": 2.6741774951617367e-05,
557
+ "loss": 0.0016,
558
+ "step": 3750
559
+ },
560
+ {
561
+ "epoch": 2.495075508864084,
562
+ "grad_norm": 0.08614476025104523,
563
+ "learning_rate": 2.6396184683439317e-05,
564
+ "loss": 0.0016,
565
+ "step": 3800
566
+ },
567
+ {
568
+ "epoch": 2.5279054497701905,
569
+ "grad_norm": 0.15596601366996765,
570
+ "learning_rate": 2.605059441526127e-05,
571
+ "loss": 0.0016,
572
+ "step": 3850
573
+ },
574
+ {
575
+ "epoch": 2.560735390676297,
576
+ "grad_norm": 0.12409207224845886,
577
+ "learning_rate": 2.5705004147083215e-05,
578
+ "loss": 0.0015,
579
+ "step": 3900
580
+ },
581
+ {
582
+ "epoch": 2.593565331582403,
583
+ "grad_norm": 0.189951092004776,
584
+ "learning_rate": 2.535941387890517e-05,
585
+ "loss": 0.0015,
586
+ "step": 3950
587
+ },
588
+ {
589
+ "epoch": 2.6263952724885096,
590
+ "grad_norm": 0.059304554015398026,
591
+ "learning_rate": 2.501382361072712e-05,
592
+ "loss": 0.0014,
593
+ "step": 4000
594
+ },
595
+ {
596
+ "epoch": 2.659225213394616,
597
+ "grad_norm": 0.24233925342559814,
598
+ "learning_rate": 2.4668233342549074e-05,
599
+ "loss": 0.0013,
600
+ "step": 4050
601
+ },
602
+ {
603
+ "epoch": 2.6920551543007223,
604
+ "grad_norm": 0.2739645838737488,
605
+ "learning_rate": 2.4322643074371025e-05,
606
+ "loss": 0.0012,
607
+ "step": 4100
608
+ },
609
+ {
610
+ "epoch": 2.7248850952068286,
611
+ "grad_norm": 0.11855873465538025,
612
+ "learning_rate": 2.397705280619298e-05,
613
+ "loss": 0.0019,
614
+ "step": 4150
615
+ },
616
+ {
617
+ "epoch": 2.757715036112935,
618
+ "grad_norm": 0.05818852037191391,
619
+ "learning_rate": 2.363146253801493e-05,
620
+ "loss": 0.0027,
621
+ "step": 4200
622
+ },
623
+ {
624
+ "epoch": 2.7905449770190414,
625
+ "grad_norm": 0.06046278029680252,
626
+ "learning_rate": 2.3285872269836884e-05,
627
+ "loss": 0.0014,
628
+ "step": 4250
629
+ },
630
+ {
631
+ "epoch": 2.8233749179251477,
632
+ "grad_norm": 0.04216454550623894,
633
+ "learning_rate": 2.2940282001658835e-05,
634
+ "loss": 0.0011,
635
+ "step": 4300
636
+ },
637
+ {
638
+ "epoch": 2.856204858831254,
639
+ "grad_norm": 0.0564955435693264,
640
+ "learning_rate": 2.2594691733480785e-05,
641
+ "loss": 0.0015,
642
+ "step": 4350
643
+ },
644
+ {
645
+ "epoch": 2.8890347997373604,
646
+ "grad_norm": 0.10374019294977188,
647
+ "learning_rate": 2.224910146530274e-05,
648
+ "loss": 0.0013,
649
+ "step": 4400
650
+ },
651
+ {
652
+ "epoch": 2.921864740643467,
653
+ "grad_norm": 0.2742884159088135,
654
+ "learning_rate": 2.190351119712469e-05,
655
+ "loss": 0.0014,
656
+ "step": 4450
657
+ },
658
+ {
659
+ "epoch": 2.954694681549573,
660
+ "grad_norm": 0.02845386229455471,
661
+ "learning_rate": 2.155792092894664e-05,
662
+ "loss": 0.0013,
663
+ "step": 4500
664
+ },
665
+ {
666
+ "epoch": 2.9875246224556795,
667
+ "grad_norm": 0.10036207735538483,
668
+ "learning_rate": 2.1212330660768595e-05,
669
+ "loss": 0.0012,
670
+ "step": 4550
671
+ },
672
+ {
673
+ "epoch": 3.0,
674
+ "eval_accuracy": 0.9997391341413165,
675
+ "eval_f1": 0.9973228263586491,
676
+ "eval_loss": 0.0009462219895794988,
677
+ "eval_precision": 0.9971588480180992,
678
+ "eval_recall": 0.9974868586390879,
679
+ "eval_runtime": 75.644,
680
+ "eval_samples_per_second": 237.957,
681
+ "eval_steps_per_second": 3.728,
682
+ "step": 4569
683
+ },
684
+ {
685
+ "epoch": 3.020354563361786,
686
+ "grad_norm": 0.08079813420772552,
687
+ "learning_rate": 2.0866740392590546e-05,
688
+ "loss": 0.0011,
689
+ "step": 4600
690
+ },
691
+ {
692
+ "epoch": 3.0531845042678922,
693
+ "grad_norm": 0.09932583570480347,
694
+ "learning_rate": 2.0521150124412497e-05,
695
+ "loss": 0.0023,
696
+ "step": 4650
697
+ },
698
+ {
699
+ "epoch": 3.0860144451739986,
700
+ "grad_norm": 0.05140871927142143,
701
+ "learning_rate": 2.017555985623445e-05,
702
+ "loss": 0.001,
703
+ "step": 4700
704
+ },
705
+ {
706
+ "epoch": 3.118844386080105,
707
+ "grad_norm": 0.19095173478126526,
708
+ "learning_rate": 1.98299695880564e-05,
709
+ "loss": 0.001,
710
+ "step": 4750
711
+ },
712
+ {
713
+ "epoch": 3.1516743269862113,
714
+ "grad_norm": 0.041814982891082764,
715
+ "learning_rate": 1.9484379319878356e-05,
716
+ "loss": 0.0018,
717
+ "step": 4800
718
+ },
719
+ {
720
+ "epoch": 3.1845042678923177,
721
+ "grad_norm": 0.025649981573224068,
722
+ "learning_rate": 1.9138789051700303e-05,
723
+ "loss": 0.0008,
724
+ "step": 4850
725
+ },
726
+ {
727
+ "epoch": 3.217334208798424,
728
+ "grad_norm": 0.12662899494171143,
729
+ "learning_rate": 1.8793198783522257e-05,
730
+ "loss": 0.0009,
731
+ "step": 4900
732
+ },
733
+ {
734
+ "epoch": 3.2501641497045304,
735
+ "grad_norm": 0.10787362605333328,
736
+ "learning_rate": 1.8447608515344208e-05,
737
+ "loss": 0.0008,
738
+ "step": 4950
739
+ },
740
+ {
741
+ "epoch": 3.2829940906106367,
742
+ "grad_norm": 0.03877755254507065,
743
+ "learning_rate": 1.8102018247166162e-05,
744
+ "loss": 0.0008,
745
+ "step": 5000
746
+ },
747
+ {
748
+ "epoch": 3.315824031516743,
749
+ "grad_norm": 0.11100368201732635,
750
+ "learning_rate": 1.7756427978988113e-05,
751
+ "loss": 0.0007,
752
+ "step": 5050
753
+ },
754
+ {
755
+ "epoch": 3.3486539724228495,
756
+ "grad_norm": 0.027431080117821693,
757
+ "learning_rate": 1.7410837710810067e-05,
758
+ "loss": 0.0008,
759
+ "step": 5100
760
+ },
761
+ {
762
+ "epoch": 3.381483913328956,
763
+ "grad_norm": 0.013812090270221233,
764
+ "learning_rate": 1.7065247442632014e-05,
765
+ "loss": 0.0008,
766
+ "step": 5150
767
+ },
768
+ {
769
+ "epoch": 3.414313854235062,
770
+ "grad_norm": 0.1110658347606659,
771
+ "learning_rate": 1.6719657174453968e-05,
772
+ "loss": 0.0022,
773
+ "step": 5200
774
+ },
775
+ {
776
+ "epoch": 3.4471437951411685,
777
+ "grad_norm": 0.11397113651037216,
778
+ "learning_rate": 1.637406690627592e-05,
779
+ "loss": 0.0009,
780
+ "step": 5250
781
+ },
782
+ {
783
+ "epoch": 3.479973736047275,
784
+ "grad_norm": 0.2407987117767334,
785
+ "learning_rate": 1.6028476638097873e-05,
786
+ "loss": 0.0008,
787
+ "step": 5300
788
+ },
789
+ {
790
+ "epoch": 3.5128036769533812,
791
+ "grad_norm": 0.06540926545858383,
792
+ "learning_rate": 1.5682886369919824e-05,
793
+ "loss": 0.001,
794
+ "step": 5350
795
+ },
796
+ {
797
+ "epoch": 3.5456336178594876,
798
+ "grad_norm": 0.08520480245351791,
799
+ "learning_rate": 1.5337296101741775e-05,
800
+ "loss": 0.0007,
801
+ "step": 5400
802
+ },
803
+ {
804
+ "epoch": 3.578463558765594,
805
+ "grad_norm": 0.091216079890728,
806
+ "learning_rate": 1.4991705833563727e-05,
807
+ "loss": 0.0011,
808
+ "step": 5450
809
+ },
810
+ {
811
+ "epoch": 3.6112934996717003,
812
+ "grad_norm": 0.1052037924528122,
813
+ "learning_rate": 1.464611556538568e-05,
814
+ "loss": 0.0008,
815
+ "step": 5500
816
+ },
817
+ {
818
+ "epoch": 3.6441234405778067,
819
+ "grad_norm": 0.30819040536880493,
820
+ "learning_rate": 1.4300525297207632e-05,
821
+ "loss": 0.0007,
822
+ "step": 5550
823
+ },
824
+ {
825
+ "epoch": 3.6769533814839135,
826
+ "grad_norm": 0.06232546642422676,
827
+ "learning_rate": 1.3954935029029584e-05,
828
+ "loss": 0.0005,
829
+ "step": 5600
830
+ },
831
+ {
832
+ "epoch": 3.70978332239002,
833
+ "grad_norm": 0.08547823131084442,
834
+ "learning_rate": 1.3609344760851537e-05,
835
+ "loss": 0.0006,
836
+ "step": 5650
837
+ },
838
+ {
839
+ "epoch": 3.742613263296126,
840
+ "grad_norm": 0.12835901975631714,
841
+ "learning_rate": 1.3263754492673486e-05,
842
+ "loss": 0.0028,
843
+ "step": 5700
844
+ },
845
+ {
846
+ "epoch": 3.7754432042022326,
847
+ "grad_norm": 0.07907555252313614,
848
+ "learning_rate": 1.2918164224495438e-05,
849
+ "loss": 0.001,
850
+ "step": 5750
851
+ },
852
+ {
853
+ "epoch": 3.808273145108339,
854
+ "grad_norm": 0.03760789334774017,
855
+ "learning_rate": 1.257257395631739e-05,
856
+ "loss": 0.0008,
857
+ "step": 5800
858
+ },
859
+ {
860
+ "epoch": 3.8411030860144453,
861
+ "grad_norm": 0.008074942976236343,
862
+ "learning_rate": 1.2226983688139343e-05,
863
+ "loss": 0.0007,
864
+ "step": 5850
865
+ },
866
+ {
867
+ "epoch": 3.8739330269205516,
868
+ "grad_norm": 0.039751049131155014,
869
+ "learning_rate": 1.1881393419961294e-05,
870
+ "loss": 0.0008,
871
+ "step": 5900
872
+ },
873
+ {
874
+ "epoch": 3.906762967826658,
875
+ "grad_norm": 0.1129092127084732,
876
+ "learning_rate": 1.1535803151783246e-05,
877
+ "loss": 0.0009,
878
+ "step": 5950
879
+ },
880
+ {
881
+ "epoch": 3.9395929087327644,
882
+ "grad_norm": 0.030842676758766174,
883
+ "learning_rate": 1.1190212883605199e-05,
884
+ "loss": 0.0006,
885
+ "step": 6000
886
+ },
887
+ {
888
+ "epoch": 3.9724228496388707,
889
+ "grad_norm": 0.24821631610393524,
890
+ "learning_rate": 1.084462261542715e-05,
891
+ "loss": 0.0009,
892
+ "step": 6050
893
+ },
894
+ {
895
+ "epoch": 4.0,
896
+ "eval_accuracy": 0.9997499325101945,
897
+ "eval_f1": 0.9977469995625562,
898
+ "eval_loss": 0.0008962151478044689,
899
+ "eval_precision": 0.9976255936015996,
900
+ "eval_recall": 0.997868435076085,
901
+ "eval_runtime": 75.9398,
902
+ "eval_samples_per_second": 237.03,
903
+ "eval_steps_per_second": 3.713,
904
+ "step": 6092
905
+ },
906
+ {
907
+ "epoch": 4.005252790544977,
908
+ "grad_norm": 0.13012520968914032,
909
+ "learning_rate": 1.0499032347249102e-05,
910
+ "loss": 0.0007,
911
+ "step": 6100
912
+ },
913
+ {
914
+ "epoch": 4.038082731451083,
915
+ "grad_norm": 0.008424765430390835,
916
+ "learning_rate": 1.0153442079071054e-05,
917
+ "loss": 0.0005,
918
+ "step": 6150
919
+ },
920
+ {
921
+ "epoch": 4.070912672357189,
922
+ "grad_norm": 0.08021287620067596,
923
+ "learning_rate": 9.807851810893005e-06,
924
+ "loss": 0.0005,
925
+ "step": 6200
926
+ },
927
+ {
928
+ "epoch": 4.103742613263296,
929
+ "grad_norm": 0.015998413786292076,
930
+ "learning_rate": 9.462261542714957e-06,
931
+ "loss": 0.0003,
932
+ "step": 6250
933
+ },
934
+ {
935
+ "epoch": 4.136572554169403,
936
+ "grad_norm": 0.09457238763570786,
937
+ "learning_rate": 9.11667127453691e-06,
938
+ "loss": 0.0004,
939
+ "step": 6300
940
+ },
941
+ {
942
+ "epoch": 4.169402495075509,
943
+ "grad_norm": 0.04868745431303978,
944
+ "learning_rate": 8.77108100635886e-06,
945
+ "loss": 0.0008,
946
+ "step": 6350
947
+ },
948
+ {
949
+ "epoch": 4.202232435981616,
950
+ "grad_norm": 0.033117685467004776,
951
+ "learning_rate": 8.425490738180813e-06,
952
+ "loss": 0.0004,
953
+ "step": 6400
954
+ },
955
+ {
956
+ "epoch": 4.235062376887722,
957
+ "grad_norm": 0.03128530830144882,
958
+ "learning_rate": 8.079900470002765e-06,
959
+ "loss": 0.0003,
960
+ "step": 6450
961
+ },
962
+ {
963
+ "epoch": 4.267892317793828,
964
+ "grad_norm": 0.017696760594844818,
965
+ "learning_rate": 7.734310201824716e-06,
966
+ "loss": 0.0004,
967
+ "step": 6500
968
+ },
969
+ {
970
+ "epoch": 4.300722258699935,
971
+ "grad_norm": 0.051392361521720886,
972
+ "learning_rate": 7.388719933646669e-06,
973
+ "loss": 0.0004,
974
+ "step": 6550
975
+ },
976
+ {
977
+ "epoch": 4.333552199606041,
978
+ "grad_norm": 0.023702796548604965,
979
+ "learning_rate": 7.04312966546862e-06,
980
+ "loss": 0.0005,
981
+ "step": 6600
982
+ },
983
+ {
984
+ "epoch": 4.3663821405121475,
985
+ "grad_norm": 0.12985366582870483,
986
+ "learning_rate": 6.6975393972905724e-06,
987
+ "loss": 0.0007,
988
+ "step": 6650
989
+ },
990
+ {
991
+ "epoch": 4.399212081418254,
992
+ "grad_norm": 0.005154111888259649,
993
+ "learning_rate": 6.351949129112525e-06,
994
+ "loss": 0.0004,
995
+ "step": 6700
996
+ },
997
+ {
998
+ "epoch": 4.43204202232436,
999
+ "grad_norm": 0.060625988990068436,
1000
+ "learning_rate": 6.0063588609344764e-06,
1001
+ "loss": 0.0004,
1002
+ "step": 6750
1003
+ },
1004
+ {
1005
+ "epoch": 4.4648719632304665,
1006
+ "grad_norm": 0.014278898015618324,
1007
+ "learning_rate": 5.660768592756428e-06,
1008
+ "loss": 0.0005,
1009
+ "step": 6800
1010
+ },
1011
+ {
1012
+ "epoch": 4.497701904136573,
1013
+ "grad_norm": 0.03604033589363098,
1014
+ "learning_rate": 5.31517832457838e-06,
1015
+ "loss": 0.0003,
1016
+ "step": 6850
1017
+ },
1018
+ {
1019
+ "epoch": 4.530531845042679,
1020
+ "grad_norm": 0.11452529579401016,
1021
+ "learning_rate": 4.969588056400332e-06,
1022
+ "loss": 0.0006,
1023
+ "step": 6900
1024
+ },
1025
+ {
1026
+ "epoch": 4.563361785948786,
1027
+ "grad_norm": 0.030383341014385223,
1028
+ "learning_rate": 4.623997788222284e-06,
1029
+ "loss": 0.0016,
1030
+ "step": 6950
1031
+ },
1032
+ {
1033
+ "epoch": 4.596191726854892,
1034
+ "grad_norm": 0.054634325206279755,
1035
+ "learning_rate": 4.278407520044236e-06,
1036
+ "loss": 0.0004,
1037
+ "step": 7000
1038
+ },
1039
+ {
1040
+ "epoch": 4.629021667760998,
1041
+ "grad_norm": 0.05445707589387894,
1042
+ "learning_rate": 3.932817251866188e-06,
1043
+ "loss": 0.0018,
1044
+ "step": 7050
1045
+ },
1046
+ {
1047
+ "epoch": 4.661851608667105,
1048
+ "grad_norm": 0.10374827682971954,
1049
+ "learning_rate": 3.5872269836881396e-06,
1050
+ "loss": 0.0007,
1051
+ "step": 7100
1052
+ },
1053
+ {
1054
+ "epoch": 4.694681549573211,
1055
+ "grad_norm": 0.07730349153280258,
1056
+ "learning_rate": 3.2416367155100916e-06,
1057
+ "loss": 0.0005,
1058
+ "step": 7150
1059
+ },
1060
+ {
1061
+ "epoch": 4.727511490479317,
1062
+ "grad_norm": 0.06179986149072647,
1063
+ "learning_rate": 2.896046447332043e-06,
1064
+ "loss": 0.0004,
1065
+ "step": 7200
1066
+ },
1067
+ {
1068
+ "epoch": 4.760341431385424,
1069
+ "grad_norm": 0.015075119212269783,
1070
+ "learning_rate": 2.550456179153995e-06,
1071
+ "loss": 0.0011,
1072
+ "step": 7250
1073
+ },
1074
+ {
1075
+ "epoch": 4.79317137229153,
1076
+ "grad_norm": 0.0656493604183197,
1077
+ "learning_rate": 2.204865910975947e-06,
1078
+ "loss": 0.0004,
1079
+ "step": 7300
1080
+ },
1081
+ {
1082
+ "epoch": 4.8260013131976365,
1083
+ "grad_norm": 0.017132466658949852,
1084
+ "learning_rate": 1.8592756427978988e-06,
1085
+ "loss": 0.0004,
1086
+ "step": 7350
1087
+ },
1088
+ {
1089
+ "epoch": 4.858831254103743,
1090
+ "grad_norm": 0.02434193529188633,
1091
+ "learning_rate": 1.5136853746198508e-06,
1092
+ "loss": 0.0005,
1093
+ "step": 7400
1094
+ },
1095
+ {
1096
+ "epoch": 4.891661195009849,
1097
+ "grad_norm": 0.0716409906744957,
1098
+ "learning_rate": 1.1680951064418028e-06,
1099
+ "loss": 0.0004,
1100
+ "step": 7450
1101
+ },
1102
+ {
1103
+ "epoch": 4.9244911359159556,
1104
+ "grad_norm": 0.017711373046040535,
1105
+ "learning_rate": 8.225048382637546e-07,
1106
+ "loss": 0.0004,
1107
+ "step": 7500
1108
+ },
1109
+ {
1110
+ "epoch": 4.957321076822062,
1111
+ "grad_norm": 0.0037664847914129496,
1112
+ "learning_rate": 4.769145700857065e-07,
1113
+ "loss": 0.0004,
1114
+ "step": 7550
1115
+ },
1116
+ {
1117
+ "epoch": 4.990151017728168,
1118
+ "grad_norm": 0.001125144655816257,
1119
+ "learning_rate": 1.3132430190765827e-07,
1120
+ "loss": 0.0006,
1121
+ "step": 7600
1122
+ },
1123
+ {
1124
+ "epoch": 5.0,
1125
+ "eval_accuracy": 0.9997948309913187,
1126
+ "eval_f1": 0.998085740410612,
1127
+ "eval_loss": 0.0007292991504073143,
1128
+ "eval_precision": 0.9979807015582144,
1129
+ "eval_recall": 0.9981908013763068,
1130
+ "eval_runtime": 76.3485,
1131
+ "eval_samples_per_second": 235.761,
1132
+ "eval_steps_per_second": 3.694,
1133
+ "step": 7615
1134
+ }
1135
+ ],
1136
+ "logging_steps": 50,
1137
+ "max_steps": 7615,
1138
+ "num_input_tokens_seen": 0,
1139
+ "num_train_epochs": 5,
1140
+ "save_steps": 500,
1141
+ "stateful_callbacks": {
1142
+ "TrainerControl": {
1143
+ "args": {
1144
+ "should_epoch_stop": false,
1145
+ "should_evaluate": false,
1146
+ "should_log": false,
1147
+ "should_save": true,
1148
+ "should_training_stop": true
1149
+ },
1150
+ "attributes": {}
1151
+ }
1152
+ },
1153
+ "total_flos": 1.27347239453568e+17,
1154
+ "train_batch_size": 64,
1155
+ "trial_name": null,
1156
+ "trial_params": null
1157
+ }
checkpoint-7615/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff86125497f499c04776e35f8f3ab0d025d38457377342b96f30a71196a241e2
3
+ size 5240
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B-BANK_ACCOUNT_NUM",
15
+ "1": "B-CC_NUM",
16
+ "2": "B-CC_PROVIDER",
17
+ "3": "B-CITY",
18
+ "4": "B-DATE",
19
+ "5": "B-EMAIL",
20
+ "6": "B-FIRST_NAME",
21
+ "7": "B-ID_NUM",
22
+ "8": "B-LAST_NAME",
23
+ "9": "B-PHONE_NUM",
24
+ "10": "B-POSTAL_CODE",
25
+ "11": "B-STREET",
26
+ "12": "I-BANK_ACCOUNT_NUM",
27
+ "13": "I-CC_NUM",
28
+ "14": "I-CC_PROVIDER",
29
+ "15": "I-CITY",
30
+ "16": "I-DATE",
31
+ "17": "I-EMAIL",
32
+ "18": "I-FIRST_NAME",
33
+ "19": "I-ID_NUM",
34
+ "20": "I-LAST_NAME",
35
+ "21": "I-PHONE_NUM",
36
+ "22": "I-POSTAL_CODE",
37
+ "23": "I-STREET",
38
+ "24": "O"
39
+ },
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 3072,
42
+ "label2id": {
43
+ "B-BANK_ACCOUNT_NUM": 0,
44
+ "B-CC_NUM": 1,
45
+ "B-CC_PROVIDER": 2,
46
+ "B-CITY": 3,
47
+ "B-DATE": 4,
48
+ "B-EMAIL": 5,
49
+ "B-FIRST_NAME": 6,
50
+ "B-ID_NUM": 7,
51
+ "B-LAST_NAME": 8,
52
+ "B-PHONE_NUM": 9,
53
+ "B-POSTAL_CODE": 10,
54
+ "B-STREET": 11,
55
+ "I-BANK_ACCOUNT_NUM": 12,
56
+ "I-CC_NUM": 13,
57
+ "I-CC_PROVIDER": 14,
58
+ "I-CITY": 15,
59
+ "I-DATE": 16,
60
+ "I-EMAIL": 17,
61
+ "I-FIRST_NAME": 18,
62
+ "I-ID_NUM": 19,
63
+ "I-LAST_NAME": 20,
64
+ "I-PHONE_NUM": 21,
65
+ "I-POSTAL_CODE": 22,
66
+ "I-STREET": 23,
67
+ "O": 24
68
+ },
69
+ "layer_norm_eps": 1e-05,
70
+ "max_position_embeddings": 514,
71
+ "model_type": "xlm-roberta",
72
+ "num_attention_heads": 12,
73
+ "num_hidden_layers": 12,
74
+ "output_past": true,
75
+ "pad_token_id": 1,
76
+ "position_embedding_type": "absolute",
77
+ "torch_dtype": "float32",
78
+ "transformers_version": "4.44.2",
79
+ "type_vocab_size": 1,
80
+ "use_cache": true,
81
+ "vocab_size": 250002
82
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb60e772f76b4f658de8a682f5851cb8fd5c2479f313f5ba3537e2eee07af663
3
+ size 1109913172
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
3
+ size 17082999
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff86125497f499c04776e35f8f3ab0d025d38457377342b96f30a71196a241e2
3
+ size 5240