xenogy commited on
Commit
68cb4fe
·
verified ·
1 Parent(s): 3c4f62f

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - token-classification
6
+ base_model: dslim/bert-base-NER
7
+ widget:
8
+ - text: "I love AutoTrain"
9
+ ---
10
+
11
+ # Model Trained Using AutoTrain
12
+
13
+ - Problem type: Token Classification
14
+
15
+ ## Validation Metrics
16
+ loss: 0.0017380028730258346
17
+
18
+ precision: 0.9979825255676087
19
+
20
+ recall: 0.9991765071472964
21
+
22
+ f1: 0.9985791594524718
23
+
24
+ accuracy: 0.9993558979540288
checkpoint-4473/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dslim/bert-base-NER",
3
+ "_num_labels": 4,
4
+ "architectures": [
5
+ "BertForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "B-BRAND",
14
+ "1": "B-MODEL",
15
+ "2": "I-MODEL",
16
+ "3": "O"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "B-BRAND": 0,
22
+ "B-MODEL": 1,
23
+ "I-MODEL": 2,
24
+ "O": 3
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "bert",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.45.0",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 28996
39
+ }
checkpoint-4473/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc70e060f387b98520c1b5d4c237bdc5fe15fe873eed468fc5ef78f017d78c46
3
+ size 430914360
checkpoint-4473/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e9fce92cfff8a036b85292f3a35de4593d6c0a7db312fa4ad10e34fad2b27b
3
+ size 861948474
checkpoint-4473/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d3376ace10175878f8948e31bd61ce72d8abf1d0ea0a006e7863b3ebcd69ea4
3
+ size 14244
checkpoint-4473/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a3967245f8150ae2a45a5ae41d1e99a2e3c6b70382818f030c995c3394df62
3
+ size 1064
checkpoint-4473/trainer_state.json ADDED
@@ -0,0 +1,1324 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0017380028730258346,
3
+ "best_model_checkpoint": "product-extractor9/checkpoint-4473",
4
+ "epoch": 2.998659217877095,
5
+ "eval_steps": 500,
6
+ "global_step": 4473,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01675977653631285,
13
+ "grad_norm": 4.497024059295654,
14
+ "learning_rate": 2.790178571428572e-06,
15
+ "loss": 1.261,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.0335195530726257,
20
+ "grad_norm": 2.1289889812469482,
21
+ "learning_rate": 5.580357142857144e-06,
22
+ "loss": 0.7357,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.05027932960893855,
27
+ "grad_norm": 0.9363784193992615,
28
+ "learning_rate": 8.370535714285715e-06,
29
+ "loss": 0.2247,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.0670391061452514,
34
+ "grad_norm": 0.8427730798721313,
35
+ "learning_rate": 1.1160714285714287e-05,
36
+ "loss": 0.0627,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.08379888268156424,
41
+ "grad_norm": 0.4806881248950958,
42
+ "learning_rate": 1.3950892857142858e-05,
43
+ "loss": 0.036,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.1005586592178771,
48
+ "grad_norm": 0.3914605975151062,
49
+ "learning_rate": 1.674107142857143e-05,
50
+ "loss": 0.0222,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.11731843575418995,
55
+ "grad_norm": 0.07788270711898804,
56
+ "learning_rate": 1.953125e-05,
57
+ "loss": 0.0145,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.1340782122905028,
62
+ "grad_norm": 0.7390716075897217,
63
+ "learning_rate": 2.2321428571428575e-05,
64
+ "loss": 0.017,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.15083798882681565,
69
+ "grad_norm": 0.7524775266647339,
70
+ "learning_rate": 2.5111607142857146e-05,
71
+ "loss": 0.0227,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.16759776536312848,
76
+ "grad_norm": 0.19414357841014862,
77
+ "learning_rate": 2.7901785714285717e-05,
78
+ "loss": 0.0101,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.18435754189944134,
83
+ "grad_norm": 0.7868555188179016,
84
+ "learning_rate": 3.069196428571429e-05,
85
+ "loss": 0.0108,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.2011173184357542,
90
+ "grad_norm": 0.24079546332359314,
91
+ "learning_rate": 3.348214285714286e-05,
92
+ "loss": 0.0264,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.21787709497206703,
97
+ "grad_norm": 0.4110458195209503,
98
+ "learning_rate": 3.627232142857143e-05,
99
+ "loss": 0.0176,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.2346368715083799,
104
+ "grad_norm": 0.7114512324333191,
105
+ "learning_rate": 3.90625e-05,
106
+ "loss": 0.0068,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.25139664804469275,
111
+ "grad_norm": 0.6014077067375183,
112
+ "learning_rate": 4.185267857142857e-05,
113
+ "loss": 0.015,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.2681564245810056,
118
+ "grad_norm": 0.2273491621017456,
119
+ "learning_rate": 4.464285714285715e-05,
120
+ "loss": 0.0076,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.2849162011173184,
125
+ "grad_norm": 0.42882394790649414,
126
+ "learning_rate": 4.743303571428572e-05,
127
+ "loss": 0.0051,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.3016759776536313,
132
+ "grad_norm": 1.0015250444412231,
133
+ "learning_rate": 4.9975155279503104e-05,
134
+ "loss": 0.016,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.31843575418994413,
139
+ "grad_norm": 0.016627248376607895,
140
+ "learning_rate": 4.966459627329193e-05,
141
+ "loss": 0.0102,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.33519553072625696,
146
+ "grad_norm": 0.6981750726699829,
147
+ "learning_rate": 4.935403726708075e-05,
148
+ "loss": 0.0037,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.35195530726256985,
153
+ "grad_norm": 0.040350522845983505,
154
+ "learning_rate": 4.904347826086957e-05,
155
+ "loss": 0.0043,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.3687150837988827,
160
+ "grad_norm": 0.08122731745243073,
161
+ "learning_rate": 4.873291925465839e-05,
162
+ "loss": 0.0042,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.3854748603351955,
167
+ "grad_norm": 0.06908822804689407,
168
+ "learning_rate": 4.842236024844721e-05,
169
+ "loss": 0.0051,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.4022346368715084,
174
+ "grad_norm": 0.1288818120956421,
175
+ "learning_rate": 4.8111801242236026e-05,
176
+ "loss": 0.0047,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.41899441340782123,
181
+ "grad_norm": 0.06162961572408676,
182
+ "learning_rate": 4.7801242236024844e-05,
183
+ "loss": 0.0036,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.43575418994413406,
188
+ "grad_norm": 4.614903926849365,
189
+ "learning_rate": 4.749068322981367e-05,
190
+ "loss": 0.0124,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.45251396648044695,
195
+ "grad_norm": 0.09076151251792908,
196
+ "learning_rate": 4.7180124223602486e-05,
197
+ "loss": 0.0075,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.4692737430167598,
202
+ "grad_norm": 0.6040611863136292,
203
+ "learning_rate": 4.686956521739131e-05,
204
+ "loss": 0.0098,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.4860335195530726,
209
+ "grad_norm": 0.011741822585463524,
210
+ "learning_rate": 4.655900621118013e-05,
211
+ "loss": 0.0053,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.5027932960893855,
216
+ "grad_norm": 0.005364563316106796,
217
+ "learning_rate": 4.624844720496895e-05,
218
+ "loss": 0.0052,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.5195530726256983,
223
+ "grad_norm": 0.07973748445510864,
224
+ "learning_rate": 4.5937888198757765e-05,
225
+ "loss": 0.0029,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.5363128491620112,
230
+ "grad_norm": 0.018571527674794197,
231
+ "learning_rate": 4.562732919254658e-05,
232
+ "loss": 0.0026,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.553072625698324,
237
+ "grad_norm": 0.4966062307357788,
238
+ "learning_rate": 4.531677018633541e-05,
239
+ "loss": 0.0028,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 0.5698324022346368,
244
+ "grad_norm": 0.024787863716483116,
245
+ "learning_rate": 4.5006211180124226e-05,
246
+ "loss": 0.0117,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 0.5865921787709497,
251
+ "grad_norm": 0.16580404341220856,
252
+ "learning_rate": 4.4695652173913044e-05,
253
+ "loss": 0.0041,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 0.6033519553072626,
258
+ "grad_norm": 0.26630890369415283,
259
+ "learning_rate": 4.438509316770186e-05,
260
+ "loss": 0.0037,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 0.6201117318435754,
265
+ "grad_norm": 0.33205315470695496,
266
+ "learning_rate": 4.407453416149068e-05,
267
+ "loss": 0.0041,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 0.6368715083798883,
272
+ "grad_norm": 0.6615919470787048,
273
+ "learning_rate": 4.3763975155279504e-05,
274
+ "loss": 0.0029,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 0.6536312849162011,
279
+ "grad_norm": 0.027883028611540794,
280
+ "learning_rate": 4.345341614906833e-05,
281
+ "loss": 0.0016,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 0.6703910614525139,
286
+ "grad_norm": 0.014666706323623657,
287
+ "learning_rate": 4.314285714285715e-05,
288
+ "loss": 0.0009,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 0.6871508379888268,
293
+ "grad_norm": 0.8317145705223083,
294
+ "learning_rate": 4.2832298136645965e-05,
295
+ "loss": 0.0032,
296
+ "step": 1025
297
+ },
298
+ {
299
+ "epoch": 0.7039106145251397,
300
+ "grad_norm": 0.01633043773472309,
301
+ "learning_rate": 4.252173913043478e-05,
302
+ "loss": 0.0076,
303
+ "step": 1050
304
+ },
305
+ {
306
+ "epoch": 0.7206703910614525,
307
+ "grad_norm": 0.15297381579875946,
308
+ "learning_rate": 4.22111801242236e-05,
309
+ "loss": 0.0042,
310
+ "step": 1075
311
+ },
312
+ {
313
+ "epoch": 0.7374301675977654,
314
+ "grad_norm": 0.01104188896715641,
315
+ "learning_rate": 4.1900621118012426e-05,
316
+ "loss": 0.0023,
317
+ "step": 1100
318
+ },
319
+ {
320
+ "epoch": 0.7541899441340782,
321
+ "grad_norm": 0.014389784075319767,
322
+ "learning_rate": 4.1590062111801244e-05,
323
+ "loss": 0.0014,
324
+ "step": 1125
325
+ },
326
+ {
327
+ "epoch": 0.770949720670391,
328
+ "grad_norm": 0.16941966116428375,
329
+ "learning_rate": 4.127950310559006e-05,
330
+ "loss": 0.0019,
331
+ "step": 1150
332
+ },
333
+ {
334
+ "epoch": 0.7877094972067039,
335
+ "grad_norm": 0.0032864799723029137,
336
+ "learning_rate": 4.0968944099378886e-05,
337
+ "loss": 0.0012,
338
+ "step": 1175
339
+ },
340
+ {
341
+ "epoch": 0.8044692737430168,
342
+ "grad_norm": 0.037840940058231354,
343
+ "learning_rate": 4.0658385093167704e-05,
344
+ "loss": 0.0028,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 0.8212290502793296,
349
+ "grad_norm": 0.21011309325695038,
350
+ "learning_rate": 4.034782608695652e-05,
351
+ "loss": 0.0023,
352
+ "step": 1225
353
+ },
354
+ {
355
+ "epoch": 0.8379888268156425,
356
+ "grad_norm": 0.03973619267344475,
357
+ "learning_rate": 4.003726708074535e-05,
358
+ "loss": 0.0028,
359
+ "step": 1250
360
+ },
361
+ {
362
+ "epoch": 0.8547486033519553,
363
+ "grad_norm": 0.19438233971595764,
364
+ "learning_rate": 3.9726708074534165e-05,
365
+ "loss": 0.0028,
366
+ "step": 1275
367
+ },
368
+ {
369
+ "epoch": 0.8715083798882681,
370
+ "grad_norm": 0.19937561452388763,
371
+ "learning_rate": 3.941614906832298e-05,
372
+ "loss": 0.0029,
373
+ "step": 1300
374
+ },
375
+ {
376
+ "epoch": 0.888268156424581,
377
+ "grad_norm": 0.037492793053388596,
378
+ "learning_rate": 3.91055900621118e-05,
379
+ "loss": 0.0045,
380
+ "step": 1325
381
+ },
382
+ {
383
+ "epoch": 0.9050279329608939,
384
+ "grad_norm": 0.050396982580423355,
385
+ "learning_rate": 3.879503105590062e-05,
386
+ "loss": 0.0107,
387
+ "step": 1350
388
+ },
389
+ {
390
+ "epoch": 0.9217877094972067,
391
+ "grad_norm": 0.0027416895609349012,
392
+ "learning_rate": 3.8484472049689444e-05,
393
+ "loss": 0.0013,
394
+ "step": 1375
395
+ },
396
+ {
397
+ "epoch": 0.9385474860335196,
398
+ "grad_norm": 0.010506534948945045,
399
+ "learning_rate": 3.817391304347827e-05,
400
+ "loss": 0.0021,
401
+ "step": 1400
402
+ },
403
+ {
404
+ "epoch": 0.9553072625698324,
405
+ "grad_norm": 0.025049397721886635,
406
+ "learning_rate": 3.7863354037267086e-05,
407
+ "loss": 0.0027,
408
+ "step": 1425
409
+ },
410
+ {
411
+ "epoch": 0.9720670391061452,
412
+ "grad_norm": 0.02355305664241314,
413
+ "learning_rate": 3.7552795031055904e-05,
414
+ "loss": 0.0009,
415
+ "step": 1450
416
+ },
417
+ {
418
+ "epoch": 0.9888268156424581,
419
+ "grad_norm": 0.0019488915568217635,
420
+ "learning_rate": 3.724223602484472e-05,
421
+ "loss": 0.0033,
422
+ "step": 1475
423
+ },
424
+ {
425
+ "epoch": 0.9995530726256984,
426
+ "eval_accuracy": 0.9990591058348067,
427
+ "eval_f1": 0.9978795293021088,
428
+ "eval_loss": 0.0026351141277700663,
429
+ "eval_precision": 0.9976857963811446,
430
+ "eval_recall": 0.9980733374766936,
431
+ "eval_runtime": 15.7421,
432
+ "eval_samples_per_second": 568.537,
433
+ "eval_steps_per_second": 35.573,
434
+ "step": 1491
435
+ },
436
+ {
437
+ "epoch": 1.005586592178771,
438
+ "grad_norm": 0.0034796572290360928,
439
+ "learning_rate": 3.693167701863354e-05,
440
+ "loss": 0.0023,
441
+ "step": 1500
442
+ },
443
+ {
444
+ "epoch": 1.0223463687150838,
445
+ "grad_norm": 0.0016808788059279323,
446
+ "learning_rate": 3.6621118012422365e-05,
447
+ "loss": 0.0021,
448
+ "step": 1525
449
+ },
450
+ {
451
+ "epoch": 1.0391061452513966,
452
+ "grad_norm": 0.6062390804290771,
453
+ "learning_rate": 3.631055900621118e-05,
454
+ "loss": 0.0056,
455
+ "step": 1550
456
+ },
457
+ {
458
+ "epoch": 1.0558659217877095,
459
+ "grad_norm": 0.005256348755210638,
460
+ "learning_rate": 3.6e-05,
461
+ "loss": 0.0032,
462
+ "step": 1575
463
+ },
464
+ {
465
+ "epoch": 1.0726256983240223,
466
+ "grad_norm": 0.019292037934064865,
467
+ "learning_rate": 3.568944099378882e-05,
468
+ "loss": 0.0014,
469
+ "step": 1600
470
+ },
471
+ {
472
+ "epoch": 1.089385474860335,
473
+ "grad_norm": 0.01752970926463604,
474
+ "learning_rate": 3.537888198757764e-05,
475
+ "loss": 0.0012,
476
+ "step": 1625
477
+ },
478
+ {
479
+ "epoch": 1.106145251396648,
480
+ "grad_norm": 0.1426161527633667,
481
+ "learning_rate": 3.506832298136646e-05,
482
+ "loss": 0.0017,
483
+ "step": 1650
484
+ },
485
+ {
486
+ "epoch": 1.1229050279329609,
487
+ "grad_norm": 0.003224730957299471,
488
+ "learning_rate": 3.4757763975155286e-05,
489
+ "loss": 0.0015,
490
+ "step": 1675
491
+ },
492
+ {
493
+ "epoch": 1.1396648044692737,
494
+ "grad_norm": 0.09022270143032074,
495
+ "learning_rate": 3.4447204968944104e-05,
496
+ "loss": 0.0029,
497
+ "step": 1700
498
+ },
499
+ {
500
+ "epoch": 1.1564245810055866,
501
+ "grad_norm": 0.08428433537483215,
502
+ "learning_rate": 3.413664596273292e-05,
503
+ "loss": 0.0101,
504
+ "step": 1725
505
+ },
506
+ {
507
+ "epoch": 1.1731843575418994,
508
+ "grad_norm": 0.1770564615726471,
509
+ "learning_rate": 3.382608695652174e-05,
510
+ "loss": 0.0039,
511
+ "step": 1750
512
+ },
513
+ {
514
+ "epoch": 1.1899441340782122,
515
+ "grad_norm": 0.011541259475052357,
516
+ "learning_rate": 3.351552795031056e-05,
517
+ "loss": 0.0027,
518
+ "step": 1775
519
+ },
520
+ {
521
+ "epoch": 1.2067039106145252,
522
+ "grad_norm": 0.16555652022361755,
523
+ "learning_rate": 3.3204968944099376e-05,
524
+ "loss": 0.0026,
525
+ "step": 1800
526
+ },
527
+ {
528
+ "epoch": 1.223463687150838,
529
+ "grad_norm": 0.006959631573408842,
530
+ "learning_rate": 3.28944099378882e-05,
531
+ "loss": 0.0088,
532
+ "step": 1825
533
+ },
534
+ {
535
+ "epoch": 1.2402234636871508,
536
+ "grad_norm": 0.051754653453826904,
537
+ "learning_rate": 3.258385093167702e-05,
538
+ "loss": 0.0023,
539
+ "step": 1850
540
+ },
541
+ {
542
+ "epoch": 1.2569832402234637,
543
+ "grad_norm": 0.10367710888385773,
544
+ "learning_rate": 3.2273291925465844e-05,
545
+ "loss": 0.0069,
546
+ "step": 1875
547
+ },
548
+ {
549
+ "epoch": 1.2737430167597765,
550
+ "grad_norm": 0.1256183534860611,
551
+ "learning_rate": 3.196273291925466e-05,
552
+ "loss": 0.0026,
553
+ "step": 1900
554
+ },
555
+ {
556
+ "epoch": 1.2905027932960893,
557
+ "grad_norm": 0.010505536571145058,
558
+ "learning_rate": 3.165217391304348e-05,
559
+ "loss": 0.0022,
560
+ "step": 1925
561
+ },
562
+ {
563
+ "epoch": 1.3072625698324023,
564
+ "grad_norm": 0.003642796538770199,
565
+ "learning_rate": 3.13416149068323e-05,
566
+ "loss": 0.0079,
567
+ "step": 1950
568
+ },
569
+ {
570
+ "epoch": 1.324022346368715,
571
+ "grad_norm": 0.005338456016033888,
572
+ "learning_rate": 3.103105590062112e-05,
573
+ "loss": 0.0014,
574
+ "step": 1975
575
+ },
576
+ {
577
+ "epoch": 1.3407821229050279,
578
+ "grad_norm": 0.00152731710113585,
579
+ "learning_rate": 3.072049689440994e-05,
580
+ "loss": 0.0022,
581
+ "step": 2000
582
+ },
583
+ {
584
+ "epoch": 1.3575418994413408,
585
+ "grad_norm": 0.003016839036718011,
586
+ "learning_rate": 3.0409937888198758e-05,
587
+ "loss": 0.0011,
588
+ "step": 2025
589
+ },
590
+ {
591
+ "epoch": 1.3743016759776536,
592
+ "grad_norm": 0.0016562914242967963,
593
+ "learning_rate": 3.0099378881987576e-05,
594
+ "loss": 0.0025,
595
+ "step": 2050
596
+ },
597
+ {
598
+ "epoch": 1.3910614525139664,
599
+ "grad_norm": 0.0380425788462162,
600
+ "learning_rate": 2.9788819875776398e-05,
601
+ "loss": 0.0021,
602
+ "step": 2075
603
+ },
604
+ {
605
+ "epoch": 1.4078212290502794,
606
+ "grad_norm": 0.023457402363419533,
607
+ "learning_rate": 2.9478260869565215e-05,
608
+ "loss": 0.0066,
609
+ "step": 2100
610
+ },
611
+ {
612
+ "epoch": 1.4245810055865922,
613
+ "grad_norm": 0.25006377696990967,
614
+ "learning_rate": 2.916770186335404e-05,
615
+ "loss": 0.0018,
616
+ "step": 2125
617
+ },
618
+ {
619
+ "epoch": 1.441340782122905,
620
+ "grad_norm": 0.001208071829751134,
621
+ "learning_rate": 2.885714285714286e-05,
622
+ "loss": 0.0025,
623
+ "step": 2150
624
+ },
625
+ {
626
+ "epoch": 1.458100558659218,
627
+ "grad_norm": 0.05316939949989319,
628
+ "learning_rate": 2.854658385093168e-05,
629
+ "loss": 0.0008,
630
+ "step": 2175
631
+ },
632
+ {
633
+ "epoch": 1.4748603351955307,
634
+ "grad_norm": 0.0016460075275972486,
635
+ "learning_rate": 2.8236024844720498e-05,
636
+ "loss": 0.0021,
637
+ "step": 2200
638
+ },
639
+ {
640
+ "epoch": 1.4916201117318435,
641
+ "grad_norm": 0.0013425371143966913,
642
+ "learning_rate": 2.792546583850932e-05,
643
+ "loss": 0.0019,
644
+ "step": 2225
645
+ },
646
+ {
647
+ "epoch": 1.5083798882681565,
648
+ "grad_norm": 0.14225272834300995,
649
+ "learning_rate": 2.7614906832298137e-05,
650
+ "loss": 0.0019,
651
+ "step": 2250
652
+ },
653
+ {
654
+ "epoch": 1.5251396648044693,
655
+ "grad_norm": 0.0722590833902359,
656
+ "learning_rate": 2.7304347826086958e-05,
657
+ "loss": 0.0011,
658
+ "step": 2275
659
+ },
660
+ {
661
+ "epoch": 1.541899441340782,
662
+ "grad_norm": 0.0007230218034237623,
663
+ "learning_rate": 2.6993788819875776e-05,
664
+ "loss": 0.0018,
665
+ "step": 2300
666
+ },
667
+ {
668
+ "epoch": 1.558659217877095,
669
+ "grad_norm": 0.06257428228855133,
670
+ "learning_rate": 2.6683229813664594e-05,
671
+ "loss": 0.0037,
672
+ "step": 2325
673
+ },
674
+ {
675
+ "epoch": 1.5754189944134078,
676
+ "grad_norm": 0.08822145313024521,
677
+ "learning_rate": 2.637267080745342e-05,
678
+ "loss": 0.0013,
679
+ "step": 2350
680
+ },
681
+ {
682
+ "epoch": 1.5921787709497206,
683
+ "grad_norm": 0.04353473708033562,
684
+ "learning_rate": 2.606211180124224e-05,
685
+ "loss": 0.0022,
686
+ "step": 2375
687
+ },
688
+ {
689
+ "epoch": 1.6089385474860336,
690
+ "grad_norm": 0.1210530623793602,
691
+ "learning_rate": 2.5751552795031058e-05,
692
+ "loss": 0.0079,
693
+ "step": 2400
694
+ },
695
+ {
696
+ "epoch": 1.6256983240223464,
697
+ "grad_norm": 0.11149182170629501,
698
+ "learning_rate": 2.544099378881988e-05,
699
+ "loss": 0.0029,
700
+ "step": 2425
701
+ },
702
+ {
703
+ "epoch": 1.6424581005586592,
704
+ "grad_norm": 0.0012023997260257602,
705
+ "learning_rate": 2.5130434782608698e-05,
706
+ "loss": 0.0012,
707
+ "step": 2450
708
+ },
709
+ {
710
+ "epoch": 1.6592178770949721,
711
+ "grad_norm": 0.024040818214416504,
712
+ "learning_rate": 2.4819875776397515e-05,
713
+ "loss": 0.0016,
714
+ "step": 2475
715
+ },
716
+ {
717
+ "epoch": 1.675977653631285,
718
+ "grad_norm": 0.0008637563441880047,
719
+ "learning_rate": 2.4509316770186337e-05,
720
+ "loss": 0.0016,
721
+ "step": 2500
722
+ },
723
+ {
724
+ "epoch": 1.6927374301675977,
725
+ "grad_norm": 0.0007544947438873351,
726
+ "learning_rate": 2.4198757763975158e-05,
727
+ "loss": 0.0025,
728
+ "step": 2525
729
+ },
730
+ {
731
+ "epoch": 1.7094972067039107,
732
+ "grad_norm": 0.1318245828151703,
733
+ "learning_rate": 2.3888198757763976e-05,
734
+ "loss": 0.0028,
735
+ "step": 2550
736
+ },
737
+ {
738
+ "epoch": 1.7262569832402235,
739
+ "grad_norm": 0.2637254595756531,
740
+ "learning_rate": 2.3577639751552798e-05,
741
+ "loss": 0.0016,
742
+ "step": 2575
743
+ },
744
+ {
745
+ "epoch": 1.7430167597765363,
746
+ "grad_norm": 0.03174907714128494,
747
+ "learning_rate": 2.3267080745341615e-05,
748
+ "loss": 0.001,
749
+ "step": 2600
750
+ },
751
+ {
752
+ "epoch": 1.7597765363128492,
753
+ "grad_norm": 0.3836451470851898,
754
+ "learning_rate": 2.2956521739130433e-05,
755
+ "loss": 0.0014,
756
+ "step": 2625
757
+ },
758
+ {
759
+ "epoch": 1.776536312849162,
760
+ "grad_norm": 0.0018227475229650736,
761
+ "learning_rate": 2.2645962732919258e-05,
762
+ "loss": 0.0013,
763
+ "step": 2650
764
+ },
765
+ {
766
+ "epoch": 1.7932960893854748,
767
+ "grad_norm": 0.0006859716959297657,
768
+ "learning_rate": 2.2335403726708076e-05,
769
+ "loss": 0.0019,
770
+ "step": 2675
771
+ },
772
+ {
773
+ "epoch": 1.8100558659217878,
774
+ "grad_norm": 0.0017274123383685946,
775
+ "learning_rate": 2.2024844720496894e-05,
776
+ "loss": 0.0005,
777
+ "step": 2700
778
+ },
779
+ {
780
+ "epoch": 1.8268156424581006,
781
+ "grad_norm": 0.0008571726502850652,
782
+ "learning_rate": 2.1714285714285715e-05,
783
+ "loss": 0.0046,
784
+ "step": 2725
785
+ },
786
+ {
787
+ "epoch": 1.8435754189944134,
788
+ "grad_norm": 0.010574797168374062,
789
+ "learning_rate": 2.1403726708074533e-05,
790
+ "loss": 0.0061,
791
+ "step": 2750
792
+ },
793
+ {
794
+ "epoch": 1.8603351955307263,
795
+ "grad_norm": 0.002403935883194208,
796
+ "learning_rate": 2.1093167701863355e-05,
797
+ "loss": 0.0077,
798
+ "step": 2775
799
+ },
800
+ {
801
+ "epoch": 1.8770949720670391,
802
+ "grad_norm": 0.011948524974286556,
803
+ "learning_rate": 2.0782608695652176e-05,
804
+ "loss": 0.0019,
805
+ "step": 2800
806
+ },
807
+ {
808
+ "epoch": 1.893854748603352,
809
+ "grad_norm": 0.013287588022649288,
810
+ "learning_rate": 2.0472049689440994e-05,
811
+ "loss": 0.0037,
812
+ "step": 2825
813
+ },
814
+ {
815
+ "epoch": 1.910614525139665,
816
+ "grad_norm": 0.6667817831039429,
817
+ "learning_rate": 2.0161490683229815e-05,
818
+ "loss": 0.0022,
819
+ "step": 2850
820
+ },
821
+ {
822
+ "epoch": 1.9273743016759777,
823
+ "grad_norm": 0.4447934627532959,
824
+ "learning_rate": 1.9850931677018633e-05,
825
+ "loss": 0.0044,
826
+ "step": 2875
827
+ },
828
+ {
829
+ "epoch": 1.9441340782122905,
830
+ "grad_norm": 0.03938614949584007,
831
+ "learning_rate": 1.9540372670807455e-05,
832
+ "loss": 0.0031,
833
+ "step": 2900
834
+ },
835
+ {
836
+ "epoch": 1.9608938547486034,
837
+ "grad_norm": 0.00843888334929943,
838
+ "learning_rate": 1.9229813664596276e-05,
839
+ "loss": 0.0004,
840
+ "step": 2925
841
+ },
842
+ {
843
+ "epoch": 1.9776536312849162,
844
+ "grad_norm": 0.015367425978183746,
845
+ "learning_rate": 1.8919254658385094e-05,
846
+ "loss": 0.0005,
847
+ "step": 2950
848
+ },
849
+ {
850
+ "epoch": 1.994413407821229,
851
+ "grad_norm": 0.0006772307096980512,
852
+ "learning_rate": 1.8608695652173912e-05,
853
+ "loss": 0.0006,
854
+ "step": 2975
855
+ },
856
+ {
857
+ "epoch": 1.999776536312849,
858
+ "eval_accuracy": 0.9992832786057085,
859
+ "eval_f1": 0.998454788989401,
860
+ "eval_loss": 0.0022277587559074163,
861
+ "eval_precision": 0.9979511059371362,
862
+ "eval_recall": 0.9989589807333747,
863
+ "eval_runtime": 15.7322,
864
+ "eval_samples_per_second": 568.898,
865
+ "eval_steps_per_second": 35.596,
866
+ "step": 2983
867
+ },
868
+ {
869
+ "epoch": 2.011173184357542,
870
+ "grad_norm": 0.006105499342083931,
871
+ "learning_rate": 1.8298136645962733e-05,
872
+ "loss": 0.0003,
873
+ "step": 3000
874
+ },
875
+ {
876
+ "epoch": 2.0279329608938546,
877
+ "grad_norm": 0.030271876603364944,
878
+ "learning_rate": 1.7987577639751555e-05,
879
+ "loss": 0.0049,
880
+ "step": 3025
881
+ },
882
+ {
883
+ "epoch": 2.0446927374301676,
884
+ "grad_norm": 0.002889511175453663,
885
+ "learning_rate": 1.7677018633540373e-05,
886
+ "loss": 0.0051,
887
+ "step": 3050
888
+ },
889
+ {
890
+ "epoch": 2.0614525139664805,
891
+ "grad_norm": 0.05693208798766136,
892
+ "learning_rate": 1.7366459627329194e-05,
893
+ "loss": 0.0027,
894
+ "step": 3075
895
+ },
896
+ {
897
+ "epoch": 2.078212290502793,
898
+ "grad_norm": 0.013555080629885197,
899
+ "learning_rate": 1.7055900621118012e-05,
900
+ "loss": 0.0047,
901
+ "step": 3100
902
+ },
903
+ {
904
+ "epoch": 2.094972067039106,
905
+ "grad_norm": 0.016025198623538017,
906
+ "learning_rate": 1.6745341614906833e-05,
907
+ "loss": 0.0018,
908
+ "step": 3125
909
+ },
910
+ {
911
+ "epoch": 2.111731843575419,
912
+ "grad_norm": 0.0006247810670174658,
913
+ "learning_rate": 1.6434782608695655e-05,
914
+ "loss": 0.002,
915
+ "step": 3150
916
+ },
917
+ {
918
+ "epoch": 2.1284916201117317,
919
+ "grad_norm": 0.0010154851479455829,
920
+ "learning_rate": 1.6124223602484473e-05,
921
+ "loss": 0.0017,
922
+ "step": 3175
923
+ },
924
+ {
925
+ "epoch": 2.1452513966480447,
926
+ "grad_norm": 0.008334319107234478,
927
+ "learning_rate": 1.581366459627329e-05,
928
+ "loss": 0.0042,
929
+ "step": 3200
930
+ },
931
+ {
932
+ "epoch": 2.1620111731843576,
933
+ "grad_norm": 0.013117179274559021,
934
+ "learning_rate": 1.5503105590062112e-05,
935
+ "loss": 0.0022,
936
+ "step": 3225
937
+ },
938
+ {
939
+ "epoch": 2.17877094972067,
940
+ "grad_norm": 0.010234753601253033,
941
+ "learning_rate": 1.5192546583850933e-05,
942
+ "loss": 0.0011,
943
+ "step": 3250
944
+ },
945
+ {
946
+ "epoch": 2.195530726256983,
947
+ "grad_norm": 0.23925523459911346,
948
+ "learning_rate": 1.4881987577639753e-05,
949
+ "loss": 0.0009,
950
+ "step": 3275
951
+ },
952
+ {
953
+ "epoch": 2.212290502793296,
954
+ "grad_norm": 0.00740668922662735,
955
+ "learning_rate": 1.4571428571428573e-05,
956
+ "loss": 0.0005,
957
+ "step": 3300
958
+ },
959
+ {
960
+ "epoch": 2.2290502793296088,
961
+ "grad_norm": 0.013464405201375484,
962
+ "learning_rate": 1.426086956521739e-05,
963
+ "loss": 0.0019,
964
+ "step": 3325
965
+ },
966
+ {
967
+ "epoch": 2.2458100558659218,
968
+ "grad_norm": 0.08446656167507172,
969
+ "learning_rate": 1.395031055900621e-05,
970
+ "loss": 0.0019,
971
+ "step": 3350
972
+ },
973
+ {
974
+ "epoch": 2.2625698324022347,
975
+ "grad_norm": 0.0008972717332653701,
976
+ "learning_rate": 1.3639751552795032e-05,
977
+ "loss": 0.0017,
978
+ "step": 3375
979
+ },
980
+ {
981
+ "epoch": 2.2793296089385473,
982
+ "grad_norm": 0.007317252457141876,
983
+ "learning_rate": 1.3329192546583851e-05,
984
+ "loss": 0.0015,
985
+ "step": 3400
986
+ },
987
+ {
988
+ "epoch": 2.2960893854748603,
989
+ "grad_norm": 0.0005608900683000684,
990
+ "learning_rate": 1.3018633540372671e-05,
991
+ "loss": 0.0008,
992
+ "step": 3425
993
+ },
994
+ {
995
+ "epoch": 2.3128491620111733,
996
+ "grad_norm": 0.015111630782485008,
997
+ "learning_rate": 1.270807453416149e-05,
998
+ "loss": 0.0018,
999
+ "step": 3450
1000
+ },
1001
+ {
1002
+ "epoch": 2.329608938547486,
1003
+ "grad_norm": 0.014350698329508305,
1004
+ "learning_rate": 1.239751552795031e-05,
1005
+ "loss": 0.0005,
1006
+ "step": 3475
1007
+ },
1008
+ {
1009
+ "epoch": 2.346368715083799,
1010
+ "grad_norm": 0.00036890068440698087,
1011
+ "learning_rate": 1.208695652173913e-05,
1012
+ "loss": 0.0006,
1013
+ "step": 3500
1014
+ },
1015
+ {
1016
+ "epoch": 2.363128491620112,
1017
+ "grad_norm": 0.005077319219708443,
1018
+ "learning_rate": 1.1776397515527951e-05,
1019
+ "loss": 0.0008,
1020
+ "step": 3525
1021
+ },
1022
+ {
1023
+ "epoch": 2.3798882681564244,
1024
+ "grad_norm": 0.003997057676315308,
1025
+ "learning_rate": 1.1465838509316771e-05,
1026
+ "loss": 0.0028,
1027
+ "step": 3550
1028
+ },
1029
+ {
1030
+ "epoch": 2.3966480446927374,
1031
+ "grad_norm": 0.02524147555232048,
1032
+ "learning_rate": 1.115527950310559e-05,
1033
+ "loss": 0.0019,
1034
+ "step": 3575
1035
+ },
1036
+ {
1037
+ "epoch": 2.4134078212290504,
1038
+ "grad_norm": 0.024869900196790695,
1039
+ "learning_rate": 1.084472049689441e-05,
1040
+ "loss": 0.0015,
1041
+ "step": 3600
1042
+ },
1043
+ {
1044
+ "epoch": 2.430167597765363,
1045
+ "grad_norm": 0.03944075480103493,
1046
+ "learning_rate": 1.053416149068323e-05,
1047
+ "loss": 0.0012,
1048
+ "step": 3625
1049
+ },
1050
+ {
1051
+ "epoch": 2.446927374301676,
1052
+ "grad_norm": 0.1299927532672882,
1053
+ "learning_rate": 1.022360248447205e-05,
1054
+ "loss": 0.002,
1055
+ "step": 3650
1056
+ },
1057
+ {
1058
+ "epoch": 2.463687150837989,
1059
+ "grad_norm": 0.0011140911374241114,
1060
+ "learning_rate": 9.91304347826087e-06,
1061
+ "loss": 0.0043,
1062
+ "step": 3675
1063
+ },
1064
+ {
1065
+ "epoch": 2.4804469273743015,
1066
+ "grad_norm": 0.00046078156447038054,
1067
+ "learning_rate": 9.60248447204969e-06,
1068
+ "loss": 0.0011,
1069
+ "step": 3700
1070
+ },
1071
+ {
1072
+ "epoch": 2.4972067039106145,
1073
+ "grad_norm": 0.15609022974967957,
1074
+ "learning_rate": 9.291925465838509e-06,
1075
+ "loss": 0.0016,
1076
+ "step": 3725
1077
+ },
1078
+ {
1079
+ "epoch": 2.5139664804469275,
1080
+ "grad_norm": 0.00034095768933184445,
1081
+ "learning_rate": 8.98136645962733e-06,
1082
+ "loss": 0.0009,
1083
+ "step": 3750
1084
+ },
1085
+ {
1086
+ "epoch": 2.5307262569832405,
1087
+ "grad_norm": 0.0031807892955839634,
1088
+ "learning_rate": 8.67080745341615e-06,
1089
+ "loss": 0.0013,
1090
+ "step": 3775
1091
+ },
1092
+ {
1093
+ "epoch": 2.547486033519553,
1094
+ "grad_norm": 0.2399129867553711,
1095
+ "learning_rate": 8.36024844720497e-06,
1096
+ "loss": 0.0019,
1097
+ "step": 3800
1098
+ },
1099
+ {
1100
+ "epoch": 2.564245810055866,
1101
+ "grad_norm": 0.10006082057952881,
1102
+ "learning_rate": 8.049689440993789e-06,
1103
+ "loss": 0.0006,
1104
+ "step": 3825
1105
+ },
1106
+ {
1107
+ "epoch": 2.5810055865921786,
1108
+ "grad_norm": 0.010174165479838848,
1109
+ "learning_rate": 7.739130434782609e-06,
1110
+ "loss": 0.0014,
1111
+ "step": 3850
1112
+ },
1113
+ {
1114
+ "epoch": 2.5977653631284916,
1115
+ "grad_norm": 0.05686904489994049,
1116
+ "learning_rate": 7.428571428571429e-06,
1117
+ "loss": 0.0005,
1118
+ "step": 3875
1119
+ },
1120
+ {
1121
+ "epoch": 2.6145251396648046,
1122
+ "grad_norm": 0.00026722607435658574,
1123
+ "learning_rate": 7.118012422360249e-06,
1124
+ "loss": 0.0006,
1125
+ "step": 3900
1126
+ },
1127
+ {
1128
+ "epoch": 2.631284916201117,
1129
+ "grad_norm": 0.0008581440197303891,
1130
+ "learning_rate": 6.807453416149069e-06,
1131
+ "loss": 0.0018,
1132
+ "step": 3925
1133
+ },
1134
+ {
1135
+ "epoch": 2.64804469273743,
1136
+ "grad_norm": 0.0003465110785327852,
1137
+ "learning_rate": 6.496894409937888e-06,
1138
+ "loss": 0.0028,
1139
+ "step": 3950
1140
+ },
1141
+ {
1142
+ "epoch": 2.664804469273743,
1143
+ "grad_norm": 0.26947882771492004,
1144
+ "learning_rate": 6.186335403726709e-06,
1145
+ "loss": 0.0008,
1146
+ "step": 3975
1147
+ },
1148
+ {
1149
+ "epoch": 2.6815642458100557,
1150
+ "grad_norm": 0.0018917308188974857,
1151
+ "learning_rate": 5.875776397515528e-06,
1152
+ "loss": 0.0004,
1153
+ "step": 4000
1154
+ },
1155
+ {
1156
+ "epoch": 2.6983240223463687,
1157
+ "grad_norm": 0.02461870200932026,
1158
+ "learning_rate": 5.565217391304348e-06,
1159
+ "loss": 0.0016,
1160
+ "step": 4025
1161
+ },
1162
+ {
1163
+ "epoch": 2.7150837988826817,
1164
+ "grad_norm": 0.0012873351806774735,
1165
+ "learning_rate": 5.2546583850931685e-06,
1166
+ "loss": 0.0015,
1167
+ "step": 4050
1168
+ },
1169
+ {
1170
+ "epoch": 2.7318435754189943,
1171
+ "grad_norm": 0.3350357711315155,
1172
+ "learning_rate": 4.944099378881987e-06,
1173
+ "loss": 0.002,
1174
+ "step": 4075
1175
+ },
1176
+ {
1177
+ "epoch": 2.7486033519553073,
1178
+ "grad_norm": 0.000343937921570614,
1179
+ "learning_rate": 4.633540372670808e-06,
1180
+ "loss": 0.0022,
1181
+ "step": 4100
1182
+ },
1183
+ {
1184
+ "epoch": 2.7653631284916202,
1185
+ "grad_norm": 0.001220704521983862,
1186
+ "learning_rate": 4.3229813664596275e-06,
1187
+ "loss": 0.0007,
1188
+ "step": 4125
1189
+ },
1190
+ {
1191
+ "epoch": 2.782122905027933,
1192
+ "grad_norm": 0.0026593124493956566,
1193
+ "learning_rate": 4.012422360248447e-06,
1194
+ "loss": 0.0014,
1195
+ "step": 4150
1196
+ },
1197
+ {
1198
+ "epoch": 2.798882681564246,
1199
+ "grad_norm": 0.0004057559126522392,
1200
+ "learning_rate": 3.7018633540372673e-06,
1201
+ "loss": 0.0007,
1202
+ "step": 4175
1203
+ },
1204
+ {
1205
+ "epoch": 2.815642458100559,
1206
+ "grad_norm": 0.0003598795155994594,
1207
+ "learning_rate": 3.3913043478260873e-06,
1208
+ "loss": 0.0011,
1209
+ "step": 4200
1210
+ },
1211
+ {
1212
+ "epoch": 2.8324022346368714,
1213
+ "grad_norm": 0.10998610407114029,
1214
+ "learning_rate": 3.080745341614907e-06,
1215
+ "loss": 0.0023,
1216
+ "step": 4225
1217
+ },
1218
+ {
1219
+ "epoch": 2.8491620111731844,
1220
+ "grad_norm": 0.013729007914662361,
1221
+ "learning_rate": 2.770186335403727e-06,
1222
+ "loss": 0.0017,
1223
+ "step": 4250
1224
+ },
1225
+ {
1226
+ "epoch": 2.8659217877094973,
1227
+ "grad_norm": 0.13692212104797363,
1228
+ "learning_rate": 2.4596273291925467e-06,
1229
+ "loss": 0.0015,
1230
+ "step": 4275
1231
+ },
1232
+ {
1233
+ "epoch": 2.88268156424581,
1234
+ "grad_norm": 0.00046403007581830025,
1235
+ "learning_rate": 2.1490683229813664e-06,
1236
+ "loss": 0.0011,
1237
+ "step": 4300
1238
+ },
1239
+ {
1240
+ "epoch": 2.899441340782123,
1241
+ "grad_norm": 0.000543824746273458,
1242
+ "learning_rate": 1.8385093167701865e-06,
1243
+ "loss": 0.002,
1244
+ "step": 4325
1245
+ },
1246
+ {
1247
+ "epoch": 2.916201117318436,
1248
+ "grad_norm": 0.007381894625723362,
1249
+ "learning_rate": 1.5279503105590064e-06,
1250
+ "loss": 0.0006,
1251
+ "step": 4350
1252
+ },
1253
+ {
1254
+ "epoch": 2.9329608938547485,
1255
+ "grad_norm": 0.00041887606494128704,
1256
+ "learning_rate": 1.217391304347826e-06,
1257
+ "loss": 0.0016,
1258
+ "step": 4375
1259
+ },
1260
+ {
1261
+ "epoch": 2.9497206703910615,
1262
+ "grad_norm": 0.08080340921878815,
1263
+ "learning_rate": 9.068322981366459e-07,
1264
+ "loss": 0.0016,
1265
+ "step": 4400
1266
+ },
1267
+ {
1268
+ "epoch": 2.9664804469273744,
1269
+ "grad_norm": 0.00032423867378383875,
1270
+ "learning_rate": 5.962732919254659e-07,
1271
+ "loss": 0.0011,
1272
+ "step": 4425
1273
+ },
1274
+ {
1275
+ "epoch": 2.983240223463687,
1276
+ "grad_norm": 0.03197231888771057,
1277
+ "learning_rate": 2.8571428571428575e-07,
1278
+ "loss": 0.0009,
1279
+ "step": 4450
1280
+ },
1281
+ {
1282
+ "epoch": 2.998659217877095,
1283
+ "eval_accuracy": 0.9993558979540288,
1284
+ "eval_f1": 0.9985791594524718,
1285
+ "eval_loss": 0.0017380028730258346,
1286
+ "eval_precision": 0.9979825255676087,
1287
+ "eval_recall": 0.9991765071472964,
1288
+ "eval_runtime": 17.5212,
1289
+ "eval_samples_per_second": 510.81,
1290
+ "eval_steps_per_second": 31.961,
1291
+ "step": 4473
1292
+ }
1293
+ ],
1294
+ "logging_steps": 25,
1295
+ "max_steps": 4473,
1296
+ "num_input_tokens_seen": 0,
1297
+ "num_train_epochs": 3,
1298
+ "save_steps": 500,
1299
+ "stateful_callbacks": {
1300
+ "EarlyStoppingCallback": {
1301
+ "args": {
1302
+ "early_stopping_patience": 5,
1303
+ "early_stopping_threshold": 0.01
1304
+ },
1305
+ "attributes": {
1306
+ "early_stopping_patience_counter": 2
1307
+ }
1308
+ },
1309
+ "TrainerControl": {
1310
+ "args": {
1311
+ "should_epoch_stop": false,
1312
+ "should_evaluate": false,
1313
+ "should_log": false,
1314
+ "should_save": true,
1315
+ "should_training_stop": true
1316
+ },
1317
+ "attributes": {}
1318
+ }
1319
+ },
1320
+ "total_flos": 7012809159745536.0,
1321
+ "train_batch_size": 8,
1322
+ "trial_name": null,
1323
+ "trial_params": null
1324
+ }
checkpoint-4473/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9199b748a6f793abbe88f7251cc15266351737ada9469df8b710e82353b047c
3
+ size 5176
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dslim/bert-base-NER",
3
+ "_num_labels": 4,
4
+ "architectures": [
5
+ "BertForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "B-BRAND",
14
+ "1": "B-MODEL",
15
+ "2": "I-MODEL",
16
+ "3": "O"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "B-BRAND": 0,
22
+ "B-MODEL": 1,
23
+ "I-MODEL": 2,
24
+ "O": 3
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "bert",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.45.0",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 28996
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc70e060f387b98520c1b5d4c237bdc5fe15fe873eed468fc5ef78f017d78c46
3
+ size 430914360
runs/Oct17_20-49-07_rh/events.out.tfevents.1729190949.rh.1472.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b1a0415391681afc4dce3460c88da7d26926cbe0b60bc5222c36d2d67e6cc24
3
- size 37480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d995a49e0eb27d2521353e66a6cb38d64e77c9659a49f3e0d1df4997f6e0d46
3
+ size 44425
runs/Oct17_20-49-07_rh/events.out.tfevents.1729191710.rh.1472.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7f7aeeb6de08b2dc72bc94dacefbd7d1b5d66906d3ebe172f56eb5e92c2c1a7
3
+ size 560
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_len": 512,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9199b748a6f793abbe88f7251cc15266351737ada9469df8b710e82353b047c
3
+ size 5176
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "product-extractor9/autotrain-data",
3
+ "model": "dslim/bert-base-NER",
4
+ "lr": 5e-05,
5
+ "epochs": 3,
6
+ "max_seq_length": 128,
7
+ "batch_size": 8,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 3,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.0,
13
+ "max_grad_norm": 1.0,
14
+ "seed": 42,
15
+ "train_split": "train",
16
+ "valid_split": "validation",
17
+ "tokens_column": "autotrain_text",
18
+ "tags_column": "autotrain_label",
19
+ "logging_steps": -1,
20
+ "project_name": "product-extractor9",
21
+ "auto_find_batch_size": false,
22
+ "mixed_precision": "fp16",
23
+ "save_total_limit": 1,
24
+ "push_to_hub": true,
25
+ "eval_strategy": "epoch",
26
+ "username": "xenogy",
27
+ "log": "tensorboard",
28
+ "early_stopping_patience": 5,
29
+ "early_stopping_threshold": 0.01
30
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff