eternalGenius commited on
Commit
df4d1db
·
verified ·
1 Parent(s): 126bf40

Upload folder using huggingface_hub

Browse files
checkpoint-548/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "dtype": "float32",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "output_past": true,
30
+ "pad_token_id": 0,
31
+ "pooler_fc_size": 768,
32
+ "pooler_num_attention_heads": 12,
33
+ "pooler_num_fc_layers": 3,
34
+ "pooler_size_per_head": 128,
35
+ "pooler_type": "first_token_transform",
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "multi_label_classification",
38
+ "transformers_version": "4.57.1",
39
+ "type_vocab_size": 2,
40
+ "use_cache": false,
41
+ "vocab_size": 119547
42
+ }
checkpoint-548/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f7673dc6ce4fbad8a45c2aa05fb306ab43b011a3170bebb6facce5ffbb86a1
3
+ size 711446532
checkpoint-548/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2223381a94d1108a0c994993a0f7a5d60d45ea5140f018c82b6089235968951
3
+ size 1423017355
checkpoint-548/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9875fc867ee7600bcc916cb51e3bef4612ba900dc4729730a91144d4773bec77
3
+ size 14645
checkpoint-548/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1277edf63a4048bd781738f2025b676fe98e18bd1b6a3ef99db1411f8cd93fb
3
+ size 1383
checkpoint-548/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4cde338b6dbe478bd3c38227d30b302da9cbdcc535280924587297de88c679
3
+ size 1465
checkpoint-548/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-548/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-548/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "backend": "tokenizers",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "is_local": false,
50
+ "mask_token": "[MASK]",
51
+ "max_length": 64,
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
checkpoint-548/trainer_state.json ADDED
@@ -0,0 +1,465 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 548,
3
+ "best_metric": 0.9628349178910977,
4
+ "best_model_checkpoint": "/tmp/finetune/l1/checkpoint-548",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 548,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.072992700729927,
14
+ "grad_norm": Infinity,
15
+ "learning_rate": 8.737864077669904e-07,
16
+ "loss": 1.1059,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.145985401459854,
21
+ "grad_norm": 44.42300796508789,
22
+ "learning_rate": 1.8446601941747574e-06,
23
+ "loss": 1.154,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.21897810218978103,
28
+ "grad_norm": 25.56485939025879,
29
+ "learning_rate": 2.8155339805825245e-06,
30
+ "loss": 1.2043,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.291970802919708,
35
+ "grad_norm": 21.406190872192383,
36
+ "learning_rate": 3.7864077669902915e-06,
37
+ "loss": 1.0319,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.36496350364963503,
42
+ "grad_norm": 33.165164947509766,
43
+ "learning_rate": 4.7572815533980585e-06,
44
+ "loss": 0.8044,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.43795620437956206,
49
+ "grad_norm": 20.365318298339844,
50
+ "learning_rate": 5.728155339805825e-06,
51
+ "loss": 0.7708,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.5109489051094891,
56
+ "grad_norm": 22.465822219848633,
57
+ "learning_rate": 6.6990291262135935e-06,
58
+ "loss": 0.6323,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.583941605839416,
63
+ "grad_norm": 16.91489601135254,
64
+ "learning_rate": 7.66990291262136e-06,
65
+ "loss": 0.4324,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.656934306569343,
70
+ "grad_norm": 21.687286376953125,
71
+ "learning_rate": 8.640776699029127e-06,
72
+ "loss": 0.4886,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.7299270072992701,
77
+ "grad_norm": 31.576948165893555,
78
+ "learning_rate": 9.611650485436894e-06,
79
+ "loss": 0.5687,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.8029197080291971,
84
+ "grad_norm": 1.9548248052597046,
85
+ "learning_rate": 1.0582524271844662e-05,
86
+ "loss": 0.2169,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.8759124087591241,
91
+ "grad_norm": 22.017236709594727,
92
+ "learning_rate": 1.1553398058252427e-05,
93
+ "loss": 0.2982,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.948905109489051,
98
+ "grad_norm": 13.639375686645508,
99
+ "learning_rate": 1.2524271844660197e-05,
100
+ "loss": 0.2452,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 1.0,
105
+ "eval_f1_macro": 0.904341174899243,
106
+ "eval_f1_micro": 0.9032800672834315,
107
+ "eval_f1_weighted": 0.9042588234821014,
108
+ "eval_loss": 0.14684204757213593,
109
+ "eval_runtime": 1.6696,
110
+ "eval_samples_per_second": 327.624,
111
+ "eval_steps_per_second": 20.963,
112
+ "step": 137
113
+ },
114
+ {
115
+ "epoch": 1.0218978102189782,
116
+ "grad_norm": 4.722266674041748,
117
+ "learning_rate": 1.3495145631067962e-05,
118
+ "loss": 0.1568,
119
+ "step": 140
120
+ },
121
+ {
122
+ "epoch": 1.094890510948905,
123
+ "grad_norm": 25.024124145507812,
124
+ "learning_rate": 1.446601941747573e-05,
125
+ "loss": 0.1066,
126
+ "step": 150
127
+ },
128
+ {
129
+ "epoch": 1.167883211678832,
130
+ "grad_norm": 5.781569957733154,
131
+ "learning_rate": 1.5436893203883496e-05,
132
+ "loss": 0.1277,
133
+ "step": 160
134
+ },
135
+ {
136
+ "epoch": 1.2408759124087592,
137
+ "grad_norm": 17.08236312866211,
138
+ "learning_rate": 1.6407766990291263e-05,
139
+ "loss": 0.0935,
140
+ "step": 170
141
+ },
142
+ {
143
+ "epoch": 1.313868613138686,
144
+ "grad_norm": 10.940235137939453,
145
+ "learning_rate": 1.737864077669903e-05,
146
+ "loss": 0.1571,
147
+ "step": 180
148
+ },
149
+ {
150
+ "epoch": 1.3868613138686132,
151
+ "grad_norm": 4.13682222366333,
152
+ "learning_rate": 1.8349514563106798e-05,
153
+ "loss": 0.1316,
154
+ "step": 190
155
+ },
156
+ {
157
+ "epoch": 1.4598540145985401,
158
+ "grad_norm": 3.4570860862731934,
159
+ "learning_rate": 1.9320388349514565e-05,
160
+ "loss": 0.1334,
161
+ "step": 200
162
+ },
163
+ {
164
+ "epoch": 1.5328467153284673,
165
+ "grad_norm": 12.481249809265137,
166
+ "learning_rate": 1.9967550027041647e-05,
167
+ "loss": 0.1491,
168
+ "step": 210
169
+ },
170
+ {
171
+ "epoch": 1.6058394160583942,
172
+ "grad_norm": 3.959305763244629,
173
+ "learning_rate": 1.9859383450513794e-05,
174
+ "loss": 0.1444,
175
+ "step": 220
176
+ },
177
+ {
178
+ "epoch": 1.6788321167883211,
179
+ "grad_norm": 2.6921675205230713,
180
+ "learning_rate": 1.9751216873985937e-05,
181
+ "loss": 0.0971,
182
+ "step": 230
183
+ },
184
+ {
185
+ "epoch": 1.7518248175182483,
186
+ "grad_norm": 3.2789011001586914,
187
+ "learning_rate": 1.9643050297458088e-05,
188
+ "loss": 0.0657,
189
+ "step": 240
190
+ },
191
+ {
192
+ "epoch": 1.8248175182481752,
193
+ "grad_norm": 47.328712463378906,
194
+ "learning_rate": 1.9534883720930235e-05,
195
+ "loss": 0.1203,
196
+ "step": 250
197
+ },
198
+ {
199
+ "epoch": 1.897810218978102,
200
+ "grad_norm": 3.395271062850952,
201
+ "learning_rate": 1.942671714440238e-05,
202
+ "loss": 0.1544,
203
+ "step": 260
204
+ },
205
+ {
206
+ "epoch": 1.9708029197080292,
207
+ "grad_norm": 12.733712196350098,
208
+ "learning_rate": 1.931855056787453e-05,
209
+ "loss": 0.1459,
210
+ "step": 270
211
+ },
212
+ {
213
+ "epoch": 2.0,
214
+ "eval_f1_macro": 0.9477708161509741,
215
+ "eval_f1_micro": 0.9472789115646258,
216
+ "eval_f1_weighted": 0.9480129474475043,
217
+ "eval_loss": 0.12245870381593704,
218
+ "eval_runtime": 1.7206,
219
+ "eval_samples_per_second": 317.907,
220
+ "eval_steps_per_second": 20.341,
221
+ "step": 274
222
+ },
223
+ {
224
+ "epoch": 2.0437956204379564,
225
+ "grad_norm": 10.530322074890137,
226
+ "learning_rate": 1.9210383991346675e-05,
227
+ "loss": 0.1021,
228
+ "step": 280
229
+ },
230
+ {
231
+ "epoch": 2.116788321167883,
232
+ "grad_norm": 2.0978612899780273,
233
+ "learning_rate": 1.9102217414818822e-05,
234
+ "loss": 0.0758,
235
+ "step": 290
236
+ },
237
+ {
238
+ "epoch": 2.18978102189781,
239
+ "grad_norm": 9.21833610534668,
240
+ "learning_rate": 1.899405083829097e-05,
241
+ "loss": 0.0923,
242
+ "step": 300
243
+ },
244
+ {
245
+ "epoch": 2.2627737226277373,
246
+ "grad_norm": 5.938577651977539,
247
+ "learning_rate": 1.8885884261763116e-05,
248
+ "loss": 0.0452,
249
+ "step": 310
250
+ },
251
+ {
252
+ "epoch": 2.335766423357664,
253
+ "grad_norm": 3.3875350952148438,
254
+ "learning_rate": 1.8777717685235263e-05,
255
+ "loss": 0.0975,
256
+ "step": 320
257
+ },
258
+ {
259
+ "epoch": 2.408759124087591,
260
+ "grad_norm": 14.354475021362305,
261
+ "learning_rate": 1.866955110870741e-05,
262
+ "loss": 0.0924,
263
+ "step": 330
264
+ },
265
+ {
266
+ "epoch": 2.4817518248175183,
267
+ "grad_norm": 1.4160842895507812,
268
+ "learning_rate": 1.8561384532179557e-05,
269
+ "loss": 0.0611,
270
+ "step": 340
271
+ },
272
+ {
273
+ "epoch": 2.554744525547445,
274
+ "grad_norm": 4.338066577911377,
275
+ "learning_rate": 1.8453217955651707e-05,
276
+ "loss": 0.0775,
277
+ "step": 350
278
+ },
279
+ {
280
+ "epoch": 2.627737226277372,
281
+ "grad_norm": 2.572096347808838,
282
+ "learning_rate": 1.8345051379123854e-05,
283
+ "loss": 0.0453,
284
+ "step": 360
285
+ },
286
+ {
287
+ "epoch": 2.7007299270072993,
288
+ "grad_norm": 1.1255489587783813,
289
+ "learning_rate": 1.8236884802596e-05,
290
+ "loss": 0.0324,
291
+ "step": 370
292
+ },
293
+ {
294
+ "epoch": 2.7737226277372264,
295
+ "grad_norm": 15.42068099975586,
296
+ "learning_rate": 1.8128718226068148e-05,
297
+ "loss": 0.0729,
298
+ "step": 380
299
+ },
300
+ {
301
+ "epoch": 2.846715328467153,
302
+ "grad_norm": 1.9290357828140259,
303
+ "learning_rate": 1.8020551649540295e-05,
304
+ "loss": 0.1018,
305
+ "step": 390
306
+ },
307
+ {
308
+ "epoch": 2.9197080291970803,
309
+ "grad_norm": 1.0439828634262085,
310
+ "learning_rate": 1.791238507301244e-05,
311
+ "loss": 0.0856,
312
+ "step": 400
313
+ },
314
+ {
315
+ "epoch": 2.9927007299270074,
316
+ "grad_norm": 10.982110977172852,
317
+ "learning_rate": 1.7804218496484588e-05,
318
+ "loss": 0.077,
319
+ "step": 410
320
+ },
321
+ {
322
+ "epoch": 3.0,
323
+ "eval_f1_macro": 0.9476025336319455,
324
+ "eval_f1_micro": 0.9478260869565217,
325
+ "eval_f1_weighted": 0.947698687741686,
326
+ "eval_loss": 0.14635968208312988,
327
+ "eval_runtime": 1.6325,
328
+ "eval_samples_per_second": 335.077,
329
+ "eval_steps_per_second": 21.44,
330
+ "step": 411
331
+ },
332
+ {
333
+ "epoch": 3.065693430656934,
334
+ "grad_norm": 1.0763516426086426,
335
+ "learning_rate": 1.7696051919956735e-05,
336
+ "loss": 0.0499,
337
+ "step": 420
338
+ },
339
+ {
340
+ "epoch": 3.1386861313868613,
341
+ "grad_norm": 4.268288612365723,
342
+ "learning_rate": 1.7587885343428882e-05,
343
+ "loss": 0.0415,
344
+ "step": 430
345
+ },
346
+ {
347
+ "epoch": 3.2116788321167884,
348
+ "grad_norm": 1.0834965705871582,
349
+ "learning_rate": 1.747971876690103e-05,
350
+ "loss": 0.0505,
351
+ "step": 440
352
+ },
353
+ {
354
+ "epoch": 3.2846715328467155,
355
+ "grad_norm": 1.1049467325210571,
356
+ "learning_rate": 1.7371552190373176e-05,
357
+ "loss": 0.0495,
358
+ "step": 450
359
+ },
360
+ {
361
+ "epoch": 3.3576642335766422,
362
+ "grad_norm": 4.047983646392822,
363
+ "learning_rate": 1.7263385613845323e-05,
364
+ "loss": 0.0615,
365
+ "step": 460
366
+ },
367
+ {
368
+ "epoch": 3.4306569343065694,
369
+ "grad_norm": 2.435213327407837,
370
+ "learning_rate": 1.715521903731747e-05,
371
+ "loss": 0.043,
372
+ "step": 470
373
+ },
374
+ {
375
+ "epoch": 3.5036496350364965,
376
+ "grad_norm": 2.0357930660247803,
377
+ "learning_rate": 1.7047052460789617e-05,
378
+ "loss": 0.1102,
379
+ "step": 480
380
+ },
381
+ {
382
+ "epoch": 3.576642335766423,
383
+ "grad_norm": 30.20710563659668,
384
+ "learning_rate": 1.6938885884261763e-05,
385
+ "loss": 0.0407,
386
+ "step": 490
387
+ },
388
+ {
389
+ "epoch": 3.6496350364963503,
390
+ "grad_norm": 1.8748276233673096,
391
+ "learning_rate": 1.683071930773391e-05,
392
+ "loss": 0.0748,
393
+ "step": 500
394
+ },
395
+ {
396
+ "epoch": 3.7226277372262775,
397
+ "grad_norm": 2.229926347732544,
398
+ "learning_rate": 1.6722552731206057e-05,
399
+ "loss": 0.0328,
400
+ "step": 510
401
+ },
402
+ {
403
+ "epoch": 3.795620437956204,
404
+ "grad_norm": 0.9702017903327942,
405
+ "learning_rate": 1.6614386154678208e-05,
406
+ "loss": 0.0491,
407
+ "step": 520
408
+ },
409
+ {
410
+ "epoch": 3.8686131386861313,
411
+ "grad_norm": 0.7791664600372314,
412
+ "learning_rate": 1.6506219578150354e-05,
413
+ "loss": 0.0218,
414
+ "step": 530
415
+ },
416
+ {
417
+ "epoch": 3.9416058394160585,
418
+ "grad_norm": 1.9696235656738281,
419
+ "learning_rate": 1.63980530016225e-05,
420
+ "loss": 0.0641,
421
+ "step": 540
422
+ },
423
+ {
424
+ "epoch": 4.0,
425
+ "eval_f1_macro": 0.9628456567083955,
426
+ "eval_f1_micro": 0.9628349178910977,
427
+ "eval_f1_weighted": 0.9628281230678446,
428
+ "eval_loss": 0.12824897468090057,
429
+ "eval_runtime": 1.8072,
430
+ "eval_samples_per_second": 302.683,
431
+ "eval_steps_per_second": 19.367,
432
+ "step": 548
433
+ }
434
+ ],
435
+ "logging_steps": 10,
436
+ "max_steps": 2055,
437
+ "num_input_tokens_seen": 0,
438
+ "num_train_epochs": 15,
439
+ "save_steps": 500,
440
+ "stateful_callbacks": {
441
+ "EarlyStoppingCallback": {
442
+ "args": {
443
+ "early_stopping_patience": 3,
444
+ "early_stopping_threshold": 0.0
445
+ },
446
+ "attributes": {
447
+ "early_stopping_patience_counter": 0
448
+ }
449
+ },
450
+ "TrainerControl": {
451
+ "args": {
452
+ "should_epoch_stop": false,
453
+ "should_evaluate": false,
454
+ "should_log": false,
455
+ "should_save": true,
456
+ "should_training_stop": false
457
+ },
458
+ "attributes": {}
459
+ }
460
+ },
461
+ "total_flos": 115136787138912.0,
462
+ "train_batch_size": 16,
463
+ "trial_name": null,
464
+ "trial_params": null
465
+ }
checkpoint-548/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e635bdeb1ac6f61966f030fcb9c04eb373e22140b8041fd2d74bf7fd77f29be6
3
+ size 5841
checkpoint-548/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-959/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "dtype": "float32",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "output_past": true,
30
+ "pad_token_id": 0,
31
+ "pooler_fc_size": 768,
32
+ "pooler_num_attention_heads": 12,
33
+ "pooler_num_fc_layers": 3,
34
+ "pooler_size_per_head": 128,
35
+ "pooler_type": "first_token_transform",
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "multi_label_classification",
38
+ "transformers_version": "4.57.1",
39
+ "type_vocab_size": 2,
40
+ "use_cache": false,
41
+ "vocab_size": 119547
42
+ }
checkpoint-959/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f3206eaa585ed6c977144b878055b45488e721a0641868143c5230ded78d64
3
+ size 711446532
checkpoint-959/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61d0666dd0fb9c062ea2b9fb8578a3788effc7825ea3f4a15ee0f922069ce957
3
+ size 1423017355
checkpoint-959/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6b7ed8712696f0020190c62b96844b2feb52c183119171d99eceae03f4b1c59
3
+ size 14645
checkpoint-959/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292f5af1a2b6fd957267f7035eebcfc5056af6939723c18efb416de283a24f86
3
+ size 1383
checkpoint-959/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a213e2d660f54fd69e08d9500b26e190ea0c4870583de5a4410272349344466
3
+ size 1465
checkpoint-959/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-959/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-959/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "backend": "tokenizers",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "is_local": false,
50
+ "mask_token": "[MASK]",
51
+ "max_length": 64,
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
checkpoint-959/trainer_state.json ADDED
@@ -0,0 +1,785 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 548,
3
+ "best_metric": 0.9628349178910977,
4
+ "best_model_checkpoint": "/tmp/finetune/l1/checkpoint-548",
5
+ "epoch": 7.0,
6
+ "eval_steps": 500,
7
+ "global_step": 959,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.072992700729927,
14
+ "grad_norm": Infinity,
15
+ "learning_rate": 8.737864077669904e-07,
16
+ "loss": 1.1059,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.145985401459854,
21
+ "grad_norm": 44.42300796508789,
22
+ "learning_rate": 1.8446601941747574e-06,
23
+ "loss": 1.154,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.21897810218978103,
28
+ "grad_norm": 25.56485939025879,
29
+ "learning_rate": 2.8155339805825245e-06,
30
+ "loss": 1.2043,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.291970802919708,
35
+ "grad_norm": 21.406190872192383,
36
+ "learning_rate": 3.7864077669902915e-06,
37
+ "loss": 1.0319,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.36496350364963503,
42
+ "grad_norm": 33.165164947509766,
43
+ "learning_rate": 4.7572815533980585e-06,
44
+ "loss": 0.8044,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.43795620437956206,
49
+ "grad_norm": 20.365318298339844,
50
+ "learning_rate": 5.728155339805825e-06,
51
+ "loss": 0.7708,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.5109489051094891,
56
+ "grad_norm": 22.465822219848633,
57
+ "learning_rate": 6.6990291262135935e-06,
58
+ "loss": 0.6323,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.583941605839416,
63
+ "grad_norm": 16.91489601135254,
64
+ "learning_rate": 7.66990291262136e-06,
65
+ "loss": 0.4324,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.656934306569343,
70
+ "grad_norm": 21.687286376953125,
71
+ "learning_rate": 8.640776699029127e-06,
72
+ "loss": 0.4886,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.7299270072992701,
77
+ "grad_norm": 31.576948165893555,
78
+ "learning_rate": 9.611650485436894e-06,
79
+ "loss": 0.5687,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.8029197080291971,
84
+ "grad_norm": 1.9548248052597046,
85
+ "learning_rate": 1.0582524271844662e-05,
86
+ "loss": 0.2169,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.8759124087591241,
91
+ "grad_norm": 22.017236709594727,
92
+ "learning_rate": 1.1553398058252427e-05,
93
+ "loss": 0.2982,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.948905109489051,
98
+ "grad_norm": 13.639375686645508,
99
+ "learning_rate": 1.2524271844660197e-05,
100
+ "loss": 0.2452,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 1.0,
105
+ "eval_f1_macro": 0.904341174899243,
106
+ "eval_f1_micro": 0.9032800672834315,
107
+ "eval_f1_weighted": 0.9042588234821014,
108
+ "eval_loss": 0.14684204757213593,
109
+ "eval_runtime": 1.6696,
110
+ "eval_samples_per_second": 327.624,
111
+ "eval_steps_per_second": 20.963,
112
+ "step": 137
113
+ },
114
+ {
115
+ "epoch": 1.0218978102189782,
116
+ "grad_norm": 4.722266674041748,
117
+ "learning_rate": 1.3495145631067962e-05,
118
+ "loss": 0.1568,
119
+ "step": 140
120
+ },
121
+ {
122
+ "epoch": 1.094890510948905,
123
+ "grad_norm": 25.024124145507812,
124
+ "learning_rate": 1.446601941747573e-05,
125
+ "loss": 0.1066,
126
+ "step": 150
127
+ },
128
+ {
129
+ "epoch": 1.167883211678832,
130
+ "grad_norm": 5.781569957733154,
131
+ "learning_rate": 1.5436893203883496e-05,
132
+ "loss": 0.1277,
133
+ "step": 160
134
+ },
135
+ {
136
+ "epoch": 1.2408759124087592,
137
+ "grad_norm": 17.08236312866211,
138
+ "learning_rate": 1.6407766990291263e-05,
139
+ "loss": 0.0935,
140
+ "step": 170
141
+ },
142
+ {
143
+ "epoch": 1.313868613138686,
144
+ "grad_norm": 10.940235137939453,
145
+ "learning_rate": 1.737864077669903e-05,
146
+ "loss": 0.1571,
147
+ "step": 180
148
+ },
149
+ {
150
+ "epoch": 1.3868613138686132,
151
+ "grad_norm": 4.13682222366333,
152
+ "learning_rate": 1.8349514563106798e-05,
153
+ "loss": 0.1316,
154
+ "step": 190
155
+ },
156
+ {
157
+ "epoch": 1.4598540145985401,
158
+ "grad_norm": 3.4570860862731934,
159
+ "learning_rate": 1.9320388349514565e-05,
160
+ "loss": 0.1334,
161
+ "step": 200
162
+ },
163
+ {
164
+ "epoch": 1.5328467153284673,
165
+ "grad_norm": 12.481249809265137,
166
+ "learning_rate": 1.9967550027041647e-05,
167
+ "loss": 0.1491,
168
+ "step": 210
169
+ },
170
+ {
171
+ "epoch": 1.6058394160583942,
172
+ "grad_norm": 3.959305763244629,
173
+ "learning_rate": 1.9859383450513794e-05,
174
+ "loss": 0.1444,
175
+ "step": 220
176
+ },
177
+ {
178
+ "epoch": 1.6788321167883211,
179
+ "grad_norm": 2.6921675205230713,
180
+ "learning_rate": 1.9751216873985937e-05,
181
+ "loss": 0.0971,
182
+ "step": 230
183
+ },
184
+ {
185
+ "epoch": 1.7518248175182483,
186
+ "grad_norm": 3.2789011001586914,
187
+ "learning_rate": 1.9643050297458088e-05,
188
+ "loss": 0.0657,
189
+ "step": 240
190
+ },
191
+ {
192
+ "epoch": 1.8248175182481752,
193
+ "grad_norm": 47.328712463378906,
194
+ "learning_rate": 1.9534883720930235e-05,
195
+ "loss": 0.1203,
196
+ "step": 250
197
+ },
198
+ {
199
+ "epoch": 1.897810218978102,
200
+ "grad_norm": 3.395271062850952,
201
+ "learning_rate": 1.942671714440238e-05,
202
+ "loss": 0.1544,
203
+ "step": 260
204
+ },
205
+ {
206
+ "epoch": 1.9708029197080292,
207
+ "grad_norm": 12.733712196350098,
208
+ "learning_rate": 1.931855056787453e-05,
209
+ "loss": 0.1459,
210
+ "step": 270
211
+ },
212
+ {
213
+ "epoch": 2.0,
214
+ "eval_f1_macro": 0.9477708161509741,
215
+ "eval_f1_micro": 0.9472789115646258,
216
+ "eval_f1_weighted": 0.9480129474475043,
217
+ "eval_loss": 0.12245870381593704,
218
+ "eval_runtime": 1.7206,
219
+ "eval_samples_per_second": 317.907,
220
+ "eval_steps_per_second": 20.341,
221
+ "step": 274
222
+ },
223
+ {
224
+ "epoch": 2.0437956204379564,
225
+ "grad_norm": 10.530322074890137,
226
+ "learning_rate": 1.9210383991346675e-05,
227
+ "loss": 0.1021,
228
+ "step": 280
229
+ },
230
+ {
231
+ "epoch": 2.116788321167883,
232
+ "grad_norm": 2.0978612899780273,
233
+ "learning_rate": 1.9102217414818822e-05,
234
+ "loss": 0.0758,
235
+ "step": 290
236
+ },
237
+ {
238
+ "epoch": 2.18978102189781,
239
+ "grad_norm": 9.21833610534668,
240
+ "learning_rate": 1.899405083829097e-05,
241
+ "loss": 0.0923,
242
+ "step": 300
243
+ },
244
+ {
245
+ "epoch": 2.2627737226277373,
246
+ "grad_norm": 5.938577651977539,
247
+ "learning_rate": 1.8885884261763116e-05,
248
+ "loss": 0.0452,
249
+ "step": 310
250
+ },
251
+ {
252
+ "epoch": 2.335766423357664,
253
+ "grad_norm": 3.3875350952148438,
254
+ "learning_rate": 1.8777717685235263e-05,
255
+ "loss": 0.0975,
256
+ "step": 320
257
+ },
258
+ {
259
+ "epoch": 2.408759124087591,
260
+ "grad_norm": 14.354475021362305,
261
+ "learning_rate": 1.866955110870741e-05,
262
+ "loss": 0.0924,
263
+ "step": 330
264
+ },
265
+ {
266
+ "epoch": 2.4817518248175183,
267
+ "grad_norm": 1.4160842895507812,
268
+ "learning_rate": 1.8561384532179557e-05,
269
+ "loss": 0.0611,
270
+ "step": 340
271
+ },
272
+ {
273
+ "epoch": 2.554744525547445,
274
+ "grad_norm": 4.338066577911377,
275
+ "learning_rate": 1.8453217955651707e-05,
276
+ "loss": 0.0775,
277
+ "step": 350
278
+ },
279
+ {
280
+ "epoch": 2.627737226277372,
281
+ "grad_norm": 2.572096347808838,
282
+ "learning_rate": 1.8345051379123854e-05,
283
+ "loss": 0.0453,
284
+ "step": 360
285
+ },
286
+ {
287
+ "epoch": 2.7007299270072993,
288
+ "grad_norm": 1.1255489587783813,
289
+ "learning_rate": 1.8236884802596e-05,
290
+ "loss": 0.0324,
291
+ "step": 370
292
+ },
293
+ {
294
+ "epoch": 2.7737226277372264,
295
+ "grad_norm": 15.42068099975586,
296
+ "learning_rate": 1.8128718226068148e-05,
297
+ "loss": 0.0729,
298
+ "step": 380
299
+ },
300
+ {
301
+ "epoch": 2.846715328467153,
302
+ "grad_norm": 1.9290357828140259,
303
+ "learning_rate": 1.8020551649540295e-05,
304
+ "loss": 0.1018,
305
+ "step": 390
306
+ },
307
+ {
308
+ "epoch": 2.9197080291970803,
309
+ "grad_norm": 1.0439828634262085,
310
+ "learning_rate": 1.791238507301244e-05,
311
+ "loss": 0.0856,
312
+ "step": 400
313
+ },
314
+ {
315
+ "epoch": 2.9927007299270074,
316
+ "grad_norm": 10.982110977172852,
317
+ "learning_rate": 1.7804218496484588e-05,
318
+ "loss": 0.077,
319
+ "step": 410
320
+ },
321
+ {
322
+ "epoch": 3.0,
323
+ "eval_f1_macro": 0.9476025336319455,
324
+ "eval_f1_micro": 0.9478260869565217,
325
+ "eval_f1_weighted": 0.947698687741686,
326
+ "eval_loss": 0.14635968208312988,
327
+ "eval_runtime": 1.6325,
328
+ "eval_samples_per_second": 335.077,
329
+ "eval_steps_per_second": 21.44,
330
+ "step": 411
331
+ },
332
+ {
333
+ "epoch": 3.065693430656934,
334
+ "grad_norm": 1.0763516426086426,
335
+ "learning_rate": 1.7696051919956735e-05,
336
+ "loss": 0.0499,
337
+ "step": 420
338
+ },
339
+ {
340
+ "epoch": 3.1386861313868613,
341
+ "grad_norm": 4.268288612365723,
342
+ "learning_rate": 1.7587885343428882e-05,
343
+ "loss": 0.0415,
344
+ "step": 430
345
+ },
346
+ {
347
+ "epoch": 3.2116788321167884,
348
+ "grad_norm": 1.0834965705871582,
349
+ "learning_rate": 1.747971876690103e-05,
350
+ "loss": 0.0505,
351
+ "step": 440
352
+ },
353
+ {
354
+ "epoch": 3.2846715328467155,
355
+ "grad_norm": 1.1049467325210571,
356
+ "learning_rate": 1.7371552190373176e-05,
357
+ "loss": 0.0495,
358
+ "step": 450
359
+ },
360
+ {
361
+ "epoch": 3.3576642335766422,
362
+ "grad_norm": 4.047983646392822,
363
+ "learning_rate": 1.7263385613845323e-05,
364
+ "loss": 0.0615,
365
+ "step": 460
366
+ },
367
+ {
368
+ "epoch": 3.4306569343065694,
369
+ "grad_norm": 2.435213327407837,
370
+ "learning_rate": 1.715521903731747e-05,
371
+ "loss": 0.043,
372
+ "step": 470
373
+ },
374
+ {
375
+ "epoch": 3.5036496350364965,
376
+ "grad_norm": 2.0357930660247803,
377
+ "learning_rate": 1.7047052460789617e-05,
378
+ "loss": 0.1102,
379
+ "step": 480
380
+ },
381
+ {
382
+ "epoch": 3.576642335766423,
383
+ "grad_norm": 30.20710563659668,
384
+ "learning_rate": 1.6938885884261763e-05,
385
+ "loss": 0.0407,
386
+ "step": 490
387
+ },
388
+ {
389
+ "epoch": 3.6496350364963503,
390
+ "grad_norm": 1.8748276233673096,
391
+ "learning_rate": 1.683071930773391e-05,
392
+ "loss": 0.0748,
393
+ "step": 500
394
+ },
395
+ {
396
+ "epoch": 3.7226277372262775,
397
+ "grad_norm": 2.229926347732544,
398
+ "learning_rate": 1.6722552731206057e-05,
399
+ "loss": 0.0328,
400
+ "step": 510
401
+ },
402
+ {
403
+ "epoch": 3.795620437956204,
404
+ "grad_norm": 0.9702017903327942,
405
+ "learning_rate": 1.6614386154678208e-05,
406
+ "loss": 0.0491,
407
+ "step": 520
408
+ },
409
+ {
410
+ "epoch": 3.8686131386861313,
411
+ "grad_norm": 0.7791664600372314,
412
+ "learning_rate": 1.6506219578150354e-05,
413
+ "loss": 0.0218,
414
+ "step": 530
415
+ },
416
+ {
417
+ "epoch": 3.9416058394160585,
418
+ "grad_norm": 1.9696235656738281,
419
+ "learning_rate": 1.63980530016225e-05,
420
+ "loss": 0.0641,
421
+ "step": 540
422
+ },
423
+ {
424
+ "epoch": 4.0,
425
+ "eval_f1_macro": 0.9628456567083955,
426
+ "eval_f1_micro": 0.9628349178910977,
427
+ "eval_f1_weighted": 0.9628281230678446,
428
+ "eval_loss": 0.12824897468090057,
429
+ "eval_runtime": 1.8072,
430
+ "eval_samples_per_second": 302.683,
431
+ "eval_steps_per_second": 19.367,
432
+ "step": 548
433
+ },
434
+ {
435
+ "epoch": 4.014598540145985,
436
+ "grad_norm": 0.8119364976882935,
437
+ "learning_rate": 1.6289886425094648e-05,
438
+ "loss": 0.0824,
439
+ "step": 550
440
+ },
441
+ {
442
+ "epoch": 4.087591240875913,
443
+ "grad_norm": 4.590900421142578,
444
+ "learning_rate": 1.6181719848566795e-05,
445
+ "loss": 0.0301,
446
+ "step": 560
447
+ },
448
+ {
449
+ "epoch": 4.160583941605839,
450
+ "grad_norm": 0.6132882237434387,
451
+ "learning_rate": 1.6073553272038942e-05,
452
+ "loss": 0.025,
453
+ "step": 570
454
+ },
455
+ {
456
+ "epoch": 4.233576642335766,
457
+ "grad_norm": 0.6952378153800964,
458
+ "learning_rate": 1.596538669551109e-05,
459
+ "loss": 0.0384,
460
+ "step": 580
461
+ },
462
+ {
463
+ "epoch": 4.306569343065694,
464
+ "grad_norm": 0.3461630940437317,
465
+ "learning_rate": 1.5857220118983236e-05,
466
+ "loss": 0.0213,
467
+ "step": 590
468
+ },
469
+ {
470
+ "epoch": 4.37956204379562,
471
+ "grad_norm": 1.4611117839813232,
472
+ "learning_rate": 1.5749053542455383e-05,
473
+ "loss": 0.0389,
474
+ "step": 600
475
+ },
476
+ {
477
+ "epoch": 4.452554744525547,
478
+ "grad_norm": 0.4132407009601593,
479
+ "learning_rate": 1.564088696592753e-05,
480
+ "loss": 0.0263,
481
+ "step": 610
482
+ },
483
+ {
484
+ "epoch": 4.525547445255475,
485
+ "grad_norm": 0.4994758069515228,
486
+ "learning_rate": 1.5532720389399676e-05,
487
+ "loss": 0.0191,
488
+ "step": 620
489
+ },
490
+ {
491
+ "epoch": 4.598540145985401,
492
+ "grad_norm": 4.1316447257995605,
493
+ "learning_rate": 1.5424553812871823e-05,
494
+ "loss": 0.0593,
495
+ "step": 630
496
+ },
497
+ {
498
+ "epoch": 4.671532846715328,
499
+ "grad_norm": 1.5681731700897217,
500
+ "learning_rate": 1.531638723634397e-05,
501
+ "loss": 0.0199,
502
+ "step": 640
503
+ },
504
+ {
505
+ "epoch": 4.744525547445256,
506
+ "grad_norm": 1.527457594871521,
507
+ "learning_rate": 1.5208220659816117e-05,
508
+ "loss": 0.0423,
509
+ "step": 650
510
+ },
511
+ {
512
+ "epoch": 4.817518248175182,
513
+ "grad_norm": 0.8105906248092651,
514
+ "learning_rate": 1.5100054083288264e-05,
515
+ "loss": 0.0468,
516
+ "step": 660
517
+ },
518
+ {
519
+ "epoch": 4.89051094890511,
520
+ "grad_norm": 1.1720935106277466,
521
+ "learning_rate": 1.4991887506760413e-05,
522
+ "loss": 0.0455,
523
+ "step": 670
524
+ },
525
+ {
526
+ "epoch": 4.963503649635037,
527
+ "grad_norm": 1.5297259092330933,
528
+ "learning_rate": 1.488372093023256e-05,
529
+ "loss": 0.0225,
530
+ "step": 680
531
+ },
532
+ {
533
+ "epoch": 5.0,
534
+ "eval_f1_macro": 0.9531422304959202,
535
+ "eval_f1_micro": 0.9528706083976007,
536
+ "eval_f1_weighted": 0.9531787151639762,
537
+ "eval_loss": 0.1541963517665863,
538
+ "eval_runtime": 1.637,
539
+ "eval_samples_per_second": 334.141,
540
+ "eval_steps_per_second": 21.38,
541
+ "step": 685
542
+ },
543
+ {
544
+ "epoch": 5.036496350364963,
545
+ "grad_norm": 1.7948929071426392,
546
+ "learning_rate": 1.4775554353704706e-05,
547
+ "loss": 0.0405,
548
+ "step": 690
549
+ },
550
+ {
551
+ "epoch": 5.109489051094891,
552
+ "grad_norm": 0.8266754150390625,
553
+ "learning_rate": 1.4667387777176853e-05,
554
+ "loss": 0.0334,
555
+ "step": 700
556
+ },
557
+ {
558
+ "epoch": 5.182481751824818,
559
+ "grad_norm": 1.0670099258422852,
560
+ "learning_rate": 1.4559221200649e-05,
561
+ "loss": 0.018,
562
+ "step": 710
563
+ },
564
+ {
565
+ "epoch": 5.255474452554744,
566
+ "grad_norm": 5.6616291999816895,
567
+ "learning_rate": 1.4451054624121149e-05,
568
+ "loss": 0.025,
569
+ "step": 720
570
+ },
571
+ {
572
+ "epoch": 5.328467153284672,
573
+ "grad_norm": 16.192676544189453,
574
+ "learning_rate": 1.4342888047593296e-05,
575
+ "loss": 0.0223,
576
+ "step": 730
577
+ },
578
+ {
579
+ "epoch": 5.401459854014599,
580
+ "grad_norm": 0.4029748737812042,
581
+ "learning_rate": 1.4234721471065443e-05,
582
+ "loss": 0.0366,
583
+ "step": 740
584
+ },
585
+ {
586
+ "epoch": 5.474452554744525,
587
+ "grad_norm": 11.750133514404297,
588
+ "learning_rate": 1.412655489453759e-05,
589
+ "loss": 0.0177,
590
+ "step": 750
591
+ },
592
+ {
593
+ "epoch": 5.547445255474453,
594
+ "grad_norm": 12.109711647033691,
595
+ "learning_rate": 1.4018388318009736e-05,
596
+ "loss": 0.0731,
597
+ "step": 760
598
+ },
599
+ {
600
+ "epoch": 5.62043795620438,
601
+ "grad_norm": 98.53327941894531,
602
+ "learning_rate": 1.3910221741481885e-05,
603
+ "loss": 0.0499,
604
+ "step": 770
605
+ },
606
+ {
607
+ "epoch": 5.693430656934306,
608
+ "grad_norm": 0.7491104602813721,
609
+ "learning_rate": 1.3802055164954032e-05,
610
+ "loss": 0.0199,
611
+ "step": 780
612
+ },
613
+ {
614
+ "epoch": 5.766423357664234,
615
+ "grad_norm": 0.5023486614227295,
616
+ "learning_rate": 1.3693888588426179e-05,
617
+ "loss": 0.0122,
618
+ "step": 790
619
+ },
620
+ {
621
+ "epoch": 5.839416058394161,
622
+ "grad_norm": 0.5226187109947205,
623
+ "learning_rate": 1.3585722011898324e-05,
624
+ "loss": 0.0304,
625
+ "step": 800
626
+ },
627
+ {
628
+ "epoch": 5.912408759124087,
629
+ "grad_norm": 0.4328407347202301,
630
+ "learning_rate": 1.347755543537047e-05,
631
+ "loss": 0.0125,
632
+ "step": 810
633
+ },
634
+ {
635
+ "epoch": 5.985401459854015,
636
+ "grad_norm": 0.6504618525505066,
637
+ "learning_rate": 1.3369388858842618e-05,
638
+ "loss": 0.0446,
639
+ "step": 820
640
+ },
641
+ {
642
+ "epoch": 6.0,
643
+ "eval_f1_macro": 0.9569069708243072,
644
+ "eval_f1_micro": 0.9568965517241379,
645
+ "eval_f1_weighted": 0.9569308909711778,
646
+ "eval_loss": 0.15012916922569275,
647
+ "eval_runtime": 1.6536,
648
+ "eval_samples_per_second": 330.786,
649
+ "eval_steps_per_second": 21.165,
650
+ "step": 822
651
+ },
652
+ {
653
+ "epoch": 6.0583941605839415,
654
+ "grad_norm": 7.894331455230713,
655
+ "learning_rate": 1.3261222282314765e-05,
656
+ "loss": 0.0259,
657
+ "step": 830
658
+ },
659
+ {
660
+ "epoch": 6.131386861313868,
661
+ "grad_norm": 1.5092934370040894,
662
+ "learning_rate": 1.3153055705786913e-05,
663
+ "loss": 0.0303,
664
+ "step": 840
665
+ },
666
+ {
667
+ "epoch": 6.204379562043796,
668
+ "grad_norm": 7.92203950881958,
669
+ "learning_rate": 1.304488912925906e-05,
670
+ "loss": 0.0292,
671
+ "step": 850
672
+ },
673
+ {
674
+ "epoch": 6.2773722627737225,
675
+ "grad_norm": 0.5470165610313416,
676
+ "learning_rate": 1.2936722552731207e-05,
677
+ "loss": 0.0386,
678
+ "step": 860
679
+ },
680
+ {
681
+ "epoch": 6.350364963503649,
682
+ "grad_norm": 0.37207308411598206,
683
+ "learning_rate": 1.2828555976203354e-05,
684
+ "loss": 0.0121,
685
+ "step": 870
686
+ },
687
+ {
688
+ "epoch": 6.423357664233577,
689
+ "grad_norm": 0.2992991805076599,
690
+ "learning_rate": 1.27203893996755e-05,
691
+ "loss": 0.0234,
692
+ "step": 880
693
+ },
694
+ {
695
+ "epoch": 6.4963503649635035,
696
+ "grad_norm": 2.771857261657715,
697
+ "learning_rate": 1.261222282314765e-05,
698
+ "loss": 0.0132,
699
+ "step": 890
700
+ },
701
+ {
702
+ "epoch": 6.569343065693431,
703
+ "grad_norm": 0.9063857793807983,
704
+ "learning_rate": 1.2504056246619796e-05,
705
+ "loss": 0.0474,
706
+ "step": 900
707
+ },
708
+ {
709
+ "epoch": 6.642335766423358,
710
+ "grad_norm": 1.0955673456192017,
711
+ "learning_rate": 1.2395889670091943e-05,
712
+ "loss": 0.0387,
713
+ "step": 910
714
+ },
715
+ {
716
+ "epoch": 6.7153284671532845,
717
+ "grad_norm": 2.7606654167175293,
718
+ "learning_rate": 1.228772309356409e-05,
719
+ "loss": 0.0229,
720
+ "step": 920
721
+ },
722
+ {
723
+ "epoch": 6.788321167883212,
724
+ "grad_norm": 1.1703284978866577,
725
+ "learning_rate": 1.2179556517036237e-05,
726
+ "loss": 0.0501,
727
+ "step": 930
728
+ },
729
+ {
730
+ "epoch": 6.861313868613139,
731
+ "grad_norm": 0.3500863015651703,
732
+ "learning_rate": 1.2071389940508384e-05,
733
+ "loss": 0.0107,
734
+ "step": 940
735
+ },
736
+ {
737
+ "epoch": 6.934306569343065,
738
+ "grad_norm": 0.4822583794593811,
739
+ "learning_rate": 1.1963223363980532e-05,
740
+ "loss": 0.0224,
741
+ "step": 950
742
+ },
743
+ {
744
+ "epoch": 7.0,
745
+ "eval_f1_macro": 0.9524315396877875,
746
+ "eval_f1_micro": 0.9522983521248916,
747
+ "eval_f1_weighted": 0.9524254856520143,
748
+ "eval_loss": 0.1707778424024582,
749
+ "eval_runtime": 1.7307,
750
+ "eval_samples_per_second": 316.065,
751
+ "eval_steps_per_second": 20.224,
752
+ "step": 959
753
+ }
754
+ ],
755
+ "logging_steps": 10,
756
+ "max_steps": 2055,
757
+ "num_input_tokens_seen": 0,
758
+ "num_train_epochs": 15,
759
+ "save_steps": 500,
760
+ "stateful_callbacks": {
761
+ "EarlyStoppingCallback": {
762
+ "args": {
763
+ "early_stopping_patience": 3,
764
+ "early_stopping_threshold": 0.0
765
+ },
766
+ "attributes": {
767
+ "early_stopping_patience_counter": 3
768
+ }
769
+ },
770
+ "TrainerControl": {
771
+ "args": {
772
+ "should_epoch_stop": false,
773
+ "should_evaluate": false,
774
+ "should_log": false,
775
+ "should_save": true,
776
+ "should_training_stop": true
777
+ },
778
+ "attributes": {}
779
+ }
780
+ },
781
+ "total_flos": 201055651468560.0,
782
+ "train_batch_size": 16,
783
+ "trial_name": null,
784
+ "trial_params": null
785
+ }
checkpoint-959/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e635bdeb1ac6f61966f030fcb9c04eb373e22140b8041fd2d74bf7fd77f29be6
3
+ size 5841
checkpoint-959/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "dtype": "float32",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "output_past": true,
30
+ "pad_token_id": 0,
31
+ "pooler_fc_size": 768,
32
+ "pooler_num_attention_heads": 12,
33
+ "pooler_num_fc_layers": 3,
34
+ "pooler_size_per_head": 128,
35
+ "pooler_type": "first_token_transform",
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "multi_label_classification",
38
+ "transformers_version": "4.57.1",
39
+ "type_vocab_size": 2,
40
+ "use_cache": false,
41
+ "vocab_size": 119547
42
+ }
continual_metrics.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_loss": 0.12824897468090057,
3
+ "eval_f1_micro": 0.9628349178910977,
4
+ "eval_f1_macro": 0.9628456567083955,
5
+ "eval_f1_weighted": 0.9628281230678446,
6
+ "eval_runtime": 2.1417,
7
+ "eval_samples_per_second": 255.406,
8
+ "eval_steps_per_second": 16.342,
9
+ "epoch": 7.0
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f7673dc6ce4fbad8a45c2aa05fb306ab43b011a3170bebb6facce5ffbb86a1
3
+ size 711446532
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
thresholds.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "IsFunctional": 0.7,
3
+ "IsBusiness": 0.1,
4
+ "Other (OT)": 0.1,
5
+ "Availability (A)": 0.6,
6
+ "Fault Tolerance (FT)": 0.35,
7
+ "Legal (L)": 0.35,
8
+ "Look & Feel (LF)": 0.15,
9
+ "Maintainability (MN)": 0.15,
10
+ "Operability (O)": 0.65,
11
+ "Performance (PE)": 0.9,
12
+ "Portability (PO)": 0.75,
13
+ "Scalability (SC)": 0.2,
14
+ "Security (SE)": 0.2,
15
+ "Usability (US)": 0.1
16
+ }
thresholds_partial.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "IsFunctional": 0.7,
3
+ "IsBusiness": 0.1,
4
+ "Other (OT)": 0.1
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "backend": "tokenizers",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "is_local": false,
50
+ "mask_token": "[MASK]",
51
+ "max_length": 64,
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e635bdeb1ac6f61966f030fcb9c04eb373e22140b8041fd2d74bf7fd77f29be6
3
+ size 5841
vocab.txt ADDED
The diff for this file is too large to render. See raw diff