NourFakih commited on
Commit
47b5952
·
verified ·
1 Parent(s): 71e1e60

Upload checkpoint and eval results at step 2500

Browse files
checkpoint-2500/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "benign",
17
+ "1": "malicious"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "is_decoder": false,
22
+ "label2id": {
23
+ "benign": 0,
24
+ "malicious": 1
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
+ "pad_token_id": 0,
32
+ "position_embedding_type": "absolute",
33
+ "tie_word_embeddings": true,
34
+ "transformers_version": "5.13.0",
35
+ "type_vocab_size": 2,
36
+ "use_cache": false,
37
+ "vocab_size": 30522
38
+ }
checkpoint-2500/eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 2500,
3
+ "epoch": 1.5772870662460567,
4
+ "time": "2026-07-08 14:12:42",
5
+ "metrics": {
6
+ "eval_loss": 0.06640289723873138,
7
+ "eval_accuracy": 0.9826498422712934,
8
+ "eval_precision": 0.976932668329177,
9
+ "eval_recall": 0.9886435331230284,
10
+ "eval_f1": 0.9827532141737222
11
+ }
12
+ }
checkpoint-2500/eval_step_002500.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 2500,
3
+ "epoch": 1.5772870662460567,
4
+ "time": "2026-07-08 14:12:42",
5
+ "metrics": {
6
+ "eval_loss": 0.06640289723873138,
7
+ "eval_accuracy": 0.9826498422712934,
8
+ "eval_precision": 0.976932668329177,
9
+ "eval_recall": 0.9886435331230284,
10
+ "eval_f1": 0.9827532141737222,
11
+ "eval_runtime": 61.7792,
12
+ "eval_samples_per_second": 51.312,
13
+ "eval_steps_per_second": 3.221,
14
+ "epoch": 1.5772870662460567
15
+ }
16
+ }
checkpoint-2500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41b25604b6b159573f54b7e133192ab0bbcf60aff42053e1bd9e68132ebe0e50
3
+ size 437958624
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0faa9e84e2627968af6bb97f52f9fec40c40f5e4a3ef8caeb3a78a3f3340bf55
3
+ size 876041611
checkpoint-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329acf2eed42557233deaca3def419f2b4b195246160fd86b4af0b5609834ec4
3
+ size 14645
checkpoint-2500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:861ce13e6ca091acee9a68ebfc5ca38479baf4b537c37b3949f071f77b81e9f0
3
+ size 1383
checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c59d12c9fe97e65905a541d4666a3ebf9be7dfcca4ed2f079ec8f2b39479ff2
3
+ size 1465
checkpoint-2500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2500/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,810 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2500,
3
+ "best_metric": 0.9827532141737222,
4
+ "best_model_checkpoint": "/kaggle/working/outputs/bert_rd_keystrokes_v3/checkpoint-2500",
5
+ "epoch": 1.5772870662460567,
6
+ "eval_steps": 500,
7
+ "global_step": 2500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0006309148264984228,
14
+ "grad_norm": 3.877613067626953,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.7508903741836548,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.015772870662460567,
21
+ "grad_norm": 3.668174982070923,
22
+ "learning_rate": 7.570977917981073e-07,
23
+ "loss": 0.7018957138061523,
24
+ "step": 25
25
+ },
26
+ {
27
+ "epoch": 0.031545741324921134,
28
+ "grad_norm": 3.111140489578247,
29
+ "learning_rate": 1.545741324921136e-06,
30
+ "loss": 0.680956039428711,
31
+ "step": 50
32
+ },
33
+ {
34
+ "epoch": 0.0473186119873817,
35
+ "grad_norm": 7.506597995758057,
36
+ "learning_rate": 2.3343848580441643e-06,
37
+ "loss": 0.6145588302612305,
38
+ "step": 75
39
+ },
40
+ {
41
+ "epoch": 0.06309148264984227,
42
+ "grad_norm": 5.972303867340088,
43
+ "learning_rate": 3.1230283911671926e-06,
44
+ "loss": 0.479757080078125,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.07886435331230283,
49
+ "grad_norm": 5.248694896697998,
50
+ "learning_rate": 3.911671924290221e-06,
51
+ "loss": 0.40485679626464843,
52
+ "step": 125
53
+ },
54
+ {
55
+ "epoch": 0.0946372239747634,
56
+ "grad_norm": 11.381202697753906,
57
+ "learning_rate": 4.70031545741325e-06,
58
+ "loss": 0.32495407104492186,
59
+ "step": 150
60
+ },
61
+ {
62
+ "epoch": 0.11041009463722397,
63
+ "grad_norm": 7.240411758422852,
64
+ "learning_rate": 5.4889589905362786e-06,
65
+ "loss": 0.2756643295288086,
66
+ "step": 175
67
+ },
68
+ {
69
+ "epoch": 0.12618296529968454,
70
+ "grad_norm": 5.1150407791137695,
71
+ "learning_rate": 6.2776025236593065e-06,
72
+ "loss": 0.20428766250610353,
73
+ "step": 200
74
+ },
75
+ {
76
+ "epoch": 0.14195583596214512,
77
+ "grad_norm": 3.947627067565918,
78
+ "learning_rate": 7.066246056782335e-06,
79
+ "loss": 0.1787812042236328,
80
+ "step": 225
81
+ },
82
+ {
83
+ "epoch": 0.15772870662460567,
84
+ "grad_norm": 4.546700954437256,
85
+ "learning_rate": 7.854889589905364e-06,
86
+ "loss": 0.13389638900756837,
87
+ "step": 250
88
+ },
89
+ {
90
+ "epoch": 0.17350157728706625,
91
+ "grad_norm": 6.136378765106201,
92
+ "learning_rate": 8.643533123028391e-06,
93
+ "loss": 0.12480428695678711,
94
+ "step": 275
95
+ },
96
+ {
97
+ "epoch": 0.1892744479495268,
98
+ "grad_norm": 1.768776535987854,
99
+ "learning_rate": 9.43217665615142e-06,
100
+ "loss": 0.1406647491455078,
101
+ "step": 300
102
+ },
103
+ {
104
+ "epoch": 0.20504731861198738,
105
+ "grad_norm": 0.5864288806915283,
106
+ "learning_rate": 1.022082018927445e-05,
107
+ "loss": 0.14702407836914064,
108
+ "step": 325
109
+ },
110
+ {
111
+ "epoch": 0.22082018927444794,
112
+ "grad_norm": 0.38222745060920715,
113
+ "learning_rate": 1.1009463722397478e-05,
114
+ "loss": 0.07499588966369629,
115
+ "step": 350
116
+ },
117
+ {
118
+ "epoch": 0.23659305993690852,
119
+ "grad_norm": 14.092840194702148,
120
+ "learning_rate": 1.1798107255520506e-05,
121
+ "loss": 0.16605567932128906,
122
+ "step": 375
123
+ },
124
+ {
125
+ "epoch": 0.25236593059936907,
126
+ "grad_norm": 2.3975512981414795,
127
+ "learning_rate": 1.2586750788643533e-05,
128
+ "loss": 0.1523967456817627,
129
+ "step": 400
130
+ },
131
+ {
132
+ "epoch": 0.26813880126182965,
133
+ "grad_norm": 0.3959171175956726,
134
+ "learning_rate": 1.3375394321766562e-05,
135
+ "loss": 0.10442778587341309,
136
+ "step": 425
137
+ },
138
+ {
139
+ "epoch": 0.28391167192429023,
140
+ "grad_norm": 3.2623980045318604,
141
+ "learning_rate": 1.4164037854889591e-05,
142
+ "loss": 0.11238637924194336,
143
+ "step": 450
144
+ },
145
+ {
146
+ "epoch": 0.2996845425867508,
147
+ "grad_norm": 4.806061744689941,
148
+ "learning_rate": 1.495268138801262e-05,
149
+ "loss": 0.1303548812866211,
150
+ "step": 475
151
+ },
152
+ {
153
+ "epoch": 0.31545741324921134,
154
+ "grad_norm": 0.18862925469875336,
155
+ "learning_rate": 1.574132492113565e-05,
156
+ "loss": 0.10338631629943848,
157
+ "step": 500
158
+ },
159
+ {
160
+ "epoch": 0.31545741324921134,
161
+ "eval_accuracy": 0.9697160883280758,
162
+ "eval_f1": 0.9696778269109286,
163
+ "eval_loss": 0.11820203810930252,
164
+ "eval_precision": 0.9709044908285895,
165
+ "eval_recall": 0.9684542586750788,
166
+ "eval_runtime": 61.8577,
167
+ "eval_samples_per_second": 51.247,
168
+ "eval_steps_per_second": 3.217,
169
+ "step": 500
170
+ },
171
+ {
172
+ "epoch": 0.3312302839116719,
173
+ "grad_norm": 0.4667949080467224,
174
+ "learning_rate": 1.6529968454258676e-05,
175
+ "loss": 0.1760481834411621,
176
+ "step": 525
177
+ },
178
+ {
179
+ "epoch": 0.3470031545741325,
180
+ "grad_norm": 4.3037638664245605,
181
+ "learning_rate": 1.7318611987381703e-05,
182
+ "loss": 0.17875127792358397,
183
+ "step": 550
184
+ },
185
+ {
186
+ "epoch": 0.3627760252365931,
187
+ "grad_norm": 2.3800172805786133,
188
+ "learning_rate": 1.8107255520504733e-05,
189
+ "loss": 0.10842983245849609,
190
+ "step": 575
191
+ },
192
+ {
193
+ "epoch": 0.3785488958990536,
194
+ "grad_norm": 5.045812129974365,
195
+ "learning_rate": 1.889589905362776e-05,
196
+ "loss": 0.1655238914489746,
197
+ "step": 600
198
+ },
199
+ {
200
+ "epoch": 0.3943217665615142,
201
+ "grad_norm": 2.556612968444824,
202
+ "learning_rate": 1.968454258675079e-05,
203
+ "loss": 0.12010204315185546,
204
+ "step": 625
205
+ },
206
+ {
207
+ "epoch": 0.41009463722397477,
208
+ "grad_norm": 0.5126667022705078,
209
+ "learning_rate": 1.999965897496297e-05,
210
+ "loss": 0.11391996383666993,
211
+ "step": 650
212
+ },
213
+ {
214
+ "epoch": 0.42586750788643535,
215
+ "grad_norm": 0.0798480287194252,
216
+ "learning_rate": 1.9997575017301754e-05,
217
+ "loss": 0.09276899337768554,
218
+ "step": 675
219
+ },
220
+ {
221
+ "epoch": 0.4416403785488959,
222
+ "grad_norm": 5.920562267303467,
223
+ "learning_rate": 1.999359695467383e-05,
224
+ "loss": 0.13868122100830077,
225
+ "step": 700
226
+ },
227
+ {
228
+ "epoch": 0.45741324921135645,
229
+ "grad_norm": 0.14535099267959595,
230
+ "learning_rate": 1.998772554074878e-05,
231
+ "loss": 0.07680845737457276,
232
+ "step": 725
233
+ },
234
+ {
235
+ "epoch": 0.47318611987381703,
236
+ "grad_norm": 0.07280685007572174,
237
+ "learning_rate": 1.9979961887903783e-05,
238
+ "loss": 0.09489853858947754,
239
+ "step": 750
240
+ },
241
+ {
242
+ "epoch": 0.4889589905362776,
243
+ "grad_norm": 0.8039259314537048,
244
+ "learning_rate": 1.9970307467012862e-05,
245
+ "loss": 0.137426700592041,
246
+ "step": 775
247
+ },
248
+ {
249
+ "epoch": 0.5047318611987381,
250
+ "grad_norm": 0.18804790079593658,
251
+ "learning_rate": 1.9958764107168226e-05,
252
+ "loss": 0.08404406547546386,
253
+ "step": 800
254
+ },
255
+ {
256
+ "epoch": 0.5205047318611987,
257
+ "grad_norm": 1.2277655601501465,
258
+ "learning_rate": 1.994533399533373e-05,
259
+ "loss": 0.06400898456573487,
260
+ "step": 825
261
+ },
262
+ {
263
+ "epoch": 0.5362776025236593,
264
+ "grad_norm": 0.34563761949539185,
265
+ "learning_rate": 1.9930019675930546e-05,
266
+ "loss": 0.10282803535461425,
267
+ "step": 850
268
+ },
269
+ {
270
+ "epoch": 0.5520504731861199,
271
+ "grad_norm": 9.899245262145996,
272
+ "learning_rate": 1.99128240503551e-05,
273
+ "loss": 0.17283258438110352,
274
+ "step": 875
275
+ },
276
+ {
277
+ "epoch": 0.5678233438485805,
278
+ "grad_norm": 2.8441741466522217,
279
+ "learning_rate": 1.9893750376429396e-05,
280
+ "loss": 0.06587859153747559,
281
+ "step": 900
282
+ },
283
+ {
284
+ "epoch": 0.583596214511041,
285
+ "grad_norm": 2.315617799758911,
286
+ "learning_rate": 1.9872802267783777e-05,
287
+ "loss": 0.1376850986480713,
288
+ "step": 925
289
+ },
290
+ {
291
+ "epoch": 0.5993690851735016,
292
+ "grad_norm": 1.8745895624160767,
293
+ "learning_rate": 1.9849983693172324e-05,
294
+ "loss": 0.14075576782226562,
295
+ "step": 950
296
+ },
297
+ {
298
+ "epoch": 0.6151419558359621,
299
+ "grad_norm": 1.8815633058547974,
300
+ "learning_rate": 1.9825298975720938e-05,
301
+ "loss": 0.1421357250213623,
302
+ "step": 975
303
+ },
304
+ {
305
+ "epoch": 0.6309148264984227,
306
+ "grad_norm": 0.15319357812404633,
307
+ "learning_rate": 1.97987527921083e-05,
308
+ "loss": 0.062098536491394046,
309
+ "step": 1000
310
+ },
311
+ {
312
+ "epoch": 0.6309148264984227,
313
+ "eval_accuracy": 0.9801261829652996,
314
+ "eval_f1": 0.9802816901408451,
315
+ "eval_loss": 0.07721533626317978,
316
+ "eval_precision": 0.9726708074534162,
317
+ "eval_recall": 0.98801261829653,
318
+ "eval_runtime": 61.7227,
319
+ "eval_samples_per_second": 51.359,
320
+ "eval_steps_per_second": 3.224,
321
+ "step": 1000
322
+ },
323
+ {
324
+ "epoch": 0.6466876971608833,
325
+ "grad_norm": 7.767244815826416,
326
+ "learning_rate": 1.977035017167984e-05,
327
+ "loss": 0.09910112380981445,
328
+ "step": 1025
329
+ },
330
+ {
331
+ "epoch": 0.6624605678233438,
332
+ "grad_norm": 0.3622685968875885,
333
+ "learning_rate": 1.974009649549489e-05,
334
+ "loss": 0.11072664260864258,
335
+ "step": 1050
336
+ },
337
+ {
338
+ "epoch": 0.6782334384858044,
339
+ "grad_norm": 0.2787080705165863,
340
+ "learning_rate": 1.9707997495307232e-05,
341
+ "loss": 0.09833921432495117,
342
+ "step": 1075
343
+ },
344
+ {
345
+ "epoch": 0.694006309148265,
346
+ "grad_norm": 2.9150843620300293,
347
+ "learning_rate": 1.9674059252479156e-05,
348
+ "loss": 0.14047959327697754,
349
+ "step": 1100
350
+ },
351
+ {
352
+ "epoch": 0.7097791798107256,
353
+ "grad_norm": 8.6441650390625,
354
+ "learning_rate": 1.9638288196829303e-05,
355
+ "loss": 0.11829081535339356,
356
+ "step": 1125
357
+ },
358
+ {
359
+ "epoch": 0.7255520504731862,
360
+ "grad_norm": 17.530630111694336,
361
+ "learning_rate": 1.9600691105414523e-05,
362
+ "loss": 0.08339802742004394,
363
+ "step": 1150
364
+ },
365
+ {
366
+ "epoch": 0.7413249211356467,
367
+ "grad_norm": 0.10623405873775482,
368
+ "learning_rate": 1.9561275101245886e-05,
369
+ "loss": 0.09576749801635742,
370
+ "step": 1175
371
+ },
372
+ {
373
+ "epoch": 0.7570977917981072,
374
+ "grad_norm": 2.705754041671753,
375
+ "learning_rate": 1.95200476519392e-05,
376
+ "loss": 0.09259629249572754,
377
+ "step": 1200
378
+ },
379
+ {
380
+ "epoch": 0.7728706624605678,
381
+ "grad_norm": 0.5176487565040588,
382
+ "learning_rate": 1.9477016568300233e-05,
383
+ "loss": 0.1117174243927002,
384
+ "step": 1225
385
+ },
386
+ {
387
+ "epoch": 0.7886435331230284,
388
+ "grad_norm": 0.12397055327892303,
389
+ "learning_rate": 1.9432190002844868e-05,
390
+ "loss": 0.03809569358825684,
391
+ "step": 1250
392
+ },
393
+ {
394
+ "epoch": 0.804416403785489,
395
+ "grad_norm": 2.5329222679138184,
396
+ "learning_rate": 1.93855764482546e-05,
397
+ "loss": 0.08740017890930175,
398
+ "step": 1275
399
+ },
400
+ {
401
+ "epoch": 0.8201892744479495,
402
+ "grad_norm": 3.738490104675293,
403
+ "learning_rate": 1.933718473576751e-05,
404
+ "loss": 0.10855884552001953,
405
+ "step": 1300
406
+ },
407
+ {
408
+ "epoch": 0.8359621451104101,
409
+ "grad_norm": 2.956233024597168,
410
+ "learning_rate": 1.9287024033505156e-05,
411
+ "loss": 0.12295740127563476,
412
+ "step": 1325
413
+ },
414
+ {
415
+ "epoch": 0.8517350157728707,
416
+ "grad_norm": 10.139039039611816,
417
+ "learning_rate": 1.9235103844735587e-05,
418
+ "loss": 0.048102741241455076,
419
+ "step": 1350
420
+ },
421
+ {
422
+ "epoch": 0.8675078864353313,
423
+ "grad_norm": 0.056244589388370514,
424
+ "learning_rate": 1.9181434006072906e-05,
425
+ "loss": 0.04849647045135498,
426
+ "step": 1375
427
+ },
428
+ {
429
+ "epoch": 0.8832807570977917,
430
+ "grad_norm": 0.053447045385837555,
431
+ "learning_rate": 1.9126024685613664e-05,
432
+ "loss": 0.05115017414093018,
433
+ "step": 1400
434
+ },
435
+ {
436
+ "epoch": 0.8990536277602523,
437
+ "grad_norm": 0.036403946578502655,
438
+ "learning_rate": 1.9068886381010424e-05,
439
+ "loss": 0.06353372573852539,
440
+ "step": 1425
441
+ },
442
+ {
443
+ "epoch": 0.9148264984227129,
444
+ "grad_norm": 0.26306140422821045,
445
+ "learning_rate": 1.9010029917482943e-05,
446
+ "loss": 0.0969051742553711,
447
+ "step": 1450
448
+ },
449
+ {
450
+ "epoch": 0.9305993690851735,
451
+ "grad_norm": 1.315486192703247,
452
+ "learning_rate": 1.894946644576724e-05,
453
+ "loss": 0.09260586738586425,
454
+ "step": 1475
455
+ },
456
+ {
457
+ "epoch": 0.9463722397476341,
458
+ "grad_norm": 2.3364198207855225,
459
+ "learning_rate": 1.8887207440003028e-05,
460
+ "loss": 0.08708816528320312,
461
+ "step": 1500
462
+ },
463
+ {
464
+ "epoch": 0.9463722397476341,
465
+ "eval_accuracy": 0.9741324921135647,
466
+ "eval_f1": 0.9746913580246913,
467
+ "eval_loss": 0.09679784625768661,
468
+ "eval_precision": 0.9540785498489426,
469
+ "eval_recall": 0.9962145110410094,
470
+ "eval_runtime": 61.8073,
471
+ "eval_samples_per_second": 51.288,
472
+ "eval_steps_per_second": 3.22,
473
+ "step": 1500
474
+ },
475
+ {
476
+ "epoch": 0.9621451104100947,
477
+ "grad_norm": 0.30046138167381287,
478
+ "learning_rate": 1.8823264695559876e-05,
479
+ "loss": 0.1200937271118164,
480
+ "step": 1525
481
+ },
482
+ {
483
+ "epoch": 0.9779179810725552,
484
+ "grad_norm": 0.6962589025497437,
485
+ "learning_rate": 1.8757650326802474e-05,
486
+ "loss": 0.09418746948242188,
487
+ "step": 1550
488
+ },
489
+ {
490
+ "epoch": 0.9936908517350158,
491
+ "grad_norm": 0.043801840394735336,
492
+ "learning_rate": 1.8690376764795512e-05,
493
+ "loss": 0.06756117820739746,
494
+ "step": 1575
495
+ },
496
+ {
497
+ "epoch": 1.0094637223974763,
498
+ "grad_norm": 0.4039168059825897,
499
+ "learning_rate": 1.8621456754948524e-05,
500
+ "loss": 0.12740618705749512,
501
+ "step": 1600
502
+ },
503
+ {
504
+ "epoch": 1.025236593059937,
505
+ "grad_norm": 0.14026908576488495,
506
+ "learning_rate": 1.8550903354601182e-05,
507
+ "loss": 0.03949842691421509,
508
+ "step": 1625
509
+ },
510
+ {
511
+ "epoch": 1.0410094637223974,
512
+ "grad_norm": 4.512003421783447,
513
+ "learning_rate": 1.847872993054952e-05,
514
+ "loss": 0.16327035903930665,
515
+ "step": 1650
516
+ },
517
+ {
518
+ "epoch": 1.0567823343848581,
519
+ "grad_norm": 19.02384376525879,
520
+ "learning_rate": 1.840495015651348e-05,
521
+ "loss": 0.05400698184967041,
522
+ "step": 1675
523
+ },
524
+ {
525
+ "epoch": 1.0725552050473186,
526
+ "grad_norm": 2.6894822120666504,
527
+ "learning_rate": 1.8329578010546364e-05,
528
+ "loss": 0.10054654121398926,
529
+ "step": 1700
530
+ },
531
+ {
532
+ "epoch": 1.088328075709779,
533
+ "grad_norm": 4.580667972564697,
534
+ "learning_rate": 1.825262777238659e-05,
535
+ "loss": 0.08389140129089355,
536
+ "step": 1725
537
+ },
538
+ {
539
+ "epoch": 1.1041009463722398,
540
+ "grad_norm": 0.07508229464292526,
541
+ "learning_rate": 1.817411402075229e-05,
542
+ "loss": 0.10561941146850586,
543
+ "step": 1750
544
+ },
545
+ {
546
+ "epoch": 1.1198738170347002,
547
+ "grad_norm": 0.15733584761619568,
548
+ "learning_rate": 1.809405163057931e-05,
549
+ "loss": 0.0838914966583252,
550
+ "step": 1775
551
+ },
552
+ {
553
+ "epoch": 1.135646687697161,
554
+ "grad_norm": 3.2914106845855713,
555
+ "learning_rate": 1.8012455770203038e-05,
556
+ "loss": 0.06280827522277832,
557
+ "step": 1800
558
+ },
559
+ {
560
+ "epoch": 1.1514195583596214,
561
+ "grad_norm": 0.14646464586257935,
562
+ "learning_rate": 1.7929341898484653e-05,
563
+ "loss": 0.08718341827392578,
564
+ "step": 1825
565
+ },
566
+ {
567
+ "epoch": 1.167192429022082,
568
+ "grad_norm": 1.474497675895691,
569
+ "learning_rate": 1.784472576188237e-05,
570
+ "loss": 0.07045670986175537,
571
+ "step": 1850
572
+ },
573
+ {
574
+ "epoch": 1.1829652996845426,
575
+ "grad_norm": 0.09543656557798386,
576
+ "learning_rate": 1.775862339146815e-05,
577
+ "loss": 0.054620800018310545,
578
+ "step": 1875
579
+ },
580
+ {
581
+ "epoch": 1.1987381703470033,
582
+ "grad_norm": 0.031090043485164642,
583
+ "learning_rate": 1.7671051099890538e-05,
584
+ "loss": 0.06679238319396973,
585
+ "step": 1900
586
+ },
587
+ {
588
+ "epoch": 1.2145110410094637,
589
+ "grad_norm": 0.08794307708740234,
590
+ "learning_rate": 1.758202547828409e-05,
591
+ "loss": 0.038062283992767336,
592
+ "step": 1925
593
+ },
594
+ {
595
+ "epoch": 1.2302839116719242,
596
+ "grad_norm": 5.799429893493652,
597
+ "learning_rate": 1.74915633931261e-05,
598
+ "loss": 0.11424206733703614,
599
+ "step": 1950
600
+ },
601
+ {
602
+ "epoch": 1.2460567823343849,
603
+ "grad_norm": 0.22451771795749664,
604
+ "learning_rate": 1.739968198304114e-05,
605
+ "loss": 0.04508783340454101,
606
+ "step": 1975
607
+ },
608
+ {
609
+ "epoch": 1.2618296529968454,
610
+ "grad_norm": 0.07231876999139786,
611
+ "learning_rate": 1.7306398655554023e-05,
612
+ "loss": 0.04203261852264404,
613
+ "step": 2000
614
+ },
615
+ {
616
+ "epoch": 1.2618296529968454,
617
+ "eval_accuracy": 0.9804416403785489,
618
+ "eval_f1": 0.980649188514357,
619
+ "eval_loss": 0.08355643600225449,
620
+ "eval_precision": 0.9703520691785052,
621
+ "eval_recall": 0.9911671924290221,
622
+ "eval_runtime": 61.6587,
623
+ "eval_samples_per_second": 51.412,
624
+ "eval_steps_per_second": 3.227,
625
+ "step": 2000
626
+ },
627
+ {
628
+ "epoch": 1.277602523659306,
629
+ "grad_norm": 0.096407450735569,
630
+ "learning_rate": 1.721173108379184e-05,
631
+ "loss": 0.13708463668823243,
632
+ "step": 2025
633
+ },
634
+ {
635
+ "epoch": 1.2933753943217665,
636
+ "grad_norm": 0.1677226722240448,
637
+ "learning_rate": 1.711569720313568e-05,
638
+ "loss": 0.06809837341308594,
639
+ "step": 2050
640
+ },
641
+ {
642
+ "epoch": 1.3091482649842272,
643
+ "grad_norm": 0.2626091241836548,
644
+ "learning_rate": 1.701831520782264e-05,
645
+ "loss": 0.08504070281982422,
646
+ "step": 2075
647
+ },
648
+ {
649
+ "epoch": 1.3249211356466877,
650
+ "grad_norm": 2.335200786590576,
651
+ "learning_rate": 1.6919603547498832e-05,
652
+ "loss": 0.06117515563964844,
653
+ "step": 2100
654
+ },
655
+ {
656
+ "epoch": 1.3406940063091484,
657
+ "grad_norm": 0.04033582657575607,
658
+ "learning_rate": 1.6819580923723957e-05,
659
+ "loss": 0.058640117645263674,
660
+ "step": 2125
661
+ },
662
+ {
663
+ "epoch": 1.3564668769716088,
664
+ "grad_norm": 0.030620798468589783,
665
+ "learning_rate": 1.671826628642819e-05,
666
+ "loss": 0.046917934417724606,
667
+ "step": 2150
668
+ },
669
+ {
670
+ "epoch": 1.3722397476340693,
671
+ "grad_norm": 0.08066167682409286,
672
+ "learning_rate": 1.6615678830321987e-05,
673
+ "loss": 0.04496946811676025,
674
+ "step": 2175
675
+ },
676
+ {
677
+ "epoch": 1.38801261829653,
678
+ "grad_norm": 4.896634578704834,
679
+ "learning_rate": 1.651183799125952e-05,
680
+ "loss": 0.085579833984375,
681
+ "step": 2200
682
+ },
683
+ {
684
+ "epoch": 1.4037854889589905,
685
+ "grad_norm": 5.254743576049805,
686
+ "learning_rate": 1.640676344255643e-05,
687
+ "loss": 0.06547237396240234,
688
+ "step": 2225
689
+ },
690
+ {
691
+ "epoch": 1.4195583596214512,
692
+ "grad_norm": 0.19317586719989777,
693
+ "learning_rate": 1.6300475091262615e-05,
694
+ "loss": 0.09360321044921875,
695
+ "step": 2250
696
+ },
697
+ {
698
+ "epoch": 1.4353312302839116,
699
+ "grad_norm": 2.6724467277526855,
700
+ "learning_rate": 1.6192993074390658e-05,
701
+ "loss": 0.08104397773742676,
702
+ "step": 2275
703
+ },
704
+ {
705
+ "epoch": 1.4511041009463723,
706
+ "grad_norm": 2.7021729946136475,
707
+ "learning_rate": 1.6084337755100795e-05,
708
+ "loss": 0.06326522827148437,
709
+ "step": 2300
710
+ },
711
+ {
712
+ "epoch": 1.4668769716088328,
713
+ "grad_norm": 6.612598896026611,
714
+ "learning_rate": 1.597452971884296e-05,
715
+ "loss": 0.09769298553466797,
716
+ "step": 2325
717
+ },
718
+ {
719
+ "epoch": 1.4826498422712935,
720
+ "grad_norm": 0.03583915904164314,
721
+ "learning_rate": 1.5863589769456725e-05,
722
+ "loss": 0.035602734088897706,
723
+ "step": 2350
724
+ },
725
+ {
726
+ "epoch": 1.498422712933754,
727
+ "grad_norm": 7.2366533279418945,
728
+ "learning_rate": 1.575153892522991e-05,
729
+ "loss": 0.05557059288024902,
730
+ "step": 2375
731
+ },
732
+ {
733
+ "epoch": 1.5141955835962144,
734
+ "grad_norm": 3.2834980487823486,
735
+ "learning_rate": 1.5638398414916504e-05,
736
+ "loss": 0.059678325653076174,
737
+ "step": 2400
738
+ },
739
+ {
740
+ "epoch": 1.5299684542586751,
741
+ "grad_norm": 0.7327181100845337,
742
+ "learning_rate": 1.552418967371476e-05,
743
+ "loss": 0.10861465454101563,
744
+ "step": 2425
745
+ },
746
+ {
747
+ "epoch": 1.5457413249211358,
748
+ "grad_norm": 7.32216215133667,
749
+ "learning_rate": 1.540893433920614e-05,
750
+ "loss": 0.062454757690429685,
751
+ "step": 2450
752
+ },
753
+ {
754
+ "epoch": 1.5615141955835963,
755
+ "grad_norm": 0.4157012701034546,
756
+ "learning_rate": 1.5292654247255976e-05,
757
+ "loss": 0.06408432960510253,
758
+ "step": 2475
759
+ },
760
+ {
761
+ "epoch": 1.5772870662460567,
762
+ "grad_norm": 0.392075777053833,
763
+ "learning_rate": 1.5175371427876462e-05,
764
+ "loss": 0.06900923252105713,
765
+ "step": 2500
766
+ },
767
+ {
768
+ "epoch": 1.5772870662460567,
769
+ "eval_accuracy": 0.9826498422712934,
770
+ "eval_f1": 0.9827532141737222,
771
+ "eval_loss": 0.06640289723873138,
772
+ "eval_precision": 0.976932668329177,
773
+ "eval_recall": 0.9886435331230284,
774
+ "eval_runtime": 61.7792,
775
+ "eval_samples_per_second": 51.312,
776
+ "eval_steps_per_second": 3.221,
777
+ "step": 2500
778
+ }
779
+ ],
780
+ "logging_steps": 25,
781
+ "max_steps": 6340,
782
+ "num_input_tokens_seen": 0,
783
+ "num_train_epochs": 4,
784
+ "save_steps": 500,
785
+ "stateful_callbacks": {
786
+ "EarlyStoppingCallback": {
787
+ "args": {
788
+ "early_stopping_patience": 2,
789
+ "early_stopping_threshold": 0.0
790
+ },
791
+ "attributes": {
792
+ "early_stopping_patience_counter": 0
793
+ }
794
+ },
795
+ "TrainerControl": {
796
+ "args": {
797
+ "should_epoch_stop": false,
798
+ "should_evaluate": false,
799
+ "should_log": false,
800
+ "should_save": true,
801
+ "should_training_stop": false
802
+ },
803
+ "attributes": {}
804
+ }
805
+ },
806
+ "total_flos": 1.049490799843584e+16,
807
+ "train_batch_size": 16,
808
+ "trial_name": null,
809
+ "trial_params": null
810
+ }
checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:828868299f9c3bb1e27941873d6c50b8aa4a9047279d9f7fe0a8c9ebc165d240
3
+ size 5201