NourFakih commited on
Commit
9ec8312
·
verified ·
1 Parent(s): 802e500

Upload checkpoint and eval results at step 2000

Browse files
checkpoint-2000/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": "5.12.1",
35
+ "type_vocab_size": 2,
36
+ "use_cache": false,
37
+ "vocab_size": 30522
38
+ }
checkpoint-2000/eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 2000,
3
+ "epoch": 1.6181229773462782,
4
+ "time": "2026-06-26 22:23:26",
5
+ "metrics": {
6
+ "eval_loss": 0.145921990275383,
7
+ "eval_accuracy": 0.9621020717534108,
8
+ "eval_precision": 0.9625564880568108,
9
+ "eval_recall": 0.9887267904509284,
10
+ "eval_f1": 0.9754661432777233
11
+ }
12
+ }
checkpoint-2000/eval_step_002000.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 2000,
3
+ "epoch": 1.6181229773462782,
4
+ "time": "2026-06-26 22:23:26",
5
+ "metrics": {
6
+ "eval_loss": 0.145921990275383,
7
+ "eval_accuracy": 0.9621020717534108,
8
+ "eval_precision": 0.9625564880568108,
9
+ "eval_recall": 0.9887267904509284,
10
+ "eval_f1": 0.9754661432777233,
11
+ "eval_runtime": 34.2514,
12
+ "eval_samples_per_second": 57.779,
13
+ "eval_steps_per_second": 3.62,
14
+ "epoch": 1.6181229773462782
15
+ }
16
+ }
checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d285641d677fa68aeeb93552d3ec493a4ad15df88ea6f22f847a62277f928010
3
+ size 437958624
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d767060f6b9c7ed068c626fb64af21f4dfa39a6e118a1abdeac4c9d38a46e8a
3
+ size 876041611
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c1ab0b39032c271ddd2317a23008c15ff14688abeafe7f098678828f3c40af8
3
+ size 14645
checkpoint-2000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
3
+ size 1383
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d97c62f846fc2150f784e7ebc4de7c6734217d3622f1dca375687ca33dcc6abc
3
+ size 1465
checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/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-2000/trainer_state.json ADDED
@@ -0,0 +1,658 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2000,
3
+ "best_metric": 0.9754661432777233,
4
+ "best_model_checkpoint": "/kaggle/working/outputs/bert_rd_keystrokes/checkpoint-2000",
5
+ "epoch": 1.6181229773462782,
6
+ "eval_steps": 500,
7
+ "global_step": 2000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0008090614886731392,
14
+ "grad_norm": 2.5394184589385986,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.6913009285926819,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.020226537216828478,
21
+ "grad_norm": 3.3882575035095215,
22
+ "learning_rate": 9.716599190283402e-07,
23
+ "loss": 0.710881233215332,
24
+ "step": 25
25
+ },
26
+ {
27
+ "epoch": 0.040453074433656956,
28
+ "grad_norm": 4.59527063369751,
29
+ "learning_rate": 1.9838056680161946e-06,
30
+ "loss": 0.6965625762939454,
31
+ "step": 50
32
+ },
33
+ {
34
+ "epoch": 0.06067961165048544,
35
+ "grad_norm": 6.466946125030518,
36
+ "learning_rate": 2.995951417004049e-06,
37
+ "loss": 0.6713954925537109,
38
+ "step": 75
39
+ },
40
+ {
41
+ "epoch": 0.08090614886731391,
42
+ "grad_norm": 5.92415714263916,
43
+ "learning_rate": 4.008097165991903e-06,
44
+ "loss": 0.6306858444213868,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.1011326860841424,
49
+ "grad_norm": 7.790467262268066,
50
+ "learning_rate": 5.020242914979757e-06,
51
+ "loss": 0.5511775207519531,
52
+ "step": 125
53
+ },
54
+ {
55
+ "epoch": 0.12135922330097088,
56
+ "grad_norm": 5.874857425689697,
57
+ "learning_rate": 6.0323886639676124e-06,
58
+ "loss": 0.5026376342773438,
59
+ "step": 150
60
+ },
61
+ {
62
+ "epoch": 0.14158576051779936,
63
+ "grad_norm": 12.701870918273926,
64
+ "learning_rate": 7.044534412955466e-06,
65
+ "loss": 0.4295468521118164,
66
+ "step": 175
67
+ },
68
+ {
69
+ "epoch": 0.16181229773462782,
70
+ "grad_norm": 5.137658596038818,
71
+ "learning_rate": 8.056680161943322e-06,
72
+ "loss": 0.3788005828857422,
73
+ "step": 200
74
+ },
75
+ {
76
+ "epoch": 0.1820388349514563,
77
+ "grad_norm": 5.249273300170898,
78
+ "learning_rate": 9.068825910931175e-06,
79
+ "loss": 0.2651861381530762,
80
+ "step": 225
81
+ },
82
+ {
83
+ "epoch": 0.2022653721682848,
84
+ "grad_norm": 38.753013610839844,
85
+ "learning_rate": 1.008097165991903e-05,
86
+ "loss": 0.3065790557861328,
87
+ "step": 250
88
+ },
89
+ {
90
+ "epoch": 0.22249190938511326,
91
+ "grad_norm": 13.836112022399902,
92
+ "learning_rate": 1.1093117408906884e-05,
93
+ "loss": 0.38094028472900393,
94
+ "step": 275
95
+ },
96
+ {
97
+ "epoch": 0.24271844660194175,
98
+ "grad_norm": 6.559873580932617,
99
+ "learning_rate": 1.2105263157894737e-05,
100
+ "loss": 0.3118729019165039,
101
+ "step": 300
102
+ },
103
+ {
104
+ "epoch": 0.26294498381877024,
105
+ "grad_norm": 7.356478214263916,
106
+ "learning_rate": 1.3117408906882592e-05,
107
+ "loss": 0.23761932373046876,
108
+ "step": 325
109
+ },
110
+ {
111
+ "epoch": 0.28317152103559873,
112
+ "grad_norm": 4.0845184326171875,
113
+ "learning_rate": 1.4129554655870446e-05,
114
+ "loss": 0.26587358474731443,
115
+ "step": 350
116
+ },
117
+ {
118
+ "epoch": 0.30339805825242716,
119
+ "grad_norm": 28.685104370117188,
120
+ "learning_rate": 1.5141700404858302e-05,
121
+ "loss": 0.3239314651489258,
122
+ "step": 375
123
+ },
124
+ {
125
+ "epoch": 0.32362459546925565,
126
+ "grad_norm": 1.7896462678909302,
127
+ "learning_rate": 1.6153846153846154e-05,
128
+ "loss": 0.24046634674072265,
129
+ "step": 400
130
+ },
131
+ {
132
+ "epoch": 0.34385113268608414,
133
+ "grad_norm": 6.960549831390381,
134
+ "learning_rate": 1.716599190283401e-05,
135
+ "loss": 0.27144105911254884,
136
+ "step": 425
137
+ },
138
+ {
139
+ "epoch": 0.3640776699029126,
140
+ "grad_norm": 22.062820434570312,
141
+ "learning_rate": 1.8178137651821864e-05,
142
+ "loss": 0.24825719833374024,
143
+ "step": 450
144
+ },
145
+ {
146
+ "epoch": 0.3843042071197411,
147
+ "grad_norm": 0.4285735785961151,
148
+ "learning_rate": 1.9190283400809718e-05,
149
+ "loss": 0.22249792098999024,
150
+ "step": 475
151
+ },
152
+ {
153
+ "epoch": 0.4045307443365696,
154
+ "grad_norm": 0.26966607570648193,
155
+ "learning_rate": 1.999993769982229e-05,
156
+ "loss": 0.25503772735595703,
157
+ "step": 500
158
+ },
159
+ {
160
+ "epoch": 0.4045307443365696,
161
+ "eval_accuracy": 0.9550277918140475,
162
+ "eval_f1": 0.9709055246812683,
163
+ "eval_loss": 0.1790667176246643,
164
+ "eval_precision": 0.9574468085106383,
165
+ "eval_recall": 0.9847480106100795,
166
+ "eval_runtime": 34.5481,
167
+ "eval_samples_per_second": 57.282,
168
+ "eval_steps_per_second": 3.589,
169
+ "step": 500
170
+ },
171
+ {
172
+ "epoch": 0.42475728155339804,
173
+ "grad_norm": 1.232269048690796,
174
+ "learning_rate": 1.9997757275108847e-05,
175
+ "loss": 0.2667963790893555,
176
+ "step": 525
177
+ },
178
+ {
179
+ "epoch": 0.4449838187702265,
180
+ "grad_norm": 12.561880111694336,
181
+ "learning_rate": 1.9992462617728763e-05,
182
+ "loss": 0.2216647148132324,
183
+ "step": 550
184
+ },
185
+ {
186
+ "epoch": 0.465210355987055,
187
+ "grad_norm": 0.4093881845474243,
188
+ "learning_rate": 1.9984055376931414e-05,
189
+ "loss": 0.23123834609985353,
190
+ "step": 575
191
+ },
192
+ {
193
+ "epoch": 0.4854368932038835,
194
+ "grad_norm": 3.573305368423462,
195
+ "learning_rate": 1.9972538171514525e-05,
196
+ "loss": 0.2226162338256836,
197
+ "step": 600
198
+ },
199
+ {
200
+ "epoch": 0.5056634304207119,
201
+ "grad_norm": 12.511730194091797,
202
+ "learning_rate": 1.9957914589008405e-05,
203
+ "loss": 0.2451229476928711,
204
+ "step": 625
205
+ },
206
+ {
207
+ "epoch": 0.5258899676375405,
208
+ "grad_norm": 11.676703453063965,
209
+ "learning_rate": 1.9940189184558487e-05,
210
+ "loss": 0.25127721786499024,
211
+ "step": 650
212
+ },
213
+ {
214
+ "epoch": 0.5461165048543689,
215
+ "grad_norm": 5.444802284240723,
216
+ "learning_rate": 1.9919367479506413e-05,
217
+ "loss": 0.30009620666503906,
218
+ "step": 675
219
+ },
220
+ {
221
+ "epoch": 0.5663430420711975,
222
+ "grad_norm": 1.9753400087356567,
223
+ "learning_rate": 1.989545595967018e-05,
224
+ "loss": 0.3415143585205078,
225
+ "step": 700
226
+ },
227
+ {
228
+ "epoch": 0.5865695792880259,
229
+ "grad_norm": 0.7816814184188843,
230
+ "learning_rate": 1.986846207332384e-05,
231
+ "loss": 0.24259204864501954,
232
+ "step": 725
233
+ },
234
+ {
235
+ "epoch": 0.6067961165048543,
236
+ "grad_norm": 20.42180061340332,
237
+ "learning_rate": 1.9838394228877443e-05,
238
+ "loss": 0.1343485450744629,
239
+ "step": 750
240
+ },
241
+ {
242
+ "epoch": 0.6270226537216829,
243
+ "grad_norm": 21.677453994750977,
244
+ "learning_rate": 1.980526179225785e-05,
245
+ "loss": 0.25507625579833987,
246
+ "step": 775
247
+ },
248
+ {
249
+ "epoch": 0.6472491909385113,
250
+ "grad_norm": 4.561895370483398,
251
+ "learning_rate": 1.97690750839913e-05,
252
+ "loss": 0.26329845428466797,
253
+ "step": 800
254
+ },
255
+ {
256
+ "epoch": 0.6674757281553398,
257
+ "grad_norm": 0.17717082798480988,
258
+ "learning_rate": 1.9729845375988694e-05,
259
+ "loss": 0.16668357849121093,
260
+ "step": 825
261
+ },
262
+ {
263
+ "epoch": 0.6877022653721683,
264
+ "grad_norm": 6.059898853302002,
265
+ "learning_rate": 1.968758488803439e-05,
266
+ "loss": 0.2621467399597168,
267
+ "step": 850
268
+ },
269
+ {
270
+ "epoch": 0.7079288025889967,
271
+ "grad_norm": 5.8439130783081055,
272
+ "learning_rate": 1.9642306783979902e-05,
273
+ "loss": 0.3152758979797363,
274
+ "step": 875
275
+ },
276
+ {
277
+ "epoch": 0.7281553398058253,
278
+ "grad_norm": 5.4012041091918945,
279
+ "learning_rate": 1.959402516764339e-05,
280
+ "loss": 0.2474656867980957,
281
+ "step": 900
282
+ },
283
+ {
284
+ "epoch": 0.7483818770226537,
285
+ "grad_norm": 13.964224815368652,
286
+ "learning_rate": 1.954275507841646e-05,
287
+ "loss": 0.22230056762695313,
288
+ "step": 925
289
+ },
290
+ {
291
+ "epoch": 0.7686084142394822,
292
+ "grad_norm": 8.115334510803223,
293
+ "learning_rate": 1.948851248657947e-05,
294
+ "loss": 0.3234273910522461,
295
+ "step": 950
296
+ },
297
+ {
298
+ "epoch": 0.7888349514563107,
299
+ "grad_norm": 0.23621903359889984,
300
+ "learning_rate": 1.9431314288326925e-05,
301
+ "loss": 0.1469671630859375,
302
+ "step": 975
303
+ },
304
+ {
305
+ "epoch": 0.8090614886731392,
306
+ "grad_norm": 3.0084638595581055,
307
+ "learning_rate": 1.9371178300504394e-05,
308
+ "loss": 0.24907604217529297,
309
+ "step": 1000
310
+ },
311
+ {
312
+ "epoch": 0.8090614886731392,
313
+ "eval_accuracy": 0.9615967660434563,
314
+ "eval_f1": 0.9752604166666666,
315
+ "eval_loss": 0.15361516177654266,
316
+ "eval_precision": 0.9578005115089514,
317
+ "eval_recall": 0.993368700265252,
318
+ "eval_runtime": 34.2684,
319
+ "eval_samples_per_second": 57.75,
320
+ "eval_steps_per_second": 3.618,
321
+ "step": 1000
322
+ },
323
+ {
324
+ "epoch": 0.8292880258899676,
325
+ "grad_norm": 0.658998429775238,
326
+ "learning_rate": 1.930812325505871e-05,
327
+ "loss": 0.128564510345459,
328
+ "step": 1025
329
+ },
330
+ {
331
+ "epoch": 0.8495145631067961,
332
+ "grad_norm": 14.597765922546387,
333
+ "learning_rate": 1.9242168793203088e-05,
334
+ "loss": 0.28263355255126954,
335
+ "step": 1050
336
+ },
337
+ {
338
+ "epoch": 0.8697411003236246,
339
+ "grad_norm": 10.520459175109863,
340
+ "learning_rate": 1.9173335459299025e-05,
341
+ "loss": 0.20550737380981446,
342
+ "step": 1075
343
+ },
344
+ {
345
+ "epoch": 0.889967637540453,
346
+ "grad_norm": 8.196412086486816,
347
+ "learning_rate": 1.9101644694456873e-05,
348
+ "loss": 0.21728286743164063,
349
+ "step": 1100
350
+ },
351
+ {
352
+ "epoch": 0.9101941747572816,
353
+ "grad_norm": 10.451470375061035,
354
+ "learning_rate": 1.902711882985708e-05,
355
+ "loss": 0.22805599212646485,
356
+ "step": 1125
357
+ },
358
+ {
359
+ "epoch": 0.93042071197411,
360
+ "grad_norm": 0.7729430794715881,
361
+ "learning_rate": 1.894978107979417e-05,
362
+ "loss": 0.19682933807373046,
363
+ "step": 1150
364
+ },
365
+ {
366
+ "epoch": 0.9506472491909385,
367
+ "grad_norm": 1.208465814590454,
368
+ "learning_rate": 1.886965553444568e-05,
369
+ "loss": 0.21496267318725587,
370
+ "step": 1175
371
+ },
372
+ {
373
+ "epoch": 0.970873786407767,
374
+ "grad_norm": 8.930377006530762,
375
+ "learning_rate": 1.8786767152368197e-05,
376
+ "loss": 0.2545662498474121,
377
+ "step": 1200
378
+ },
379
+ {
380
+ "epoch": 0.9911003236245954,
381
+ "grad_norm": 8.784140586853027,
382
+ "learning_rate": 1.8701141752722966e-05,
383
+ "loss": 0.15711795806884765,
384
+ "step": 1225
385
+ },
386
+ {
387
+ "epoch": 1.0113268608414239,
388
+ "grad_norm": 6.048089504241943,
389
+ "learning_rate": 1.8612806007233382e-05,
390
+ "loss": 0.18027606964111328,
391
+ "step": 1250
392
+ },
393
+ {
394
+ "epoch": 1.0315533980582525,
395
+ "grad_norm": 2.1826491355895996,
396
+ "learning_rate": 1.8521787431876954e-05,
397
+ "loss": 0.1467225170135498,
398
+ "step": 1275
399
+ },
400
+ {
401
+ "epoch": 1.051779935275081,
402
+ "grad_norm": 13.113622665405273,
403
+ "learning_rate": 1.8428114378314237e-05,
404
+ "loss": 0.21480131149291992,
405
+ "step": 1300
406
+ },
407
+ {
408
+ "epoch": 1.0720064724919094,
409
+ "grad_norm": 6.212342262268066,
410
+ "learning_rate": 1.8331816025057508e-05,
411
+ "loss": 0.22947580337524415,
412
+ "step": 1325
413
+ },
414
+ {
415
+ "epoch": 1.0922330097087378,
416
+ "grad_norm": 0.22277741134166718,
417
+ "learning_rate": 1.823292236838186e-05,
418
+ "loss": 0.10173338890075684,
419
+ "step": 1350
420
+ },
421
+ {
422
+ "epoch": 1.1124595469255663,
423
+ "grad_norm": 11.058046340942383,
424
+ "learning_rate": 1.813146421298154e-05,
425
+ "loss": 0.2582175064086914,
426
+ "step": 1375
427
+ },
428
+ {
429
+ "epoch": 1.132686084142395,
430
+ "grad_norm": 9.502155303955078,
431
+ "learning_rate": 1.802747316237454e-05,
432
+ "loss": 0.23467300415039063,
433
+ "step": 1400
434
+ },
435
+ {
436
+ "epoch": 1.1529126213592233,
437
+ "grad_norm": 5.091904640197754,
438
+ "learning_rate": 1.792098160905829e-05,
439
+ "loss": 0.18842180252075194,
440
+ "step": 1425
441
+ },
442
+ {
443
+ "epoch": 1.1731391585760518,
444
+ "grad_norm": 0.2650909721851349,
445
+ "learning_rate": 1.7812022724419624e-05,
446
+ "loss": 0.13545321464538573,
447
+ "step": 1450
448
+ },
449
+ {
450
+ "epoch": 1.1933656957928802,
451
+ "grad_norm": 3.7782185077667236,
452
+ "learning_rate": 1.7700630448402125e-05,
453
+ "loss": 0.16887168884277343,
454
+ "step": 1475
455
+ },
456
+ {
457
+ "epoch": 1.2135922330097086,
458
+ "grad_norm": 0.5704866051673889,
459
+ "learning_rate": 1.758683947893406e-05,
460
+ "loss": 0.22910015106201173,
461
+ "step": 1500
462
+ },
463
+ {
464
+ "epoch": 1.2135922330097086,
465
+ "eval_accuracy": 0.9605861546235472,
466
+ "eval_f1": 0.974559686888454,
467
+ "eval_loss": 0.14868734776973724,
468
+ "eval_precision": 0.9589216944801027,
469
+ "eval_recall": 0.9907161803713528,
470
+ "eval_runtime": 34.2705,
471
+ "eval_samples_per_second": 57.746,
472
+ "eval_steps_per_second": 3.618,
473
+ "step": 1500
474
+ },
475
+ {
476
+ "epoch": 1.2338187702265373,
477
+ "grad_norm": 16.6047306060791,
478
+ "learning_rate": 1.747068526112022e-05,
479
+ "loss": 0.14131352424621582,
480
+ "step": 1525
481
+ },
482
+ {
483
+ "epoch": 1.2540453074433657,
484
+ "grad_norm": 5.992398262023926,
485
+ "learning_rate": 1.735220397620101e-05,
486
+ "loss": 0.15291913986206054,
487
+ "step": 1550
488
+ },
489
+ {
490
+ "epoch": 1.2742718446601942,
491
+ "grad_norm": 0.36782047152519226,
492
+ "learning_rate": 1.7231432530282246e-05,
493
+ "loss": 0.09922373771667481,
494
+ "step": 1575
495
+ },
496
+ {
497
+ "epoch": 1.2944983818770226,
498
+ "grad_norm": 1.3172669410705566,
499
+ "learning_rate": 1.7108408542839146e-05,
500
+ "loss": 0.1941922378540039,
501
+ "step": 1600
502
+ },
503
+ {
504
+ "epoch": 1.3147249190938513,
505
+ "grad_norm": 0.693942666053772,
506
+ "learning_rate": 1.698317033499813e-05,
507
+ "loss": 0.16940629959106446,
508
+ "step": 1625
509
+ },
510
+ {
511
+ "epoch": 1.3349514563106797,
512
+ "grad_norm": 0.1476801335811615,
513
+ "learning_rate": 1.6855756917600057e-05,
514
+ "loss": 0.12692631721496583,
515
+ "step": 1650
516
+ },
517
+ {
518
+ "epoch": 1.3551779935275081,
519
+ "grad_norm": 23.20606231689453,
520
+ "learning_rate": 1.6726207979048604e-05,
521
+ "loss": 0.25180328369140625,
522
+ "step": 1675
523
+ },
524
+ {
525
+ "epoch": 1.3754045307443366,
526
+ "grad_norm": 0.3847394287586212,
527
+ "learning_rate": 1.6594563872947613e-05,
528
+ "loss": 0.13337421417236328,
529
+ "step": 1700
530
+ },
531
+ {
532
+ "epoch": 1.395631067961165,
533
+ "grad_norm": 7.629310131072998,
534
+ "learning_rate": 1.6460865605531214e-05,
535
+ "loss": 0.17984333038330078,
536
+ "step": 1725
537
+ },
538
+ {
539
+ "epoch": 1.4158576051779934,
540
+ "grad_norm": 0.40370574593544006,
541
+ "learning_rate": 1.6325154822890663e-05,
542
+ "loss": 0.15392546653747557,
543
+ "step": 1750
544
+ },
545
+ {
546
+ "epoch": 1.436084142394822,
547
+ "grad_norm": 3.1435182094573975,
548
+ "learning_rate": 1.618747379800188e-05,
549
+ "loss": 0.1560378646850586,
550
+ "step": 1775
551
+ },
552
+ {
553
+ "epoch": 1.4563106796116505,
554
+ "grad_norm": 6.557313919067383,
555
+ "learning_rate": 1.6047865417557695e-05,
556
+ "loss": 0.23071422576904296,
557
+ "step": 1800
558
+ },
559
+ {
560
+ "epoch": 1.476537216828479,
561
+ "grad_norm": 4.851151943206787,
562
+ "learning_rate": 1.5906373168608952e-05,
563
+ "loss": 0.17919015884399414,
564
+ "step": 1825
565
+ },
566
+ {
567
+ "epoch": 1.4967637540453074,
568
+ "grad_norm": 6.987358093261719,
569
+ "learning_rate": 1.576304112501858e-05,
570
+ "loss": 0.22098312377929688,
571
+ "step": 1850
572
+ },
573
+ {
574
+ "epoch": 1.516990291262136,
575
+ "grad_norm": 4.638033390045166,
576
+ "learning_rate": 1.5617913933732892e-05,
577
+ "loss": 0.1659644889831543,
578
+ "step": 1875
579
+ },
580
+ {
581
+ "epoch": 1.5372168284789645,
582
+ "grad_norm": 3.2221922874450684,
583
+ "learning_rate": 1.5471036800874375e-05,
584
+ "loss": 0.18479549407958984,
585
+ "step": 1900
586
+ },
587
+ {
588
+ "epoch": 1.557443365695793,
589
+ "grad_norm": 0.3064526617527008,
590
+ "learning_rate": 1.5322455477660274e-05,
591
+ "loss": 0.18851667404174804,
592
+ "step": 1925
593
+ },
594
+ {
595
+ "epoch": 1.5776699029126213,
596
+ "grad_norm": 15.610395431518555,
597
+ "learning_rate": 1.5172216246151426e-05,
598
+ "loss": 0.23035451889038086,
599
+ "step": 1950
600
+ },
601
+ {
602
+ "epoch": 1.5978964401294498,
603
+ "grad_norm": 8.045638084411621,
604
+ "learning_rate": 1.50203659048357e-05,
605
+ "loss": 0.05388895988464355,
606
+ "step": 1975
607
+ },
608
+ {
609
+ "epoch": 1.6181229773462782,
610
+ "grad_norm": 12.035682678222656,
611
+ "learning_rate": 1.4866951754050605e-05,
612
+ "loss": 0.2584081268310547,
613
+ "step": 2000
614
+ },
615
+ {
616
+ "epoch": 1.6181229773462782,
617
+ "eval_accuracy": 0.9621020717534108,
618
+ "eval_f1": 0.9754661432777233,
619
+ "eval_loss": 0.145921990275383,
620
+ "eval_precision": 0.9625564880568108,
621
+ "eval_recall": 0.9887267904509284,
622
+ "eval_runtime": 34.2514,
623
+ "eval_samples_per_second": 57.779,
624
+ "eval_steps_per_second": 3.62,
625
+ "step": 2000
626
+ }
627
+ ],
628
+ "logging_steps": 25,
629
+ "max_steps": 4944,
630
+ "num_input_tokens_seen": 0,
631
+ "num_train_epochs": 4,
632
+ "save_steps": 500,
633
+ "stateful_callbacks": {
634
+ "EarlyStoppingCallback": {
635
+ "args": {
636
+ "early_stopping_patience": 2,
637
+ "early_stopping_threshold": 0.0
638
+ },
639
+ "attributes": {
640
+ "early_stopping_patience_counter": 0
641
+ }
642
+ },
643
+ "TrainerControl": {
644
+ "args": {
645
+ "should_epoch_stop": false,
646
+ "should_evaluate": false,
647
+ "should_log": false,
648
+ "should_save": true,
649
+ "should_training_stop": false
650
+ },
651
+ "attributes": {}
652
+ }
653
+ },
654
+ "total_flos": 8416396438855680.0,
655
+ "train_batch_size": 16,
656
+ "trial_name": null,
657
+ "trial_params": null
658
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6356dffa425669d6696f329ab57522ceda02ab7fadb057794c10a172cb56de1f
3
+ size 5201