rdpahalavan commited on
Commit
cc601ce
1 Parent(s): fba94c4

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Analysis",
13
+ "1": "Backdoor",
14
+ "2": "Bot",
15
+ "3": "DDoS",
16
+ "4": "DoS",
17
+ "5": "DoS GoldenEye",
18
+ "6": "DoS Hulk",
19
+ "7": "DoS SlowHTTPTest",
20
+ "8": "DoS Slowloris",
21
+ "9": "Exploits",
22
+ "10": "FTP Patator",
23
+ "11": "Fuzzers",
24
+ "12": "Generic",
25
+ "13": "Heartbleed",
26
+ "14": "Infiltration",
27
+ "15": "Normal",
28
+ "16": "Port Scan",
29
+ "17": "Reconnaissance",
30
+ "18": "SSH Patator",
31
+ "19": "Shellcode",
32
+ "20": "Web Attack - Brute Force",
33
+ "21": "Web Attack - SQL Injection",
34
+ "22": "Web Attack - XSS",
35
+ "23": "Worms"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "label2id": {
39
+ "Analysis": 0,
40
+ "Backdoor": 1,
41
+ "Bot": 2,
42
+ "DDoS": 3,
43
+ "DoS": 4,
44
+ "DoS GoldenEye": 5,
45
+ "DoS Hulk": 6,
46
+ "DoS SlowHTTPTest": 7,
47
+ "DoS Slowloris": 8,
48
+ "Exploits": 9,
49
+ "FTP Patator": 10,
50
+ "Fuzzers": 11,
51
+ "Generic": 12,
52
+ "Heartbleed": 13,
53
+ "Infiltration": 14,
54
+ "Normal": 15,
55
+ "Port Scan": 16,
56
+ "Reconnaissance": 17,
57
+ "SSH Patator": 18,
58
+ "Shellcode": 19,
59
+ "Web Attack - Brute Force": 20,
60
+ "Web Attack - SQL Injection": 21,
61
+ "Web Attack - XSS": 22,
62
+ "Worms": 23
63
+ },
64
+ "max_position_embeddings": 512,
65
+ "model_type": "distilbert",
66
+ "n_heads": 12,
67
+ "n_layers": 6,
68
+ "output_past": true,
69
+ "pad_token_id": 0,
70
+ "problem_type": "single_label_classification",
71
+ "qa_dropout": 0.1,
72
+ "seq_classif_dropout": 0.2,
73
+ "sinusoidal_pos_embds": false,
74
+ "tie_weights_": true,
75
+ "torch_dtype": "float32",
76
+ "transformers_version": "4.30.2",
77
+ "vocab_size": 28996
78
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059f43dc93a520109fc0fda4c8c925c36865da7351e3234b912d0d4ee9133cb6
3
+ size 526460805
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71b8ed2ff231901109c0de64f66590ec303ab198c2d07f66e8d476ed7f878723
3
+ size 263235309
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cbb33081bdb51ced60d6dc33a197664b22a258d9de6179c60d35d681ba7bb60
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e40d5859d19101a59ed51035b2517664c5fd520514c98b61746442b16d0432d7
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
trainer_state.json ADDED
@@ -0,0 +1,988 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 78750,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 4.968253968253969e-05,
13
+ "loss": 0.8671,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.936507936507937e-05,
19
+ "loss": 0.2133,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 4.904761904761905e-05,
25
+ "loss": 0.1414,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.08,
30
+ "learning_rate": 4.873015873015873e-05,
31
+ "loss": 0.1091,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.1,
36
+ "learning_rate": 4.841269841269841e-05,
37
+ "loss": 0.0924,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.11,
42
+ "learning_rate": 4.80952380952381e-05,
43
+ "loss": 0.0813,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.13,
48
+ "learning_rate": 4.7777777777777784e-05,
49
+ "loss": 0.0782,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.15,
54
+ "learning_rate": 4.746031746031746e-05,
55
+ "loss": 0.0707,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.17,
60
+ "learning_rate": 4.714285714285714e-05,
61
+ "loss": 0.0672,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.19,
66
+ "learning_rate": 4.682539682539683e-05,
67
+ "loss": 0.0624,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.21,
72
+ "learning_rate": 4.6507936507936515e-05,
73
+ "loss": 0.0595,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.23,
78
+ "learning_rate": 4.6190476190476194e-05,
79
+ "loss": 0.0584,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.25,
84
+ "learning_rate": 4.587301587301587e-05,
85
+ "loss": 0.0518,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.27,
90
+ "learning_rate": 4.555555555555556e-05,
91
+ "loss": 0.05,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.29,
96
+ "learning_rate": 4.523809523809524e-05,
97
+ "loss": 0.0498,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.3,
102
+ "learning_rate": 4.4920634920634924e-05,
103
+ "loss": 0.0451,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.32,
108
+ "learning_rate": 4.460317460317461e-05,
109
+ "loss": 0.0513,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.34,
114
+ "learning_rate": 4.428571428571428e-05,
115
+ "loss": 0.0516,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.36,
120
+ "learning_rate": 4.396825396825397e-05,
121
+ "loss": 0.0464,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.38,
126
+ "learning_rate": 4.3650793650793655e-05,
127
+ "loss": 0.0464,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.4,
132
+ "learning_rate": 4.3333333333333334e-05,
133
+ "loss": 0.0424,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.42,
138
+ "learning_rate": 4.301587301587302e-05,
139
+ "loss": 0.044,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.44,
144
+ "learning_rate": 4.26984126984127e-05,
145
+ "loss": 0.0441,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.46,
150
+ "learning_rate": 4.2380952380952385e-05,
151
+ "loss": 0.0382,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.48,
156
+ "learning_rate": 4.2063492063492065e-05,
157
+ "loss": 0.0428,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.5,
162
+ "learning_rate": 4.174603174603175e-05,
163
+ "loss": 0.038,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.51,
168
+ "learning_rate": 4.1428571428571437e-05,
169
+ "loss": 0.0416,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.53,
174
+ "learning_rate": 4.111111111111111e-05,
175
+ "loss": 0.0385,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.55,
180
+ "learning_rate": 4.0793650793650795e-05,
181
+ "loss": 0.0387,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.57,
186
+ "learning_rate": 4.047619047619048e-05,
187
+ "loss": 0.0392,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.59,
192
+ "learning_rate": 4.015873015873016e-05,
193
+ "loss": 0.0365,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.61,
198
+ "learning_rate": 3.984126984126984e-05,
199
+ "loss": 0.0409,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.63,
204
+ "learning_rate": 3.9523809523809526e-05,
205
+ "loss": 0.0385,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.65,
210
+ "learning_rate": 3.9206349206349205e-05,
211
+ "loss": 0.0361,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.67,
216
+ "learning_rate": 3.888888888888889e-05,
217
+ "loss": 0.0309,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.69,
222
+ "learning_rate": 3.857142857142858e-05,
223
+ "loss": 0.0348,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.7,
228
+ "learning_rate": 3.8253968253968256e-05,
229
+ "loss": 0.0321,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.72,
234
+ "learning_rate": 3.7936507936507935e-05,
235
+ "loss": 0.0331,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.74,
240
+ "learning_rate": 3.761904761904762e-05,
241
+ "loss": 0.0332,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.76,
246
+ "learning_rate": 3.730158730158731e-05,
247
+ "loss": 0.0304,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.78,
252
+ "learning_rate": 3.6984126984126986e-05,
253
+ "loss": 0.0348,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.8,
258
+ "learning_rate": 3.6666666666666666e-05,
259
+ "loss": 0.0328,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.82,
264
+ "learning_rate": 3.634920634920635e-05,
265
+ "loss": 0.0297,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.84,
270
+ "learning_rate": 3.603174603174603e-05,
271
+ "loss": 0.0316,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.86,
276
+ "learning_rate": 3.571428571428572e-05,
277
+ "loss": 0.0294,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.88,
282
+ "learning_rate": 3.53968253968254e-05,
283
+ "loss": 0.0311,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 0.9,
288
+ "learning_rate": 3.5079365079365075e-05,
289
+ "loss": 0.0281,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 0.91,
294
+ "learning_rate": 3.476190476190476e-05,
295
+ "loss": 0.0286,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 0.93,
300
+ "learning_rate": 3.444444444444445e-05,
301
+ "loss": 0.0316,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 0.95,
306
+ "learning_rate": 3.412698412698413e-05,
307
+ "loss": 0.0308,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 0.97,
312
+ "learning_rate": 3.380952380952381e-05,
313
+ "loss": 0.0263,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 0.99,
318
+ "learning_rate": 3.349206349206349e-05,
319
+ "loss": 0.0329,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 1.0,
324
+ "eval_accuracy": 0.9930055555555556,
325
+ "eval_f1-score": 0.9929596586748287,
326
+ "eval_loss": 0.024911481887102127,
327
+ "eval_runtime": 2756.559,
328
+ "eval_samples_per_second": 261.195,
329
+ "eval_steps_per_second": 2.041,
330
+ "step": 26250
331
+ },
332
+ {
333
+ "epoch": 1.01,
334
+ "learning_rate": 3.317460317460318e-05,
335
+ "loss": 0.0262,
336
+ "step": 26500
337
+ },
338
+ {
339
+ "epoch": 1.03,
340
+ "learning_rate": 3.285714285714286e-05,
341
+ "loss": 0.0259,
342
+ "step": 27000
343
+ },
344
+ {
345
+ "epoch": 1.05,
346
+ "learning_rate": 3.253968253968254e-05,
347
+ "loss": 0.0283,
348
+ "step": 27500
349
+ },
350
+ {
351
+ "epoch": 1.07,
352
+ "learning_rate": 3.222222222222223e-05,
353
+ "loss": 0.0264,
354
+ "step": 28000
355
+ },
356
+ {
357
+ "epoch": 1.09,
358
+ "learning_rate": 3.19047619047619e-05,
359
+ "loss": 0.0243,
360
+ "step": 28500
361
+ },
362
+ {
363
+ "epoch": 1.1,
364
+ "learning_rate": 3.158730158730159e-05,
365
+ "loss": 0.0275,
366
+ "step": 29000
367
+ },
368
+ {
369
+ "epoch": 1.12,
370
+ "learning_rate": 3.1269841269841274e-05,
371
+ "loss": 0.0284,
372
+ "step": 29500
373
+ },
374
+ {
375
+ "epoch": 1.14,
376
+ "learning_rate": 3.095238095238095e-05,
377
+ "loss": 0.0249,
378
+ "step": 30000
379
+ },
380
+ {
381
+ "epoch": 1.16,
382
+ "learning_rate": 3.063492063492064e-05,
383
+ "loss": 0.0267,
384
+ "step": 30500
385
+ },
386
+ {
387
+ "epoch": 1.18,
388
+ "learning_rate": 3.0317460317460318e-05,
389
+ "loss": 0.0283,
390
+ "step": 31000
391
+ },
392
+ {
393
+ "epoch": 1.2,
394
+ "learning_rate": 3e-05,
395
+ "loss": 0.0223,
396
+ "step": 31500
397
+ },
398
+ {
399
+ "epoch": 1.22,
400
+ "learning_rate": 2.9682539682539683e-05,
401
+ "loss": 0.0267,
402
+ "step": 32000
403
+ },
404
+ {
405
+ "epoch": 1.24,
406
+ "learning_rate": 2.9365079365079366e-05,
407
+ "loss": 0.0211,
408
+ "step": 32500
409
+ },
410
+ {
411
+ "epoch": 1.26,
412
+ "learning_rate": 2.9047619047619052e-05,
413
+ "loss": 0.0226,
414
+ "step": 33000
415
+ },
416
+ {
417
+ "epoch": 1.28,
418
+ "learning_rate": 2.8730158730158728e-05,
419
+ "loss": 0.0221,
420
+ "step": 33500
421
+ },
422
+ {
423
+ "epoch": 1.3,
424
+ "learning_rate": 2.8412698412698414e-05,
425
+ "loss": 0.0227,
426
+ "step": 34000
427
+ },
428
+ {
429
+ "epoch": 1.31,
430
+ "learning_rate": 2.8095238095238096e-05,
431
+ "loss": 0.0239,
432
+ "step": 34500
433
+ },
434
+ {
435
+ "epoch": 1.33,
436
+ "learning_rate": 2.777777777777778e-05,
437
+ "loss": 0.0254,
438
+ "step": 35000
439
+ },
440
+ {
441
+ "epoch": 1.35,
442
+ "learning_rate": 2.7460317460317465e-05,
443
+ "loss": 0.0236,
444
+ "step": 35500
445
+ },
446
+ {
447
+ "epoch": 1.37,
448
+ "learning_rate": 2.714285714285714e-05,
449
+ "loss": 0.0226,
450
+ "step": 36000
451
+ },
452
+ {
453
+ "epoch": 1.39,
454
+ "learning_rate": 2.6825396825396827e-05,
455
+ "loss": 0.021,
456
+ "step": 36500
457
+ },
458
+ {
459
+ "epoch": 1.41,
460
+ "learning_rate": 2.650793650793651e-05,
461
+ "loss": 0.0259,
462
+ "step": 37000
463
+ },
464
+ {
465
+ "epoch": 1.43,
466
+ "learning_rate": 2.6190476190476192e-05,
467
+ "loss": 0.0241,
468
+ "step": 37500
469
+ },
470
+ {
471
+ "epoch": 1.45,
472
+ "learning_rate": 2.5873015873015878e-05,
473
+ "loss": 0.0226,
474
+ "step": 38000
475
+ },
476
+ {
477
+ "epoch": 1.47,
478
+ "learning_rate": 2.5555555555555554e-05,
479
+ "loss": 0.023,
480
+ "step": 38500
481
+ },
482
+ {
483
+ "epoch": 1.49,
484
+ "learning_rate": 2.523809523809524e-05,
485
+ "loss": 0.0236,
486
+ "step": 39000
487
+ },
488
+ {
489
+ "epoch": 1.5,
490
+ "learning_rate": 2.4920634920634923e-05,
491
+ "loss": 0.0216,
492
+ "step": 39500
493
+ },
494
+ {
495
+ "epoch": 1.52,
496
+ "learning_rate": 2.4603174603174602e-05,
497
+ "loss": 0.0221,
498
+ "step": 40000
499
+ },
500
+ {
501
+ "epoch": 1.54,
502
+ "learning_rate": 2.4285714285714288e-05,
503
+ "loss": 0.0219,
504
+ "step": 40500
505
+ },
506
+ {
507
+ "epoch": 1.56,
508
+ "learning_rate": 2.396825396825397e-05,
509
+ "loss": 0.022,
510
+ "step": 41000
511
+ },
512
+ {
513
+ "epoch": 1.58,
514
+ "learning_rate": 2.365079365079365e-05,
515
+ "loss": 0.024,
516
+ "step": 41500
517
+ },
518
+ {
519
+ "epoch": 1.6,
520
+ "learning_rate": 2.3333333333333336e-05,
521
+ "loss": 0.021,
522
+ "step": 42000
523
+ },
524
+ {
525
+ "epoch": 1.62,
526
+ "learning_rate": 2.3015873015873015e-05,
527
+ "loss": 0.0219,
528
+ "step": 42500
529
+ },
530
+ {
531
+ "epoch": 1.64,
532
+ "learning_rate": 2.2698412698412698e-05,
533
+ "loss": 0.0199,
534
+ "step": 43000
535
+ },
536
+ {
537
+ "epoch": 1.66,
538
+ "learning_rate": 2.2380952380952384e-05,
539
+ "loss": 0.0208,
540
+ "step": 43500
541
+ },
542
+ {
543
+ "epoch": 1.68,
544
+ "learning_rate": 2.2063492063492063e-05,
545
+ "loss": 0.0198,
546
+ "step": 44000
547
+ },
548
+ {
549
+ "epoch": 1.7,
550
+ "learning_rate": 2.174603174603175e-05,
551
+ "loss": 0.0217,
552
+ "step": 44500
553
+ },
554
+ {
555
+ "epoch": 1.71,
556
+ "learning_rate": 2.1428571428571428e-05,
557
+ "loss": 0.0189,
558
+ "step": 45000
559
+ },
560
+ {
561
+ "epoch": 1.73,
562
+ "learning_rate": 2.111111111111111e-05,
563
+ "loss": 0.0199,
564
+ "step": 45500
565
+ },
566
+ {
567
+ "epoch": 1.75,
568
+ "learning_rate": 2.0793650793650797e-05,
569
+ "loss": 0.0208,
570
+ "step": 46000
571
+ },
572
+ {
573
+ "epoch": 1.77,
574
+ "learning_rate": 2.0476190476190476e-05,
575
+ "loss": 0.0196,
576
+ "step": 46500
577
+ },
578
+ {
579
+ "epoch": 1.79,
580
+ "learning_rate": 2.015873015873016e-05,
581
+ "loss": 0.0197,
582
+ "step": 47000
583
+ },
584
+ {
585
+ "epoch": 1.81,
586
+ "learning_rate": 1.984126984126984e-05,
587
+ "loss": 0.0197,
588
+ "step": 47500
589
+ },
590
+ {
591
+ "epoch": 1.83,
592
+ "learning_rate": 1.9523809523809524e-05,
593
+ "loss": 0.0184,
594
+ "step": 48000
595
+ },
596
+ {
597
+ "epoch": 1.85,
598
+ "learning_rate": 1.920634920634921e-05,
599
+ "loss": 0.0166,
600
+ "step": 48500
601
+ },
602
+ {
603
+ "epoch": 1.87,
604
+ "learning_rate": 1.888888888888889e-05,
605
+ "loss": 0.0217,
606
+ "step": 49000
607
+ },
608
+ {
609
+ "epoch": 1.89,
610
+ "learning_rate": 1.8571428571428572e-05,
611
+ "loss": 0.0189,
612
+ "step": 49500
613
+ },
614
+ {
615
+ "epoch": 1.9,
616
+ "learning_rate": 1.8253968253968254e-05,
617
+ "loss": 0.018,
618
+ "step": 50000
619
+ },
620
+ {
621
+ "epoch": 1.92,
622
+ "learning_rate": 1.7936507936507937e-05,
623
+ "loss": 0.0182,
624
+ "step": 50500
625
+ },
626
+ {
627
+ "epoch": 1.94,
628
+ "learning_rate": 1.761904761904762e-05,
629
+ "loss": 0.0176,
630
+ "step": 51000
631
+ },
632
+ {
633
+ "epoch": 1.96,
634
+ "learning_rate": 1.7301587301587302e-05,
635
+ "loss": 0.0163,
636
+ "step": 51500
637
+ },
638
+ {
639
+ "epoch": 1.98,
640
+ "learning_rate": 1.6984126984126985e-05,
641
+ "loss": 0.0174,
642
+ "step": 52000
643
+ },
644
+ {
645
+ "epoch": 2.0,
646
+ "learning_rate": 1.6666666666666667e-05,
647
+ "loss": 0.0168,
648
+ "step": 52500
649
+ },
650
+ {
651
+ "epoch": 2.0,
652
+ "eval_accuracy": 0.9950902777777778,
653
+ "eval_f1-score": 0.99507649644856,
654
+ "eval_loss": 0.01802189275622368,
655
+ "eval_runtime": 2757.205,
656
+ "eval_samples_per_second": 261.134,
657
+ "eval_steps_per_second": 2.04,
658
+ "step": 52500
659
+ },
660
+ {
661
+ "epoch": 2.02,
662
+ "learning_rate": 1.634920634920635e-05,
663
+ "loss": 0.0165,
664
+ "step": 53000
665
+ },
666
+ {
667
+ "epoch": 2.04,
668
+ "learning_rate": 1.6031746031746033e-05,
669
+ "loss": 0.0165,
670
+ "step": 53500
671
+ },
672
+ {
673
+ "epoch": 2.06,
674
+ "learning_rate": 1.5714285714285715e-05,
675
+ "loss": 0.0168,
676
+ "step": 54000
677
+ },
678
+ {
679
+ "epoch": 2.08,
680
+ "learning_rate": 1.5396825396825398e-05,
681
+ "loss": 0.0169,
682
+ "step": 54500
683
+ },
684
+ {
685
+ "epoch": 2.1,
686
+ "learning_rate": 1.5079365079365079e-05,
687
+ "loss": 0.0149,
688
+ "step": 55000
689
+ },
690
+ {
691
+ "epoch": 2.11,
692
+ "learning_rate": 1.4761904761904763e-05,
693
+ "loss": 0.0157,
694
+ "step": 55500
695
+ },
696
+ {
697
+ "epoch": 2.13,
698
+ "learning_rate": 1.4444444444444444e-05,
699
+ "loss": 0.0146,
700
+ "step": 56000
701
+ },
702
+ {
703
+ "epoch": 2.15,
704
+ "learning_rate": 1.4126984126984127e-05,
705
+ "loss": 0.0139,
706
+ "step": 56500
707
+ },
708
+ {
709
+ "epoch": 2.17,
710
+ "learning_rate": 1.3809523809523811e-05,
711
+ "loss": 0.0158,
712
+ "step": 57000
713
+ },
714
+ {
715
+ "epoch": 2.19,
716
+ "learning_rate": 1.3492063492063492e-05,
717
+ "loss": 0.0148,
718
+ "step": 57500
719
+ },
720
+ {
721
+ "epoch": 2.21,
722
+ "learning_rate": 1.3174603174603176e-05,
723
+ "loss": 0.0153,
724
+ "step": 58000
725
+ },
726
+ {
727
+ "epoch": 2.23,
728
+ "learning_rate": 1.2857142857142857e-05,
729
+ "loss": 0.0154,
730
+ "step": 58500
731
+ },
732
+ {
733
+ "epoch": 2.25,
734
+ "learning_rate": 1.253968253968254e-05,
735
+ "loss": 0.016,
736
+ "step": 59000
737
+ },
738
+ {
739
+ "epoch": 2.27,
740
+ "learning_rate": 1.2222222222222222e-05,
741
+ "loss": 0.0146,
742
+ "step": 59500
743
+ },
744
+ {
745
+ "epoch": 2.29,
746
+ "learning_rate": 1.1904761904761905e-05,
747
+ "loss": 0.0162,
748
+ "step": 60000
749
+ },
750
+ {
751
+ "epoch": 2.3,
752
+ "learning_rate": 1.1587301587301588e-05,
753
+ "loss": 0.0156,
754
+ "step": 60500
755
+ },
756
+ {
757
+ "epoch": 2.32,
758
+ "learning_rate": 1.126984126984127e-05,
759
+ "loss": 0.0151,
760
+ "step": 61000
761
+ },
762
+ {
763
+ "epoch": 2.34,
764
+ "learning_rate": 1.0952380952380953e-05,
765
+ "loss": 0.0138,
766
+ "step": 61500
767
+ },
768
+ {
769
+ "epoch": 2.36,
770
+ "learning_rate": 1.0634920634920636e-05,
771
+ "loss": 0.0144,
772
+ "step": 62000
773
+ },
774
+ {
775
+ "epoch": 2.38,
776
+ "learning_rate": 1.0317460317460318e-05,
777
+ "loss": 0.0151,
778
+ "step": 62500
779
+ },
780
+ {
781
+ "epoch": 2.4,
782
+ "learning_rate": 1e-05,
783
+ "loss": 0.0163,
784
+ "step": 63000
785
+ },
786
+ {
787
+ "epoch": 2.42,
788
+ "learning_rate": 9.682539682539683e-06,
789
+ "loss": 0.0131,
790
+ "step": 63500
791
+ },
792
+ {
793
+ "epoch": 2.44,
794
+ "learning_rate": 9.365079365079366e-06,
795
+ "loss": 0.015,
796
+ "step": 64000
797
+ },
798
+ {
799
+ "epoch": 2.46,
800
+ "learning_rate": 9.047619047619047e-06,
801
+ "loss": 0.0142,
802
+ "step": 64500
803
+ },
804
+ {
805
+ "epoch": 2.48,
806
+ "learning_rate": 8.73015873015873e-06,
807
+ "loss": 0.0145,
808
+ "step": 65000
809
+ },
810
+ {
811
+ "epoch": 2.5,
812
+ "learning_rate": 8.412698412698414e-06,
813
+ "loss": 0.0147,
814
+ "step": 65500
815
+ },
816
+ {
817
+ "epoch": 2.51,
818
+ "learning_rate": 8.095238095238097e-06,
819
+ "loss": 0.0163,
820
+ "step": 66000
821
+ },
822
+ {
823
+ "epoch": 2.53,
824
+ "learning_rate": 7.777777777777777e-06,
825
+ "loss": 0.0138,
826
+ "step": 66500
827
+ },
828
+ {
829
+ "epoch": 2.55,
830
+ "learning_rate": 7.460317460317461e-06,
831
+ "loss": 0.0145,
832
+ "step": 67000
833
+ },
834
+ {
835
+ "epoch": 2.57,
836
+ "learning_rate": 7.142857142857143e-06,
837
+ "loss": 0.0135,
838
+ "step": 67500
839
+ },
840
+ {
841
+ "epoch": 2.59,
842
+ "learning_rate": 6.825396825396825e-06,
843
+ "loss": 0.0141,
844
+ "step": 68000
845
+ },
846
+ {
847
+ "epoch": 2.61,
848
+ "learning_rate": 6.507936507936509e-06,
849
+ "loss": 0.013,
850
+ "step": 68500
851
+ },
852
+ {
853
+ "epoch": 2.63,
854
+ "learning_rate": 6.190476190476191e-06,
855
+ "loss": 0.0125,
856
+ "step": 69000
857
+ },
858
+ {
859
+ "epoch": 2.65,
860
+ "learning_rate": 5.873015873015873e-06,
861
+ "loss": 0.0116,
862
+ "step": 69500
863
+ },
864
+ {
865
+ "epoch": 2.67,
866
+ "learning_rate": 5.555555555555556e-06,
867
+ "loss": 0.0165,
868
+ "step": 70000
869
+ },
870
+ {
871
+ "epoch": 2.69,
872
+ "learning_rate": 5.2380952380952384e-06,
873
+ "loss": 0.0135,
874
+ "step": 70500
875
+ },
876
+ {
877
+ "epoch": 2.7,
878
+ "learning_rate": 4.920634920634921e-06,
879
+ "loss": 0.012,
880
+ "step": 71000
881
+ },
882
+ {
883
+ "epoch": 2.72,
884
+ "learning_rate": 4.603174603174604e-06,
885
+ "loss": 0.0115,
886
+ "step": 71500
887
+ },
888
+ {
889
+ "epoch": 2.74,
890
+ "learning_rate": 4.285714285714286e-06,
891
+ "loss": 0.0137,
892
+ "step": 72000
893
+ },
894
+ {
895
+ "epoch": 2.76,
896
+ "learning_rate": 3.968253968253968e-06,
897
+ "loss": 0.0141,
898
+ "step": 72500
899
+ },
900
+ {
901
+ "epoch": 2.78,
902
+ "learning_rate": 3.650793650793651e-06,
903
+ "loss": 0.0112,
904
+ "step": 73000
905
+ },
906
+ {
907
+ "epoch": 2.8,
908
+ "learning_rate": 3.3333333333333333e-06,
909
+ "loss": 0.014,
910
+ "step": 73500
911
+ },
912
+ {
913
+ "epoch": 2.82,
914
+ "learning_rate": 3.015873015873016e-06,
915
+ "loss": 0.0123,
916
+ "step": 74000
917
+ },
918
+ {
919
+ "epoch": 2.84,
920
+ "learning_rate": 2.6984126984126986e-06,
921
+ "loss": 0.0151,
922
+ "step": 74500
923
+ },
924
+ {
925
+ "epoch": 2.86,
926
+ "learning_rate": 2.3809523809523808e-06,
927
+ "loss": 0.0141,
928
+ "step": 75000
929
+ },
930
+ {
931
+ "epoch": 2.88,
932
+ "learning_rate": 2.0634920634920634e-06,
933
+ "loss": 0.0134,
934
+ "step": 75500
935
+ },
936
+ {
937
+ "epoch": 2.9,
938
+ "learning_rate": 1.7460317460317462e-06,
939
+ "loss": 0.0124,
940
+ "step": 76000
941
+ },
942
+ {
943
+ "epoch": 2.91,
944
+ "learning_rate": 1.4285714285714286e-06,
945
+ "loss": 0.011,
946
+ "step": 76500
947
+ },
948
+ {
949
+ "epoch": 2.93,
950
+ "learning_rate": 1.1111111111111112e-06,
951
+ "loss": 0.0113,
952
+ "step": 77000
953
+ },
954
+ {
955
+ "epoch": 2.95,
956
+ "learning_rate": 7.936507936507937e-07,
957
+ "loss": 0.0123,
958
+ "step": 77500
959
+ },
960
+ {
961
+ "epoch": 2.97,
962
+ "learning_rate": 4.761904761904763e-07,
963
+ "loss": 0.0119,
964
+ "step": 78000
965
+ },
966
+ {
967
+ "epoch": 2.99,
968
+ "learning_rate": 1.5873015873015874e-07,
969
+ "loss": 0.011,
970
+ "step": 78500
971
+ },
972
+ {
973
+ "epoch": 3.0,
974
+ "eval_accuracy": 0.9963097222222222,
975
+ "eval_f1-score": 0.9963028995135582,
976
+ "eval_loss": 0.013718551024794579,
977
+ "eval_runtime": 2760.1832,
978
+ "eval_samples_per_second": 260.852,
979
+ "eval_steps_per_second": 2.038,
980
+ "step": 78750
981
+ }
982
+ ],
983
+ "max_steps": 78750,
984
+ "num_train_epochs": 3,
985
+ "total_flos": 6.6789762859008e+17,
986
+ "trial_name": null,
987
+ "trial_params": null
988
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4945601e29db7c27de52e89393ae863eea27d42f9d451f710aa01624499eb09c
3
+ size 3899
vocab.txt ADDED
The diff for this file is too large to render. See raw diff