andreas122001 commited on
Commit
3220104
1 Parent(s): 88c5cfc

Upload 12 files

Browse files
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "human-produced",
15
+ "1": "machine-generated"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "human-produced": 0,
21
+ "machine-generated": 1
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "roberta",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.26.1",
33
+ "type_vocab_size": 1,
34
+ "use_cache": true,
35
+ "vocab_size": 50265
36
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62ed5770521a85f113fdd0774eb021c956dc82eddfc6535cdfe8ffbb1a5ad62d
3
+ size 997344965
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:859544efbbdf6101d9c5942ddaa5a5f354d1304e8f77b2494857c039d83d0e41
3
+ size 498662069
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3abc20d2e5160012eeb9a7bc55135c50ee206fb00ba7f19f6f18aa81880e752f
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19c575370b6179b490f435df9c74d0ea7aabd16f264cf932690c39af9fca6ebb
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "roberta-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
trainer_state.json ADDED
@@ -0,0 +1,922 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 1750,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 4.9971428571428576e-05,
13
+ "loss": 0.6862,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 4.9e-05,
19
+ "loss": 0.4775,
20
+ "step": 35
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "eval_accuracy": 0.857,
25
+ "eval_f1": 0.8737864077669902,
26
+ "eval_loss": 0.40033745765686035,
27
+ "eval_precision": 0.7819905213270142,
28
+ "eval_recall": 0.99,
29
+ "eval_runtime": 39.2752,
30
+ "eval_samples_per_second": 76.384,
31
+ "eval_steps_per_second": 9.548,
32
+ "step": 35
33
+ },
34
+ {
35
+ "epoch": 0.04,
36
+ "learning_rate": 4.8e-05,
37
+ "loss": 0.3051,
38
+ "step": 70
39
+ },
40
+ {
41
+ "epoch": 0.04,
42
+ "eval_accuracy": 0.8823333333333333,
43
+ "eval_f1": 0.8942163620017981,
44
+ "eval_loss": 0.6440998911857605,
45
+ "eval_precision": 0.8121937942297224,
46
+ "eval_recall": 0.9946666666666667,
47
+ "eval_runtime": 37.422,
48
+ "eval_samples_per_second": 80.167,
49
+ "eval_steps_per_second": 10.021,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.06,
54
+ "learning_rate": 4.7e-05,
55
+ "loss": 0.492,
56
+ "step": 105
57
+ },
58
+ {
59
+ "epoch": 0.06,
60
+ "eval_accuracy": 0.8696666666666667,
61
+ "eval_f1": 0.8846947803007963,
62
+ "eval_loss": 0.6633870601654053,
63
+ "eval_precision": 0.7932310946589106,
64
+ "eval_recall": 1.0,
65
+ "eval_runtime": 36.0985,
66
+ "eval_samples_per_second": 83.106,
67
+ "eval_steps_per_second": 10.388,
68
+ "step": 105
69
+ },
70
+ {
71
+ "epoch": 0.08,
72
+ "learning_rate": 4.600000000000001e-05,
73
+ "loss": 0.2019,
74
+ "step": 140
75
+ },
76
+ {
77
+ "epoch": 0.08,
78
+ "eval_accuracy": 0.9256666666666666,
79
+ "eval_f1": 0.9306376360808709,
80
+ "eval_loss": 0.46288976073265076,
81
+ "eval_precision": 0.8723032069970845,
82
+ "eval_recall": 0.9973333333333333,
83
+ "eval_runtime": 36.0593,
84
+ "eval_samples_per_second": 83.196,
85
+ "eval_steps_per_second": 10.4,
86
+ "step": 140
87
+ },
88
+ {
89
+ "epoch": 0.1,
90
+ "learning_rate": 4.5e-05,
91
+ "loss": 0.2224,
92
+ "step": 175
93
+ },
94
+ {
95
+ "epoch": 0.1,
96
+ "eval_accuracy": 0.9183333333333333,
97
+ "eval_f1": 0.9243126351560087,
98
+ "eval_loss": 0.34658756852149963,
99
+ "eval_precision": 0.8612550374208405,
100
+ "eval_recall": 0.9973333333333333,
101
+ "eval_runtime": 36.7878,
102
+ "eval_samples_per_second": 81.549,
103
+ "eval_steps_per_second": 10.194,
104
+ "step": 175
105
+ },
106
+ {
107
+ "epoch": 0.12,
108
+ "learning_rate": 4.4000000000000006e-05,
109
+ "loss": 0.1034,
110
+ "step": 210
111
+ },
112
+ {
113
+ "epoch": 0.12,
114
+ "eval_accuracy": 0.9716666666666667,
115
+ "eval_f1": 0.9722312969617772,
116
+ "eval_loss": 0.12845683097839355,
117
+ "eval_precision": 0.9532351057014734,
118
+ "eval_recall": 0.992,
119
+ "eval_runtime": 37.1714,
120
+ "eval_samples_per_second": 80.707,
121
+ "eval_steps_per_second": 10.088,
122
+ "step": 210
123
+ },
124
+ {
125
+ "epoch": 0.14,
126
+ "learning_rate": 4.3e-05,
127
+ "loss": 0.0783,
128
+ "step": 245
129
+ },
130
+ {
131
+ "epoch": 0.14,
132
+ "eval_accuracy": 0.98,
133
+ "eval_f1": 0.9803149606299214,
134
+ "eval_loss": 0.09441035240888596,
135
+ "eval_precision": 0.9651162790697675,
136
+ "eval_recall": 0.996,
137
+ "eval_runtime": 37.1535,
138
+ "eval_samples_per_second": 80.746,
139
+ "eval_steps_per_second": 10.093,
140
+ "step": 245
141
+ },
142
+ {
143
+ "epoch": 0.16,
144
+ "learning_rate": 4.2e-05,
145
+ "loss": 0.2329,
146
+ "step": 280
147
+ },
148
+ {
149
+ "epoch": 0.16,
150
+ "eval_accuracy": 0.91,
151
+ "eval_f1": 0.9173806609547123,
152
+ "eval_loss": 0.33303627371788025,
153
+ "eval_precision": 0.8478506787330317,
154
+ "eval_recall": 0.9993333333333333,
155
+ "eval_runtime": 37.5239,
156
+ "eval_samples_per_second": 79.949,
157
+ "eval_steps_per_second": 9.994,
158
+ "step": 280
159
+ },
160
+ {
161
+ "epoch": 0.18,
162
+ "learning_rate": 4.1e-05,
163
+ "loss": 0.0883,
164
+ "step": 315
165
+ },
166
+ {
167
+ "epoch": 0.18,
168
+ "eval_accuracy": 0.9436666666666667,
169
+ "eval_f1": 0.946603475513428,
170
+ "eval_loss": 0.32765254378318787,
171
+ "eval_precision": 0.8996996996996997,
172
+ "eval_recall": 0.9986666666666667,
173
+ "eval_runtime": 36.0524,
174
+ "eval_samples_per_second": 83.212,
175
+ "eval_steps_per_second": 10.402,
176
+ "step": 315
177
+ },
178
+ {
179
+ "epoch": 0.2,
180
+ "learning_rate": 4e-05,
181
+ "loss": 0.1818,
182
+ "step": 350
183
+ },
184
+ {
185
+ "epoch": 0.2,
186
+ "eval_accuracy": 0.9783333333333334,
187
+ "eval_f1": 0.9786535303776683,
188
+ "eval_loss": 0.06494130194187164,
189
+ "eval_precision": 0.9644012944983819,
190
+ "eval_recall": 0.9933333333333333,
191
+ "eval_runtime": 37.1476,
192
+ "eval_samples_per_second": 80.759,
193
+ "eval_steps_per_second": 10.095,
194
+ "step": 350
195
+ },
196
+ {
197
+ "epoch": 0.22,
198
+ "learning_rate": 3.9000000000000006e-05,
199
+ "loss": 0.1854,
200
+ "step": 385
201
+ },
202
+ {
203
+ "epoch": 0.22,
204
+ "eval_accuracy": 0.9913333333333333,
205
+ "eval_f1": 0.991315965263861,
206
+ "eval_loss": 0.04114186391234398,
207
+ "eval_precision": 0.9933065595716198,
208
+ "eval_recall": 0.9893333333333333,
209
+ "eval_runtime": 37.1144,
210
+ "eval_samples_per_second": 80.831,
211
+ "eval_steps_per_second": 10.104,
212
+ "step": 385
213
+ },
214
+ {
215
+ "epoch": 0.24,
216
+ "learning_rate": 3.8e-05,
217
+ "loss": 0.085,
218
+ "step": 420
219
+ },
220
+ {
221
+ "epoch": 0.24,
222
+ "eval_accuracy": 0.988,
223
+ "eval_f1": 0.9879437374413931,
224
+ "eval_loss": 0.05784890055656433,
225
+ "eval_precision": 0.9925975773889637,
226
+ "eval_recall": 0.9833333333333333,
227
+ "eval_runtime": 35.9925,
228
+ "eval_samples_per_second": 83.351,
229
+ "eval_steps_per_second": 10.419,
230
+ "step": 420
231
+ },
232
+ {
233
+ "epoch": 0.26,
234
+ "learning_rate": 3.7e-05,
235
+ "loss": 0.1281,
236
+ "step": 455
237
+ },
238
+ {
239
+ "epoch": 0.26,
240
+ "eval_accuracy": 0.963,
241
+ "eval_f1": 0.9642281662906864,
242
+ "eval_loss": 0.23219378292560577,
243
+ "eval_precision": 0.9332501559575795,
244
+ "eval_recall": 0.9973333333333333,
245
+ "eval_runtime": 36.1167,
246
+ "eval_samples_per_second": 83.064,
247
+ "eval_steps_per_second": 10.383,
248
+ "step": 455
249
+ },
250
+ {
251
+ "epoch": 0.28,
252
+ "learning_rate": 3.6e-05,
253
+ "loss": 0.155,
254
+ "step": 490
255
+ },
256
+ {
257
+ "epoch": 0.28,
258
+ "eval_accuracy": 0.9793333333333333,
259
+ "eval_f1": 0.9795783926218709,
260
+ "eval_loss": 0.0876053124666214,
261
+ "eval_precision": 0.9680989583333334,
262
+ "eval_recall": 0.9913333333333333,
263
+ "eval_runtime": 37.4935,
264
+ "eval_samples_per_second": 80.014,
265
+ "eval_steps_per_second": 10.002,
266
+ "step": 490
267
+ },
268
+ {
269
+ "epoch": 0.3,
270
+ "learning_rate": 3.5e-05,
271
+ "loss": 0.1536,
272
+ "step": 525
273
+ },
274
+ {
275
+ "epoch": 0.3,
276
+ "eval_accuracy": 0.98,
277
+ "eval_f1": 0.98022412656559,
278
+ "eval_loss": 0.08141922205686569,
279
+ "eval_precision": 0.969361147327249,
280
+ "eval_recall": 0.9913333333333333,
281
+ "eval_runtime": 36.207,
282
+ "eval_samples_per_second": 82.857,
283
+ "eval_steps_per_second": 10.357,
284
+ "step": 525
285
+ },
286
+ {
287
+ "epoch": 0.32,
288
+ "learning_rate": 3.4000000000000007e-05,
289
+ "loss": 0.0686,
290
+ "step": 560
291
+ },
292
+ {
293
+ "epoch": 0.32,
294
+ "eval_accuracy": 0.8446666666666667,
295
+ "eval_f1": 0.8654734411085451,
296
+ "eval_loss": 0.7843948602676392,
297
+ "eval_precision": 0.7632382892057027,
298
+ "eval_recall": 0.9993333333333333,
299
+ "eval_runtime": 37.456,
300
+ "eval_samples_per_second": 80.094,
301
+ "eval_steps_per_second": 10.012,
302
+ "step": 560
303
+ },
304
+ {
305
+ "epoch": 0.34,
306
+ "learning_rate": 3.3e-05,
307
+ "loss": 0.0569,
308
+ "step": 595
309
+ },
310
+ {
311
+ "epoch": 0.34,
312
+ "eval_accuracy": 0.99,
313
+ "eval_f1": 0.99,
314
+ "eval_loss": 0.04974000155925751,
315
+ "eval_precision": 0.99,
316
+ "eval_recall": 0.99,
317
+ "eval_runtime": 36.1808,
318
+ "eval_samples_per_second": 82.917,
319
+ "eval_steps_per_second": 10.365,
320
+ "step": 595
321
+ },
322
+ {
323
+ "epoch": 0.36,
324
+ "learning_rate": 3.2000000000000005e-05,
325
+ "loss": 0.0951,
326
+ "step": 630
327
+ },
328
+ {
329
+ "epoch": 0.36,
330
+ "eval_accuracy": 0.9733333333333334,
331
+ "eval_f1": 0.9739243807040417,
332
+ "eval_loss": 0.14421893656253815,
333
+ "eval_precision": 0.9528061224489796,
334
+ "eval_recall": 0.996,
335
+ "eval_runtime": 36.1151,
336
+ "eval_samples_per_second": 83.068,
337
+ "eval_steps_per_second": 10.383,
338
+ "step": 630
339
+ },
340
+ {
341
+ "epoch": 0.38,
342
+ "learning_rate": 3.1e-05,
343
+ "loss": 0.0434,
344
+ "step": 665
345
+ },
346
+ {
347
+ "epoch": 0.38,
348
+ "eval_accuracy": 0.9026666666666666,
349
+ "eval_f1": 0.9111922141119222,
350
+ "eval_loss": 0.6636046767234802,
351
+ "eval_precision": 0.8378076062639821,
352
+ "eval_recall": 0.9986666666666667,
353
+ "eval_runtime": 37.4412,
354
+ "eval_samples_per_second": 80.126,
355
+ "eval_steps_per_second": 10.016,
356
+ "step": 665
357
+ },
358
+ {
359
+ "epoch": 0.4,
360
+ "learning_rate": 3e-05,
361
+ "loss": 0.1023,
362
+ "step": 700
363
+ },
364
+ {
365
+ "epoch": 0.4,
366
+ "eval_accuracy": 0.9653333333333334,
367
+ "eval_f1": 0.9664082687338501,
368
+ "eval_loss": 0.17706581950187683,
369
+ "eval_precision": 0.9373433583959899,
370
+ "eval_recall": 0.9973333333333333,
371
+ "eval_runtime": 36.7932,
372
+ "eval_samples_per_second": 81.537,
373
+ "eval_steps_per_second": 10.192,
374
+ "step": 700
375
+ },
376
+ {
377
+ "epoch": 0.42,
378
+ "learning_rate": 2.9e-05,
379
+ "loss": 0.0619,
380
+ "step": 735
381
+ },
382
+ {
383
+ "epoch": 0.42,
384
+ "eval_accuracy": 0.9893333333333333,
385
+ "eval_f1": 0.9893617021276595,
386
+ "eval_loss": 0.051007628440856934,
387
+ "eval_precision": 0.986737400530504,
388
+ "eval_recall": 0.992,
389
+ "eval_runtime": 36.0289,
390
+ "eval_samples_per_second": 83.267,
391
+ "eval_steps_per_second": 10.408,
392
+ "step": 735
393
+ },
394
+ {
395
+ "epoch": 0.44,
396
+ "learning_rate": 2.8000000000000003e-05,
397
+ "loss": 0.0367,
398
+ "step": 770
399
+ },
400
+ {
401
+ "epoch": 0.44,
402
+ "eval_accuracy": 0.9913333333333333,
403
+ "eval_f1": 0.9913275517011341,
404
+ "eval_loss": 0.04358353838324547,
405
+ "eval_precision": 0.9919893190921228,
406
+ "eval_recall": 0.9906666666666667,
407
+ "eval_runtime": 36.0918,
408
+ "eval_samples_per_second": 83.121,
409
+ "eval_steps_per_second": 10.39,
410
+ "step": 770
411
+ },
412
+ {
413
+ "epoch": 0.46,
414
+ "learning_rate": 2.7000000000000002e-05,
415
+ "loss": 0.0011,
416
+ "step": 805
417
+ },
418
+ {
419
+ "epoch": 0.46,
420
+ "eval_accuracy": 0.9896666666666667,
421
+ "eval_f1": 0.9896355733868272,
422
+ "eval_loss": 0.06585267186164856,
423
+ "eval_precision": 0.9926224010731053,
424
+ "eval_recall": 0.9866666666666667,
425
+ "eval_runtime": 36.0308,
426
+ "eval_samples_per_second": 83.262,
427
+ "eval_steps_per_second": 10.408,
428
+ "step": 805
429
+ },
430
+ {
431
+ "epoch": 0.48,
432
+ "learning_rate": 2.6000000000000002e-05,
433
+ "loss": 0.0241,
434
+ "step": 840
435
+ },
436
+ {
437
+ "epoch": 0.48,
438
+ "eval_accuracy": 0.976,
439
+ "eval_f1": 0.9764705882352941,
440
+ "eval_loss": 0.1684291660785675,
441
+ "eval_precision": 0.9576923076923077,
442
+ "eval_recall": 0.996,
443
+ "eval_runtime": 37.039,
444
+ "eval_samples_per_second": 80.996,
445
+ "eval_steps_per_second": 10.124,
446
+ "step": 840
447
+ },
448
+ {
449
+ "epoch": 0.5,
450
+ "learning_rate": 2.5e-05,
451
+ "loss": 0.1195,
452
+ "step": 875
453
+ },
454
+ {
455
+ "epoch": 0.5,
456
+ "eval_accuracy": 0.9793333333333333,
457
+ "eval_f1": 0.9797120418848168,
458
+ "eval_loss": 0.12230364978313446,
459
+ "eval_precision": 0.962082262210797,
460
+ "eval_recall": 0.998,
461
+ "eval_runtime": 36.0431,
462
+ "eval_samples_per_second": 83.234,
463
+ "eval_steps_per_second": 10.404,
464
+ "step": 875
465
+ },
466
+ {
467
+ "epoch": 0.52,
468
+ "learning_rate": 2.4e-05,
469
+ "loss": 0.0557,
470
+ "step": 910
471
+ },
472
+ {
473
+ "epoch": 0.52,
474
+ "eval_accuracy": 0.9916666666666667,
475
+ "eval_f1": 0.9916805324459235,
476
+ "eval_loss": 0.04335600137710571,
477
+ "eval_precision": 0.9900332225913622,
478
+ "eval_recall": 0.9933333333333333,
479
+ "eval_runtime": 36.1241,
480
+ "eval_samples_per_second": 83.047,
481
+ "eval_steps_per_second": 10.381,
482
+ "step": 910
483
+ },
484
+ {
485
+ "epoch": 0.54,
486
+ "learning_rate": 2.3000000000000003e-05,
487
+ "loss": 0.054,
488
+ "step": 945
489
+ },
490
+ {
491
+ "epoch": 0.54,
492
+ "eval_accuracy": 0.9913333333333333,
493
+ "eval_f1": 0.9913563829787235,
494
+ "eval_loss": 0.03961500525474548,
495
+ "eval_precision": 0.9887267904509284,
496
+ "eval_recall": 0.994,
497
+ "eval_runtime": 36.0623,
498
+ "eval_samples_per_second": 83.189,
499
+ "eval_steps_per_second": 10.399,
500
+ "step": 945
501
+ },
502
+ {
503
+ "epoch": 0.56,
504
+ "learning_rate": 2.2000000000000003e-05,
505
+ "loss": 0.0345,
506
+ "step": 980
507
+ },
508
+ {
509
+ "epoch": 0.56,
510
+ "eval_accuracy": 0.991,
511
+ "eval_f1": 0.9909426366990942,
512
+ "eval_loss": 0.05297405645251274,
513
+ "eval_precision": 0.9972991222147198,
514
+ "eval_recall": 0.9846666666666667,
515
+ "eval_runtime": 36.0625,
516
+ "eval_samples_per_second": 83.189,
517
+ "eval_steps_per_second": 10.399,
518
+ "step": 980
519
+ },
520
+ {
521
+ "epoch": 0.58,
522
+ "learning_rate": 2.1e-05,
523
+ "loss": 0.0582,
524
+ "step": 1015
525
+ },
526
+ {
527
+ "epoch": 0.58,
528
+ "eval_accuracy": 0.9636666666666667,
529
+ "eval_f1": 0.9648953301127215,
530
+ "eval_loss": 0.23049569129943848,
531
+ "eval_precision": 0.9333333333333333,
532
+ "eval_recall": 0.9986666666666667,
533
+ "eval_runtime": 36.0114,
534
+ "eval_samples_per_second": 83.307,
535
+ "eval_steps_per_second": 10.413,
536
+ "step": 1015
537
+ },
538
+ {
539
+ "epoch": 0.6,
540
+ "learning_rate": 2e-05,
541
+ "loss": 0.0451,
542
+ "step": 1050
543
+ },
544
+ {
545
+ "epoch": 0.6,
546
+ "eval_accuracy": 0.954,
547
+ "eval_f1": 0.9559948979591837,
548
+ "eval_loss": 0.2961997985839844,
549
+ "eval_precision": 0.9162591687041565,
550
+ "eval_recall": 0.9993333333333333,
551
+ "eval_runtime": 36.0251,
552
+ "eval_samples_per_second": 83.275,
553
+ "eval_steps_per_second": 10.409,
554
+ "step": 1050
555
+ },
556
+ {
557
+ "epoch": 0.62,
558
+ "learning_rate": 1.9e-05,
559
+ "loss": 0.134,
560
+ "step": 1085
561
+ },
562
+ {
563
+ "epoch": 0.62,
564
+ "eval_accuracy": 0.9836666666666667,
565
+ "eval_f1": 0.9839080459770116,
566
+ "eval_loss": 0.08320324122905731,
567
+ "eval_precision": 0.96957928802589,
568
+ "eval_recall": 0.9986666666666667,
569
+ "eval_runtime": 36.0675,
570
+ "eval_samples_per_second": 83.177,
571
+ "eval_steps_per_second": 10.397,
572
+ "step": 1085
573
+ },
574
+ {
575
+ "epoch": 0.64,
576
+ "learning_rate": 1.8e-05,
577
+ "loss": 0.0852,
578
+ "step": 1120
579
+ },
580
+ {
581
+ "epoch": 0.64,
582
+ "eval_accuracy": 0.987,
583
+ "eval_f1": 0.9871329594193335,
584
+ "eval_loss": 0.06261658668518066,
585
+ "eval_precision": 0.977139124755062,
586
+ "eval_recall": 0.9973333333333333,
587
+ "eval_runtime": 36.0739,
588
+ "eval_samples_per_second": 83.163,
589
+ "eval_steps_per_second": 10.395,
590
+ "step": 1120
591
+ },
592
+ {
593
+ "epoch": 0.66,
594
+ "learning_rate": 1.7000000000000003e-05,
595
+ "loss": 0.1262,
596
+ "step": 1155
597
+ },
598
+ {
599
+ "epoch": 0.66,
600
+ "eval_accuracy": 0.9516666666666667,
601
+ "eval_f1": 0.9538363578478192,
602
+ "eval_loss": 0.21791885793209076,
603
+ "eval_precision": 0.9128580134064594,
604
+ "eval_recall": 0.9986666666666667,
605
+ "eval_runtime": 36.0083,
606
+ "eval_samples_per_second": 83.314,
607
+ "eval_steps_per_second": 10.414,
608
+ "step": 1155
609
+ },
610
+ {
611
+ "epoch": 0.68,
612
+ "learning_rate": 1.6000000000000003e-05,
613
+ "loss": 0.0167,
614
+ "step": 1190
615
+ },
616
+ {
617
+ "epoch": 0.68,
618
+ "eval_accuracy": 0.9873333333333333,
619
+ "eval_f1": 0.9874587458745875,
620
+ "eval_loss": 0.060804687440395355,
621
+ "eval_precision": 0.9777777777777777,
622
+ "eval_recall": 0.9973333333333333,
623
+ "eval_runtime": 37.0856,
624
+ "eval_samples_per_second": 80.894,
625
+ "eval_steps_per_second": 10.112,
626
+ "step": 1190
627
+ },
628
+ {
629
+ "epoch": 0.7,
630
+ "learning_rate": 1.5e-05,
631
+ "loss": 0.1207,
632
+ "step": 1225
633
+ },
634
+ {
635
+ "epoch": 0.7,
636
+ "eval_accuracy": 0.993,
637
+ "eval_f1": 0.993025572899369,
638
+ "eval_loss": 0.025707580149173737,
639
+ "eval_precision": 0.9894109861019192,
640
+ "eval_recall": 0.9966666666666667,
641
+ "eval_runtime": 36.8077,
642
+ "eval_samples_per_second": 81.505,
643
+ "eval_steps_per_second": 10.188,
644
+ "step": 1225
645
+ },
646
+ {
647
+ "epoch": 0.72,
648
+ "learning_rate": 1.4000000000000001e-05,
649
+ "loss": 0.033,
650
+ "step": 1260
651
+ },
652
+ {
653
+ "epoch": 0.72,
654
+ "eval_accuracy": 0.994,
655
+ "eval_f1": 0.9940159574468085,
656
+ "eval_loss": 0.029781479388475418,
657
+ "eval_precision": 0.9913793103448276,
658
+ "eval_recall": 0.9966666666666667,
659
+ "eval_runtime": 36.0985,
660
+ "eval_samples_per_second": 83.106,
661
+ "eval_steps_per_second": 10.388,
662
+ "step": 1260
663
+ },
664
+ {
665
+ "epoch": 0.74,
666
+ "learning_rate": 1.3000000000000001e-05,
667
+ "loss": 0.0403,
668
+ "step": 1295
669
+ },
670
+ {
671
+ "epoch": 0.74,
672
+ "eval_accuracy": 0.97,
673
+ "eval_f1": 0.9708360337005832,
674
+ "eval_loss": 0.17279422283172607,
675
+ "eval_precision": 0.9445145018915511,
676
+ "eval_recall": 0.9986666666666667,
677
+ "eval_runtime": 36.0515,
678
+ "eval_samples_per_second": 83.214,
679
+ "eval_steps_per_second": 10.402,
680
+ "step": 1295
681
+ },
682
+ {
683
+ "epoch": 0.76,
684
+ "learning_rate": 1.2e-05,
685
+ "loss": 0.0554,
686
+ "step": 1330
687
+ },
688
+ {
689
+ "epoch": 0.76,
690
+ "eval_accuracy": 0.9866666666666667,
691
+ "eval_f1": 0.98681608437706,
692
+ "eval_loss": 0.0723133310675621,
693
+ "eval_precision": 0.9758800521512386,
694
+ "eval_recall": 0.998,
695
+ "eval_runtime": 36.0327,
696
+ "eval_samples_per_second": 83.258,
697
+ "eval_steps_per_second": 10.407,
698
+ "step": 1330
699
+ },
700
+ {
701
+ "epoch": 0.78,
702
+ "learning_rate": 1.1000000000000001e-05,
703
+ "loss": 0.0443,
704
+ "step": 1365
705
+ },
706
+ {
707
+ "epoch": 0.78,
708
+ "eval_accuracy": 0.9916666666666667,
709
+ "eval_f1": 0.99171362280411,
710
+ "eval_loss": 0.04444814473390579,
711
+ "eval_precision": 0.986156888595913,
712
+ "eval_recall": 0.9973333333333333,
713
+ "eval_runtime": 36.8515,
714
+ "eval_samples_per_second": 81.408,
715
+ "eval_steps_per_second": 10.176,
716
+ "step": 1365
717
+ },
718
+ {
719
+ "epoch": 0.8,
720
+ "learning_rate": 1e-05,
721
+ "loss": 0.0308,
722
+ "step": 1400
723
+ },
724
+ {
725
+ "epoch": 0.8,
726
+ "eval_accuracy": 0.9773333333333334,
727
+ "eval_f1": 0.9778067885117493,
728
+ "eval_loss": 0.1104651615023613,
729
+ "eval_precision": 0.9578005115089514,
730
+ "eval_recall": 0.9986666666666667,
731
+ "eval_runtime": 37.2021,
732
+ "eval_samples_per_second": 80.641,
733
+ "eval_steps_per_second": 10.08,
734
+ "step": 1400
735
+ },
736
+ {
737
+ "epoch": 0.82,
738
+ "learning_rate": 9e-06,
739
+ "loss": 0.0519,
740
+ "step": 1435
741
+ },
742
+ {
743
+ "epoch": 0.82,
744
+ "eval_accuracy": 0.9946666666666667,
745
+ "eval_f1": 0.9946559786239145,
746
+ "eval_loss": 0.023080775514245033,
747
+ "eval_precision": 0.9966532797858099,
748
+ "eval_recall": 0.9926666666666667,
749
+ "eval_runtime": 36.06,
750
+ "eval_samples_per_second": 83.195,
751
+ "eval_steps_per_second": 10.399,
752
+ "step": 1435
753
+ },
754
+ {
755
+ "epoch": 0.84,
756
+ "learning_rate": 8.000000000000001e-06,
757
+ "loss": 0.0007,
758
+ "step": 1470
759
+ },
760
+ {
761
+ "epoch": 0.84,
762
+ "eval_accuracy": 0.9856666666666667,
763
+ "eval_f1": 0.9858506087528792,
764
+ "eval_loss": 0.08097357302904129,
765
+ "eval_precision": 0.9733593242365172,
766
+ "eval_recall": 0.9986666666666667,
767
+ "eval_runtime": 35.9829,
768
+ "eval_samples_per_second": 83.373,
769
+ "eval_steps_per_second": 10.422,
770
+ "step": 1470
771
+ },
772
+ {
773
+ "epoch": 0.86,
774
+ "learning_rate": 7.000000000000001e-06,
775
+ "loss": 0.0167,
776
+ "step": 1505
777
+ },
778
+ {
779
+ "epoch": 0.86,
780
+ "eval_accuracy": 0.9883333333333333,
781
+ "eval_f1": 0.9884526558891455,
782
+ "eval_loss": 0.05811823159456253,
783
+ "eval_precision": 0.9784454604833442,
784
+ "eval_recall": 0.9986666666666667,
785
+ "eval_runtime": 37.0549,
786
+ "eval_samples_per_second": 80.961,
787
+ "eval_steps_per_second": 10.12,
788
+ "step": 1505
789
+ },
790
+ {
791
+ "epoch": 0.88,
792
+ "learning_rate": 6e-06,
793
+ "loss": 0.0514,
794
+ "step": 1540
795
+ },
796
+ {
797
+ "epoch": 0.88,
798
+ "eval_accuracy": 0.995,
799
+ "eval_f1": 0.995008319467554,
800
+ "eval_loss": 0.024803927168250084,
801
+ "eval_precision": 0.9933554817275747,
802
+ "eval_recall": 0.9966666666666667,
803
+ "eval_runtime": 36.1623,
804
+ "eval_samples_per_second": 82.959,
805
+ "eval_steps_per_second": 10.37,
806
+ "step": 1540
807
+ },
808
+ {
809
+ "epoch": 0.9,
810
+ "learning_rate": 5e-06,
811
+ "loss": 0.0005,
812
+ "step": 1575
813
+ },
814
+ {
815
+ "epoch": 0.9,
816
+ "eval_accuracy": 0.9943333333333333,
817
+ "eval_f1": 0.994354035204251,
818
+ "eval_loss": 0.03251485526561737,
819
+ "eval_precision": 0.9907346128391793,
820
+ "eval_recall": 0.998,
821
+ "eval_runtime": 36.0076,
822
+ "eval_samples_per_second": 83.316,
823
+ "eval_steps_per_second": 10.414,
824
+ "step": 1575
825
+ },
826
+ {
827
+ "epoch": 0.92,
828
+ "learning_rate": 4.000000000000001e-06,
829
+ "loss": 0.0003,
830
+ "step": 1610
831
+ },
832
+ {
833
+ "epoch": 0.92,
834
+ "eval_accuracy": 0.992,
835
+ "eval_f1": 0.9920477137176937,
836
+ "eval_loss": 0.04252306744456291,
837
+ "eval_precision": 0.9861660079051383,
838
+ "eval_recall": 0.998,
839
+ "eval_runtime": 36.1851,
840
+ "eval_samples_per_second": 82.907,
841
+ "eval_steps_per_second": 10.363,
842
+ "step": 1610
843
+ },
844
+ {
845
+ "epoch": 0.94,
846
+ "learning_rate": 3e-06,
847
+ "loss": 0.0688,
848
+ "step": 1645
849
+ },
850
+ {
851
+ "epoch": 0.94,
852
+ "eval_accuracy": 0.9903333333333333,
853
+ "eval_f1": 0.9904132231404958,
854
+ "eval_loss": 0.054892849177122116,
855
+ "eval_precision": 0.9822950819672132,
856
+ "eval_recall": 0.9986666666666667,
857
+ "eval_runtime": 36.0592,
858
+ "eval_samples_per_second": 83.197,
859
+ "eval_steps_per_second": 10.4,
860
+ "step": 1645
861
+ },
862
+ {
863
+ "epoch": 0.96,
864
+ "learning_rate": 2.0000000000000003e-06,
865
+ "loss": 0.0289,
866
+ "step": 1680
867
+ },
868
+ {
869
+ "epoch": 0.96,
870
+ "eval_accuracy": 0.987,
871
+ "eval_f1": 0.9871499176276771,
872
+ "eval_loss": 0.07362984865903854,
873
+ "eval_precision": 0.9758957654723127,
874
+ "eval_recall": 0.9986666666666667,
875
+ "eval_runtime": 36.8485,
876
+ "eval_samples_per_second": 81.415,
877
+ "eval_steps_per_second": 10.177,
878
+ "step": 1680
879
+ },
880
+ {
881
+ "epoch": 0.98,
882
+ "learning_rate": 1.0000000000000002e-06,
883
+ "loss": 0.0291,
884
+ "step": 1715
885
+ },
886
+ {
887
+ "epoch": 0.98,
888
+ "eval_accuracy": 0.9856666666666667,
889
+ "eval_f1": 0.9858506087528792,
890
+ "eval_loss": 0.07627929002046585,
891
+ "eval_precision": 0.9733593242365172,
892
+ "eval_recall": 0.9986666666666667,
893
+ "eval_runtime": 37.3831,
894
+ "eval_samples_per_second": 80.25,
895
+ "eval_steps_per_second": 10.031,
896
+ "step": 1715
897
+ },
898
+ {
899
+ "epoch": 1.0,
900
+ "learning_rate": 0.0,
901
+ "loss": 0.0004,
902
+ "step": 1750
903
+ },
904
+ {
905
+ "epoch": 1.0,
906
+ "eval_accuracy": 0.987,
907
+ "eval_f1": 0.9871499176276771,
908
+ "eval_loss": 0.07068450003862381,
909
+ "eval_precision": 0.9758957654723127,
910
+ "eval_recall": 0.9986666666666667,
911
+ "eval_runtime": 36.1142,
912
+ "eval_samples_per_second": 83.07,
913
+ "eval_steps_per_second": 10.384,
914
+ "step": 1750
915
+ }
916
+ ],
917
+ "max_steps": 1750,
918
+ "num_train_epochs": 1,
919
+ "total_flos": 3683554775040000.0,
920
+ "trial_name": null,
921
+ "trial_params": null
922
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c6cee71f7c1b5b03381212ea1fc14009e2878981494b27a11da611e97389bd
3
+ size 3451
vocab.json ADDED
The diff for this file is too large to render. See raw diff