rlagustn35 commited on
Commit
43f6ff2
·
verified ·
1 Parent(s): f02ad09

Finetuned model upload

Browse files
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ElectraForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "embedding_size": 768,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "IT\uacfc\ud559",
13
+ "1": "\uacbd\uc81c",
14
+ "2": "\uc0ac\ud68c",
15
+ "3": "\uc0dd\ud65c\ubb38\ud654",
16
+ "4": "\uc138\uacc4",
17
+ "5": "\uc2a4\ud3ec\uce20",
18
+ "6": "\uc815\uce58"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "IT\uacfc\ud559": 0,
24
+ "\uacbd\uc81c": 1,
25
+ "\uc0ac\ud68c": 2,
26
+ "\uc0dd\ud65c\ubb38\ud654": 3,
27
+ "\uc138\uacc4": 4,
28
+ "\uc2a4\ud3ec\uce20": 5,
29
+ "\uc815\uce58": 6
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "electra",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "summary_activation": "gelu",
40
+ "summary_last_dropout": 0.1,
41
+ "summary_type": "first",
42
+ "summary_use_proj": true,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.54.1",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 35000
48
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84127c2ed509cd277a56015c941921ba3edab93b68742c40caecff23ad09bf1a
3
+ size 451731052
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d351128476f99491e64373855f28e45fdff9f255ae30c9091b7e223974425aee
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fce1715cf846af5cea8d2755e693db5231c666351aec6f6b3e3edb8e9550a1de
3
+ size 1064
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "ElectraTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
trainer_state.json ADDED
@@ -0,0 +1,364 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2142,
3
+ "best_metric": 0.8572526627868673,
4
+ "best_model_checkpoint": "./data/ynat-model/checkpoint-2142",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2142,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0700280112044818,
14
+ "grad_norm": 4.37371301651001,
15
+ "learning_rate": 4.88562091503268e-05,
16
+ "loss": 0.368,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.1400560224089636,
21
+ "grad_norm": 2.0869579315185547,
22
+ "learning_rate": 4.7689075630252105e-05,
23
+ "loss": 0.3318,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.21008403361344538,
28
+ "grad_norm": 5.720030784606934,
29
+ "learning_rate": 4.6521942110177405e-05,
30
+ "loss": 0.3172,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.2801120448179272,
35
+ "grad_norm": 11.471839904785156,
36
+ "learning_rate": 4.535480859010271e-05,
37
+ "loss": 0.2934,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.35014005602240894,
42
+ "grad_norm": 3.376629114151001,
43
+ "learning_rate": 4.418767507002801e-05,
44
+ "loss": 0.3005,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.42016806722689076,
49
+ "grad_norm": 4.57407808303833,
50
+ "learning_rate": 4.302054154995332e-05,
51
+ "loss": 0.2652,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.49019607843137253,
56
+ "grad_norm": 4.265451431274414,
57
+ "learning_rate": 4.185340802987862e-05,
58
+ "loss": 0.2649,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.5602240896358543,
63
+ "grad_norm": 4.1893086433410645,
64
+ "learning_rate": 4.068627450980392e-05,
65
+ "loss": 0.2446,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.6302521008403361,
70
+ "grad_norm": 2.6485085487365723,
71
+ "learning_rate": 3.951914098972922e-05,
72
+ "loss": 0.2269,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.7002801120448179,
77
+ "grad_norm": 3.4019579887390137,
78
+ "learning_rate": 3.8352007469654535e-05,
79
+ "loss": 0.2324,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.7703081232492998,
84
+ "grad_norm": 1.2434275150299072,
85
+ "learning_rate": 3.7184873949579834e-05,
86
+ "loss": 0.2329,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.8403361344537815,
91
+ "grad_norm": 5.956329345703125,
92
+ "learning_rate": 3.6017740429505134e-05,
93
+ "loss": 0.207,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.9103641456582633,
98
+ "grad_norm": 2.210266351699829,
99
+ "learning_rate": 3.485060690943044e-05,
100
+ "loss": 0.2278,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.9803921568627451,
105
+ "grad_norm": 3.8561065196990967,
106
+ "learning_rate": 3.3683473389355746e-05,
107
+ "loss": 0.2255,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 1.0,
112
+ "eval_accuracy": 0.8529702426704733,
113
+ "eval_f1": 0.8516564005044691,
114
+ "eval_loss": 0.4749363362789154,
115
+ "eval_precision": 0.8525157577020369,
116
+ "eval_recall": 0.8535400561743023,
117
+ "eval_runtime": 12.9676,
118
+ "eval_samples_per_second": 702.29,
119
+ "eval_steps_per_second": 11.028,
120
+ "step": 714
121
+ },
122
+ {
123
+ "epoch": 1.050420168067227,
124
+ "grad_norm": 2.6144492626190186,
125
+ "learning_rate": 3.2516339869281046e-05,
126
+ "loss": 0.2636,
127
+ "step": 750
128
+ },
129
+ {
130
+ "epoch": 1.1204481792717087,
131
+ "grad_norm": 4.134031772613525,
132
+ "learning_rate": 3.134920634920635e-05,
133
+ "loss": 0.2475,
134
+ "step": 800
135
+ },
136
+ {
137
+ "epoch": 1.1904761904761905,
138
+ "grad_norm": 4.822914123535156,
139
+ "learning_rate": 3.018207282913165e-05,
140
+ "loss": 0.2398,
141
+ "step": 850
142
+ },
143
+ {
144
+ "epoch": 1.2605042016806722,
145
+ "grad_norm": 4.078502655029297,
146
+ "learning_rate": 2.901493930905696e-05,
147
+ "loss": 0.2369,
148
+ "step": 900
149
+ },
150
+ {
151
+ "epoch": 1.330532212885154,
152
+ "grad_norm": 5.511151313781738,
153
+ "learning_rate": 2.784780578898226e-05,
154
+ "loss": 0.2519,
155
+ "step": 950
156
+ },
157
+ {
158
+ "epoch": 1.4005602240896358,
159
+ "grad_norm": 14.258254051208496,
160
+ "learning_rate": 2.6680672268907564e-05,
161
+ "loss": 0.2603,
162
+ "step": 1000
163
+ },
164
+ {
165
+ "epoch": 1.4705882352941178,
166
+ "grad_norm": 37.48504638671875,
167
+ "learning_rate": 2.5513538748832866e-05,
168
+ "loss": 0.2329,
169
+ "step": 1050
170
+ },
171
+ {
172
+ "epoch": 1.5406162464985993,
173
+ "grad_norm": 9.023612976074219,
174
+ "learning_rate": 2.434640522875817e-05,
175
+ "loss": 0.2524,
176
+ "step": 1100
177
+ },
178
+ {
179
+ "epoch": 1.6106442577030813,
180
+ "grad_norm": 4.550325870513916,
181
+ "learning_rate": 2.3179271708683476e-05,
182
+ "loss": 0.2249,
183
+ "step": 1150
184
+ },
185
+ {
186
+ "epoch": 1.680672268907563,
187
+ "grad_norm": 5.294163227081299,
188
+ "learning_rate": 2.201213818860878e-05,
189
+ "loss": 0.229,
190
+ "step": 1200
191
+ },
192
+ {
193
+ "epoch": 1.7507002801120448,
194
+ "grad_norm": 5.975066661834717,
195
+ "learning_rate": 2.084500466853408e-05,
196
+ "loss": 0.2346,
197
+ "step": 1250
198
+ },
199
+ {
200
+ "epoch": 1.8207282913165266,
201
+ "grad_norm": 9.633162498474121,
202
+ "learning_rate": 1.9677871148459384e-05,
203
+ "loss": 0.2388,
204
+ "step": 1300
205
+ },
206
+ {
207
+ "epoch": 1.8907563025210083,
208
+ "grad_norm": 2.6880970001220703,
209
+ "learning_rate": 1.851073762838469e-05,
210
+ "loss": 0.2372,
211
+ "step": 1350
212
+ },
213
+ {
214
+ "epoch": 1.9607843137254903,
215
+ "grad_norm": 5.544015884399414,
216
+ "learning_rate": 1.734360410830999e-05,
217
+ "loss": 0.2296,
218
+ "step": 1400
219
+ },
220
+ {
221
+ "epoch": 2.0,
222
+ "eval_accuracy": 0.855825189414736,
223
+ "eval_f1": 0.8561722862205893,
224
+ "eval_loss": 0.44257503747940063,
225
+ "eval_precision": 0.8489764689633209,
226
+ "eval_recall": 0.865244799193242,
227
+ "eval_runtime": 13.04,
228
+ "eval_samples_per_second": 698.387,
229
+ "eval_steps_per_second": 10.966,
230
+ "step": 1428
231
+ },
232
+ {
233
+ "epoch": 2.030812324929972,
234
+ "grad_norm": 3.5343873500823975,
235
+ "learning_rate": 1.6176470588235296e-05,
236
+ "loss": 0.204,
237
+ "step": 1450
238
+ },
239
+ {
240
+ "epoch": 2.100840336134454,
241
+ "grad_norm": 2.5762808322906494,
242
+ "learning_rate": 1.5009337068160597e-05,
243
+ "loss": 0.182,
244
+ "step": 1500
245
+ },
246
+ {
247
+ "epoch": 2.1708683473389354,
248
+ "grad_norm": 2.4014556407928467,
249
+ "learning_rate": 1.3842203548085902e-05,
250
+ "loss": 0.1659,
251
+ "step": 1550
252
+ },
253
+ {
254
+ "epoch": 2.2408963585434174,
255
+ "grad_norm": 5.196502685546875,
256
+ "learning_rate": 1.2675070028011205e-05,
257
+ "loss": 0.1721,
258
+ "step": 1600
259
+ },
260
+ {
261
+ "epoch": 2.310924369747899,
262
+ "grad_norm": 2.636826992034912,
263
+ "learning_rate": 1.1507936507936508e-05,
264
+ "loss": 0.1781,
265
+ "step": 1650
266
+ },
267
+ {
268
+ "epoch": 2.380952380952381,
269
+ "grad_norm": 3.6006743907928467,
270
+ "learning_rate": 1.0340802987861812e-05,
271
+ "loss": 0.1788,
272
+ "step": 1700
273
+ },
274
+ {
275
+ "epoch": 2.450980392156863,
276
+ "grad_norm": 3.009672164916992,
277
+ "learning_rate": 9.173669467787115e-06,
278
+ "loss": 0.1574,
279
+ "step": 1750
280
+ },
281
+ {
282
+ "epoch": 2.5210084033613445,
283
+ "grad_norm": 2.854926586151123,
284
+ "learning_rate": 8.006535947712418e-06,
285
+ "loss": 0.1511,
286
+ "step": 1800
287
+ },
288
+ {
289
+ "epoch": 2.5910364145658265,
290
+ "grad_norm": 5.09183406829834,
291
+ "learning_rate": 6.839402427637723e-06,
292
+ "loss": 0.1993,
293
+ "step": 1850
294
+ },
295
+ {
296
+ "epoch": 2.661064425770308,
297
+ "grad_norm": 1.9752312898635864,
298
+ "learning_rate": 5.672268907563025e-06,
299
+ "loss": 0.1701,
300
+ "step": 1900
301
+ },
302
+ {
303
+ "epoch": 2.73109243697479,
304
+ "grad_norm": 3.669840097427368,
305
+ "learning_rate": 4.505135387488329e-06,
306
+ "loss": 0.1698,
307
+ "step": 1950
308
+ },
309
+ {
310
+ "epoch": 2.8011204481792715,
311
+ "grad_norm": 2.8419978618621826,
312
+ "learning_rate": 3.338001867413632e-06,
313
+ "loss": 0.1637,
314
+ "step": 2000
315
+ },
316
+ {
317
+ "epoch": 2.8711484593837535,
318
+ "grad_norm": 3.0742175579071045,
319
+ "learning_rate": 2.1708683473389355e-06,
320
+ "loss": 0.1591,
321
+ "step": 2050
322
+ },
323
+ {
324
+ "epoch": 2.9411764705882355,
325
+ "grad_norm": 3.2953155040740967,
326
+ "learning_rate": 1.0037348272642392e-06,
327
+ "loss": 0.1686,
328
+ "step": 2100
329
+ },
330
+ {
331
+ "epoch": 3.0,
332
+ "eval_accuracy": 0.8572526627868673,
333
+ "eval_f1": 0.8569137587108026,
334
+ "eval_loss": 0.4840508997440338,
335
+ "eval_precision": 0.848038822955364,
336
+ "eval_recall": 0.8670435119879699,
337
+ "eval_runtime": 12.9882,
338
+ "eval_samples_per_second": 701.177,
339
+ "eval_steps_per_second": 11.01,
340
+ "step": 2142
341
+ }
342
+ ],
343
+ "logging_steps": 50,
344
+ "max_steps": 2142,
345
+ "num_input_tokens_seen": 0,
346
+ "num_train_epochs": 3,
347
+ "save_steps": 500,
348
+ "stateful_callbacks": {
349
+ "TrainerControl": {
350
+ "args": {
351
+ "should_epoch_stop": false,
352
+ "should_evaluate": false,
353
+ "should_log": false,
354
+ "should_save": true,
355
+ "should_training_stop": true
356
+ },
357
+ "attributes": {}
358
+ }
359
+ },
360
+ "total_flos": 1616745095802300.0,
361
+ "train_batch_size": 64,
362
+ "trial_name": null,
363
+ "trial_params": null
364
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aca69bc924be80eafe2d855c503acb4ffa8145ce90b569a5dff63f054e80527
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff