Sooyeon03 commited on
Commit
a4e0bd2
·
verified ·
1 Parent(s): f165c1d

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ library_name: transformers
4
+ tags:
5
+ - autotrain
6
+ - text-classification
7
+ base_model: beomi/KcELECTRA-base
8
+ widget:
9
+ - text: "I love AutoTrain"
10
+ ---
11
+
12
+ # Model Trained Using AutoTrain
13
+
14
+ - Problem type: Text Classification
15
+
16
+ ## Validation Metrics
17
+ loss: 0.6811079382896423
18
+
19
+ f1_macro: 0.27878787878787875
20
+
21
+ f1_micro: 0.71875
22
+
23
+ f1_weighted: 0.6011363636363636
24
+
25
+ precision_macro: 0.23958333333333334
26
+
27
+ precision_micro: 0.71875
28
+
29
+ precision_weighted: 0.5166015625
30
+
31
+ recall_macro: 0.3333333333333333
32
+
33
+ recall_micro: 0.71875
34
+
35
+ recall_weighted: 0.71875
36
+
37
+ accuracy: 0.71875
checkpoint-144/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "beomi/KcELECTRA-base",
3
+ "_num_labels": 3,
4
+ "architectures": [
5
+ "ElectraForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "embedding_size": 768,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "0",
15
+ "1": "1",
16
+ "2": "2"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "0": 0,
22
+ "1": 1,
23
+ "2": 2
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "electra",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 3,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "summary_activation": "gelu",
34
+ "summary_last_dropout": 0.1,
35
+ "summary_type": "first",
36
+ "summary_use_proj": true,
37
+ "tokenizer_class": "PreTrainedTokenizerFast",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.48.0",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 30000
43
+ }
checkpoint-144/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df852f0b54a5375ecc9fdd196459e80db01327216baad231390ee2ffe3d58fc
3
+ size 436358732
checkpoint-144/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddcca2d8d499b4ab90d4f8d6e3a1dd0db6c113c24db2f3ef3c18b907b32ccfde
3
+ size 872831738
checkpoint-144/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90c6b0034de4d8ae067be5d21e9ac860de53947609f6a0c466f90b13ec2f3954
3
+ size 13990
checkpoint-144/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a949ed3376a9a4a304f122136113b4c5f21dfd67a7b9a8fc7bdacc0383de61c
3
+ size 1064
checkpoint-144/trainer_state.json ADDED
@@ -0,0 +1,600 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6811079382896423,
3
+ "best_model_checkpoint": "autotrain-sentiment-analysis/checkpoint-144",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 144,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.041666666666666664,
13
+ "grad_norm": 2.61773419380188,
14
+ "learning_rate": 6.666666666666667e-06,
15
+ "loss": 1.1097,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.08333333333333333,
20
+ "grad_norm": 4.698597431182861,
21
+ "learning_rate": 1.3333333333333333e-05,
22
+ "loss": 1.1207,
23
+ "step": 4
24
+ },
25
+ {
26
+ "epoch": 0.125,
27
+ "grad_norm": 3.428281545639038,
28
+ "learning_rate": 2e-05,
29
+ "loss": 1.1048,
30
+ "step": 6
31
+ },
32
+ {
33
+ "epoch": 0.16666666666666666,
34
+ "grad_norm": 3.1913719177246094,
35
+ "learning_rate": 2.6666666666666667e-05,
36
+ "loss": 1.083,
37
+ "step": 8
38
+ },
39
+ {
40
+ "epoch": 0.20833333333333334,
41
+ "grad_norm": 3.64862060546875,
42
+ "learning_rate": 3.3333333333333335e-05,
43
+ "loss": 0.9868,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 0.25,
48
+ "grad_norm": 4.067363739013672,
49
+ "learning_rate": 4e-05,
50
+ "loss": 0.9255,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 0.2916666666666667,
55
+ "grad_norm": 3.104797601699829,
56
+ "learning_rate": 4.666666666666667e-05,
57
+ "loss": 0.8136,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 0.3333333333333333,
62
+ "grad_norm": 2.2000064849853516,
63
+ "learning_rate": 4.96124031007752e-05,
64
+ "loss": 0.8614,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 0.375,
69
+ "grad_norm": 1.573570728302002,
70
+ "learning_rate": 4.883720930232558e-05,
71
+ "loss": 0.7383,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 0.4166666666666667,
76
+ "grad_norm": 1.3823363780975342,
77
+ "learning_rate": 4.8062015503875976e-05,
78
+ "loss": 0.7695,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 0.4583333333333333,
83
+ "grad_norm": 2.1016550064086914,
84
+ "learning_rate": 4.728682170542636e-05,
85
+ "loss": 0.932,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 0.5,
90
+ "grad_norm": 5.811567783355713,
91
+ "learning_rate": 4.651162790697675e-05,
92
+ "loss": 0.6523,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 0.5416666666666666,
97
+ "grad_norm": 3.2167797088623047,
98
+ "learning_rate": 4.573643410852713e-05,
99
+ "loss": 1.0534,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 0.5833333333333334,
104
+ "grad_norm": 2.892798900604248,
105
+ "learning_rate": 4.496124031007753e-05,
106
+ "loss": 0.7581,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 0.625,
111
+ "grad_norm": 2.0418224334716797,
112
+ "learning_rate": 4.418604651162791e-05,
113
+ "loss": 0.8344,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.6666666666666666,
118
+ "grad_norm": 2.9645307064056396,
119
+ "learning_rate": 4.34108527131783e-05,
120
+ "loss": 0.7183,
121
+ "step": 32
122
+ },
123
+ {
124
+ "epoch": 0.7083333333333334,
125
+ "grad_norm": 3.4876549243927,
126
+ "learning_rate": 4.263565891472868e-05,
127
+ "loss": 0.8234,
128
+ "step": 34
129
+ },
130
+ {
131
+ "epoch": 0.75,
132
+ "grad_norm": 2.0125443935394287,
133
+ "learning_rate": 4.186046511627907e-05,
134
+ "loss": 1.0816,
135
+ "step": 36
136
+ },
137
+ {
138
+ "epoch": 0.7916666666666666,
139
+ "grad_norm": 2.0428311824798584,
140
+ "learning_rate": 4.108527131782946e-05,
141
+ "loss": 0.9007,
142
+ "step": 38
143
+ },
144
+ {
145
+ "epoch": 0.8333333333333334,
146
+ "grad_norm": 1.7238165140151978,
147
+ "learning_rate": 4.0310077519379843e-05,
148
+ "loss": 0.497,
149
+ "step": 40
150
+ },
151
+ {
152
+ "epoch": 0.875,
153
+ "grad_norm": 2.6068952083587646,
154
+ "learning_rate": 3.953488372093023e-05,
155
+ "loss": 0.7311,
156
+ "step": 42
157
+ },
158
+ {
159
+ "epoch": 0.9166666666666666,
160
+ "grad_norm": 1.734787106513977,
161
+ "learning_rate": 3.875968992248062e-05,
162
+ "loss": 0.9503,
163
+ "step": 44
164
+ },
165
+ {
166
+ "epoch": 0.9583333333333334,
167
+ "grad_norm": 2.9760279655456543,
168
+ "learning_rate": 3.798449612403101e-05,
169
+ "loss": 0.6021,
170
+ "step": 46
171
+ },
172
+ {
173
+ "epoch": 1.0,
174
+ "grad_norm": 1.2471810579299927,
175
+ "learning_rate": 3.7209302325581394e-05,
176
+ "loss": 1.0543,
177
+ "step": 48
178
+ },
179
+ {
180
+ "epoch": 1.0,
181
+ "eval_accuracy": 0.71875,
182
+ "eval_f1_macro": 0.27878787878787875,
183
+ "eval_f1_micro": 0.71875,
184
+ "eval_f1_weighted": 0.6011363636363636,
185
+ "eval_loss": 0.7673549056053162,
186
+ "eval_precision_macro": 0.23958333333333334,
187
+ "eval_precision_micro": 0.71875,
188
+ "eval_precision_weighted": 0.5166015625,
189
+ "eval_recall_macro": 0.3333333333333333,
190
+ "eval_recall_micro": 0.71875,
191
+ "eval_recall_weighted": 0.71875,
192
+ "eval_runtime": 24.0397,
193
+ "eval_samples_per_second": 3.993,
194
+ "eval_steps_per_second": 0.25,
195
+ "step": 48
196
+ },
197
+ {
198
+ "epoch": 1.0416666666666667,
199
+ "grad_norm": 1.3500399589538574,
200
+ "learning_rate": 3.6434108527131784e-05,
201
+ "loss": 0.68,
202
+ "step": 50
203
+ },
204
+ {
205
+ "epoch": 1.0833333333333333,
206
+ "grad_norm": 1.40060293674469,
207
+ "learning_rate": 3.565891472868217e-05,
208
+ "loss": 0.8973,
209
+ "step": 52
210
+ },
211
+ {
212
+ "epoch": 1.125,
213
+ "grad_norm": 1.7774051427841187,
214
+ "learning_rate": 3.488372093023256e-05,
215
+ "loss": 0.8056,
216
+ "step": 54
217
+ },
218
+ {
219
+ "epoch": 1.1666666666666667,
220
+ "grad_norm": 3.3298189640045166,
221
+ "learning_rate": 3.4108527131782945e-05,
222
+ "loss": 0.8549,
223
+ "step": 56
224
+ },
225
+ {
226
+ "epoch": 1.2083333333333333,
227
+ "grad_norm": 2.947392463684082,
228
+ "learning_rate": 3.3333333333333335e-05,
229
+ "loss": 0.9906,
230
+ "step": 58
231
+ },
232
+ {
233
+ "epoch": 1.25,
234
+ "grad_norm": 3.4643170833587646,
235
+ "learning_rate": 3.2558139534883724e-05,
236
+ "loss": 0.8688,
237
+ "step": 60
238
+ },
239
+ {
240
+ "epoch": 1.2916666666666667,
241
+ "grad_norm": 3.8225324153900146,
242
+ "learning_rate": 3.1782945736434114e-05,
243
+ "loss": 0.6709,
244
+ "step": 62
245
+ },
246
+ {
247
+ "epoch": 1.3333333333333333,
248
+ "grad_norm": 3.1090219020843506,
249
+ "learning_rate": 3.1007751937984497e-05,
250
+ "loss": 0.6474,
251
+ "step": 64
252
+ },
253
+ {
254
+ "epoch": 1.375,
255
+ "grad_norm": 2.2563295364379883,
256
+ "learning_rate": 3.0232558139534883e-05,
257
+ "loss": 0.7428,
258
+ "step": 66
259
+ },
260
+ {
261
+ "epoch": 1.4166666666666667,
262
+ "grad_norm": 1.6209709644317627,
263
+ "learning_rate": 2.9457364341085275e-05,
264
+ "loss": 0.8073,
265
+ "step": 68
266
+ },
267
+ {
268
+ "epoch": 1.4583333333333333,
269
+ "grad_norm": 1.8441722393035889,
270
+ "learning_rate": 2.868217054263566e-05,
271
+ "loss": 0.8651,
272
+ "step": 70
273
+ },
274
+ {
275
+ "epoch": 1.5,
276
+ "grad_norm": 2.2973005771636963,
277
+ "learning_rate": 2.7906976744186048e-05,
278
+ "loss": 0.8014,
279
+ "step": 72
280
+ },
281
+ {
282
+ "epoch": 1.5416666666666665,
283
+ "grad_norm": 2.146662950515747,
284
+ "learning_rate": 2.7131782945736434e-05,
285
+ "loss": 0.685,
286
+ "step": 74
287
+ },
288
+ {
289
+ "epoch": 1.5833333333333335,
290
+ "grad_norm": 2.087498426437378,
291
+ "learning_rate": 2.6356589147286826e-05,
292
+ "loss": 0.6317,
293
+ "step": 76
294
+ },
295
+ {
296
+ "epoch": 1.625,
297
+ "grad_norm": 2.4231820106506348,
298
+ "learning_rate": 2.5581395348837212e-05,
299
+ "loss": 0.924,
300
+ "step": 78
301
+ },
302
+ {
303
+ "epoch": 1.6666666666666665,
304
+ "grad_norm": 2.6310791969299316,
305
+ "learning_rate": 2.48062015503876e-05,
306
+ "loss": 0.9485,
307
+ "step": 80
308
+ },
309
+ {
310
+ "epoch": 1.7083333333333335,
311
+ "grad_norm": 3.849123477935791,
312
+ "learning_rate": 2.4031007751937988e-05,
313
+ "loss": 0.3247,
314
+ "step": 82
315
+ },
316
+ {
317
+ "epoch": 1.75,
318
+ "grad_norm": 2.9805049896240234,
319
+ "learning_rate": 2.3255813953488374e-05,
320
+ "loss": 0.406,
321
+ "step": 84
322
+ },
323
+ {
324
+ "epoch": 1.7916666666666665,
325
+ "grad_norm": 1.514115571975708,
326
+ "learning_rate": 2.2480620155038764e-05,
327
+ "loss": 0.7446,
328
+ "step": 86
329
+ },
330
+ {
331
+ "epoch": 1.8333333333333335,
332
+ "grad_norm": 1.3838368654251099,
333
+ "learning_rate": 2.170542635658915e-05,
334
+ "loss": 0.741,
335
+ "step": 88
336
+ },
337
+ {
338
+ "epoch": 1.875,
339
+ "grad_norm": 3.1611580848693848,
340
+ "learning_rate": 2.0930232558139536e-05,
341
+ "loss": 0.6876,
342
+ "step": 90
343
+ },
344
+ {
345
+ "epoch": 1.9166666666666665,
346
+ "grad_norm": 2.6954050064086914,
347
+ "learning_rate": 2.0155038759689922e-05,
348
+ "loss": 0.7502,
349
+ "step": 92
350
+ },
351
+ {
352
+ "epoch": 1.9583333333333335,
353
+ "grad_norm": 3.9244301319122314,
354
+ "learning_rate": 1.937984496124031e-05,
355
+ "loss": 0.7001,
356
+ "step": 94
357
+ },
358
+ {
359
+ "epoch": 2.0,
360
+ "grad_norm": 2.3937811851501465,
361
+ "learning_rate": 1.8604651162790697e-05,
362
+ "loss": 0.624,
363
+ "step": 96
364
+ },
365
+ {
366
+ "epoch": 2.0,
367
+ "eval_accuracy": 0.71875,
368
+ "eval_f1_macro": 0.27878787878787875,
369
+ "eval_f1_micro": 0.71875,
370
+ "eval_f1_weighted": 0.6011363636363636,
371
+ "eval_loss": 0.7328377366065979,
372
+ "eval_precision_macro": 0.23958333333333334,
373
+ "eval_precision_micro": 0.71875,
374
+ "eval_precision_weighted": 0.5166015625,
375
+ "eval_recall_macro": 0.3333333333333333,
376
+ "eval_recall_micro": 0.71875,
377
+ "eval_recall_weighted": 0.71875,
378
+ "eval_runtime": 23.5119,
379
+ "eval_samples_per_second": 4.083,
380
+ "eval_steps_per_second": 0.255,
381
+ "step": 96
382
+ },
383
+ {
384
+ "epoch": 2.0416666666666665,
385
+ "grad_norm": 1.6089367866516113,
386
+ "learning_rate": 1.7829457364341087e-05,
387
+ "loss": 0.547,
388
+ "step": 98
389
+ },
390
+ {
391
+ "epoch": 2.0833333333333335,
392
+ "grad_norm": 1.5757851600646973,
393
+ "learning_rate": 1.7054263565891473e-05,
394
+ "loss": 0.5843,
395
+ "step": 100
396
+ },
397
+ {
398
+ "epoch": 2.125,
399
+ "grad_norm": 1.5463695526123047,
400
+ "learning_rate": 1.6279069767441862e-05,
401
+ "loss": 0.4361,
402
+ "step": 102
403
+ },
404
+ {
405
+ "epoch": 2.1666666666666665,
406
+ "grad_norm": 2.580299139022827,
407
+ "learning_rate": 1.5503875968992248e-05,
408
+ "loss": 0.4907,
409
+ "step": 104
410
+ },
411
+ {
412
+ "epoch": 2.2083333333333335,
413
+ "grad_norm": 2.695828676223755,
414
+ "learning_rate": 1.4728682170542638e-05,
415
+ "loss": 0.8353,
416
+ "step": 106
417
+ },
418
+ {
419
+ "epoch": 2.25,
420
+ "grad_norm": 2.140033006668091,
421
+ "learning_rate": 1.3953488372093024e-05,
422
+ "loss": 0.5777,
423
+ "step": 108
424
+ },
425
+ {
426
+ "epoch": 2.2916666666666665,
427
+ "grad_norm": 3.8345487117767334,
428
+ "learning_rate": 1.3178294573643413e-05,
429
+ "loss": 0.7843,
430
+ "step": 110
431
+ },
432
+ {
433
+ "epoch": 2.3333333333333335,
434
+ "grad_norm": 2.3163905143737793,
435
+ "learning_rate": 1.24031007751938e-05,
436
+ "loss": 0.6893,
437
+ "step": 112
438
+ },
439
+ {
440
+ "epoch": 2.375,
441
+ "grad_norm": 3.516930341720581,
442
+ "learning_rate": 1.1627906976744187e-05,
443
+ "loss": 0.6864,
444
+ "step": 114
445
+ },
446
+ {
447
+ "epoch": 2.4166666666666665,
448
+ "grad_norm": 3.0617573261260986,
449
+ "learning_rate": 1.0852713178294575e-05,
450
+ "loss": 0.6138,
451
+ "step": 116
452
+ },
453
+ {
454
+ "epoch": 2.4583333333333335,
455
+ "grad_norm": 3.0156357288360596,
456
+ "learning_rate": 1.0077519379844961e-05,
457
+ "loss": 0.4153,
458
+ "step": 118
459
+ },
460
+ {
461
+ "epoch": 2.5,
462
+ "grad_norm": 2.8226044178009033,
463
+ "learning_rate": 9.302325581395349e-06,
464
+ "loss": 0.6466,
465
+ "step": 120
466
+ },
467
+ {
468
+ "epoch": 2.5416666666666665,
469
+ "grad_norm": 3.725145101547241,
470
+ "learning_rate": 8.527131782945736e-06,
471
+ "loss": 0.7085,
472
+ "step": 122
473
+ },
474
+ {
475
+ "epoch": 2.5833333333333335,
476
+ "grad_norm": 4.078347206115723,
477
+ "learning_rate": 7.751937984496124e-06,
478
+ "loss": 0.7082,
479
+ "step": 124
480
+ },
481
+ {
482
+ "epoch": 2.625,
483
+ "grad_norm": 5.447461128234863,
484
+ "learning_rate": 6.976744186046512e-06,
485
+ "loss": 0.5261,
486
+ "step": 126
487
+ },
488
+ {
489
+ "epoch": 2.6666666666666665,
490
+ "grad_norm": 2.5857555866241455,
491
+ "learning_rate": 6.2015503875969e-06,
492
+ "loss": 0.4489,
493
+ "step": 128
494
+ },
495
+ {
496
+ "epoch": 2.7083333333333335,
497
+ "grad_norm": 3.1875112056732178,
498
+ "learning_rate": 5.426356589147287e-06,
499
+ "loss": 0.4491,
500
+ "step": 130
501
+ },
502
+ {
503
+ "epoch": 2.75,
504
+ "grad_norm": 5.04345178604126,
505
+ "learning_rate": 4.651162790697674e-06,
506
+ "loss": 0.5488,
507
+ "step": 132
508
+ },
509
+ {
510
+ "epoch": 2.7916666666666665,
511
+ "grad_norm": 2.73793888092041,
512
+ "learning_rate": 3.875968992248062e-06,
513
+ "loss": 0.68,
514
+ "step": 134
515
+ },
516
+ {
517
+ "epoch": 2.8333333333333335,
518
+ "grad_norm": 2.1447975635528564,
519
+ "learning_rate": 3.10077519379845e-06,
520
+ "loss": 0.4895,
521
+ "step": 136
522
+ },
523
+ {
524
+ "epoch": 2.875,
525
+ "grad_norm": 2.5409231185913086,
526
+ "learning_rate": 2.325581395348837e-06,
527
+ "loss": 0.65,
528
+ "step": 138
529
+ },
530
+ {
531
+ "epoch": 2.9166666666666665,
532
+ "grad_norm": 9.605962753295898,
533
+ "learning_rate": 1.550387596899225e-06,
534
+ "loss": 0.7381,
535
+ "step": 140
536
+ },
537
+ {
538
+ "epoch": 2.9583333333333335,
539
+ "grad_norm": 3.561542272567749,
540
+ "learning_rate": 7.751937984496125e-07,
541
+ "loss": 0.6063,
542
+ "step": 142
543
+ },
544
+ {
545
+ "epoch": 3.0,
546
+ "grad_norm": 1.8243706226348877,
547
+ "learning_rate": 0.0,
548
+ "loss": 0.8917,
549
+ "step": 144
550
+ },
551
+ {
552
+ "epoch": 3.0,
553
+ "eval_accuracy": 0.71875,
554
+ "eval_f1_macro": 0.27878787878787875,
555
+ "eval_f1_micro": 0.71875,
556
+ "eval_f1_weighted": 0.6011363636363636,
557
+ "eval_loss": 0.6811079382896423,
558
+ "eval_precision_macro": 0.23958333333333334,
559
+ "eval_precision_micro": 0.71875,
560
+ "eval_precision_weighted": 0.5166015625,
561
+ "eval_recall_macro": 0.3333333333333333,
562
+ "eval_recall_micro": 0.71875,
563
+ "eval_recall_weighted": 0.71875,
564
+ "eval_runtime": 23.6003,
565
+ "eval_samples_per_second": 4.068,
566
+ "eval_steps_per_second": 0.254,
567
+ "step": 144
568
+ }
569
+ ],
570
+ "logging_steps": 2,
571
+ "max_steps": 144,
572
+ "num_input_tokens_seen": 0,
573
+ "num_train_epochs": 3,
574
+ "save_steps": 500,
575
+ "stateful_callbacks": {
576
+ "EarlyStoppingCallback": {
577
+ "args": {
578
+ "early_stopping_patience": 5,
579
+ "early_stopping_threshold": 0.01
580
+ },
581
+ "attributes": {
582
+ "early_stopping_patience_counter": 0
583
+ }
584
+ },
585
+ "TrainerControl": {
586
+ "args": {
587
+ "should_epoch_stop": false,
588
+ "should_evaluate": false,
589
+ "should_log": false,
590
+ "should_save": true,
591
+ "should_training_stop": true
592
+ },
593
+ "attributes": {}
594
+ }
595
+ },
596
+ "total_flos": 75776664305664.0,
597
+ "train_batch_size": 8,
598
+ "trial_name": null,
599
+ "trial_params": null
600
+ }
checkpoint-144/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab218cb1dca77be64a10bbd690db252edf0210d0fc42b09d011ec726dab5d7fc
3
+ size 5368
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "beomi/KcELECTRA-base",
3
+ "_num_labels": 3,
4
+ "architectures": [
5
+ "ElectraForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "embedding_size": 768,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "0",
15
+ "1": "1",
16
+ "2": "2"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "0": 0,
22
+ "1": 1,
23
+ "2": 2
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "electra",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 3,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "summary_activation": "gelu",
34
+ "summary_last_dropout": 0.1,
35
+ "summary_type": "first",
36
+ "summary_use_proj": true,
37
+ "tokenizer_class": "PreTrainedTokenizerFast",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.48.0",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 30000
43
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df852f0b54a5375ecc9fdd196459e80db01327216baad231390ee2ffe3d58fc
3
+ size 436358732
runs/Jun09_13-33-38_r-sooyeon03-autotrain-advanced-j0sc94mf-b38f3-ai7pc/events.out.tfevents.1749476020.r-sooyeon03-autotrain-advanced-j0sc94mf-b38f3-ai7pc.548.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a95dd8df308f884f330f21f5d94708f36e4f2af0d6f575a50658d7332fcc99b5
3
- size 14715
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69eb185ba320ebd1d111a493c52dfbac46e0cd1fd2225874d847a53ece6f3ccf
3
+ size 23173
runs/Jun09_13-33-38_r-sooyeon03-autotrain-advanced-j0sc94mf-b38f3-ai7pc/events.out.tfevents.1749477144.r-sooyeon03-autotrain-advanced-j0sc94mf-b38f3-ai7pc.548.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac68bebaf29e300d8c77b9d41c3251ce97be5d81e1cc5c53caecb33bc7da899f
3
+ size 921
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
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": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
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": false,
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": "PreTrainedTokenizerFast",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab218cb1dca77be64a10bbd690db252edf0210d0fc42b09d011ec726dab5d7fc
3
+ size 5368
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-sentiment-analysis/autotrain-data",
3
+ "model": "beomi/KcELECTRA-base",
4
+ "lr": 5e-05,
5
+ "epochs": 3,
6
+ "max_seq_length": 128,
7
+ "batch_size": 8,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 1,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.0,
13
+ "max_grad_norm": 1.0,
14
+ "seed": 42,
15
+ "train_split": "train",
16
+ "valid_split": "validation",
17
+ "text_column": "autotrain_text",
18
+ "target_column": "autotrain_label",
19
+ "logging_steps": -1,
20
+ "project_name": "autotrain-sentiment-analysis",
21
+ "auto_find_batch_size": false,
22
+ "mixed_precision": "fp16",
23
+ "save_total_limit": 1,
24
+ "push_to_hub": true,
25
+ "eval_strategy": "epoch",
26
+ "username": "Sooyeon03",
27
+ "log": "tensorboard",
28
+ "early_stopping_patience": 5,
29
+ "early_stopping_threshold": 0.01
30
+ }