syarulzaffi commited on
Commit
f27543e
·
verified ·
1 Parent(s): 6085e76

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - text-classification
6
+ base_model: distilbert/distilbert-base-uncased
7
+ widget:
8
+ - text: "I love AutoTrain"
9
+ ---
10
+
11
+ # Model Trained Using AutoTrain
12
+
13
+ - Problem type: Text Classification
14
+
15
+ ## Validation Metrics
16
+ loss: 6.676162593066692e-05
17
+
18
+ f1_macro: 1.0
19
+
20
+ f1_micro: 1.0
21
+
22
+ f1_weighted: 1.0
23
+
24
+ precision_macro: 1.0
25
+
26
+ precision_micro: 1.0
27
+
28
+ precision_weighted: 1.0
29
+
30
+ recall_macro: 1.0
31
+
32
+ recall_micro: 1.0
33
+
34
+ recall_weighted: 1.0
35
+
36
+ accuracy: 1.0
checkpoint-3000/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "_num_labels": 7,
4
+ "activation": "gelu",
5
+ "architectures": [
6
+ "DistilBertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "dim": 768,
10
+ "dropout": 0.1,
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "%Y-%m-%d",
14
+ "1": "%Y-%m-%d %H:%M:%S %Z",
15
+ "2": "%Y-%m-%dT%H:%M:%S",
16
+ "3": "%Y-%m-%dT%H:%M:%SZ",
17
+ "4": "%a, %d %b %Y",
18
+ "5": "%d/%m/%Y",
19
+ "6": "%m-%d-%Y %H:%M"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "label2id": {
23
+ "%Y-%m-%d": 0,
24
+ "%Y-%m-%d %H:%M:%S %Z": 1,
25
+ "%Y-%m-%dT%H:%M:%S": 2,
26
+ "%Y-%m-%dT%H:%M:%SZ": 3,
27
+ "%a, %d %b %Y": 4,
28
+ "%d/%m/%Y": 5,
29
+ "%m-%d-%Y %H:%M": 6
30
+ },
31
+ "max_position_embeddings": 512,
32
+ "model_type": "distilbert",
33
+ "n_heads": 12,
34
+ "n_layers": 6,
35
+ "pad_token_id": 0,
36
+ "problem_type": "single_label_classification",
37
+ "qa_dropout": 0.1,
38
+ "seq_classif_dropout": 0.2,
39
+ "sinusoidal_pos_embds": false,
40
+ "tie_weights_": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.45.0",
43
+ "vocab_size": 30522
44
+ }
checkpoint-3000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea8cceee374d910b34dcd4f0a90e80e8b07773f77f9be1e1000d372e6cd725ab
3
+ size 267847948
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8bf4ccc92b5e0dda1f21bba0395f80aa860d08c6403871480472eaa8b7321e4
3
+ size 535755130
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:167b75afaa359749ba1dff80fe9348a0507c1f330f452c0d2c0a91ecf63aae5f
3
+ size 13990
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d63e80ad6bbc2adc3564ccc8a754139157db8b58f99722236b6035ec26a46fcd
3
+ size 1064
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,936 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 6.676162593066692e-05,
3
+ "best_model_checkpoint": "autotrain-7odil-vp48l/checkpoint-3000",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.025,
13
+ "grad_norm": 1.9831761121749878,
14
+ "learning_rate": 4.166666666666667e-06,
15
+ "loss": 1.9634,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.05,
20
+ "grad_norm": 3.9359655380249023,
21
+ "learning_rate": 8.333333333333334e-06,
22
+ "loss": 1.8703,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.075,
27
+ "grad_norm": 5.147686004638672,
28
+ "learning_rate": 1.25e-05,
29
+ "loss": 1.5786,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.1,
34
+ "grad_norm": 4.199033260345459,
35
+ "learning_rate": 1.6666666666666667e-05,
36
+ "loss": 1.0025,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.125,
41
+ "grad_norm": 2.716735601425171,
42
+ "learning_rate": 2.0833333333333336e-05,
43
+ "loss": 0.4952,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.15,
48
+ "grad_norm": 1.7983918190002441,
49
+ "learning_rate": 2.5e-05,
50
+ "loss": 0.2272,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.175,
55
+ "grad_norm": 0.49452969431877136,
56
+ "learning_rate": 2.916666666666667e-05,
57
+ "loss": 0.078,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.2,
62
+ "grad_norm": 0.23962058126926422,
63
+ "learning_rate": 3.3333333333333335e-05,
64
+ "loss": 0.0345,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.225,
69
+ "grad_norm": 0.1509809046983719,
70
+ "learning_rate": 3.7500000000000003e-05,
71
+ "loss": 0.0195,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.25,
76
+ "grad_norm": 0.13671720027923584,
77
+ "learning_rate": 4.166666666666667e-05,
78
+ "loss": 0.0132,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.275,
83
+ "grad_norm": 0.07179934531450272,
84
+ "learning_rate": 4.5833333333333334e-05,
85
+ "loss": 0.0094,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.3,
90
+ "grad_norm": 0.06333258748054504,
91
+ "learning_rate": 5e-05,
92
+ "loss": 0.0074,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.325,
97
+ "grad_norm": 0.07822247594594955,
98
+ "learning_rate": 4.9537037037037035e-05,
99
+ "loss": 0.0056,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.35,
104
+ "grad_norm": 0.05372656136751175,
105
+ "learning_rate": 4.9074074074074075e-05,
106
+ "loss": 0.0046,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.375,
111
+ "grad_norm": 0.035013675689697266,
112
+ "learning_rate": 4.8611111111111115e-05,
113
+ "loss": 0.004,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.4,
118
+ "grad_norm": 0.041423212736845016,
119
+ "learning_rate": 4.814814814814815e-05,
120
+ "loss": 0.0035,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.425,
125
+ "grad_norm": 0.041730575263500214,
126
+ "learning_rate": 4.768518518518519e-05,
127
+ "loss": 0.0028,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.45,
132
+ "grad_norm": 0.029097281396389008,
133
+ "learning_rate": 4.722222222222222e-05,
134
+ "loss": 0.0024,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.475,
139
+ "grad_norm": 0.018743053078651428,
140
+ "learning_rate": 4.675925925925926e-05,
141
+ "loss": 0.0022,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.5,
146
+ "grad_norm": 0.024263164028525352,
147
+ "learning_rate": 4.62962962962963e-05,
148
+ "loss": 0.0019,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.525,
153
+ "grad_norm": 0.026380807161331177,
154
+ "learning_rate": 4.5833333333333334e-05,
155
+ "loss": 0.0018,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.55,
160
+ "grad_norm": 0.011210402473807335,
161
+ "learning_rate": 4.5370370370370374e-05,
162
+ "loss": 0.0016,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.575,
167
+ "grad_norm": 0.018315857276320457,
168
+ "learning_rate": 4.490740740740741e-05,
169
+ "loss": 0.0014,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.6,
174
+ "grad_norm": 0.01992151141166687,
175
+ "learning_rate": 4.4444444444444447e-05,
176
+ "loss": 0.0014,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.625,
181
+ "grad_norm": 0.013192097656428814,
182
+ "learning_rate": 4.3981481481481486e-05,
183
+ "loss": 0.0012,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.65,
188
+ "grad_norm": 0.012587452307343483,
189
+ "learning_rate": 4.351851851851852e-05,
190
+ "loss": 0.0011,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.675,
195
+ "grad_norm": 0.01079911831766367,
196
+ "learning_rate": 4.305555555555556e-05,
197
+ "loss": 0.001,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.7,
202
+ "grad_norm": 0.012937197461724281,
203
+ "learning_rate": 4.259259259259259e-05,
204
+ "loss": 0.001,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.725,
209
+ "grad_norm": 0.010724306106567383,
210
+ "learning_rate": 4.212962962962963e-05,
211
+ "loss": 0.0009,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.75,
216
+ "grad_norm": 0.01117613259702921,
217
+ "learning_rate": 4.166666666666667e-05,
218
+ "loss": 0.0009,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.775,
223
+ "grad_norm": 0.009770487435162067,
224
+ "learning_rate": 4.1203703703703705e-05,
225
+ "loss": 0.0008,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.8,
230
+ "grad_norm": 0.009905874729156494,
231
+ "learning_rate": 4.074074074074074e-05,
232
+ "loss": 0.0008,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.825,
237
+ "grad_norm": 0.007548601366579533,
238
+ "learning_rate": 4.027777777777778e-05,
239
+ "loss": 0.0007,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 0.85,
244
+ "grad_norm": 0.006770648993551731,
245
+ "learning_rate": 3.981481481481482e-05,
246
+ "loss": 0.0007,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 0.875,
251
+ "grad_norm": 0.010729338973760605,
252
+ "learning_rate": 3.935185185185186e-05,
253
+ "loss": 0.0007,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 0.9,
258
+ "grad_norm": 0.009794618003070354,
259
+ "learning_rate": 3.888888888888889e-05,
260
+ "loss": 0.0006,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 0.925,
265
+ "grad_norm": 0.007390674669295549,
266
+ "learning_rate": 3.8425925925925924e-05,
267
+ "loss": 0.0006,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 0.95,
272
+ "grad_norm": 0.006331269163638353,
273
+ "learning_rate": 3.7962962962962964e-05,
274
+ "loss": 0.0005,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 0.975,
279
+ "grad_norm": 0.009682104922831059,
280
+ "learning_rate": 3.7500000000000003e-05,
281
+ "loss": 0.0005,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 1.0,
286
+ "grad_norm": 0.008350877091288567,
287
+ "learning_rate": 3.7037037037037037e-05,
288
+ "loss": 0.0005,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 1.0,
293
+ "eval_accuracy": 1.0,
294
+ "eval_f1_macro": 1.0,
295
+ "eval_f1_micro": 1.0,
296
+ "eval_f1_weighted": 1.0,
297
+ "eval_loss": 0.0003003589517902583,
298
+ "eval_precision_macro": 1.0,
299
+ "eval_precision_micro": 1.0,
300
+ "eval_precision_weighted": 1.0,
301
+ "eval_recall_macro": 1.0,
302
+ "eval_recall_micro": 1.0,
303
+ "eval_recall_weighted": 1.0,
304
+ "eval_runtime": 252.8474,
305
+ "eval_samples_per_second": 7.91,
306
+ "eval_steps_per_second": 0.494,
307
+ "step": 1000
308
+ },
309
+ {
310
+ "epoch": 1.025,
311
+ "grad_norm": 0.0058663454838097095,
312
+ "learning_rate": 3.6574074074074076e-05,
313
+ "loss": 0.0005,
314
+ "step": 1025
315
+ },
316
+ {
317
+ "epoch": 1.05,
318
+ "grad_norm": 0.005394589621573687,
319
+ "learning_rate": 3.611111111111111e-05,
320
+ "loss": 0.0005,
321
+ "step": 1050
322
+ },
323
+ {
324
+ "epoch": 1.075,
325
+ "grad_norm": 0.006175881251692772,
326
+ "learning_rate": 3.564814814814815e-05,
327
+ "loss": 0.0005,
328
+ "step": 1075
329
+ },
330
+ {
331
+ "epoch": 1.1,
332
+ "grad_norm": 0.003940545488148928,
333
+ "learning_rate": 3.518518518518519e-05,
334
+ "loss": 0.0004,
335
+ "step": 1100
336
+ },
337
+ {
338
+ "epoch": 1.125,
339
+ "grad_norm": 0.004921493120491505,
340
+ "learning_rate": 3.472222222222222e-05,
341
+ "loss": 0.0004,
342
+ "step": 1125
343
+ },
344
+ {
345
+ "epoch": 1.15,
346
+ "grad_norm": 0.004267093725502491,
347
+ "learning_rate": 3.425925925925926e-05,
348
+ "loss": 0.0004,
349
+ "step": 1150
350
+ },
351
+ {
352
+ "epoch": 1.175,
353
+ "grad_norm": 0.004450589884072542,
354
+ "learning_rate": 3.3796296296296295e-05,
355
+ "loss": 0.0004,
356
+ "step": 1175
357
+ },
358
+ {
359
+ "epoch": 1.2,
360
+ "grad_norm": 0.004894304554909468,
361
+ "learning_rate": 3.3333333333333335e-05,
362
+ "loss": 0.0004,
363
+ "step": 1200
364
+ },
365
+ {
366
+ "epoch": 1.225,
367
+ "grad_norm": 0.005115053616464138,
368
+ "learning_rate": 3.2870370370370375e-05,
369
+ "loss": 0.0004,
370
+ "step": 1225
371
+ },
372
+ {
373
+ "epoch": 1.25,
374
+ "grad_norm": 0.00417192792519927,
375
+ "learning_rate": 3.240740740740741e-05,
376
+ "loss": 0.0003,
377
+ "step": 1250
378
+ },
379
+ {
380
+ "epoch": 1.275,
381
+ "grad_norm": 0.003110726596787572,
382
+ "learning_rate": 3.194444444444444e-05,
383
+ "loss": 0.0003,
384
+ "step": 1275
385
+ },
386
+ {
387
+ "epoch": 1.3,
388
+ "grad_norm": 0.004500871989876032,
389
+ "learning_rate": 3.148148148148148e-05,
390
+ "loss": 0.0003,
391
+ "step": 1300
392
+ },
393
+ {
394
+ "epoch": 1.325,
395
+ "grad_norm": 0.007220442872494459,
396
+ "learning_rate": 3.101851851851852e-05,
397
+ "loss": 0.0003,
398
+ "step": 1325
399
+ },
400
+ {
401
+ "epoch": 1.35,
402
+ "grad_norm": 0.004517797380685806,
403
+ "learning_rate": 3.055555555555556e-05,
404
+ "loss": 0.0003,
405
+ "step": 1350
406
+ },
407
+ {
408
+ "epoch": 1.375,
409
+ "grad_norm": 0.004377953242510557,
410
+ "learning_rate": 3.0092592592592593e-05,
411
+ "loss": 0.0003,
412
+ "step": 1375
413
+ },
414
+ {
415
+ "epoch": 1.4,
416
+ "grad_norm": 0.003857560455799103,
417
+ "learning_rate": 2.962962962962963e-05,
418
+ "loss": 0.0003,
419
+ "step": 1400
420
+ },
421
+ {
422
+ "epoch": 1.425,
423
+ "grad_norm": 0.0031161897350102663,
424
+ "learning_rate": 2.916666666666667e-05,
425
+ "loss": 0.0003,
426
+ "step": 1425
427
+ },
428
+ {
429
+ "epoch": 1.45,
430
+ "grad_norm": 0.00418724725022912,
431
+ "learning_rate": 2.8703703703703706e-05,
432
+ "loss": 0.0003,
433
+ "step": 1450
434
+ },
435
+ {
436
+ "epoch": 1.475,
437
+ "grad_norm": 0.0038644387386739254,
438
+ "learning_rate": 2.824074074074074e-05,
439
+ "loss": 0.0003,
440
+ "step": 1475
441
+ },
442
+ {
443
+ "epoch": 1.5,
444
+ "grad_norm": 0.0028685845900326967,
445
+ "learning_rate": 2.777777777777778e-05,
446
+ "loss": 0.0003,
447
+ "step": 1500
448
+ },
449
+ {
450
+ "epoch": 1.525,
451
+ "grad_norm": 0.0030455435626208782,
452
+ "learning_rate": 2.7314814814814816e-05,
453
+ "loss": 0.0003,
454
+ "step": 1525
455
+ },
456
+ {
457
+ "epoch": 1.55,
458
+ "grad_norm": 0.004415576346218586,
459
+ "learning_rate": 2.6851851851851855e-05,
460
+ "loss": 0.0002,
461
+ "step": 1550
462
+ },
463
+ {
464
+ "epoch": 1.575,
465
+ "grad_norm": 0.0032394465524703264,
466
+ "learning_rate": 2.6388888888888892e-05,
467
+ "loss": 0.0002,
468
+ "step": 1575
469
+ },
470
+ {
471
+ "epoch": 1.6,
472
+ "grad_norm": 0.0036883000284433365,
473
+ "learning_rate": 2.5925925925925925e-05,
474
+ "loss": 0.0002,
475
+ "step": 1600
476
+ },
477
+ {
478
+ "epoch": 1.625,
479
+ "grad_norm": 0.002775784581899643,
480
+ "learning_rate": 2.5462962962962965e-05,
481
+ "loss": 0.0002,
482
+ "step": 1625
483
+ },
484
+ {
485
+ "epoch": 1.65,
486
+ "grad_norm": 0.00252612610347569,
487
+ "learning_rate": 2.5e-05,
488
+ "loss": 0.0002,
489
+ "step": 1650
490
+ },
491
+ {
492
+ "epoch": 1.675,
493
+ "grad_norm": 0.003114240476861596,
494
+ "learning_rate": 2.4537037037037038e-05,
495
+ "loss": 0.0002,
496
+ "step": 1675
497
+ },
498
+ {
499
+ "epoch": 1.7,
500
+ "grad_norm": 0.0045029474422335625,
501
+ "learning_rate": 2.4074074074074074e-05,
502
+ "loss": 0.0002,
503
+ "step": 1700
504
+ },
505
+ {
506
+ "epoch": 1.725,
507
+ "grad_norm": 0.0029288099613040686,
508
+ "learning_rate": 2.361111111111111e-05,
509
+ "loss": 0.0002,
510
+ "step": 1725
511
+ },
512
+ {
513
+ "epoch": 1.75,
514
+ "grad_norm": 0.0029125239234417677,
515
+ "learning_rate": 2.314814814814815e-05,
516
+ "loss": 0.0002,
517
+ "step": 1750
518
+ },
519
+ {
520
+ "epoch": 1.775,
521
+ "grad_norm": 0.0026727975346148014,
522
+ "learning_rate": 2.2685185185185187e-05,
523
+ "loss": 0.0002,
524
+ "step": 1775
525
+ },
526
+ {
527
+ "epoch": 1.8,
528
+ "grad_norm": 0.0019383927574381232,
529
+ "learning_rate": 2.2222222222222223e-05,
530
+ "loss": 0.0002,
531
+ "step": 1800
532
+ },
533
+ {
534
+ "epoch": 1.825,
535
+ "grad_norm": 0.0030314610339701176,
536
+ "learning_rate": 2.175925925925926e-05,
537
+ "loss": 0.0002,
538
+ "step": 1825
539
+ },
540
+ {
541
+ "epoch": 1.85,
542
+ "grad_norm": 0.0029118990059942007,
543
+ "learning_rate": 2.1296296296296296e-05,
544
+ "loss": 0.0002,
545
+ "step": 1850
546
+ },
547
+ {
548
+ "epoch": 1.875,
549
+ "grad_norm": 0.002271339064463973,
550
+ "learning_rate": 2.0833333333333336e-05,
551
+ "loss": 0.0002,
552
+ "step": 1875
553
+ },
554
+ {
555
+ "epoch": 1.9,
556
+ "grad_norm": 0.0020249192602932453,
557
+ "learning_rate": 2.037037037037037e-05,
558
+ "loss": 0.0002,
559
+ "step": 1900
560
+ },
561
+ {
562
+ "epoch": 1.925,
563
+ "grad_norm": 0.002170481951907277,
564
+ "learning_rate": 1.990740740740741e-05,
565
+ "loss": 0.0002,
566
+ "step": 1925
567
+ },
568
+ {
569
+ "epoch": 1.95,
570
+ "grad_norm": 0.0021853959187865257,
571
+ "learning_rate": 1.9444444444444445e-05,
572
+ "loss": 0.0002,
573
+ "step": 1950
574
+ },
575
+ {
576
+ "epoch": 1.975,
577
+ "grad_norm": 0.0024531374219805002,
578
+ "learning_rate": 1.8981481481481482e-05,
579
+ "loss": 0.0002,
580
+ "step": 1975
581
+ },
582
+ {
583
+ "epoch": 2.0,
584
+ "grad_norm": 0.0020948376040905714,
585
+ "learning_rate": 1.8518518518518518e-05,
586
+ "loss": 0.0002,
587
+ "step": 2000
588
+ },
589
+ {
590
+ "epoch": 2.0,
591
+ "eval_accuracy": 1.0,
592
+ "eval_f1_macro": 1.0,
593
+ "eval_f1_micro": 1.0,
594
+ "eval_f1_weighted": 1.0,
595
+ "eval_loss": 9.583658538758755e-05,
596
+ "eval_precision_macro": 1.0,
597
+ "eval_precision_micro": 1.0,
598
+ "eval_precision_weighted": 1.0,
599
+ "eval_recall_macro": 1.0,
600
+ "eval_recall_micro": 1.0,
601
+ "eval_recall_weighted": 1.0,
602
+ "eval_runtime": 274.5731,
603
+ "eval_samples_per_second": 7.284,
604
+ "eval_steps_per_second": 0.455,
605
+ "step": 2000
606
+ },
607
+ {
608
+ "epoch": 2.025,
609
+ "grad_norm": 0.0017642254242673516,
610
+ "learning_rate": 1.8055555555555555e-05,
611
+ "loss": 0.0002,
612
+ "step": 2025
613
+ },
614
+ {
615
+ "epoch": 2.05,
616
+ "grad_norm": 0.002351736184209585,
617
+ "learning_rate": 1.7592592592592595e-05,
618
+ "loss": 0.0002,
619
+ "step": 2050
620
+ },
621
+ {
622
+ "epoch": 2.075,
623
+ "grad_norm": 0.001802345854230225,
624
+ "learning_rate": 1.712962962962963e-05,
625
+ "loss": 0.0002,
626
+ "step": 2075
627
+ },
628
+ {
629
+ "epoch": 2.1,
630
+ "grad_norm": 0.004205259494483471,
631
+ "learning_rate": 1.6666666666666667e-05,
632
+ "loss": 0.0002,
633
+ "step": 2100
634
+ },
635
+ {
636
+ "epoch": 2.125,
637
+ "grad_norm": 0.0024293495807796717,
638
+ "learning_rate": 1.6203703703703704e-05,
639
+ "loss": 0.0001,
640
+ "step": 2125
641
+ },
642
+ {
643
+ "epoch": 2.15,
644
+ "grad_norm": 0.002529233694076538,
645
+ "learning_rate": 1.574074074074074e-05,
646
+ "loss": 0.0002,
647
+ "step": 2150
648
+ },
649
+ {
650
+ "epoch": 2.175,
651
+ "grad_norm": 0.00464004697278142,
652
+ "learning_rate": 1.527777777777778e-05,
653
+ "loss": 0.0002,
654
+ "step": 2175
655
+ },
656
+ {
657
+ "epoch": 2.2,
658
+ "grad_norm": 0.0022527112159878016,
659
+ "learning_rate": 1.4814814814814815e-05,
660
+ "loss": 0.0002,
661
+ "step": 2200
662
+ },
663
+ {
664
+ "epoch": 2.225,
665
+ "grad_norm": 0.0029627634212374687,
666
+ "learning_rate": 1.4351851851851853e-05,
667
+ "loss": 0.0001,
668
+ "step": 2225
669
+ },
670
+ {
671
+ "epoch": 2.25,
672
+ "grad_norm": 0.003177474718540907,
673
+ "learning_rate": 1.388888888888889e-05,
674
+ "loss": 0.0002,
675
+ "step": 2250
676
+ },
677
+ {
678
+ "epoch": 2.275,
679
+ "grad_norm": 0.0013587498106062412,
680
+ "learning_rate": 1.3425925925925928e-05,
681
+ "loss": 0.0001,
682
+ "step": 2275
683
+ },
684
+ {
685
+ "epoch": 2.3,
686
+ "grad_norm": 0.002243857365101576,
687
+ "learning_rate": 1.2962962962962962e-05,
688
+ "loss": 0.0001,
689
+ "step": 2300
690
+ },
691
+ {
692
+ "epoch": 2.325,
693
+ "grad_norm": 0.001520108082331717,
694
+ "learning_rate": 1.25e-05,
695
+ "loss": 0.0001,
696
+ "step": 2325
697
+ },
698
+ {
699
+ "epoch": 2.35,
700
+ "grad_norm": 0.001689109718427062,
701
+ "learning_rate": 1.2037037037037037e-05,
702
+ "loss": 0.0001,
703
+ "step": 2350
704
+ },
705
+ {
706
+ "epoch": 2.375,
707
+ "grad_norm": 0.0024859753903001547,
708
+ "learning_rate": 1.1574074074074075e-05,
709
+ "loss": 0.0001,
710
+ "step": 2375
711
+ },
712
+ {
713
+ "epoch": 2.4,
714
+ "grad_norm": 0.0026000950019806623,
715
+ "learning_rate": 1.1111111111111112e-05,
716
+ "loss": 0.0001,
717
+ "step": 2400
718
+ },
719
+ {
720
+ "epoch": 2.425,
721
+ "grad_norm": 0.002047985326498747,
722
+ "learning_rate": 1.0648148148148148e-05,
723
+ "loss": 0.0001,
724
+ "step": 2425
725
+ },
726
+ {
727
+ "epoch": 2.45,
728
+ "grad_norm": 0.0015425788005813956,
729
+ "learning_rate": 1.0185185185185185e-05,
730
+ "loss": 0.0001,
731
+ "step": 2450
732
+ },
733
+ {
734
+ "epoch": 2.475,
735
+ "grad_norm": 0.0018854117952287197,
736
+ "learning_rate": 9.722222222222223e-06,
737
+ "loss": 0.0001,
738
+ "step": 2475
739
+ },
740
+ {
741
+ "epoch": 2.5,
742
+ "grad_norm": 0.0014580640709027648,
743
+ "learning_rate": 9.259259259259259e-06,
744
+ "loss": 0.0001,
745
+ "step": 2500
746
+ },
747
+ {
748
+ "epoch": 2.525,
749
+ "grad_norm": 0.0019544586539268494,
750
+ "learning_rate": 8.796296296296297e-06,
751
+ "loss": 0.0001,
752
+ "step": 2525
753
+ },
754
+ {
755
+ "epoch": 2.55,
756
+ "grad_norm": 0.0023410411085933447,
757
+ "learning_rate": 8.333333333333334e-06,
758
+ "loss": 0.0001,
759
+ "step": 2550
760
+ },
761
+ {
762
+ "epoch": 2.575,
763
+ "grad_norm": 0.0013650900218635798,
764
+ "learning_rate": 7.87037037037037e-06,
765
+ "loss": 0.0001,
766
+ "step": 2575
767
+ },
768
+ {
769
+ "epoch": 2.6,
770
+ "grad_norm": 0.008295529522001743,
771
+ "learning_rate": 7.4074074074074075e-06,
772
+ "loss": 0.0001,
773
+ "step": 2600
774
+ },
775
+ {
776
+ "epoch": 2.625,
777
+ "grad_norm": 0.0017800548812374473,
778
+ "learning_rate": 6.944444444444445e-06,
779
+ "loss": 0.0001,
780
+ "step": 2625
781
+ },
782
+ {
783
+ "epoch": 2.65,
784
+ "grad_norm": 0.0020650553051382303,
785
+ "learning_rate": 6.481481481481481e-06,
786
+ "loss": 0.0001,
787
+ "step": 2650
788
+ },
789
+ {
790
+ "epoch": 2.675,
791
+ "grad_norm": 0.002936688484624028,
792
+ "learning_rate": 6.0185185185185185e-06,
793
+ "loss": 0.0001,
794
+ "step": 2675
795
+ },
796
+ {
797
+ "epoch": 2.7,
798
+ "grad_norm": 0.0020264526829123497,
799
+ "learning_rate": 5.555555555555556e-06,
800
+ "loss": 0.0001,
801
+ "step": 2700
802
+ },
803
+ {
804
+ "epoch": 2.725,
805
+ "grad_norm": 0.001260068267583847,
806
+ "learning_rate": 5.092592592592592e-06,
807
+ "loss": 0.0001,
808
+ "step": 2725
809
+ },
810
+ {
811
+ "epoch": 2.75,
812
+ "grad_norm": 0.0013758167624473572,
813
+ "learning_rate": 4.6296296296296296e-06,
814
+ "loss": 0.0001,
815
+ "step": 2750
816
+ },
817
+ {
818
+ "epoch": 2.775,
819
+ "grad_norm": 0.0018719694344326854,
820
+ "learning_rate": 4.166666666666667e-06,
821
+ "loss": 0.0001,
822
+ "step": 2775
823
+ },
824
+ {
825
+ "epoch": 2.8,
826
+ "grad_norm": 0.0019297786056995392,
827
+ "learning_rate": 3.7037037037037037e-06,
828
+ "loss": 0.0001,
829
+ "step": 2800
830
+ },
831
+ {
832
+ "epoch": 2.825,
833
+ "grad_norm": 0.0015490080695599318,
834
+ "learning_rate": 3.2407407407407406e-06,
835
+ "loss": 0.0001,
836
+ "step": 2825
837
+ },
838
+ {
839
+ "epoch": 2.85,
840
+ "grad_norm": 0.0017714012647047639,
841
+ "learning_rate": 2.777777777777778e-06,
842
+ "loss": 0.0001,
843
+ "step": 2850
844
+ },
845
+ {
846
+ "epoch": 2.875,
847
+ "grad_norm": 0.001514387782663107,
848
+ "learning_rate": 2.3148148148148148e-06,
849
+ "loss": 0.0001,
850
+ "step": 2875
851
+ },
852
+ {
853
+ "epoch": 2.9,
854
+ "grad_norm": 0.0017558818217366934,
855
+ "learning_rate": 1.8518518518518519e-06,
856
+ "loss": 0.0001,
857
+ "step": 2900
858
+ },
859
+ {
860
+ "epoch": 2.925,
861
+ "grad_norm": 0.0014736577868461609,
862
+ "learning_rate": 1.388888888888889e-06,
863
+ "loss": 0.0001,
864
+ "step": 2925
865
+ },
866
+ {
867
+ "epoch": 2.95,
868
+ "grad_norm": 0.0018687807023525238,
869
+ "learning_rate": 9.259259259259259e-07,
870
+ "loss": 0.0001,
871
+ "step": 2950
872
+ },
873
+ {
874
+ "epoch": 2.975,
875
+ "grad_norm": 0.0012901716399937868,
876
+ "learning_rate": 4.6296296296296297e-07,
877
+ "loss": 0.0001,
878
+ "step": 2975
879
+ },
880
+ {
881
+ "epoch": 3.0,
882
+ "grad_norm": 0.001818928518332541,
883
+ "learning_rate": 0.0,
884
+ "loss": 0.0001,
885
+ "step": 3000
886
+ },
887
+ {
888
+ "epoch": 3.0,
889
+ "eval_accuracy": 1.0,
890
+ "eval_f1_macro": 1.0,
891
+ "eval_f1_micro": 1.0,
892
+ "eval_f1_weighted": 1.0,
893
+ "eval_loss": 6.676162593066692e-05,
894
+ "eval_precision_macro": 1.0,
895
+ "eval_precision_micro": 1.0,
896
+ "eval_precision_weighted": 1.0,
897
+ "eval_recall_macro": 1.0,
898
+ "eval_recall_micro": 1.0,
899
+ "eval_recall_weighted": 1.0,
900
+ "eval_runtime": 241.5667,
901
+ "eval_samples_per_second": 8.279,
902
+ "eval_steps_per_second": 0.517,
903
+ "step": 3000
904
+ }
905
+ ],
906
+ "logging_steps": 25,
907
+ "max_steps": 3000,
908
+ "num_input_tokens_seen": 0,
909
+ "num_train_epochs": 3,
910
+ "save_steps": 500,
911
+ "stateful_callbacks": {
912
+ "EarlyStoppingCallback": {
913
+ "args": {
914
+ "early_stopping_patience": 5,
915
+ "early_stopping_threshold": 0.01
916
+ },
917
+ "attributes": {
918
+ "early_stopping_patience_counter": 2
919
+ }
920
+ },
921
+ "TrainerControl": {
922
+ "args": {
923
+ "should_epoch_stop": false,
924
+ "should_evaluate": false,
925
+ "should_log": false,
926
+ "should_save": true,
927
+ "should_training_stop": true
928
+ },
929
+ "attributes": {}
930
+ }
931
+ },
932
+ "total_flos": 794875262976000.0,
933
+ "train_batch_size": 8,
934
+ "trial_name": null,
935
+ "trial_params": null
936
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87e152d871171f913c4e73706c8ac28fdcd89ac33b145dd45c9a48e8d5fe224
3
+ size 5240
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "_num_labels": 7,
4
+ "activation": "gelu",
5
+ "architectures": [
6
+ "DistilBertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "dim": 768,
10
+ "dropout": 0.1,
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "%Y-%m-%d",
14
+ "1": "%Y-%m-%d %H:%M:%S %Z",
15
+ "2": "%Y-%m-%dT%H:%M:%S",
16
+ "3": "%Y-%m-%dT%H:%M:%SZ",
17
+ "4": "%a, %d %b %Y",
18
+ "5": "%d/%m/%Y",
19
+ "6": "%m-%d-%Y %H:%M"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "label2id": {
23
+ "%Y-%m-%d": 0,
24
+ "%Y-%m-%d %H:%M:%S %Z": 1,
25
+ "%Y-%m-%dT%H:%M:%S": 2,
26
+ "%Y-%m-%dT%H:%M:%SZ": 3,
27
+ "%a, %d %b %Y": 4,
28
+ "%d/%m/%Y": 5,
29
+ "%m-%d-%Y %H:%M": 6
30
+ },
31
+ "max_position_embeddings": 512,
32
+ "model_type": "distilbert",
33
+ "n_heads": 12,
34
+ "n_layers": 6,
35
+ "pad_token_id": 0,
36
+ "problem_type": "single_label_classification",
37
+ "qa_dropout": 0.1,
38
+ "seq_classif_dropout": 0.2,
39
+ "sinusoidal_pos_embds": false,
40
+ "tie_weights_": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.45.0",
43
+ "vocab_size": 30522
44
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea8cceee374d910b34dcd4f0a90e80e8b07773f77f9be1e1000d372e6cd725ab
3
+ size 267847948
runs/Oct16_09-32-48_r-syarulzaffi-autotrain-advanced-q0iwc8qv-aa92d-gecw6/events.out.tfevents.1729071171.r-syarulzaffi-autotrain-advanced-q0iwc8qv-aa92d-gecw6.112.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00d923b8f5f451ad32675661c5d6801b105f0c4f260337e957feda6ecc1bf437
3
- size 32052
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37762e5f55f0e04539315186f7841c5f509ce42ee1259a7e3b68e7a27312d041
3
+ size 33450
runs/Oct16_09-32-48_r-syarulzaffi-autotrain-advanced-q0iwc8qv-aa92d-gecw6/events.out.tfevents.1729084203.r-syarulzaffi-autotrain-advanced-q0iwc8qv-aa92d-gecw6.112.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fae76f4dfe33254df8ef9f8686ad1900f303d6a4dedbc0c272bcb265f5194a2
3
+ size 921
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87e152d871171f913c4e73706c8ac28fdcd89ac33b145dd45c9a48e8d5fe224
3
+ size 5240
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-7odil-vp48l/autotrain-data",
3
+ "model": "distilbert/distilbert-base-uncased",
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-7odil-vp48l",
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": "syarulzaffi",
27
+ "log": "tensorboard",
28
+ "early_stopping_patience": 5,
29
+ "early_stopping_threshold": 0.01
30
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff