Hugging Face's logo

MichellPayano
/
first-trial

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
text-embeddings-inference
Model card Files
xet
 Metrics Community
MichellPayano commited on
Commit
bf25213
·
1 Parent(s): dcc12a3

Training in progress, epoch 6

Browse files
Files changed (13) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-29754/config.json +25 -0
  3. run-0/checkpoint-29754/model.safetensors +3 -0
  4. run-0/checkpoint-29754/optimizer.pt +3 -0
  5. run-0/checkpoint-29754/rng_state.pth +3 -0
  6. run-0/checkpoint-29754/scheduler.pt +3 -0
  7. run-0/checkpoint-29754/special_tokens_map.json +7 -0
  8. run-0/checkpoint-29754/tokenizer.json +0 -0
  9. run-0/checkpoint-29754/tokenizer_config.json +55 -0
  10. run-0/checkpoint-29754/trainer_state.json +377 -0
  11. run-0/checkpoint-29754/training_args.bin +3 -0
  12. run-0/checkpoint-29754/vocab.txt +0 -0
  13. runs/Dec01_16-51-56_516e27a14fd3/events.out.tfevents.1701452487.516e27a14fd3.673.8 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6e300ac70152f03d19ced7d0dfe82a1cd3124ee21ea46db0804d09a8235306d
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e197da63d4cf7d31f4b387a9b0ac791f72909fd4f9b57e58f8cc19c497534c0c
3
  size 267832560
run-0/checkpoint-29754/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.35.2",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-29754/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e197da63d4cf7d31f4b387a9b0ac791f72909fd4f9b57e58f8cc19c497534c0c
3
+ size 267832560
run-0/checkpoint-29754/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd364fa85c80144e2310a8089e2c927152197de62cb98685f7a75ed92c81d502
3
+ size 535727290
run-0/checkpoint-29754/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de39b2426f04236313ed461af126680e6d67b51aa10d4604c23bc3926f96abdb
3
+ size 14244
run-0/checkpoint-29754/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01eb1f7e40ffe6459ea5adf19eba4591bfab47c1676e4c9181965072cc765873
3
+ size 1064
run-0/checkpoint-29754/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
+ }
run-0/checkpoint-29754/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-29754/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
+ }
run-0/checkpoint-29754/trainer_state.json ADDED
@@ -0,0 +1,377 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 29754,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1,
13
+ "learning_rate": 0.00019663910734691136,
14
+ "loss": 0.7019,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.2,
19
+ "learning_rate": 0.00019327821469382269,
20
+ "loss": 0.6968,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.3,
25
+ "learning_rate": 0.00018991732204073404,
26
+ "loss": 0.6953,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.4,
31
+ "learning_rate": 0.00018655642938764536,
32
+ "loss": 0.6994,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.5,
37
+ "learning_rate": 0.0001831955367345567,
38
+ "loss": 0.7019,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.6,
43
+ "learning_rate": 0.00017983464408146804,
44
+ "loss": 0.6966,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.71,
49
+ "learning_rate": 0.0001764737514283794,
50
+ "loss": 0.6943,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.81,
55
+ "learning_rate": 0.00017311285877529074,
56
+ "loss": 0.6956,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.91,
61
+ "learning_rate": 0.00016975196612220206,
62
+ "loss": 0.697,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 1.01,
67
+ "learning_rate": 0.0001663910734691134,
68
+ "loss": 0.6944,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 1.11,
73
+ "learning_rate": 0.00016303018081602474,
74
+ "loss": 0.6936,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 1.21,
79
+ "learning_rate": 0.0001596692881629361,
80
+ "loss": 0.6945,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 1.31,
85
+ "learning_rate": 0.00015630839550984742,
86
+ "loss": 0.6938,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 1.41,
91
+ "learning_rate": 0.00015294750285675877,
92
+ "loss": 0.6937,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 1.51,
97
+ "learning_rate": 0.00014958661020367012,
98
+ "loss": 0.6934,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 1.61,
103
+ "learning_rate": 0.00014622571755058144,
104
+ "loss": 0.6946,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 1.71,
109
+ "learning_rate": 0.00014286482489749277,
110
+ "loss": 0.6939,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 1.81,
115
+ "learning_rate": 0.00013950393224440412,
116
+ "loss": 0.6933,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 1.92,
121
+ "learning_rate": 0.00013614303959131547,
122
+ "loss": 0.6936,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 2.02,
127
+ "learning_rate": 0.0001327821469382268,
128
+ "loss": 0.6938,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 2.12,
133
+ "learning_rate": 0.00012942125428513815,
134
+ "loss": 0.6939,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 2.22,
139
+ "learning_rate": 0.0001260603616320495,
140
+ "loss": 0.6936,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 2.32,
145
+ "learning_rate": 0.0001226994689789608,
146
+ "loss": 0.6934,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 2.42,
151
+ "learning_rate": 0.00011933857632587216,
152
+ "loss": 0.6931,
153
+ "step": 12000
154
+ },
155
+ {
156
+ "epoch": 2.52,
157
+ "learning_rate": 0.0001159776836727835,
158
+ "loss": 0.6935,
159
+ "step": 12500
160
+ },
161
+ {
162
+ "epoch": 2.62,
163
+ "learning_rate": 0.00011261679101969485,
164
+ "loss": 0.6935,
165
+ "step": 13000
166
+ },
167
+ {
168
+ "epoch": 2.72,
169
+ "learning_rate": 0.00010925589836660617,
170
+ "loss": 0.6933,
171
+ "step": 13500
172
+ },
173
+ {
174
+ "epoch": 2.82,
175
+ "learning_rate": 0.00010589500571351751,
176
+ "loss": 0.6936,
177
+ "step": 14000
178
+ },
179
+ {
180
+ "epoch": 2.92,
181
+ "learning_rate": 0.00010253411306042886,
182
+ "loss": 0.6933,
183
+ "step": 14500
184
+ },
185
+ {
186
+ "epoch": 3.02,
187
+ "learning_rate": 9.91732204073402e-05,
188
+ "loss": 0.6932,
189
+ "step": 15000
190
+ },
191
+ {
192
+ "epoch": 3.13,
193
+ "learning_rate": 9.581232775425152e-05,
194
+ "loss": 0.693,
195
+ "step": 15500
196
+ },
197
+ {
198
+ "epoch": 3.23,
199
+ "learning_rate": 9.245143510116288e-05,
200
+ "loss": 0.6937,
201
+ "step": 16000
202
+ },
203
+ {
204
+ "epoch": 3.33,
205
+ "learning_rate": 8.909054244807421e-05,
206
+ "loss": 0.6934,
207
+ "step": 16500
208
+ },
209
+ {
210
+ "epoch": 3.43,
211
+ "learning_rate": 8.572964979498555e-05,
212
+ "loss": 0.693,
213
+ "step": 17000
214
+ },
215
+ {
216
+ "epoch": 3.53,
217
+ "learning_rate": 8.236875714189689e-05,
218
+ "loss": 0.6937,
219
+ "step": 17500
220
+ },
221
+ {
222
+ "epoch": 3.63,
223
+ "learning_rate": 7.900786448880824e-05,
224
+ "loss": 0.6935,
225
+ "step": 18000
226
+ },
227
+ {
228
+ "epoch": 3.73,
229
+ "learning_rate": 7.564697183571957e-05,
230
+ "loss": 0.6933,
231
+ "step": 18500
232
+ },
233
+ {
234
+ "epoch": 3.83,
235
+ "learning_rate": 7.22860791826309e-05,
236
+ "loss": 0.6925,
237
+ "step": 19000
238
+ },
239
+ {
240
+ "epoch": 3.93,
241
+ "learning_rate": 6.892518652954225e-05,
242
+ "loss": 0.694,
243
+ "step": 19500
244
+ },
245
+ {
246
+ "epoch": 4.03,
247
+ "learning_rate": 6.556429387645359e-05,
248
+ "loss": 0.6931,
249
+ "step": 20000
250
+ },
251
+ {
252
+ "epoch": 4.13,
253
+ "learning_rate": 6.220340122336493e-05,
254
+ "loss": 0.6934,
255
+ "step": 20500
256
+ },
257
+ {
258
+ "epoch": 4.23,
259
+ "learning_rate": 5.884250857027627e-05,
260
+ "loss": 0.6934,
261
+ "step": 21000
262
+ },
263
+ {
264
+ "epoch": 4.34,
265
+ "learning_rate": 5.548161591718761e-05,
266
+ "loss": 0.6933,
267
+ "step": 21500
268
+ },
269
+ {
270
+ "epoch": 4.44,
271
+ "learning_rate": 5.212072326409895e-05,
272
+ "loss": 0.6933,
273
+ "step": 22000
274
+ },
275
+ {
276
+ "epoch": 4.54,
277
+ "learning_rate": 4.875983061101029e-05,
278
+ "loss": 0.6933,
279
+ "step": 22500
280
+ },
281
+ {
282
+ "epoch": 4.64,
283
+ "learning_rate": 4.5398937957921626e-05,
284
+ "loss": 0.6935,
285
+ "step": 23000
286
+ },
287
+ {
288
+ "epoch": 4.74,
289
+ "learning_rate": 4.203804530483297e-05,
290
+ "loss": 0.6931,
291
+ "step": 23500
292
+ },
293
+ {
294
+ "epoch": 4.84,
295
+ "learning_rate": 3.86771526517443e-05,
296
+ "loss": 0.6933,
297
+ "step": 24000
298
+ },
299
+ {
300
+ "epoch": 4.94,
301
+ "learning_rate": 3.531625999865564e-05,
302
+ "loss": 0.6931,
303
+ "step": 24500
304
+ },
305
+ {
306
+ "epoch": 5.04,
307
+ "learning_rate": 3.1955367345566985e-05,
308
+ "loss": 0.6932,
309
+ "step": 25000
310
+ },
311
+ {
312
+ "epoch": 5.14,
313
+ "learning_rate": 2.8594474692478323e-05,
314
+ "loss": 0.6933,
315
+ "step": 25500
316
+ },
317
+ {
318
+ "epoch": 5.24,
319
+ "learning_rate": 2.5233582039389664e-05,
320
+ "loss": 0.693,
321
+ "step": 26000
322
+ },
323
+ {
324
+ "epoch": 5.34,
325
+ "learning_rate": 2.1872689386301002e-05,
326
+ "loss": 0.6933,
327
+ "step": 26500
328
+ },
329
+ {
330
+ "epoch": 5.44,
331
+ "learning_rate": 1.8511796733212343e-05,
332
+ "loss": 0.6932,
333
+ "step": 27000
334
+ },
335
+ {
336
+ "epoch": 5.55,
337
+ "learning_rate": 1.5150904080123683e-05,
338
+ "loss": 0.6931,
339
+ "step": 27500
340
+ },
341
+ {
342
+ "epoch": 5.65,
343
+ "learning_rate": 1.179001142703502e-05,
344
+ "loss": 0.6932,
345
+ "step": 28000
346
+ },
347
+ {
348
+ "epoch": 5.75,
349
+ "learning_rate": 8.429118773946362e-06,
350
+ "loss": 0.6932,
351
+ "step": 28500
352
+ },
353
+ {
354
+ "epoch": 5.85,
355
+ "learning_rate": 5.0682261208576995e-06,
356
+ "loss": 0.6934,
357
+ "step": 29000
358
+ },
359
+ {
360
+ "epoch": 5.95,
361
+ "learning_rate": 1.7073334677690397e-06,
362
+ "loss": 0.6932,
363
+ "step": 29500
364
+ }
365
+ ],
366
+ "logging_steps": 500,
367
+ "max_steps": 29754,
368
+ "num_train_epochs": 6,
369
+ "save_steps": 500,
370
+ "total_flos": 1.89697260437559e+16,
371
+ "trial_name": null,
372
+ "trial_params": {
373
+ "learning_rate": 0.0002,
374
+ "num_train_epochs": 6,
375
+ "weight_decay": 0.005
376
+ }
377
+ }
run-0/checkpoint-29754/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63282809f1f1a653e90828ade20d71b6232fb78a3a1932c6cb6661fe169b687c
3
+ size 4600
run-0/checkpoint-29754/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec01_16-51-56_516e27a14fd3/events.out.tfevents.1701452487.516e27a14fd3.673.8 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bc5ecd08fbef8b384274cf2290024fd12c420360a7eaac48ce77c758d9ca5e8
3
- size 12452
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe9e61614222aa01bd4759a44ac81feb7d8eb89ed55528605f3fe6fc781eb54
3
+ size 14252