Hugging Face's logo

vuk123
/
QaagiFilter3

TensorBoard
Safetensors
bert
Trained with AutoTrain
text-regression
Model card Files
xet
 Metrics Community
vuk123 commited on
Commit
44973f9
·
verified ·
1 Parent(s): 65cd943

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. README.md +26 -0
  2. checkpoint-1500/config.json +34 -0
  3. checkpoint-1500/model.safetensors +3 -0
  4. checkpoint-1500/optimizer.pt +3 -0
  5. checkpoint-1500/rng_state_0.pth +3 -0
  6. checkpoint-1500/rng_state_1.pth +3 -0
  7. checkpoint-1500/scheduler.pt +3 -0
  8. checkpoint-1500/trainer_state.json +527 -0
  9. checkpoint-1500/training_args.bin +3 -0
  10. config.json +34 -0
  11. model.safetensors +3 -0
  12. runs/Oct16_08-32-42_bora-Lambda-Vector/events.out.tfevents.1729092764.bora-Lambda-Vector.174839.0 +2 -2
  13. runs/Oct16_08-32-42_bora-Lambda-Vector/events.out.tfevents.1729093158.bora-Lambda-Vector.174839.1 +3 -0
  14. special_tokens_map.json +7 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +55 -0
  17. training_args.bin +3 -0
  18. training_params.json +30 -0
  19. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - text-regression
6
+ base_model: google-bert/bert-base-uncased
7
+ widget:
8
+ - text: "I love AutoTrain"
9
+ ---
10
+
11
+ # Model Trained Using AutoTrain
12
+
13
+ - Problem type: Text Regression
14
+
15
+ ## Validation Metrics
16
+ loss: 2.2920706272125244
17
+
18
+ mse: 2.2920706272125244
19
+
20
+ mae: 1.1123970746994019
21
+
22
+ r2: 0.6393013000488281
23
+
24
+ rmse: 1.5139585733413696
25
+
26
+ explained_variance: 0.6458940505981445
checkpoint-1500/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
3
+ "_num_labels": 1,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "target"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "target": 0
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "regression",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.45.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
checkpoint-1500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1862d3955c239cb3f081e5e1b53d030f3f6760b01d41356300e021e0c23febdb
3
+ size 437955572
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b874950a91f0b9da307abe0fcd3d5fbb427c3d74e2faca0d5badfc058f876505
3
+ size 876032250
checkpoint-1500/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b07c8c37eda8d4f006603379d98896d7f6fb80cfa6a33f933a25a186688c527
3
+ size 14512
checkpoint-1500/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41a93e1d02f1b71112a369dc7db970bdf0188cb2e67bf98341f57f7fbe850c3
3
+ size 14512
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e36dcf1406cb6f00a5fd59306778a22c04dd6d71ae69be82989a2e1ddc7d018
3
+ size 1064
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,527 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.2920706272125244,
3
+ "best_model_checkpoint": "QaagiFilter3/checkpoint-1500",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08333333333333333,
13
+ "grad_norm": 203.57440185546875,
14
+ "learning_rate": 3.166666666666667e-06,
15
+ "loss": 27.8593,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.16666666666666666,
20
+ "grad_norm": 163.1396484375,
21
+ "learning_rate": 7.333333333333334e-06,
22
+ "loss": 23.387,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.25,
27
+ "grad_norm": 81.33038330078125,
28
+ "learning_rate": 1.1500000000000002e-05,
29
+ "loss": 13.9295,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.3333333333333333,
34
+ "grad_norm": 33.5482292175293,
35
+ "learning_rate": 1.5666666666666667e-05,
36
+ "loss": 7.7122,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.4166666666666667,
41
+ "grad_norm": 36.23005676269531,
42
+ "learning_rate": 1.9833333333333335e-05,
43
+ "loss": 5.0666,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.5,
48
+ "grad_norm": 36.48677444458008,
49
+ "learning_rate": 2.4e-05,
50
+ "loss": 3.9894,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.5833333333333334,
55
+ "grad_norm": 74.38584899902344,
56
+ "learning_rate": 2.816666666666667e-05,
57
+ "loss": 3.8645,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.6666666666666666,
62
+ "grad_norm": 49.025814056396484,
63
+ "learning_rate": 3.233333333333333e-05,
64
+ "loss": 3.9696,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.75,
69
+ "grad_norm": 50.01852798461914,
70
+ "learning_rate": 3.65e-05,
71
+ "loss": 3.283,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.8333333333333334,
76
+ "grad_norm": 37.934364318847656,
77
+ "learning_rate": 4.066666666666667e-05,
78
+ "loss": 3.735,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.9166666666666666,
83
+ "grad_norm": 92.65830993652344,
84
+ "learning_rate": 4.483333333333333e-05,
85
+ "loss": 3.4056,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 1.0,
90
+ "grad_norm": 70.39775085449219,
91
+ "learning_rate": 4.9e-05,
92
+ "loss": 4.1434,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 1.0,
97
+ "eval_explained_variance": 0.484250545501709,
98
+ "eval_loss": 3.7199275493621826,
99
+ "eval_mae": 1.5320930480957031,
100
+ "eval_mse": 3.7199275493621826,
101
+ "eval_r2": 0.41460227966308594,
102
+ "eval_rmse": 1.9287114143371582,
103
+ "eval_runtime": 1.4061,
104
+ "eval_samples_per_second": 853.43,
105
+ "eval_steps_per_second": 27.025,
106
+ "step": 300
107
+ },
108
+ {
109
+ "epoch": 1.0833333333333333,
110
+ "grad_norm": 72.37615203857422,
111
+ "learning_rate": 4.964814814814815e-05,
112
+ "loss": 2.8186,
113
+ "step": 325
114
+ },
115
+ {
116
+ "epoch": 1.1666666666666667,
117
+ "grad_norm": 36.7435417175293,
118
+ "learning_rate": 4.918518518518519e-05,
119
+ "loss": 2.6416,
120
+ "step": 350
121
+ },
122
+ {
123
+ "epoch": 1.25,
124
+ "grad_norm": 43.16706848144531,
125
+ "learning_rate": 4.8722222222222224e-05,
126
+ "loss": 2.2014,
127
+ "step": 375
128
+ },
129
+ {
130
+ "epoch": 1.3333333333333333,
131
+ "grad_norm": 35.85356521606445,
132
+ "learning_rate": 4.825925925925926e-05,
133
+ "loss": 2.344,
134
+ "step": 400
135
+ },
136
+ {
137
+ "epoch": 1.4166666666666667,
138
+ "grad_norm": 38.85523986816406,
139
+ "learning_rate": 4.77962962962963e-05,
140
+ "loss": 2.3029,
141
+ "step": 425
142
+ },
143
+ {
144
+ "epoch": 1.5,
145
+ "grad_norm": 40.83808135986328,
146
+ "learning_rate": 4.7333333333333336e-05,
147
+ "loss": 2.5387,
148
+ "step": 450
149
+ },
150
+ {
151
+ "epoch": 1.5833333333333335,
152
+ "grad_norm": 73.15798950195312,
153
+ "learning_rate": 4.687037037037037e-05,
154
+ "loss": 2.2528,
155
+ "step": 475
156
+ },
157
+ {
158
+ "epoch": 1.6666666666666665,
159
+ "grad_norm": 32.92269515991211,
160
+ "learning_rate": 4.640740740740741e-05,
161
+ "loss": 2.1096,
162
+ "step": 500
163
+ },
164
+ {
165
+ "epoch": 1.75,
166
+ "grad_norm": 37.778804779052734,
167
+ "learning_rate": 4.594444444444444e-05,
168
+ "loss": 2.4907,
169
+ "step": 525
170
+ },
171
+ {
172
+ "epoch": 1.8333333333333335,
173
+ "grad_norm": 35.420013427734375,
174
+ "learning_rate": 4.548148148148149e-05,
175
+ "loss": 2.3215,
176
+ "step": 550
177
+ },
178
+ {
179
+ "epoch": 1.9166666666666665,
180
+ "grad_norm": 42.403602600097656,
181
+ "learning_rate": 4.501851851851852e-05,
182
+ "loss": 2.0804,
183
+ "step": 575
184
+ },
185
+ {
186
+ "epoch": 2.0,
187
+ "grad_norm": 71.63874053955078,
188
+ "learning_rate": 4.4555555555555555e-05,
189
+ "loss": 2.304,
190
+ "step": 600
191
+ },
192
+ {
193
+ "epoch": 2.0,
194
+ "eval_explained_variance": 0.6256482601165771,
195
+ "eval_loss": 2.3827290534973145,
196
+ "eval_mae": 1.163964867591858,
197
+ "eval_mse": 2.3827288150787354,
198
+ "eval_r2": 0.6250346302986145,
199
+ "eval_rmse": 1.5436090230941772,
200
+ "eval_runtime": 1.4029,
201
+ "eval_samples_per_second": 855.399,
202
+ "eval_steps_per_second": 27.088,
203
+ "step": 600
204
+ },
205
+ {
206
+ "epoch": 2.0833333333333335,
207
+ "grad_norm": 19.71274757385254,
208
+ "learning_rate": 4.4092592592592595e-05,
209
+ "loss": 1.2565,
210
+ "step": 625
211
+ },
212
+ {
213
+ "epoch": 2.1666666666666665,
214
+ "grad_norm": 31.47469711303711,
215
+ "learning_rate": 4.3629629629629635e-05,
216
+ "loss": 1.2529,
217
+ "step": 650
218
+ },
219
+ {
220
+ "epoch": 2.25,
221
+ "grad_norm": 23.2291259765625,
222
+ "learning_rate": 4.316666666666667e-05,
223
+ "loss": 1.2316,
224
+ "step": 675
225
+ },
226
+ {
227
+ "epoch": 2.3333333333333335,
228
+ "grad_norm": 46.9771614074707,
229
+ "learning_rate": 4.270370370370371e-05,
230
+ "loss": 0.9652,
231
+ "step": 700
232
+ },
233
+ {
234
+ "epoch": 2.4166666666666665,
235
+ "grad_norm": 28.63280487060547,
236
+ "learning_rate": 4.224074074074074e-05,
237
+ "loss": 1.0859,
238
+ "step": 725
239
+ },
240
+ {
241
+ "epoch": 2.5,
242
+ "grad_norm": 40.56156921386719,
243
+ "learning_rate": 4.177777777777778e-05,
244
+ "loss": 1.0052,
245
+ "step": 750
246
+ },
247
+ {
248
+ "epoch": 2.5833333333333335,
249
+ "grad_norm": 53.79902267456055,
250
+ "learning_rate": 4.131481481481482e-05,
251
+ "loss": 1.1899,
252
+ "step": 775
253
+ },
254
+ {
255
+ "epoch": 2.6666666666666665,
256
+ "grad_norm": 40.577327728271484,
257
+ "learning_rate": 4.0851851851851853e-05,
258
+ "loss": 0.8368,
259
+ "step": 800
260
+ },
261
+ {
262
+ "epoch": 2.75,
263
+ "grad_norm": 53.498016357421875,
264
+ "learning_rate": 4.038888888888889e-05,
265
+ "loss": 0.8995,
266
+ "step": 825
267
+ },
268
+ {
269
+ "epoch": 2.8333333333333335,
270
+ "grad_norm": 23.701671600341797,
271
+ "learning_rate": 3.9925925925925926e-05,
272
+ "loss": 1.0837,
273
+ "step": 850
274
+ },
275
+ {
276
+ "epoch": 2.9166666666666665,
277
+ "grad_norm": 39.308101654052734,
278
+ "learning_rate": 3.946296296296296e-05,
279
+ "loss": 0.9715,
280
+ "step": 875
281
+ },
282
+ {
283
+ "epoch": 3.0,
284
+ "grad_norm": 47.296966552734375,
285
+ "learning_rate": 3.9000000000000006e-05,
286
+ "loss": 1.3128,
287
+ "step": 900
288
+ },
289
+ {
290
+ "epoch": 3.0,
291
+ "eval_explained_variance": 0.6129987239837646,
292
+ "eval_loss": 2.6801981925964355,
293
+ "eval_mae": 1.1843883991241455,
294
+ "eval_mse": 2.6801979541778564,
295
+ "eval_r2": 0.5782225131988525,
296
+ "eval_rmse": 1.6371309757232666,
297
+ "eval_runtime": 1.3833,
298
+ "eval_samples_per_second": 867.517,
299
+ "eval_steps_per_second": 27.471,
300
+ "step": 900
301
+ },
302
+ {
303
+ "epoch": 3.0833333333333335,
304
+ "grad_norm": 27.515487670898438,
305
+ "learning_rate": 3.853703703703704e-05,
306
+ "loss": 0.5462,
307
+ "step": 925
308
+ },
309
+ {
310
+ "epoch": 3.1666666666666665,
311
+ "grad_norm": 27.193992614746094,
312
+ "learning_rate": 3.807407407407408e-05,
313
+ "loss": 0.6948,
314
+ "step": 950
315
+ },
316
+ {
317
+ "epoch": 3.25,
318
+ "grad_norm": 32.09097671508789,
319
+ "learning_rate": 3.761111111111111e-05,
320
+ "loss": 0.6207,
321
+ "step": 975
322
+ },
323
+ {
324
+ "epoch": 3.3333333333333335,
325
+ "grad_norm": 20.979494094848633,
326
+ "learning_rate": 3.714814814814815e-05,
327
+ "loss": 0.6791,
328
+ "step": 1000
329
+ },
330
+ {
331
+ "epoch": 3.4166666666666665,
332
+ "grad_norm": 22.093290328979492,
333
+ "learning_rate": 3.668518518518519e-05,
334
+ "loss": 0.6075,
335
+ "step": 1025
336
+ },
337
+ {
338
+ "epoch": 3.5,
339
+ "grad_norm": 24.52804183959961,
340
+ "learning_rate": 3.6222222222222225e-05,
341
+ "loss": 0.796,
342
+ "step": 1050
343
+ },
344
+ {
345
+ "epoch": 3.5833333333333335,
346
+ "grad_norm": 13.169271469116211,
347
+ "learning_rate": 3.575925925925926e-05,
348
+ "loss": 0.5455,
349
+ "step": 1075
350
+ },
351
+ {
352
+ "epoch": 3.6666666666666665,
353
+ "grad_norm": 23.37912368774414,
354
+ "learning_rate": 3.52962962962963e-05,
355
+ "loss": 0.5924,
356
+ "step": 1100
357
+ },
358
+ {
359
+ "epoch": 3.75,
360
+ "grad_norm": 23.409942626953125,
361
+ "learning_rate": 3.483333333333334e-05,
362
+ "loss": 0.5839,
363
+ "step": 1125
364
+ },
365
+ {
366
+ "epoch": 3.8333333333333335,
367
+ "grad_norm": 14.830960273742676,
368
+ "learning_rate": 3.437037037037037e-05,
369
+ "loss": 0.6003,
370
+ "step": 1150
371
+ },
372
+ {
373
+ "epoch": 3.9166666666666665,
374
+ "grad_norm": 29.192399978637695,
375
+ "learning_rate": 3.390740740740741e-05,
376
+ "loss": 0.5715,
377
+ "step": 1175
378
+ },
379
+ {
380
+ "epoch": 4.0,
381
+ "grad_norm": 19.0704402923584,
382
+ "learning_rate": 3.3444444444444443e-05,
383
+ "loss": 0.632,
384
+ "step": 1200
385
+ },
386
+ {
387
+ "epoch": 4.0,
388
+ "eval_explained_variance": 0.6389033794403076,
389
+ "eval_loss": 2.541696071624756,
390
+ "eval_mae": 1.168035864830017,
391
+ "eval_mse": 2.541696071624756,
392
+ "eval_r2": 0.6000182628631592,
393
+ "eval_rmse": 1.5942697525024414,
394
+ "eval_runtime": 1.4053,
395
+ "eval_samples_per_second": 853.915,
396
+ "eval_steps_per_second": 27.041,
397
+ "step": 1200
398
+ },
399
+ {
400
+ "epoch": 4.083333333333333,
401
+ "grad_norm": 10.236458778381348,
402
+ "learning_rate": 3.298148148148148e-05,
403
+ "loss": 0.3609,
404
+ "step": 1225
405
+ },
406
+ {
407
+ "epoch": 4.166666666666667,
408
+ "grad_norm": 15.39724349975586,
409
+ "learning_rate": 3.251851851851852e-05,
410
+ "loss": 0.3721,
411
+ "step": 1250
412
+ },
413
+ {
414
+ "epoch": 4.25,
415
+ "grad_norm": 16.447935104370117,
416
+ "learning_rate": 3.2055555555555556e-05,
417
+ "loss": 0.3554,
418
+ "step": 1275
419
+ },
420
+ {
421
+ "epoch": 4.333333333333333,
422
+ "grad_norm": 10.421647071838379,
423
+ "learning_rate": 3.1592592592592596e-05,
424
+ "loss": 0.4262,
425
+ "step": 1300
426
+ },
427
+ {
428
+ "epoch": 4.416666666666667,
429
+ "grad_norm": 15.514717102050781,
430
+ "learning_rate": 3.112962962962963e-05,
431
+ "loss": 0.4036,
432
+ "step": 1325
433
+ },
434
+ {
435
+ "epoch": 4.5,
436
+ "grad_norm": 9.377070426940918,
437
+ "learning_rate": 3.066666666666667e-05,
438
+ "loss": 0.3811,
439
+ "step": 1350
440
+ },
441
+ {
442
+ "epoch": 4.583333333333333,
443
+ "grad_norm": 12.767688751220703,
444
+ "learning_rate": 3.0203703703703705e-05,
445
+ "loss": 0.4501,
446
+ "step": 1375
447
+ },
448
+ {
449
+ "epoch": 4.666666666666667,
450
+ "grad_norm": 20.651182174682617,
451
+ "learning_rate": 2.9740740740740742e-05,
452
+ "loss": 0.3876,
453
+ "step": 1400
454
+ },
455
+ {
456
+ "epoch": 4.75,
457
+ "grad_norm": 10.500899314880371,
458
+ "learning_rate": 2.927777777777778e-05,
459
+ "loss": 0.3856,
460
+ "step": 1425
461
+ },
462
+ {
463
+ "epoch": 4.833333333333333,
464
+ "grad_norm": 11.204659461975098,
465
+ "learning_rate": 2.8814814814814818e-05,
466
+ "loss": 0.4262,
467
+ "step": 1450
468
+ },
469
+ {
470
+ "epoch": 4.916666666666667,
471
+ "grad_norm": 26.508119583129883,
472
+ "learning_rate": 2.835185185185185e-05,
473
+ "loss": 0.4429,
474
+ "step": 1475
475
+ },
476
+ {
477
+ "epoch": 5.0,
478
+ "grad_norm": 23.41118621826172,
479
+ "learning_rate": 2.788888888888889e-05,
480
+ "loss": 0.3862,
481
+ "step": 1500
482
+ },
483
+ {
484
+ "epoch": 5.0,
485
+ "eval_explained_variance": 0.6458940505981445,
486
+ "eval_loss": 2.2920706272125244,
487
+ "eval_mae": 1.1123970746994019,
488
+ "eval_mse": 2.2920706272125244,
489
+ "eval_r2": 0.6393013000488281,
490
+ "eval_rmse": 1.5139585733413696,
491
+ "eval_runtime": 1.386,
492
+ "eval_samples_per_second": 865.825,
493
+ "eval_steps_per_second": 27.418,
494
+ "step": 1500
495
+ }
496
+ ],
497
+ "logging_steps": 25,
498
+ "max_steps": 3000,
499
+ "num_input_tokens_seen": 0,
500
+ "num_train_epochs": 10,
501
+ "save_steps": 500,
502
+ "stateful_callbacks": {
503
+ "EarlyStoppingCallback": {
504
+ "args": {
505
+ "early_stopping_patience": 5,
506
+ "early_stopping_threshold": 0.01
507
+ },
508
+ "attributes": {
509
+ "early_stopping_patience_counter": 0
510
+ }
511
+ },
512
+ "TrainerControl": {
513
+ "args": {
514
+ "should_epoch_stop": false,
515
+ "should_evaluate": false,
516
+ "should_log": false,
517
+ "should_save": true,
518
+ "should_training_stop": false
519
+ },
520
+ "attributes": {}
521
+ }
522
+ },
523
+ "total_flos": 1578652139520000.0,
524
+ "train_batch_size": 8,
525
+ "trial_name": null,
526
+ "trial_params": null
527
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78430683b6ede99522478a9b4b76c6f8811dd22f6166dd46ff939c9f1f9a0432
3
+ size 5240
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
3
+ "_num_labels": 1,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "target"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "target": 0
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "regression",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.45.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1862d3955c239cb3f081e5e1b53d030f3f6760b01d41356300e021e0c23febdb
3
+ size 437955572
runs/Oct16_08-32-42_bora-Lambda-Vector/events.out.tfevents.1729092764.bora-Lambda-Vector.174839.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:622feb9a97031f92a15be60ec6cf8afd71dfef326a1b95fdad32eb629fbc6d96
3
- size 5023
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091d1177ec6bdbe3d3e0d6a4832f24a18108ccd889964c460785b79dec88e83d
3
+ size 35887
runs/Oct16_08-32-42_bora-Lambda-Vector/events.out.tfevents.1729093158.bora-Lambda-Vector.174839.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50725f2265be6755a200b13e853f4edd493094cd6ae8a8c38a73d8979dc85fb9
3
+ size 609
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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78430683b6ede99522478a9b4b76c6f8811dd22f6166dd46ff939c9f1f9a0432
3
+ size 5240
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "QaagiFilter3/autotrain-data",
3
+ "model": "google-bert/bert-base-uncased",
4
+ "lr": 5e-05,
5
+ "epochs": 10,
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": "QaagiFilter3",
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": "vuk123",
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