Abgegrieft commited on
Commit
356f80c
·
verified ·
1 Parent(s): 947dd37

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - text-regression
6
+ base_model: google-bert/bert-base-german-cased
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: 0.027760107070207596
17
+
18
+ mse: 0.027760105207562447
19
+
20
+ mae: 0.1187298521399498
21
+
22
+ r2: 0.6345672607421875
23
+
24
+ rmse: 0.1666136405207042
25
+
26
+ explained_variance: 0.6521931886672974
checkpoint-2232/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-german-cased",
3
+ "_num_labels": 1,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "target"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "target": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "problem_type": "regression",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.48.0",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 30000
33
+ }
checkpoint-2232/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4c09c509249de28f1ab20a576a6b89ba83f2f82c29442900a93e817b7b4da1
3
+ size 436351980
checkpoint-2232/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6de7799134095d6c791d6542e43701dc3c2c73fbafd3c9fc4787cb61076160a1
3
+ size 872825082
checkpoint-2232/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bab75406201b086186586a8379a56b115ae0abb33a078c01ee847c96cff92af3
3
+ size 14244
checkpoint-2232/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee335796698c8afe1af226ae5cc09aebcc8c2eb098c4ff747d0ad77b6bd9fde
3
+ size 1064
checkpoint-2232/trainer_state.json ADDED
@@ -0,0 +1,1037 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.027760107070207596,
3
+ "best_model_checkpoint": "autotrain-lv9vc-kt81s/checkpoint-2232",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2232,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0456989247311828,
13
+ "grad_norm": 4.31789493560791,
14
+ "learning_rate": 1.901565995525727e-06,
15
+ "loss": 0.0918,
16
+ "step": 17
17
+ },
18
+ {
19
+ "epoch": 0.0913978494623656,
20
+ "grad_norm": 4.4698166847229,
21
+ "learning_rate": 3.803131991051454e-06,
22
+ "loss": 0.0902,
23
+ "step": 34
24
+ },
25
+ {
26
+ "epoch": 0.13709677419354838,
27
+ "grad_norm": 3.42223858833313,
28
+ "learning_rate": 5.704697986577182e-06,
29
+ "loss": 0.0778,
30
+ "step": 51
31
+ },
32
+ {
33
+ "epoch": 0.1827956989247312,
34
+ "grad_norm": 11.799783706665039,
35
+ "learning_rate": 7.606263982102908e-06,
36
+ "loss": 0.086,
37
+ "step": 68
38
+ },
39
+ {
40
+ "epoch": 0.22849462365591397,
41
+ "grad_norm": 7.080126762390137,
42
+ "learning_rate": 9.507829977628636e-06,
43
+ "loss": 0.0663,
44
+ "step": 85
45
+ },
46
+ {
47
+ "epoch": 0.27419354838709675,
48
+ "grad_norm": 3.4527671337127686,
49
+ "learning_rate": 1.1409395973154363e-05,
50
+ "loss": 0.0647,
51
+ "step": 102
52
+ },
53
+ {
54
+ "epoch": 0.31989247311827956,
55
+ "grad_norm": 3.801008701324463,
56
+ "learning_rate": 1.331096196868009e-05,
57
+ "loss": 0.0571,
58
+ "step": 119
59
+ },
60
+ {
61
+ "epoch": 0.3655913978494624,
62
+ "grad_norm": 12.45450496673584,
63
+ "learning_rate": 1.5212527964205816e-05,
64
+ "loss": 0.0749,
65
+ "step": 136
66
+ },
67
+ {
68
+ "epoch": 0.4112903225806452,
69
+ "grad_norm": 5.401353359222412,
70
+ "learning_rate": 1.7114093959731545e-05,
71
+ "loss": 0.0929,
72
+ "step": 153
73
+ },
74
+ {
75
+ "epoch": 0.45698924731182794,
76
+ "grad_norm": 4.28618049621582,
77
+ "learning_rate": 1.9015659955257272e-05,
78
+ "loss": 0.0693,
79
+ "step": 170
80
+ },
81
+ {
82
+ "epoch": 0.5026881720430108,
83
+ "grad_norm": 6.603745937347412,
84
+ "learning_rate": 2.0917225950783e-05,
85
+ "loss": 0.0659,
86
+ "step": 187
87
+ },
88
+ {
89
+ "epoch": 0.5483870967741935,
90
+ "grad_norm": 7.406251907348633,
91
+ "learning_rate": 2.2818791946308727e-05,
92
+ "loss": 0.0731,
93
+ "step": 204
94
+ },
95
+ {
96
+ "epoch": 0.5940860215053764,
97
+ "grad_norm": 10.292195320129395,
98
+ "learning_rate": 2.4720357941834454e-05,
99
+ "loss": 0.0802,
100
+ "step": 221
101
+ },
102
+ {
103
+ "epoch": 0.6397849462365591,
104
+ "grad_norm": 2.9652514457702637,
105
+ "learning_rate": 2.662192393736018e-05,
106
+ "loss": 0.0592,
107
+ "step": 238
108
+ },
109
+ {
110
+ "epoch": 0.6854838709677419,
111
+ "grad_norm": 2.540503740310669,
112
+ "learning_rate": 2.8523489932885905e-05,
113
+ "loss": 0.0693,
114
+ "step": 255
115
+ },
116
+ {
117
+ "epoch": 0.7311827956989247,
118
+ "grad_norm": 4.972765922546387,
119
+ "learning_rate": 3.0425055928411632e-05,
120
+ "loss": 0.0538,
121
+ "step": 272
122
+ },
123
+ {
124
+ "epoch": 0.7768817204301075,
125
+ "grad_norm": 6.958789348602295,
126
+ "learning_rate": 3.232662192393736e-05,
127
+ "loss": 0.0784,
128
+ "step": 289
129
+ },
130
+ {
131
+ "epoch": 0.8225806451612904,
132
+ "grad_norm": 11.929637908935547,
133
+ "learning_rate": 3.422818791946309e-05,
134
+ "loss": 0.0829,
135
+ "step": 306
136
+ },
137
+ {
138
+ "epoch": 0.8682795698924731,
139
+ "grad_norm": 5.011415481567383,
140
+ "learning_rate": 3.612975391498882e-05,
141
+ "loss": 0.0844,
142
+ "step": 323
143
+ },
144
+ {
145
+ "epoch": 0.9139784946236559,
146
+ "grad_norm": 2.751051664352417,
147
+ "learning_rate": 3.8031319910514545e-05,
148
+ "loss": 0.0642,
149
+ "step": 340
150
+ },
151
+ {
152
+ "epoch": 0.9596774193548387,
153
+ "grad_norm": 4.713333606719971,
154
+ "learning_rate": 3.993288590604027e-05,
155
+ "loss": 0.0543,
156
+ "step": 357
157
+ },
158
+ {
159
+ "epoch": 1.0,
160
+ "eval_explained_variance": 0.4571152329444885,
161
+ "eval_loss": 0.04460810869932175,
162
+ "eval_mae": 0.17250476777553558,
163
+ "eval_mse": 0.04460810869932175,
164
+ "eval_r2": 0.41278088092803955,
165
+ "eval_rmse": 0.21120631784897378,
166
+ "eval_runtime": 0.8149,
167
+ "eval_samples_per_second": 834.48,
168
+ "eval_steps_per_second": 52.769,
169
+ "step": 372
170
+ },
171
+ {
172
+ "epoch": 1.0053763440860215,
173
+ "grad_norm": 9.579811096191406,
174
+ "learning_rate": 4.1834451901566e-05,
175
+ "loss": 0.0676,
176
+ "step": 374
177
+ },
178
+ {
179
+ "epoch": 1.0510752688172043,
180
+ "grad_norm": 1.473509669303894,
181
+ "learning_rate": 4.373601789709172e-05,
182
+ "loss": 0.0532,
183
+ "step": 391
184
+ },
185
+ {
186
+ "epoch": 1.096774193548387,
187
+ "grad_norm": 5.4681596755981445,
188
+ "learning_rate": 4.5637583892617453e-05,
189
+ "loss": 0.063,
190
+ "step": 408
191
+ },
192
+ {
193
+ "epoch": 1.14247311827957,
194
+ "grad_norm": 1.8373321294784546,
195
+ "learning_rate": 4.753914988814318e-05,
196
+ "loss": 0.0425,
197
+ "step": 425
198
+ },
199
+ {
200
+ "epoch": 1.1881720430107527,
201
+ "grad_norm": 1.803191900253296,
202
+ "learning_rate": 4.944071588366891e-05,
203
+ "loss": 0.0457,
204
+ "step": 442
205
+ },
206
+ {
207
+ "epoch": 1.2338709677419355,
208
+ "grad_norm": 2.3846850395202637,
209
+ "learning_rate": 4.985063480209112e-05,
210
+ "loss": 0.042,
211
+ "step": 459
212
+ },
213
+ {
214
+ "epoch": 1.2795698924731183,
215
+ "grad_norm": 5.699389457702637,
216
+ "learning_rate": 4.963903410505352e-05,
217
+ "loss": 0.0452,
218
+ "step": 476
219
+ },
220
+ {
221
+ "epoch": 1.325268817204301,
222
+ "grad_norm": 4.71431303024292,
223
+ "learning_rate": 4.942743340801593e-05,
224
+ "loss": 0.0488,
225
+ "step": 493
226
+ },
227
+ {
228
+ "epoch": 1.370967741935484,
229
+ "grad_norm": 3.2016053199768066,
230
+ "learning_rate": 4.9215832710978346e-05,
231
+ "loss": 0.0705,
232
+ "step": 510
233
+ },
234
+ {
235
+ "epoch": 1.4166666666666667,
236
+ "grad_norm": 4.895547389984131,
237
+ "learning_rate": 4.9004232013940755e-05,
238
+ "loss": 0.0418,
239
+ "step": 527
240
+ },
241
+ {
242
+ "epoch": 1.4623655913978495,
243
+ "grad_norm": 1.8652331829071045,
244
+ "learning_rate": 4.879263131690316e-05,
245
+ "loss": 0.043,
246
+ "step": 544
247
+ },
248
+ {
249
+ "epoch": 1.5080645161290323,
250
+ "grad_norm": 2.7822670936584473,
251
+ "learning_rate": 4.858103061986558e-05,
252
+ "loss": 0.0528,
253
+ "step": 561
254
+ },
255
+ {
256
+ "epoch": 1.553763440860215,
257
+ "grad_norm": 1.143685221672058,
258
+ "learning_rate": 4.836942992282799e-05,
259
+ "loss": 0.04,
260
+ "step": 578
261
+ },
262
+ {
263
+ "epoch": 1.599462365591398,
264
+ "grad_norm": 1.6108208894729614,
265
+ "learning_rate": 4.815782922579039e-05,
266
+ "loss": 0.0602,
267
+ "step": 595
268
+ },
269
+ {
270
+ "epoch": 1.6451612903225805,
271
+ "grad_norm": 5.366172790527344,
272
+ "learning_rate": 4.7946228528752804e-05,
273
+ "loss": 0.0411,
274
+ "step": 612
275
+ },
276
+ {
277
+ "epoch": 1.6908602150537635,
278
+ "grad_norm": 1.4409973621368408,
279
+ "learning_rate": 4.773462783171521e-05,
280
+ "loss": 0.0356,
281
+ "step": 629
282
+ },
283
+ {
284
+ "epoch": 1.7365591397849462,
285
+ "grad_norm": 2.665142059326172,
286
+ "learning_rate": 4.752302713467762e-05,
287
+ "loss": 0.0398,
288
+ "step": 646
289
+ },
290
+ {
291
+ "epoch": 1.782258064516129,
292
+ "grad_norm": 2.4110679626464844,
293
+ "learning_rate": 4.731142643764003e-05,
294
+ "loss": 0.0432,
295
+ "step": 663
296
+ },
297
+ {
298
+ "epoch": 1.827956989247312,
299
+ "grad_norm": 1.0476489067077637,
300
+ "learning_rate": 4.7099825740602445e-05,
301
+ "loss": 0.0647,
302
+ "step": 680
303
+ },
304
+ {
305
+ "epoch": 1.8736559139784945,
306
+ "grad_norm": 2.0937328338623047,
307
+ "learning_rate": 4.6888225043564854e-05,
308
+ "loss": 0.0508,
309
+ "step": 697
310
+ },
311
+ {
312
+ "epoch": 1.9193548387096775,
313
+ "grad_norm": 1.6009521484375,
314
+ "learning_rate": 4.667662434652726e-05,
315
+ "loss": 0.0362,
316
+ "step": 714
317
+ },
318
+ {
319
+ "epoch": 1.9650537634408602,
320
+ "grad_norm": 2.7363243103027344,
321
+ "learning_rate": 4.646502364948967e-05,
322
+ "loss": 0.0299,
323
+ "step": 731
324
+ },
325
+ {
326
+ "epoch": 2.0,
327
+ "eval_explained_variance": 0.5425602197647095,
328
+ "eval_loss": 0.044957660138607025,
329
+ "eval_mae": 0.17004044353961945,
330
+ "eval_mse": 0.044957663863897324,
331
+ "eval_r2": 0.4081794023513794,
332
+ "eval_rmse": 0.2120322236451274,
333
+ "eval_runtime": 0.8158,
334
+ "eval_samples_per_second": 833.513,
335
+ "eval_steps_per_second": 52.707,
336
+ "step": 744
337
+ },
338
+ {
339
+ "epoch": 2.010752688172043,
340
+ "grad_norm": 4.17310905456543,
341
+ "learning_rate": 4.625342295245208e-05,
342
+ "loss": 0.0516,
343
+ "step": 748
344
+ },
345
+ {
346
+ "epoch": 2.056451612903226,
347
+ "grad_norm": 1.8113194704055786,
348
+ "learning_rate": 4.604182225541449e-05,
349
+ "loss": 0.0293,
350
+ "step": 765
351
+ },
352
+ {
353
+ "epoch": 2.1021505376344085,
354
+ "grad_norm": 3.3152263164520264,
355
+ "learning_rate": 4.5830221558376903e-05,
356
+ "loss": 0.0264,
357
+ "step": 782
358
+ },
359
+ {
360
+ "epoch": 2.1478494623655915,
361
+ "grad_norm": 3.094778299331665,
362
+ "learning_rate": 4.561862086133931e-05,
363
+ "loss": 0.0235,
364
+ "step": 799
365
+ },
366
+ {
367
+ "epoch": 2.193548387096774,
368
+ "grad_norm": 3.240532159805298,
369
+ "learning_rate": 4.540702016430172e-05,
370
+ "loss": 0.0295,
371
+ "step": 816
372
+ },
373
+ {
374
+ "epoch": 2.239247311827957,
375
+ "grad_norm": 0.9303725957870483,
376
+ "learning_rate": 4.519541946726413e-05,
377
+ "loss": 0.0394,
378
+ "step": 833
379
+ },
380
+ {
381
+ "epoch": 2.28494623655914,
382
+ "grad_norm": 0.8306027054786682,
383
+ "learning_rate": 4.498381877022654e-05,
384
+ "loss": 0.0271,
385
+ "step": 850
386
+ },
387
+ {
388
+ "epoch": 2.3306451612903225,
389
+ "grad_norm": 1.9762545824050903,
390
+ "learning_rate": 4.4772218073188946e-05,
391
+ "loss": 0.036,
392
+ "step": 867
393
+ },
394
+ {
395
+ "epoch": 2.3763440860215055,
396
+ "grad_norm": 1.5883570909500122,
397
+ "learning_rate": 4.456061737615136e-05,
398
+ "loss": 0.0376,
399
+ "step": 884
400
+ },
401
+ {
402
+ "epoch": 2.422043010752688,
403
+ "grad_norm": 2.6263465881347656,
404
+ "learning_rate": 4.434901667911377e-05,
405
+ "loss": 0.0245,
406
+ "step": 901
407
+ },
408
+ {
409
+ "epoch": 2.467741935483871,
410
+ "grad_norm": 2.91164493560791,
411
+ "learning_rate": 4.413741598207618e-05,
412
+ "loss": 0.0241,
413
+ "step": 918
414
+ },
415
+ {
416
+ "epoch": 2.513440860215054,
417
+ "grad_norm": 1.1037144660949707,
418
+ "learning_rate": 4.392581528503859e-05,
419
+ "loss": 0.0271,
420
+ "step": 935
421
+ },
422
+ {
423
+ "epoch": 2.5591397849462365,
424
+ "grad_norm": 1.6593691110610962,
425
+ "learning_rate": 4.3714214588000996e-05,
426
+ "loss": 0.023,
427
+ "step": 952
428
+ },
429
+ {
430
+ "epoch": 2.6048387096774195,
431
+ "grad_norm": 1.416928768157959,
432
+ "learning_rate": 4.3502613890963404e-05,
433
+ "loss": 0.0257,
434
+ "step": 969
435
+ },
436
+ {
437
+ "epoch": 2.650537634408602,
438
+ "grad_norm": 0.5436545014381409,
439
+ "learning_rate": 4.329101319392582e-05,
440
+ "loss": 0.0282,
441
+ "step": 986
442
+ },
443
+ {
444
+ "epoch": 2.696236559139785,
445
+ "grad_norm": 2.5085415840148926,
446
+ "learning_rate": 4.307941249688823e-05,
447
+ "loss": 0.0411,
448
+ "step": 1003
449
+ },
450
+ {
451
+ "epoch": 2.741935483870968,
452
+ "grad_norm": 2.031670093536377,
453
+ "learning_rate": 4.286781179985064e-05,
454
+ "loss": 0.0261,
455
+ "step": 1020
456
+ },
457
+ {
458
+ "epoch": 2.7876344086021505,
459
+ "grad_norm": 1.2079259157180786,
460
+ "learning_rate": 4.2656211102813046e-05,
461
+ "loss": 0.021,
462
+ "step": 1037
463
+ },
464
+ {
465
+ "epoch": 2.8333333333333335,
466
+ "grad_norm": 2.322828769683838,
467
+ "learning_rate": 4.244461040577546e-05,
468
+ "loss": 0.0267,
469
+ "step": 1054
470
+ },
471
+ {
472
+ "epoch": 2.879032258064516,
473
+ "grad_norm": 1.6457505226135254,
474
+ "learning_rate": 4.223300970873786e-05,
475
+ "loss": 0.0247,
476
+ "step": 1071
477
+ },
478
+ {
479
+ "epoch": 2.924731182795699,
480
+ "grad_norm": 1.2150781154632568,
481
+ "learning_rate": 4.202140901170027e-05,
482
+ "loss": 0.0266,
483
+ "step": 1088
484
+ },
485
+ {
486
+ "epoch": 2.970430107526882,
487
+ "grad_norm": 3.3846487998962402,
488
+ "learning_rate": 4.1809808314662687e-05,
489
+ "loss": 0.0209,
490
+ "step": 1105
491
+ },
492
+ {
493
+ "epoch": 3.0,
494
+ "eval_explained_variance": 0.5332338213920593,
495
+ "eval_loss": 0.037166669964790344,
496
+ "eval_mae": 0.13921906054019928,
497
+ "eval_mse": 0.037166669964790344,
498
+ "eval_r2": 0.5107396841049194,
499
+ "eval_rmse": 0.19278659176610374,
500
+ "eval_runtime": 0.8144,
501
+ "eval_samples_per_second": 834.952,
502
+ "eval_steps_per_second": 52.798,
503
+ "step": 1116
504
+ },
505
+ {
506
+ "epoch": 3.0161290322580645,
507
+ "grad_norm": 1.5886852741241455,
508
+ "learning_rate": 4.1598207617625095e-05,
509
+ "loss": 0.0241,
510
+ "step": 1122
511
+ },
512
+ {
513
+ "epoch": 3.0618279569892475,
514
+ "grad_norm": 0.4105478823184967,
515
+ "learning_rate": 4.1386606920587504e-05,
516
+ "loss": 0.0167,
517
+ "step": 1139
518
+ },
519
+ {
520
+ "epoch": 3.10752688172043,
521
+ "grad_norm": 0.9727150201797485,
522
+ "learning_rate": 4.117500622354992e-05,
523
+ "loss": 0.0187,
524
+ "step": 1156
525
+ },
526
+ {
527
+ "epoch": 3.153225806451613,
528
+ "grad_norm": 1.0809416770935059,
529
+ "learning_rate": 4.096340552651233e-05,
530
+ "loss": 0.0199,
531
+ "step": 1173
532
+ },
533
+ {
534
+ "epoch": 3.1989247311827955,
535
+ "grad_norm": 1.147793173789978,
536
+ "learning_rate": 4.075180482947473e-05,
537
+ "loss": 0.0145,
538
+ "step": 1190
539
+ },
540
+ {
541
+ "epoch": 3.2446236559139785,
542
+ "grad_norm": 1.8357558250427246,
543
+ "learning_rate": 4.0540204132437145e-05,
544
+ "loss": 0.022,
545
+ "step": 1207
546
+ },
547
+ {
548
+ "epoch": 3.2903225806451615,
549
+ "grad_norm": 0.48548048734664917,
550
+ "learning_rate": 4.032860343539955e-05,
551
+ "loss": 0.0154,
552
+ "step": 1224
553
+ },
554
+ {
555
+ "epoch": 3.336021505376344,
556
+ "grad_norm": 2.7312467098236084,
557
+ "learning_rate": 4.011700273836196e-05,
558
+ "loss": 0.017,
559
+ "step": 1241
560
+ },
561
+ {
562
+ "epoch": 3.381720430107527,
563
+ "grad_norm": 1.3595783710479736,
564
+ "learning_rate": 3.990540204132438e-05,
565
+ "loss": 0.0153,
566
+ "step": 1258
567
+ },
568
+ {
569
+ "epoch": 3.4274193548387095,
570
+ "grad_norm": 0.47709521651268005,
571
+ "learning_rate": 3.9693801344286786e-05,
572
+ "loss": 0.0179,
573
+ "step": 1275
574
+ },
575
+ {
576
+ "epoch": 3.4731182795698925,
577
+ "grad_norm": 1.3275291919708252,
578
+ "learning_rate": 3.948220064724919e-05,
579
+ "loss": 0.0151,
580
+ "step": 1292
581
+ },
582
+ {
583
+ "epoch": 3.518817204301075,
584
+ "grad_norm": 2.7548911571502686,
585
+ "learning_rate": 3.92705999502116e-05,
586
+ "loss": 0.0179,
587
+ "step": 1309
588
+ },
589
+ {
590
+ "epoch": 3.564516129032258,
591
+ "grad_norm": 0.7818028330802917,
592
+ "learning_rate": 3.905899925317401e-05,
593
+ "loss": 0.016,
594
+ "step": 1326
595
+ },
596
+ {
597
+ "epoch": 3.610215053763441,
598
+ "grad_norm": 1.4333502054214478,
599
+ "learning_rate": 3.884739855613642e-05,
600
+ "loss": 0.0176,
601
+ "step": 1343
602
+ },
603
+ {
604
+ "epoch": 3.6559139784946235,
605
+ "grad_norm": 2.125917673110962,
606
+ "learning_rate": 3.8635797859098835e-05,
607
+ "loss": 0.012,
608
+ "step": 1360
609
+ },
610
+ {
611
+ "epoch": 3.7016129032258065,
612
+ "grad_norm": 0.5580664873123169,
613
+ "learning_rate": 3.8424197162061244e-05,
614
+ "loss": 0.0198,
615
+ "step": 1377
616
+ },
617
+ {
618
+ "epoch": 3.747311827956989,
619
+ "grad_norm": 1.8968793153762817,
620
+ "learning_rate": 3.821259646502365e-05,
621
+ "loss": 0.0186,
622
+ "step": 1394
623
+ },
624
+ {
625
+ "epoch": 3.793010752688172,
626
+ "grad_norm": 1.190463662147522,
627
+ "learning_rate": 3.800099576798606e-05,
628
+ "loss": 0.0139,
629
+ "step": 1411
630
+ },
631
+ {
632
+ "epoch": 3.838709677419355,
633
+ "grad_norm": 1.7319374084472656,
634
+ "learning_rate": 3.778939507094847e-05,
635
+ "loss": 0.0223,
636
+ "step": 1428
637
+ },
638
+ {
639
+ "epoch": 3.8844086021505375,
640
+ "grad_norm": 3.1801421642303467,
641
+ "learning_rate": 3.757779437391088e-05,
642
+ "loss": 0.0187,
643
+ "step": 1445
644
+ },
645
+ {
646
+ "epoch": 3.9301075268817205,
647
+ "grad_norm": 0.6739754676818848,
648
+ "learning_rate": 3.736619367687329e-05,
649
+ "loss": 0.0183,
650
+ "step": 1462
651
+ },
652
+ {
653
+ "epoch": 3.975806451612903,
654
+ "grad_norm": 1.2100051641464233,
655
+ "learning_rate": 3.71545929798357e-05,
656
+ "loss": 0.0188,
657
+ "step": 1479
658
+ },
659
+ {
660
+ "epoch": 4.0,
661
+ "eval_explained_variance": 0.5227994322776794,
662
+ "eval_loss": 0.03625540807843208,
663
+ "eval_mae": 0.13945059478282928,
664
+ "eval_mse": 0.03625541180372238,
665
+ "eval_r2": 0.5227354764938354,
666
+ "eval_rmse": 0.19040853920904488,
667
+ "eval_runtime": 0.8143,
668
+ "eval_samples_per_second": 835.105,
669
+ "eval_steps_per_second": 52.808,
670
+ "step": 1488
671
+ },
672
+ {
673
+ "epoch": 4.021505376344086,
674
+ "grad_norm": 0.5380852818489075,
675
+ "learning_rate": 3.694299228279811e-05,
676
+ "loss": 0.0138,
677
+ "step": 1496
678
+ },
679
+ {
680
+ "epoch": 4.067204301075269,
681
+ "grad_norm": 1.7809816598892212,
682
+ "learning_rate": 3.673139158576052e-05,
683
+ "loss": 0.0129,
684
+ "step": 1513
685
+ },
686
+ {
687
+ "epoch": 4.112903225806452,
688
+ "grad_norm": 0.6375765204429626,
689
+ "learning_rate": 3.651979088872293e-05,
690
+ "loss": 0.0125,
691
+ "step": 1530
692
+ },
693
+ {
694
+ "epoch": 4.158602150537634,
695
+ "grad_norm": 0.4600857198238373,
696
+ "learning_rate": 3.6308190191685337e-05,
697
+ "loss": 0.0118,
698
+ "step": 1547
699
+ },
700
+ {
701
+ "epoch": 4.204301075268817,
702
+ "grad_norm": 1.3683054447174072,
703
+ "learning_rate": 3.6096589494647745e-05,
704
+ "loss": 0.0123,
705
+ "step": 1564
706
+ },
707
+ {
708
+ "epoch": 4.25,
709
+ "grad_norm": 2.814866781234741,
710
+ "learning_rate": 3.588498879761016e-05,
711
+ "loss": 0.0124,
712
+ "step": 1581
713
+ },
714
+ {
715
+ "epoch": 4.295698924731183,
716
+ "grad_norm": 1.0241236686706543,
717
+ "learning_rate": 3.567338810057257e-05,
718
+ "loss": 0.0157,
719
+ "step": 1598
720
+ },
721
+ {
722
+ "epoch": 4.341397849462366,
723
+ "grad_norm": 1.0439250469207764,
724
+ "learning_rate": 3.546178740353498e-05,
725
+ "loss": 0.0191,
726
+ "step": 1615
727
+ },
728
+ {
729
+ "epoch": 4.387096774193548,
730
+ "grad_norm": 0.9102874994277954,
731
+ "learning_rate": 3.525018670649739e-05,
732
+ "loss": 0.0109,
733
+ "step": 1632
734
+ },
735
+ {
736
+ "epoch": 4.432795698924731,
737
+ "grad_norm": 2.352029800415039,
738
+ "learning_rate": 3.5038586009459795e-05,
739
+ "loss": 0.0126,
740
+ "step": 1649
741
+ },
742
+ {
743
+ "epoch": 4.478494623655914,
744
+ "grad_norm": 0.6944193243980408,
745
+ "learning_rate": 3.48269853124222e-05,
746
+ "loss": 0.0146,
747
+ "step": 1666
748
+ },
749
+ {
750
+ "epoch": 4.524193548387097,
751
+ "grad_norm": 1.522194743156433,
752
+ "learning_rate": 3.461538461538462e-05,
753
+ "loss": 0.0115,
754
+ "step": 1683
755
+ },
756
+ {
757
+ "epoch": 4.56989247311828,
758
+ "grad_norm": 1.6608046293258667,
759
+ "learning_rate": 3.440378391834703e-05,
760
+ "loss": 0.0147,
761
+ "step": 1700
762
+ },
763
+ {
764
+ "epoch": 4.615591397849462,
765
+ "grad_norm": 0.7349043488502502,
766
+ "learning_rate": 3.4192183221309436e-05,
767
+ "loss": 0.015,
768
+ "step": 1717
769
+ },
770
+ {
771
+ "epoch": 4.661290322580645,
772
+ "grad_norm": 2.419685125350952,
773
+ "learning_rate": 3.398058252427185e-05,
774
+ "loss": 0.0139,
775
+ "step": 1734
776
+ },
777
+ {
778
+ "epoch": 4.706989247311828,
779
+ "grad_norm": 0.6720536947250366,
780
+ "learning_rate": 3.376898182723426e-05,
781
+ "loss": 0.0133,
782
+ "step": 1751
783
+ },
784
+ {
785
+ "epoch": 4.752688172043011,
786
+ "grad_norm": 0.660599946975708,
787
+ "learning_rate": 3.355738113019666e-05,
788
+ "loss": 0.0195,
789
+ "step": 1768
790
+ },
791
+ {
792
+ "epoch": 4.798387096774194,
793
+ "grad_norm": 2.824357271194458,
794
+ "learning_rate": 3.334578043315908e-05,
795
+ "loss": 0.014,
796
+ "step": 1785
797
+ },
798
+ {
799
+ "epoch": 4.844086021505376,
800
+ "grad_norm": 1.6389164924621582,
801
+ "learning_rate": 3.3134179736121485e-05,
802
+ "loss": 0.0154,
803
+ "step": 1802
804
+ },
805
+ {
806
+ "epoch": 4.889784946236559,
807
+ "grad_norm": 2.430635929107666,
808
+ "learning_rate": 3.2922579039083894e-05,
809
+ "loss": 0.0133,
810
+ "step": 1819
811
+ },
812
+ {
813
+ "epoch": 4.935483870967742,
814
+ "grad_norm": 1.9341001510620117,
815
+ "learning_rate": 3.27109783420463e-05,
816
+ "loss": 0.0116,
817
+ "step": 1836
818
+ },
819
+ {
820
+ "epoch": 4.981182795698925,
821
+ "grad_norm": 1.3898817300796509,
822
+ "learning_rate": 3.249937764500872e-05,
823
+ "loss": 0.0098,
824
+ "step": 1853
825
+ },
826
+ {
827
+ "epoch": 5.0,
828
+ "eval_explained_variance": 0.6362735033035278,
829
+ "eval_loss": 0.032306160777807236,
830
+ "eval_mae": 0.13216176629066467,
831
+ "eval_mse": 0.032306160777807236,
832
+ "eval_r2": 0.5747231841087341,
833
+ "eval_rmse": 0.1797391464812472,
834
+ "eval_runtime": 0.8139,
835
+ "eval_samples_per_second": 835.446,
836
+ "eval_steps_per_second": 52.83,
837
+ "step": 1860
838
+ },
839
+ {
840
+ "epoch": 5.026881720430108,
841
+ "grad_norm": 0.5715427398681641,
842
+ "learning_rate": 3.2287776947971126e-05,
843
+ "loss": 0.0093,
844
+ "step": 1870
845
+ },
846
+ {
847
+ "epoch": 5.07258064516129,
848
+ "grad_norm": 2.644664764404297,
849
+ "learning_rate": 3.2076176250933535e-05,
850
+ "loss": 0.0103,
851
+ "step": 1887
852
+ },
853
+ {
854
+ "epoch": 5.118279569892473,
855
+ "grad_norm": 1.221136450767517,
856
+ "learning_rate": 3.1864575553895944e-05,
857
+ "loss": 0.0103,
858
+ "step": 1904
859
+ },
860
+ {
861
+ "epoch": 5.163978494623656,
862
+ "grad_norm": 1.2012200355529785,
863
+ "learning_rate": 3.165297485685835e-05,
864
+ "loss": 0.0075,
865
+ "step": 1921
866
+ },
867
+ {
868
+ "epoch": 5.209677419354839,
869
+ "grad_norm": 0.7213040590286255,
870
+ "learning_rate": 3.144137415982076e-05,
871
+ "loss": 0.0114,
872
+ "step": 1938
873
+ },
874
+ {
875
+ "epoch": 5.255376344086022,
876
+ "grad_norm": 2.609241008758545,
877
+ "learning_rate": 3.1229773462783176e-05,
878
+ "loss": 0.0106,
879
+ "step": 1955
880
+ },
881
+ {
882
+ "epoch": 5.301075268817204,
883
+ "grad_norm": 0.7639603018760681,
884
+ "learning_rate": 3.1018172765745585e-05,
885
+ "loss": 0.0088,
886
+ "step": 1972
887
+ },
888
+ {
889
+ "epoch": 5.346774193548387,
890
+ "grad_norm": 2.3716659545898438,
891
+ "learning_rate": 3.080657206870799e-05,
892
+ "loss": 0.012,
893
+ "step": 1989
894
+ },
895
+ {
896
+ "epoch": 5.39247311827957,
897
+ "grad_norm": 1.3058593273162842,
898
+ "learning_rate": 3.05949713716704e-05,
899
+ "loss": 0.0132,
900
+ "step": 2006
901
+ },
902
+ {
903
+ "epoch": 5.438172043010753,
904
+ "grad_norm": 1.2785415649414062,
905
+ "learning_rate": 3.038337067463281e-05,
906
+ "loss": 0.0138,
907
+ "step": 2023
908
+ },
909
+ {
910
+ "epoch": 5.483870967741936,
911
+ "grad_norm": 0.7421461939811707,
912
+ "learning_rate": 3.0171769977595222e-05,
913
+ "loss": 0.0079,
914
+ "step": 2040
915
+ },
916
+ {
917
+ "epoch": 5.529569892473118,
918
+ "grad_norm": 0.9595834612846375,
919
+ "learning_rate": 2.996016928055763e-05,
920
+ "loss": 0.0103,
921
+ "step": 2057
922
+ },
923
+ {
924
+ "epoch": 5.575268817204301,
925
+ "grad_norm": 0.7429810762405396,
926
+ "learning_rate": 2.9748568583520043e-05,
927
+ "loss": 0.0096,
928
+ "step": 2074
929
+ },
930
+ {
931
+ "epoch": 5.620967741935484,
932
+ "grad_norm": 0.5318065881729126,
933
+ "learning_rate": 2.953696788648245e-05,
934
+ "loss": 0.0104,
935
+ "step": 2091
936
+ },
937
+ {
938
+ "epoch": 5.666666666666667,
939
+ "grad_norm": 0.6054395437240601,
940
+ "learning_rate": 2.9325367189444863e-05,
941
+ "loss": 0.0087,
942
+ "step": 2108
943
+ },
944
+ {
945
+ "epoch": 5.71236559139785,
946
+ "grad_norm": 0.3141707479953766,
947
+ "learning_rate": 2.911376649240727e-05,
948
+ "loss": 0.0085,
949
+ "step": 2125
950
+ },
951
+ {
952
+ "epoch": 5.758064516129032,
953
+ "grad_norm": 0.8221209049224854,
954
+ "learning_rate": 2.890216579536968e-05,
955
+ "loss": 0.0093,
956
+ "step": 2142
957
+ },
958
+ {
959
+ "epoch": 5.803763440860215,
960
+ "grad_norm": 0.649782657623291,
961
+ "learning_rate": 2.869056509833209e-05,
962
+ "loss": 0.0064,
963
+ "step": 2159
964
+ },
965
+ {
966
+ "epoch": 5.849462365591398,
967
+ "grad_norm": 0.36768993735313416,
968
+ "learning_rate": 2.84789644012945e-05,
969
+ "loss": 0.0082,
970
+ "step": 2176
971
+ },
972
+ {
973
+ "epoch": 5.895161290322581,
974
+ "grad_norm": 0.9037314653396606,
975
+ "learning_rate": 2.826736370425691e-05,
976
+ "loss": 0.008,
977
+ "step": 2193
978
+ },
979
+ {
980
+ "epoch": 5.940860215053764,
981
+ "grad_norm": 1.033964991569519,
982
+ "learning_rate": 2.805576300721932e-05,
983
+ "loss": 0.0066,
984
+ "step": 2210
985
+ },
986
+ {
987
+ "epoch": 5.986559139784946,
988
+ "grad_norm": 1.0793079137802124,
989
+ "learning_rate": 2.784416231018173e-05,
990
+ "loss": 0.009,
991
+ "step": 2227
992
+ },
993
+ {
994
+ "epoch": 6.0,
995
+ "eval_explained_variance": 0.6521931886672974,
996
+ "eval_loss": 0.027760107070207596,
997
+ "eval_mae": 0.1187298521399498,
998
+ "eval_mse": 0.027760105207562447,
999
+ "eval_r2": 0.6345672607421875,
1000
+ "eval_rmse": 0.1666136405207042,
1001
+ "eval_runtime": 0.8175,
1002
+ "eval_samples_per_second": 831.837,
1003
+ "eval_steps_per_second": 52.601,
1004
+ "step": 2232
1005
+ }
1006
+ ],
1007
+ "logging_steps": 17,
1008
+ "max_steps": 4464,
1009
+ "num_input_tokens_seen": 0,
1010
+ "num_train_epochs": 12,
1011
+ "save_steps": 500,
1012
+ "stateful_callbacks": {
1013
+ "EarlyStoppingCallback": {
1014
+ "args": {
1015
+ "early_stopping_patience": 5,
1016
+ "early_stopping_threshold": 0.01
1017
+ },
1018
+ "attributes": {
1019
+ "early_stopping_patience_counter": 5
1020
+ }
1021
+ },
1022
+ "TrainerControl": {
1023
+ "args": {
1024
+ "should_epoch_stop": false,
1025
+ "should_evaluate": false,
1026
+ "should_log": false,
1027
+ "should_save": true,
1028
+ "should_training_stop": true
1029
+ },
1030
+ "attributes": {}
1031
+ }
1032
+ },
1033
+ "total_flos": 1172149227279360.0,
1034
+ "train_batch_size": 8,
1035
+ "trial_name": null,
1036
+ "trial_params": null
1037
+ }
checkpoint-2232/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b1f2cc5ebbcb7d511152a28c47b574f11472fadfada205e2abec8eddfc984b
3
+ size 5368
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-german-cased",
3
+ "_num_labels": 1,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "target"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "target": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "problem_type": "regression",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.48.0",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 30000
33
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4c09c509249de28f1ab20a576a6b89ba83f2f82c29442900a93e817b7b4da1
3
+ size 436351980
runs/Feb21_12-51-10_r-abgegrieft-train-german-bert-griefergames-toxicity--ee7a3-g9j/events.out.tfevents.1740142272.r-abgegrieft-train-german-bert-griefergames-toxicity--ee7a3-g9j.201.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78073c908b9432d98fa43a4633140e527416d8ca8fffc332d9451fd9db1b1b9f
3
- size 5175
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae402d836423a6f93a5a6570ed5a2f2a3254929ec46debf189c7effaeb31db71
3
+ size 36268
runs/Feb21_12-51-10_r-abgegrieft-train-german-bert-griefergames-toxicity--ee7a3-g9j/events.out.tfevents.1740142409.r-abgegrieft-train-german-bert-griefergames-toxicity--ee7a3-g9j.201.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:445496ee69549925b1a6cbd0bd6dce6c92c9cdb876f333a6a86dd3b79bd19730
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "2": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "3": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
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_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b1f2cc5ebbcb7d511152a28c47b574f11472fadfada205e2abec8eddfc984b
3
+ size 5368
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-lv9vc-kt81s/autotrain-data",
3
+ "model": "google-bert/bert-base-german-cased",
4
+ "lr": 5e-05,
5
+ "epochs": 12,
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-lv9vc-kt81s",
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": "Abgegrieft",
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