schemulord commited on
Commit
269d8b2
1 Parent(s): 4bf5a26

Upload 8 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.31.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1317c463d093afa140225ebfeb747433a191d97ce4f1198eac2e4b721c6c8127
3
+ size 1113250229
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fceae2a29efea41804e8e31761f6f793c46d8e5bb8c687ad38d67d69b712a9c7
3
+ size 14575
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 512,
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }
trainer_state.json ADDED
@@ -0,0 +1,376 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.906413485758574,
5
+ "global_step": 30000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 4.9192662920622624e-05,
13
+ "loss": 3.6238,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "learning_rate": 4.838532584124524e-05,
19
+ "loss": 2.7692,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.15,
24
+ "learning_rate": 4.757798876186786e-05,
25
+ "loss": 2.5108,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.19,
30
+ "learning_rate": 4.677065168249048e-05,
31
+ "loss": 2.3409,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.24,
36
+ "learning_rate": 4.596331460311309e-05,
37
+ "loss": 2.2195,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.29,
42
+ "learning_rate": 4.515597752373571e-05,
43
+ "loss": 2.1371,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.34,
48
+ "learning_rate": 4.434864044435833e-05,
49
+ "loss": 2.057,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.39,
54
+ "learning_rate": 4.354130336498095e-05,
55
+ "loss": 1.9966,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.44,
60
+ "learning_rate": 4.273396628560357e-05,
61
+ "loss": 1.9476,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.48,
66
+ "learning_rate": 4.192662920622619e-05,
67
+ "loss": 1.8893,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.53,
72
+ "learning_rate": 4.1119292126848804e-05,
73
+ "loss": 1.8574,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.58,
78
+ "learning_rate": 4.031195504747142e-05,
79
+ "loss": 1.8144,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.63,
84
+ "learning_rate": 3.950461796809404e-05,
85
+ "loss": 1.7866,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.68,
90
+ "learning_rate": 3.8697280888716657e-05,
91
+ "loss": 1.7497,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.73,
96
+ "learning_rate": 3.788994380933928e-05,
97
+ "loss": 1.7287,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.78,
102
+ "learning_rate": 3.7082606729961894e-05,
103
+ "loss": 1.6999,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.82,
108
+ "learning_rate": 3.6275269650584516e-05,
109
+ "loss": 1.6749,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.87,
114
+ "learning_rate": 3.546793257120713e-05,
115
+ "loss": 1.6554,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.92,
120
+ "learning_rate": 3.466059549182975e-05,
121
+ "loss": 1.6307,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.97,
126
+ "learning_rate": 3.385325841245237e-05,
127
+ "loss": 1.6148,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.02,
132
+ "learning_rate": 3.3045921333074984e-05,
133
+ "loss": 1.5938,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.07,
138
+ "learning_rate": 3.2238584253697606e-05,
139
+ "loss": 1.5652,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 1.11,
144
+ "learning_rate": 3.143124717432022e-05,
145
+ "loss": 1.5597,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 1.16,
150
+ "learning_rate": 3.062391009494284e-05,
151
+ "loss": 1.5457,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 1.21,
156
+ "learning_rate": 2.9816573015565458e-05,
157
+ "loss": 1.5278,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 1.26,
162
+ "learning_rate": 2.9009235936188077e-05,
163
+ "loss": 1.5221,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 1.31,
168
+ "learning_rate": 2.82018988568107e-05,
169
+ "loss": 1.4991,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 1.36,
174
+ "learning_rate": 2.7394561777433314e-05,
175
+ "loss": 1.4876,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 1.4,
180
+ "learning_rate": 2.6587224698055936e-05,
181
+ "loss": 1.4747,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 1.45,
186
+ "learning_rate": 2.577988761867855e-05,
187
+ "loss": 1.4647,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 1.5,
192
+ "learning_rate": 2.497255053930117e-05,
193
+ "loss": 1.4566,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 1.55,
198
+ "learning_rate": 2.416521345992379e-05,
199
+ "loss": 1.4414,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 1.6,
204
+ "learning_rate": 2.3357876380546407e-05,
205
+ "loss": 1.4315,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 1.65,
210
+ "learning_rate": 2.2550539301169023e-05,
211
+ "loss": 1.4296,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 1.7,
216
+ "learning_rate": 2.1743202221791645e-05,
217
+ "loss": 1.4214,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 1.74,
222
+ "learning_rate": 2.0935865142414263e-05,
223
+ "loss": 1.4073,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 1.79,
228
+ "learning_rate": 2.0128528063036882e-05,
229
+ "loss": 1.4001,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 1.84,
234
+ "learning_rate": 1.9321190983659497e-05,
235
+ "loss": 1.4014,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 1.89,
240
+ "learning_rate": 1.8513853904282116e-05,
241
+ "loss": 1.3846,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 1.94,
246
+ "learning_rate": 1.7706516824904734e-05,
247
+ "loss": 1.3777,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 1.99,
252
+ "learning_rate": 1.6899179745527353e-05,
253
+ "loss": 1.3754,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 2.03,
258
+ "learning_rate": 1.609184266614997e-05,
259
+ "loss": 1.3593,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 2.08,
264
+ "learning_rate": 1.528450558677259e-05,
265
+ "loss": 1.356,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 2.13,
270
+ "learning_rate": 1.4477168507395209e-05,
271
+ "loss": 1.3527,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 2.18,
276
+ "learning_rate": 1.3669831428017826e-05,
277
+ "loss": 1.3366,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 2.23,
282
+ "learning_rate": 1.2862494348640444e-05,
283
+ "loss": 1.3392,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 2.28,
288
+ "learning_rate": 1.2055157269263063e-05,
289
+ "loss": 1.3282,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 2.33,
294
+ "learning_rate": 1.1247820189885682e-05,
295
+ "loss": 1.3309,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 2.37,
300
+ "learning_rate": 1.0440483110508299e-05,
301
+ "loss": 1.3235,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 2.42,
306
+ "learning_rate": 9.633146031130919e-06,
307
+ "loss": 1.3232,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 2.47,
312
+ "learning_rate": 8.825808951753536e-06,
313
+ "loss": 1.3155,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 2.52,
318
+ "learning_rate": 8.018471872376155e-06,
319
+ "loss": 1.309,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 2.57,
324
+ "learning_rate": 7.211134792998773e-06,
325
+ "loss": 1.3101,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 2.62,
330
+ "learning_rate": 6.403797713621391e-06,
331
+ "loss": 1.304,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 2.66,
336
+ "learning_rate": 5.59646063424401e-06,
337
+ "loss": 1.3035,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 2.71,
342
+ "learning_rate": 4.7891235548666275e-06,
343
+ "loss": 1.2952,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 2.76,
348
+ "learning_rate": 3.981786475489246e-06,
349
+ "loss": 1.2988,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 2.81,
354
+ "learning_rate": 3.174449396111865e-06,
355
+ "loss": 1.2876,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 2.86,
360
+ "learning_rate": 2.3671123167344834e-06,
361
+ "loss": 1.2922,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 2.91,
366
+ "learning_rate": 1.5597752373571014e-06,
367
+ "loss": 1.2881,
368
+ "step": 30000
369
+ }
370
+ ],
371
+ "max_steps": 30966,
372
+ "num_train_epochs": 3,
373
+ "total_flos": 1.5832637769977856e+17,
374
+ "trial_name": null,
375
+ "trial_params": null
376
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5bdbe57fa94ebcf113e280143ba4ed95d3e9c2ec396f3b551a8d236171fadb
3
+ size 3963