Yunika commited on
Commit
52c31f2
1 Parent(s): ccff2ad

Upload 11 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 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "deepset/xlm-roberta-base-squad2",
3
+ "architectures": [
4
+ "XLMRobertaForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "language": "english",
17
+ "layer_norm_eps": 1e-05,
18
+ "max_position_embeddings": 514,
19
+ "model_type": "xlm-roberta",
20
+ "name": "XLMRoberta",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 1,
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.35.2",
28
+ "type_vocab_size": 1,
29
+ "use_cache": true,
30
+ "vocab_size": 250002
31
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b04a1a53e08a033d2cf9f0ffb51ec80a0b4f1fc9201a3c1a5e2b198a0c767185
3
+ size 1109842416
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d3bd86d67b4f9030084d4c8be2e595907d456a02bdbaf9400e701162b2ec636
3
+ size 2219802757
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b40db13fccf1d8eef492ad004fe9c1d9f20e456a3abd2c2d581933f1c94993
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a69334faf469a30e37ec24067beff73ffacb809513a5a74e878b2aa22fe6f28
3
+ size 627
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
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 sha256:2ebea46568b699bd09a767efdb0fc3e6536202a6ed8727d75290b9c29df9a331
3
+ size 17098437
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "do_lower_case": false,
48
+ "eos_token": "</s>",
49
+ "full_tokenizer_file": null,
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "sp_model_kwargs": {},
55
+ "tokenizer_class": "XLMRobertaTokenizer",
56
+ "unk_token": "<unk>"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,373 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 29658,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1,
13
+ "learning_rate": 9.83309730932632e-06,
14
+ "loss": 1.8178,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.2,
19
+ "learning_rate": 9.66450873288826e-06,
20
+ "loss": 1.5781,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.3,
25
+ "learning_rate": 9.4959201564502e-06,
26
+ "loss": 1.5743,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.4,
31
+ "learning_rate": 9.327331580012139e-06,
32
+ "loss": 1.5106,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.51,
37
+ "learning_rate": 9.159080180726955e-06,
38
+ "loss": 1.4435,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.61,
43
+ "learning_rate": 8.990491604288895e-06,
44
+ "loss": 1.4369,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.71,
49
+ "learning_rate": 8.821903027850834e-06,
50
+ "loss": 1.4113,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.81,
55
+ "learning_rate": 8.653314451412773e-06,
56
+ "loss": 1.3945,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.91,
61
+ "learning_rate": 8.484725874974711e-06,
62
+ "loss": 1.4233,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 1.01,
67
+ "learning_rate": 8.316137298536652e-06,
68
+ "loss": 1.3204,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 1.11,
73
+ "learning_rate": 8.147885899251467e-06,
74
+ "loss": 1.1246,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 1.21,
79
+ "learning_rate": 7.979297322813406e-06,
80
+ "loss": 1.1869,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 1.31,
85
+ "learning_rate": 7.810708746375346e-06,
86
+ "loss": 1.149,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 1.42,
91
+ "learning_rate": 7.642120169937287e-06,
92
+ "loss": 1.1295,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 1.52,
97
+ "learning_rate": 7.4735315934992245e-06,
98
+ "loss": 1.1715,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 1.62,
103
+ "learning_rate": 7.304943017061165e-06,
104
+ "loss": 1.149,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 1.72,
109
+ "learning_rate": 7.136691617775981e-06,
110
+ "loss": 1.1239,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 1.82,
115
+ "learning_rate": 6.968103041337919e-06,
116
+ "loss": 1.1282,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 1.92,
121
+ "learning_rate": 6.799514464899859e-06,
122
+ "loss": 1.1427,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 2.02,
127
+ "learning_rate": 6.630925888461799e-06,
128
+ "loss": 1.0791,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 2.12,
133
+ "learning_rate": 6.462337312023738e-06,
134
+ "loss": 0.9169,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 2.23,
139
+ "learning_rate": 6.293748735585677e-06,
140
+ "loss": 0.9361,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 2.33,
145
+ "learning_rate": 6.125497336300493e-06,
146
+ "loss": 0.9294,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 2.43,
151
+ "learning_rate": 5.956908759862432e-06,
152
+ "loss": 0.9456,
153
+ "step": 12000
154
+ },
155
+ {
156
+ "epoch": 2.53,
157
+ "learning_rate": 5.7886573605772475e-06,
158
+ "loss": 0.9395,
159
+ "step": 12500
160
+ },
161
+ {
162
+ "epoch": 2.63,
163
+ "learning_rate": 5.620068784139188e-06,
164
+ "loss": 0.9367,
165
+ "step": 13000
166
+ },
167
+ {
168
+ "epoch": 2.73,
169
+ "learning_rate": 5.4514802077011266e-06,
170
+ "loss": 0.9096,
171
+ "step": 13500
172
+ },
173
+ {
174
+ "epoch": 2.83,
175
+ "learning_rate": 5.282891631263066e-06,
176
+ "loss": 0.9506,
177
+ "step": 14000
178
+ },
179
+ {
180
+ "epoch": 2.93,
181
+ "learning_rate": 5.114303054825005e-06,
182
+ "loss": 0.9047,
183
+ "step": 14500
184
+ },
185
+ {
186
+ "epoch": 3.03,
187
+ "learning_rate": 4.945714478386945e-06,
188
+ "loss": 0.8577,
189
+ "step": 15000
190
+ },
191
+ {
192
+ "epoch": 3.14,
193
+ "learning_rate": 4.777125901948884e-06,
194
+ "loss": 0.7538,
195
+ "step": 15500
196
+ },
197
+ {
198
+ "epoch": 3.24,
199
+ "learning_rate": 4.608537325510824e-06,
200
+ "loss": 0.8059,
201
+ "step": 16000
202
+ },
203
+ {
204
+ "epoch": 3.34,
205
+ "learning_rate": 4.439948749072764e-06,
206
+ "loss": 0.7702,
207
+ "step": 16500
208
+ },
209
+ {
210
+ "epoch": 3.44,
211
+ "learning_rate": 4.271360172634702e-06,
212
+ "loss": 0.7905,
213
+ "step": 17000
214
+ },
215
+ {
216
+ "epoch": 3.54,
217
+ "learning_rate": 4.103108773349518e-06,
218
+ "loss": 0.7902,
219
+ "step": 17500
220
+ },
221
+ {
222
+ "epoch": 3.64,
223
+ "learning_rate": 3.934520196911458e-06,
224
+ "loss": 0.7931,
225
+ "step": 18000
226
+ },
227
+ {
228
+ "epoch": 3.74,
229
+ "learning_rate": 3.765931620473397e-06,
230
+ "loss": 0.7793,
231
+ "step": 18500
232
+ },
233
+ {
234
+ "epoch": 3.84,
235
+ "learning_rate": 3.5973430440353362e-06,
236
+ "loss": 0.7803,
237
+ "step": 19000
238
+ },
239
+ {
240
+ "epoch": 3.94,
241
+ "learning_rate": 3.428754467597276e-06,
242
+ "loss": 0.7636,
243
+ "step": 19500
244
+ },
245
+ {
246
+ "epoch": 4.05,
247
+ "learning_rate": 3.2605030683120915e-06,
248
+ "loss": 0.6841,
249
+ "step": 20000
250
+ },
251
+ {
252
+ "epoch": 4.15,
253
+ "learning_rate": 3.0919144918740306e-06,
254
+ "loss": 0.6618,
255
+ "step": 20500
256
+ },
257
+ {
258
+ "epoch": 4.25,
259
+ "learning_rate": 2.9233259154359705e-06,
260
+ "loss": 0.6649,
261
+ "step": 21000
262
+ },
263
+ {
264
+ "epoch": 4.35,
265
+ "learning_rate": 2.75473733899791e-06,
266
+ "loss": 0.6313,
267
+ "step": 21500
268
+ },
269
+ {
270
+ "epoch": 4.45,
271
+ "learning_rate": 2.586148762559849e-06,
272
+ "loss": 0.6625,
273
+ "step": 22000
274
+ },
275
+ {
276
+ "epoch": 4.55,
277
+ "learning_rate": 2.417897363274665e-06,
278
+ "loss": 0.6405,
279
+ "step": 22500
280
+ },
281
+ {
282
+ "epoch": 4.65,
283
+ "learning_rate": 2.2493087868366044e-06,
284
+ "loss": 0.7022,
285
+ "step": 23000
286
+ },
287
+ {
288
+ "epoch": 4.75,
289
+ "learning_rate": 2.0807202103985435e-06,
290
+ "loss": 0.6901,
291
+ "step": 23500
292
+ },
293
+ {
294
+ "epoch": 4.86,
295
+ "learning_rate": 1.912131633960483e-06,
296
+ "loss": 0.6647,
297
+ "step": 24000
298
+ },
299
+ {
300
+ "epoch": 4.96,
301
+ "learning_rate": 1.7438802346752987e-06,
302
+ "loss": 0.6386,
303
+ "step": 24500
304
+ },
305
+ {
306
+ "epoch": 5.06,
307
+ "learning_rate": 1.575291658237238e-06,
308
+ "loss": 0.6375,
309
+ "step": 25000
310
+ },
311
+ {
312
+ "epoch": 5.16,
313
+ "learning_rate": 1.4067030817991776e-06,
314
+ "loss": 0.5791,
315
+ "step": 25500
316
+ },
317
+ {
318
+ "epoch": 5.26,
319
+ "learning_rate": 1.2381145053611169e-06,
320
+ "loss": 0.5941,
321
+ "step": 26000
322
+ },
323
+ {
324
+ "epoch": 5.36,
325
+ "learning_rate": 1.0695259289230562e-06,
326
+ "loss": 0.5801,
327
+ "step": 26500
328
+ },
329
+ {
330
+ "epoch": 5.46,
331
+ "learning_rate": 9.009373524849957e-07,
332
+ "loss": 0.5734,
333
+ "step": 27000
334
+ },
335
+ {
336
+ "epoch": 5.56,
337
+ "learning_rate": 7.323487760469351e-07,
338
+ "loss": 0.5798,
339
+ "step": 27500
340
+ },
341
+ {
342
+ "epoch": 5.66,
343
+ "learning_rate": 5.640973767617506e-07,
344
+ "loss": 0.5903,
345
+ "step": 28000
346
+ },
347
+ {
348
+ "epoch": 5.77,
349
+ "learning_rate": 3.955088003236901e-07,
350
+ "loss": 0.5849,
351
+ "step": 28500
352
+ },
353
+ {
354
+ "epoch": 5.87,
355
+ "learning_rate": 2.2692022388562955e-07,
356
+ "loss": 0.5885,
357
+ "step": 29000
358
+ },
359
+ {
360
+ "epoch": 5.97,
361
+ "learning_rate": 5.833164744756895e-08,
362
+ "loss": 0.5763,
363
+ "step": 29500
364
+ }
365
+ ],
366
+ "logging_steps": 500,
367
+ "max_steps": 29658,
368
+ "num_train_epochs": 6,
369
+ "save_steps": 500,
370
+ "total_flos": 6.198533922642739e+16,
371
+ "trial_name": null,
372
+ "trial_params": null
373
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef2badc000e36f9903b7b1eda88fa372ee4ce759cfe0a95fb9796531369bae53
3
+ size 4155