lx865712528 commited on
Commit
932f4d6
1 Parent(s): ccc8049
README.md CHANGED
@@ -1,3 +1,28 @@
1
  ---
2
  license: mit
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
+ datasets:
4
+ - wikipedia
5
+ language:
6
+ - en
7
+ pipeline_tag: feature-extraction
8
  ---
9
+
10
+ # MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers
11
+
12
+ Paper: [https://arxiv.org/abs/2212.07841](https://arxiv.org/abs/2212.07841).
13
+
14
+ Code: [https://github.com/microsoft/SimXNS/tree/main/MASTER](https://github.com/microsoft/SimXNS/tree/main/MASTER).
15
+
16
+ ## Overview
17
+
18
+ This is the checkpoint after pretraining on the NQ, TQ, WQ and Squad's Wikipedia corpus. **You may use this checkpoint as the initialization for finetuning.**
19
+
20
+ ## Useage
21
+
22
+
23
+ To load this checkpoint for initialization, you may follow:
24
+ ```python
25
+ from transformers import AutoModel
26
+
27
+ model = AutoModel.from_pretrained('lx865712528/master-base-pretrained-wiki')
28
+ ```
args.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1439cc607072746600118078deacff654edf6d51e47c88bd6d3385ebf3a20590
3
+ size 3951
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.18.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c343563657eea85f4124a11ba619a812ee64ab04a25c7c850e2e3ad4ea32071
3
+ size 283595215
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9acc56ed837d072e9bbb355773d26f0a4a4dcf164a7f74826bfca663a4ed800
3
+ size 1443372131
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:405df306ba658071fb99b0ba60280bd3fd9d73f672c26e10371ae7e53ae17dfb
3
+ size 438134098
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6ca633fb0ed23e5ac71e9ddac76a9dcd732b5b8c28cc21b865e581008a78e5
3
+ size 14657
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ab03f68cca98fc0abd4a88f49099257a34fcb8ec79a70846a1b9bdf5653496
3
+ size 14657
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af07c866be87f0d67ab5af2639047e1f2070b7d262c91e93c2510a42a75f4348
3
+ size 14657
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3c0c7422d1c82ecfb6b7b7b48b33576dd881e55e2b1a4f48937699f11832952
3
+ size 14657
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:046693d6c53a34ae574daa367567b68b1c499daf431a8198bdc13825ecdcb1b9
3
+ size 14657
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cadce130e8edcf76062244bb3111bb26b146929e65e60b93d82c8b9fd783b3af
3
+ size 14657
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c2a1ba5357645713654bb9c787c7050c3f95c9d1a3493e0b473157cc81f75c
3
+ size 14657
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1dfa7272295afe0f16fc36d303186c09d16f3ce773ed98371e624bfeb898f64
3
+ size 14657
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ea39c9f13e88517e810f376570f55da55be4c250a827c088f03c4849e27ca8
3
+ size 559
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10a6d1f2955446a2cf5019183d53c2744d397e57aefadc38846fd5f821cdf41e
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,976 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.61392489388835,
5
+ "global_step": 80000,
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": 7.109546016941087e-06,
13
+ "loss": 49.9771,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "learning_rate": 1.4247644427524506e-05,
19
+ "loss": 43.393,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.14,
24
+ "learning_rate": 2.1385742838107926e-05,
25
+ "loss": 39.2346,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.19,
30
+ "learning_rate": 2.852384124869135e-05,
31
+ "loss": 35.6806,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.24,
36
+ "learning_rate": 3.566193965927477e-05,
37
+ "loss": 33.5102,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.29,
42
+ "learning_rate": 4.280003806985819e-05,
43
+ "loss": 32.3278,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.33,
48
+ "learning_rate": 4.993813648044161e-05,
49
+ "loss": 31.4953,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.38,
54
+ "learning_rate": 5.707623489102503e-05,
55
+ "loss": 30.816,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.43,
60
+ "learning_rate": 6.421433330160845e-05,
61
+ "loss": 30.252,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.48,
66
+ "learning_rate": 7.135243171219186e-05,
67
+ "loss": 29.7712,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.52,
72
+ "learning_rate": 7.849053012277528e-05,
73
+ "loss": 29.3302,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.57,
78
+ "learning_rate": 8.56286285333587e-05,
79
+ "loss": 28.9378,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.62,
84
+ "learning_rate": 9.276672694394213e-05,
85
+ "loss": 28.5842,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.67,
90
+ "learning_rate": 9.990482535452555e-05,
91
+ "loss": 28.2426,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.71,
96
+ "learning_rate": 0.00010704292376510896,
97
+ "loss": 27.9328,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.76,
102
+ "learning_rate": 0.00011416674597887122,
103
+ "loss": 27.6412,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.81,
108
+ "learning_rate": 0.00012129056819263346,
109
+ "loss": 27.364,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.86,
114
+ "learning_rate": 0.0001284286666032169,
115
+ "loss": 27.1143,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.9,
120
+ "learning_rate": 0.00013556676501380032,
121
+ "loss": 26.8555,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.95,
126
+ "learning_rate": 0.00014270486342438373,
127
+ "loss": 26.6034,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.0,
132
+ "learning_rate": 0.00014984296183496716,
133
+ "loss": 26.3698,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.05,
138
+ "learning_rate": 0.00015698106024555057,
139
+ "loss": 26.1622,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 1.09,
144
+ "learning_rate": 0.000164119158656134,
145
+ "loss": 25.9071,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 1.14,
150
+ "learning_rate": 0.0001712572570667174,
151
+ "loss": 25.7091,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 1.19,
156
+ "learning_rate": 0.0001783953554773008,
157
+ "loss": 25.5191,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 1.24,
162
+ "learning_rate": 0.00018553345388788427,
163
+ "loss": 25.3345,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 1.28,
168
+ "learning_rate": 0.0001926572761016465,
169
+ "loss": 25.1661,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 1.33,
174
+ "learning_rate": 0.0001997953745122299,
175
+ "loss": 25.0167,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 1.38,
180
+ "learning_rate": 0.00020693347292281334,
181
+ "loss": 24.8676,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 1.43,
186
+ "learning_rate": 0.00021407157133339675,
187
+ "loss": 24.7221,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 1.48,
192
+ "learning_rate": 0.00022119539354715904,
193
+ "loss": 24.5844,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 1.52,
198
+ "learning_rate": 0.00022831921576092128,
199
+ "loss": 24.4609,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 1.57,
204
+ "learning_rate": 0.00023545731417150468,
205
+ "loss": 24.3188,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 1.62,
210
+ "learning_rate": 0.0002425954125820881,
211
+ "loss": 24.1855,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 1.67,
216
+ "learning_rate": 0.0002497049585990292,
217
+ "loss": 24.0573,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 1.71,
222
+ "learning_rate": 0.0002568430570096126,
223
+ "loss": 23.9433,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 1.76,
228
+ "learning_rate": 0.000263981155420196,
229
+ "loss": 23.8441,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 1.81,
234
+ "learning_rate": 0.0002711192538307794,
235
+ "loss": 23.7344,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 1.86,
240
+ "learning_rate": 0.0002782573522413629,
241
+ "loss": 23.6054,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 1.9,
246
+ "learning_rate": 0.0002853811744551251,
247
+ "loss": 23.5031,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 1.95,
252
+ "learning_rate": 0.0002925192728657086,
253
+ "loss": 23.409,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 2.0,
258
+ "learning_rate": 0.000299657371276292,
259
+ "loss": 23.2973,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 2.05,
264
+ "learning_rate": 0.00029924653405666063,
265
+ "loss": 23.1983,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 2.09,
270
+ "learning_rate": 0.00029845341201104026,
271
+ "loss": 23.0667,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 2.14,
276
+ "learning_rate": 0.00029766028996541983,
277
+ "loss": 22.9586,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 2.19,
282
+ "learning_rate": 0.00029686716791979946,
283
+ "loss": 22.8611,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 2.24,
288
+ "learning_rate": 0.0002960740458741791,
289
+ "loss": 22.7729,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 2.28,
294
+ "learning_rate": 0.0002952809238285587,
295
+ "loss": 22.6924,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 2.33,
300
+ "learning_rate": 0.00029448780178293834,
301
+ "loss": 22.6076,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 2.38,
306
+ "learning_rate": 0.00029369467973731797,
307
+ "loss": 22.536,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 2.43,
312
+ "learning_rate": 0.0002929015576916976,
313
+ "loss": 22.4573,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 2.47,
318
+ "learning_rate": 0.00029210843564607717,
319
+ "loss": 22.3945,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 2.52,
324
+ "learning_rate": 0.0002913153136004568,
325
+ "loss": 22.3224,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 2.57,
330
+ "learning_rate": 0.0002905221915548364,
331
+ "loss": 22.2743,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 2.62,
336
+ "learning_rate": 0.00028972906950921605,
337
+ "loss": 22.2017,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 2.66,
342
+ "learning_rate": 0.0002889359474635957,
343
+ "loss": 22.1405,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 2.71,
348
+ "learning_rate": 0.0002881428254179753,
349
+ "loss": 22.0828,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 2.76,
354
+ "learning_rate": 0.00028734970337235494,
355
+ "loss": 22.0215,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 2.81,
360
+ "learning_rate": 0.00028655658132673457,
361
+ "loss": 21.9786,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 2.86,
366
+ "learning_rate": 0.0002857650455252054,
367
+ "loss": 21.9217,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 2.9,
372
+ "learning_rate": 0.0002849750959677675,
373
+ "loss": 21.8631,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 2.95,
378
+ "learning_rate": 0.00028418197392214713,
379
+ "loss": 21.8205,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 3.0,
384
+ "learning_rate": 0.00028338885187652676,
385
+ "loss": 21.7683,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 3.05,
390
+ "learning_rate": 0.0002825957298309064,
391
+ "loss": 21.7244,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 3.09,
396
+ "learning_rate": 0.00028180260778528596,
397
+ "loss": 21.6501,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 3.14,
402
+ "learning_rate": 0.0002810094857396656,
403
+ "loss": 21.6091,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 3.19,
408
+ "learning_rate": 0.00028021794993813643,
409
+ "loss": 21.5633,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 3.24,
414
+ "learning_rate": 0.0002794280003806986,
415
+ "loss": 21.521,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 3.28,
420
+ "learning_rate": 0.0002786348783350782,
421
+ "loss": 21.485,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 3.33,
426
+ "learning_rate": 0.0002778417562894578,
427
+ "loss": 21.4439,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 3.38,
432
+ "learning_rate": 0.0002770486342438374,
433
+ "loss": 21.3951,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 3.43,
438
+ "learning_rate": 0.00027625551219821704,
439
+ "loss": 21.3558,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 3.47,
444
+ "learning_rate": 0.00027546239015259667,
445
+ "loss": 21.3135,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 3.52,
450
+ "learning_rate": 0.0002746692681069763,
451
+ "loss": 21.2646,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 3.57,
456
+ "learning_rate": 0.0002738761460613559,
457
+ "loss": 21.2365,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 3.62,
462
+ "learning_rate": 0.00027308302401573555,
463
+ "loss": 21.2025,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 3.66,
468
+ "learning_rate": 0.00027228990197011513,
469
+ "loss": 21.156,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 3.71,
474
+ "learning_rate": 0.00027149677992449476,
475
+ "loss": 21.1298,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 3.76,
480
+ "learning_rate": 0.0002707036578788744,
481
+ "loss": 21.1058,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 3.81,
486
+ "learning_rate": 0.000269910535833254,
487
+ "loss": 21.0673,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 3.85,
492
+ "learning_rate": 0.00026911741378763364,
493
+ "loss": 21.0313,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 3.9,
498
+ "learning_rate": 0.00026832429174201327,
499
+ "loss": 21.003,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 3.95,
504
+ "learning_rate": 0.00026753116969639284,
505
+ "loss": 20.9636,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 4.0,
510
+ "learning_rate": 0.00026673804765077247,
511
+ "loss": 20.9453,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 4.04,
516
+ "learning_rate": 0.0002659449256051521,
517
+ "loss": 20.9264,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 4.09,
522
+ "learning_rate": 0.0002651518035595317,
523
+ "loss": 20.8611,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 4.14,
528
+ "learning_rate": 0.00026436026775800256,
529
+ "loss": 20.8391,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 4.19,
534
+ "learning_rate": 0.0002635671457123822,
535
+ "loss": 20.8082,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 4.24,
540
+ "learning_rate": 0.0002627740236667618,
541
+ "loss": 20.7882,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 4.28,
546
+ "learning_rate": 0.00026198090162114144,
547
+ "loss": 20.7546,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 4.33,
552
+ "learning_rate": 0.00026118777957552107,
553
+ "loss": 20.7187,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 4.38,
558
+ "learning_rate": 0.00026039465752990065,
559
+ "loss": 20.7079,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 4.43,
564
+ "learning_rate": 0.0002596047079724628,
565
+ "loss": 20.6731,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 4.47,
570
+ "learning_rate": 0.0002588115859268424,
571
+ "loss": 20.656,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 4.52,
576
+ "learning_rate": 0.000258018463881222,
577
+ "loss": 20.6342,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 4.57,
582
+ "learning_rate": 0.00025722534183560163,
583
+ "loss": 20.6155,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 4.62,
588
+ "learning_rate": 0.00025643380603407247,
589
+ "loss": 20.587,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 4.66,
594
+ "learning_rate": 0.0002556406839884521,
595
+ "loss": 20.5652,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 4.71,
600
+ "learning_rate": 0.0002548475619428317,
601
+ "loss": 20.5426,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 4.76,
606
+ "learning_rate": 0.00025405443989721135,
607
+ "loss": 20.5183,
608
+ "step": 50000
609
+ },
610
+ {
611
+ "epoch": 4.81,
612
+ "learning_rate": 0.000253261317851591,
613
+ "loss": 20.4988,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 4.85,
618
+ "learning_rate": 0.0002524681958059706,
619
+ "loss": 20.4794,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 4.9,
624
+ "learning_rate": 0.00025167507376035024,
625
+ "loss": 20.4558,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 4.95,
630
+ "learning_rate": 0.00025088195171472986,
631
+ "loss": 20.4292,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 5.0,
636
+ "learning_rate": 0.00025008882966910944,
637
+ "loss": 20.4047,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 5.04,
642
+ "learning_rate": 0.00024929888011167154,
643
+ "loss": 20.404,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 5.09,
648
+ "learning_rate": 0.00024850575806605117,
649
+ "loss": 20.3589,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 5.14,
654
+ "learning_rate": 0.00024771422226452206,
655
+ "loss": 20.3373,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 5.19,
660
+ "learning_rate": 0.0002469211002189017,
661
+ "loss": 20.3208,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 5.23,
666
+ "learning_rate": 0.00024612797817328126,
667
+ "loss": 20.2981,
668
+ "step": 55000
669
+ },
670
+ {
671
+ "epoch": 5.28,
672
+ "learning_rate": 0.0002453348561276609,
673
+ "loss": 20.2951,
674
+ "step": 55500
675
+ },
676
+ {
677
+ "epoch": 5.33,
678
+ "learning_rate": 0.0002445417340820405,
679
+ "loss": 20.2748,
680
+ "step": 56000
681
+ },
682
+ {
683
+ "epoch": 5.38,
684
+ "learning_rate": 0.00024374861203642015,
685
+ "loss": 20.2582,
686
+ "step": 56500
687
+ },
688
+ {
689
+ "epoch": 5.42,
690
+ "learning_rate": 0.00024295548999079977,
691
+ "loss": 20.2498,
692
+ "step": 57000
693
+ },
694
+ {
695
+ "epoch": 5.47,
696
+ "learning_rate": 0.0002421623679451794,
697
+ "loss": 20.2228,
698
+ "step": 57500
699
+ },
700
+ {
701
+ "epoch": 5.52,
702
+ "learning_rate": 0.00024136924589955903,
703
+ "loss": 20.2119,
704
+ "step": 58000
705
+ },
706
+ {
707
+ "epoch": 5.57,
708
+ "learning_rate": 0.0002405761238539386,
709
+ "loss": 20.1897,
710
+ "step": 58500
711
+ },
712
+ {
713
+ "epoch": 5.62,
714
+ "learning_rate": 0.00023978300180831823,
715
+ "loss": 20.1715,
716
+ "step": 59000
717
+ },
718
+ {
719
+ "epoch": 5.66,
720
+ "learning_rate": 0.00023898987976269786,
721
+ "loss": 20.1637,
722
+ "step": 59500
723
+ },
724
+ {
725
+ "epoch": 5.71,
726
+ "learning_rate": 0.00023819675771707748,
727
+ "loss": 20.1498,
728
+ "step": 60000
729
+ },
730
+ {
731
+ "epoch": 5.76,
732
+ "learning_rate": 0.0002374036356714571,
733
+ "loss": 20.1365,
734
+ "step": 60500
735
+ },
736
+ {
737
+ "epoch": 5.81,
738
+ "learning_rate": 0.00023661209986992798,
739
+ "loss": 20.119,
740
+ "step": 61000
741
+ },
742
+ {
743
+ "epoch": 5.85,
744
+ "learning_rate": 0.0002358189778243076,
745
+ "loss": 20.1109,
746
+ "step": 61500
747
+ },
748
+ {
749
+ "epoch": 5.9,
750
+ "learning_rate": 0.00023502585577868718,
751
+ "loss": 20.1085,
752
+ "step": 62000
753
+ },
754
+ {
755
+ "epoch": 5.95,
756
+ "learning_rate": 0.0002342327337330668,
757
+ "loss": 20.0777,
758
+ "step": 62500
759
+ },
760
+ {
761
+ "epoch": 6.0,
762
+ "learning_rate": 0.00023344278417562894,
763
+ "loss": 20.0649,
764
+ "step": 63000
765
+ },
766
+ {
767
+ "epoch": 6.04,
768
+ "learning_rate": 0.00023264966213000857,
769
+ "loss": 20.0717,
770
+ "step": 63500
771
+ },
772
+ {
773
+ "epoch": 6.09,
774
+ "learning_rate": 0.00023185654008438817,
775
+ "loss": 20.0345,
776
+ "step": 64000
777
+ },
778
+ {
779
+ "epoch": 6.14,
780
+ "learning_rate": 0.0002310634180387678,
781
+ "loss": 20.0282,
782
+ "step": 64500
783
+ },
784
+ {
785
+ "epoch": 6.19,
786
+ "learning_rate": 0.0002302702959931474,
787
+ "loss": 20.012,
788
+ "step": 65000
789
+ },
790
+ {
791
+ "epoch": 6.23,
792
+ "learning_rate": 0.00022947717394752702,
793
+ "loss": 20.0094,
794
+ "step": 65500
795
+ },
796
+ {
797
+ "epoch": 6.28,
798
+ "learning_rate": 0.00022868405190190665,
799
+ "loss": 19.9956,
800
+ "step": 66000
801
+ },
802
+ {
803
+ "epoch": 6.33,
804
+ "learning_rate": 0.00022789092985628628,
805
+ "loss": 19.9879,
806
+ "step": 66500
807
+ },
808
+ {
809
+ "epoch": 6.38,
810
+ "learning_rate": 0.00022710098029884838,
811
+ "loss": 19.9747,
812
+ "step": 67000
813
+ },
814
+ {
815
+ "epoch": 6.42,
816
+ "learning_rate": 0.000226307858253228,
817
+ "loss": 19.9557,
818
+ "step": 67500
819
+ },
820
+ {
821
+ "epoch": 6.47,
822
+ "learning_rate": 0.00022551473620760758,
823
+ "loss": 19.9602,
824
+ "step": 68000
825
+ },
826
+ {
827
+ "epoch": 6.52,
828
+ "learning_rate": 0.0002247216141619872,
829
+ "loss": 19.9466,
830
+ "step": 68500
831
+ },
832
+ {
833
+ "epoch": 6.57,
834
+ "learning_rate": 0.00022392849211636684,
835
+ "loss": 19.9366,
836
+ "step": 69000
837
+ },
838
+ {
839
+ "epoch": 6.61,
840
+ "learning_rate": 0.00022314171504711142,
841
+ "loss": 19.9531,
842
+ "step": 69500
843
+ },
844
+ {
845
+ "epoch": 6.66,
846
+ "learning_rate": 0.00022234859300149104,
847
+ "loss": 19.929,
848
+ "step": 70000
849
+ },
850
+ {
851
+ "epoch": 6.71,
852
+ "learning_rate": 0.00022155547095587067,
853
+ "loss": 19.9242,
854
+ "step": 70500
855
+ },
856
+ {
857
+ "epoch": 6.76,
858
+ "learning_rate": 0.0002207623489102503,
859
+ "loss": 19.9227,
860
+ "step": 71000
861
+ },
862
+ {
863
+ "epoch": 6.8,
864
+ "learning_rate": 0.0002199692268646299,
865
+ "loss": 19.9067,
866
+ "step": 71500
867
+ },
868
+ {
869
+ "epoch": 6.85,
870
+ "learning_rate": 0.00021917610481900953,
871
+ "loss": 19.8972,
872
+ "step": 72000
873
+ },
874
+ {
875
+ "epoch": 6.9,
876
+ "learning_rate": 0.00021838298277338916,
877
+ "loss": 19.8938,
878
+ "step": 72500
879
+ },
880
+ {
881
+ "epoch": 6.95,
882
+ "learning_rate": 0.00021758986072776878,
883
+ "loss": 19.8794,
884
+ "step": 73000
885
+ },
886
+ {
887
+ "epoch": 7.0,
888
+ "learning_rate": 0.00021679673868214838,
889
+ "loss": 19.8704,
890
+ "step": 73500
891
+ },
892
+ {
893
+ "epoch": 7.04,
894
+ "learning_rate": 0.000216003616636528,
895
+ "loss": 19.8757,
896
+ "step": 74000
897
+ },
898
+ {
899
+ "epoch": 7.09,
900
+ "learning_rate": 0.0002152104945909076,
901
+ "loss": 19.8342,
902
+ "step": 74500
903
+ },
904
+ {
905
+ "epoch": 7.14,
906
+ "learning_rate": 0.00021441737254528724,
907
+ "loss": 19.8257,
908
+ "step": 75000
909
+ },
910
+ {
911
+ "epoch": 7.19,
912
+ "learning_rate": 0.00021362425049966687,
913
+ "loss": 19.8177,
914
+ "step": 75500
915
+ },
916
+ {
917
+ "epoch": 7.23,
918
+ "learning_rate": 0.0002128311284540465,
919
+ "loss": 19.8072,
920
+ "step": 76000
921
+ },
922
+ {
923
+ "epoch": 7.28,
924
+ "learning_rate": 0.00021203800640842612,
925
+ "loss": 19.7952,
926
+ "step": 76500
927
+ },
928
+ {
929
+ "epoch": 7.33,
930
+ "learning_rate": 0.00021124488436280575,
931
+ "loss": 19.7894,
932
+ "step": 77000
933
+ },
934
+ {
935
+ "epoch": 7.38,
936
+ "learning_rate": 0.00021045652104945906,
937
+ "loss": 19.8001,
938
+ "step": 77500
939
+ },
940
+ {
941
+ "epoch": 7.42,
942
+ "learning_rate": 0.0002096633990038387,
943
+ "loss": 19.7767,
944
+ "step": 78000
945
+ },
946
+ {
947
+ "epoch": 7.47,
948
+ "learning_rate": 0.00020887027695821832,
949
+ "loss": 19.7795,
950
+ "step": 78500
951
+ },
952
+ {
953
+ "epoch": 7.52,
954
+ "learning_rate": 0.00020807715491259795,
955
+ "loss": 19.7661,
956
+ "step": 79000
957
+ },
958
+ {
959
+ "epoch": 7.57,
960
+ "learning_rate": 0.00020728561911106879,
961
+ "loss": 19.7486,
962
+ "step": 79500
963
+ },
964
+ {
965
+ "epoch": 7.61,
966
+ "learning_rate": 0.0002064924970654484,
967
+ "loss": 19.7425,
968
+ "step": 80000
969
+ }
970
+ ],
971
+ "max_steps": 210140,
972
+ "num_train_epochs": 20,
973
+ "total_flos": 0.0,
974
+ "trial_name": null,
975
+ "trial_params": null
976
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c3c8a562e891b34110db985bda6cf331fb1c1a6082094cea74d4e465d49983
3
+ size 3055
vocab.txt ADDED
The diff for this file is too large to render. See raw diff