duyvu8373 commited on
Commit
f0e9492
1 Parent(s): 93033e7

Upload 12 files

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "VietAI/vit5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 3072,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.37.0",
30
+ "use_cache": false,
31
+ "vocab_size": 36096
32
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.37.0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737956d39f2d29a5bb3a5cdde5fa144e614a1e40c629c559d9eaf70749989ab5
3
+ size 903834408
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af77b7a4a3fd5bd310f1904695b4bea92af4a9ce683f57c34a5e82fefc2dc88
3
+ size 1807824186
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5626c250864563ab32ab675b3bc621ff087c1391b44956c71481c1cd16ee96
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39c9dabd3f17803cbde9a81b23fa0e472de2fc9c8ccfd2fda1669a56c9a04b77
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>"
99
+ ],
100
+ "eos_token": "</s>",
101
+ "pad_token": "<pad>",
102
+ "unk_token": "<unk>"
103
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59986b62f9f0b90edafb9b073ea7b93d21114a5841219a1ea2399ade73f729c6
3
+ size 820370
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,902 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "36000": {
28
+ "content": "<extra_id_95>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "36001": {
36
+ "content": "<extra_id_94>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "36002": {
44
+ "content": "<extra_id_93>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "36003": {
52
+ "content": "<extra_id_92>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "36004": {
60
+ "content": "<extra_id_91>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "36005": {
68
+ "content": "<extra_id_90>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "36006": {
76
+ "content": "<extra_id_89>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "36007": {
84
+ "content": "<extra_id_88>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "36008": {
92
+ "content": "<extra_id_87>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "36009": {
100
+ "content": "<extra_id_86>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "36010": {
108
+ "content": "<extra_id_85>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "36011": {
116
+ "content": "<extra_id_84>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "36012": {
124
+ "content": "<extra_id_83>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "36013": {
132
+ "content": "<extra_id_82>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "36014": {
140
+ "content": "<extra_id_81>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "36015": {
148
+ "content": "<extra_id_80>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "36016": {
156
+ "content": "<extra_id_79>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "36017": {
164
+ "content": "<extra_id_78>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "36018": {
172
+ "content": "<extra_id_77>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "36019": {
180
+ "content": "<extra_id_76>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "36020": {
188
+ "content": "<extra_id_75>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "36021": {
196
+ "content": "<extra_id_74>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "36022": {
204
+ "content": "<extra_id_73>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "36023": {
212
+ "content": "<extra_id_72>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "36024": {
220
+ "content": "<extra_id_71>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "36025": {
228
+ "content": "<extra_id_70>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "36026": {
236
+ "content": "<extra_id_69>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "36027": {
244
+ "content": "<extra_id_68>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "36028": {
252
+ "content": "<extra_id_67>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "36029": {
260
+ "content": "<extra_id_66>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "36030": {
268
+ "content": "<extra_id_65>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "36031": {
276
+ "content": "<extra_id_64>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "36032": {
284
+ "content": "<extra_id_63>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "36033": {
292
+ "content": "<extra_id_62>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "36034": {
300
+ "content": "<extra_id_61>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "36035": {
308
+ "content": "<extra_id_60>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "36036": {
316
+ "content": "<extra_id_59>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "36037": {
324
+ "content": "<extra_id_58>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "36038": {
332
+ "content": "<extra_id_57>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "36039": {
340
+ "content": "<extra_id_56>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "36040": {
348
+ "content": "<extra_id_55>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "36041": {
356
+ "content": "<extra_id_54>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "36042": {
364
+ "content": "<extra_id_53>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "36043": {
372
+ "content": "<extra_id_52>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "36044": {
380
+ "content": "<extra_id_51>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "36045": {
388
+ "content": "<extra_id_50>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "36046": {
396
+ "content": "<extra_id_49>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "36047": {
404
+ "content": "<extra_id_48>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "36048": {
412
+ "content": "<extra_id_47>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "36049": {
420
+ "content": "<extra_id_46>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "36050": {
428
+ "content": "<extra_id_45>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "36051": {
436
+ "content": "<extra_id_44>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "36052": {
444
+ "content": "<extra_id_43>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "36053": {
452
+ "content": "<extra_id_42>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "36054": {
460
+ "content": "<extra_id_41>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "36055": {
468
+ "content": "<extra_id_40>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "36056": {
476
+ "content": "<extra_id_39>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "36057": {
484
+ "content": "<extra_id_38>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "36058": {
492
+ "content": "<extra_id_37>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "36059": {
500
+ "content": "<extra_id_36>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "36060": {
508
+ "content": "<extra_id_35>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "36061": {
516
+ "content": "<extra_id_34>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "36062": {
524
+ "content": "<extra_id_33>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "36063": {
532
+ "content": "<extra_id_32>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "36064": {
540
+ "content": "<extra_id_31>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "36065": {
548
+ "content": "<extra_id_30>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "36066": {
556
+ "content": "<extra_id_29>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "36067": {
564
+ "content": "<extra_id_28>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "36068": {
572
+ "content": "<extra_id_27>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "36069": {
580
+ "content": "<extra_id_26>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "36070": {
588
+ "content": "<extra_id_25>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "36071": {
596
+ "content": "<extra_id_24>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "36072": {
604
+ "content": "<extra_id_23>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "36073": {
612
+ "content": "<extra_id_22>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "36074": {
620
+ "content": "<extra_id_21>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "36075": {
628
+ "content": "<extra_id_20>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "36076": {
636
+ "content": "<extra_id_19>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "36077": {
644
+ "content": "<extra_id_18>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "36078": {
652
+ "content": "<extra_id_17>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "36079": {
660
+ "content": "<extra_id_16>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "36080": {
668
+ "content": "<extra_id_15>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "36081": {
676
+ "content": "<extra_id_14>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "36082": {
684
+ "content": "<extra_id_13>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "36083": {
692
+ "content": "<extra_id_12>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "36084": {
700
+ "content": "<extra_id_11>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "36085": {
708
+ "content": "<extra_id_10>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "36086": {
716
+ "content": "<extra_id_9>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "36087": {
724
+ "content": "<extra_id_8>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "36088": {
732
+ "content": "<extra_id_7>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "36089": {
740
+ "content": "<extra_id_6>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "36090": {
748
+ "content": "<extra_id_5>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "36091": {
756
+ "content": "<extra_id_4>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "36092": {
764
+ "content": "<extra_id_3>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "36093": {
772
+ "content": "<extra_id_2>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "36094": {
780
+ "content": "<extra_id_1>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "36095": {
788
+ "content": "<extra_id_0>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ }
795
+ },
796
+ "additional_special_tokens": [
797
+ "<extra_id_0>",
798
+ "<extra_id_1>",
799
+ "<extra_id_2>",
800
+ "<extra_id_3>",
801
+ "<extra_id_4>",
802
+ "<extra_id_5>",
803
+ "<extra_id_6>",
804
+ "<extra_id_7>",
805
+ "<extra_id_8>",
806
+ "<extra_id_9>",
807
+ "<extra_id_10>",
808
+ "<extra_id_11>",
809
+ "<extra_id_12>",
810
+ "<extra_id_13>",
811
+ "<extra_id_14>",
812
+ "<extra_id_15>",
813
+ "<extra_id_16>",
814
+ "<extra_id_17>",
815
+ "<extra_id_18>",
816
+ "<extra_id_19>",
817
+ "<extra_id_20>",
818
+ "<extra_id_21>",
819
+ "<extra_id_22>",
820
+ "<extra_id_23>",
821
+ "<extra_id_24>",
822
+ "<extra_id_25>",
823
+ "<extra_id_26>",
824
+ "<extra_id_27>",
825
+ "<extra_id_28>",
826
+ "<extra_id_29>",
827
+ "<extra_id_30>",
828
+ "<extra_id_31>",
829
+ "<extra_id_32>",
830
+ "<extra_id_33>",
831
+ "<extra_id_34>",
832
+ "<extra_id_35>",
833
+ "<extra_id_36>",
834
+ "<extra_id_37>",
835
+ "<extra_id_38>",
836
+ "<extra_id_39>",
837
+ "<extra_id_40>",
838
+ "<extra_id_41>",
839
+ "<extra_id_42>",
840
+ "<extra_id_43>",
841
+ "<extra_id_44>",
842
+ "<extra_id_45>",
843
+ "<extra_id_46>",
844
+ "<extra_id_47>",
845
+ "<extra_id_48>",
846
+ "<extra_id_49>",
847
+ "<extra_id_50>",
848
+ "<extra_id_51>",
849
+ "<extra_id_52>",
850
+ "<extra_id_53>",
851
+ "<extra_id_54>",
852
+ "<extra_id_55>",
853
+ "<extra_id_56>",
854
+ "<extra_id_57>",
855
+ "<extra_id_58>",
856
+ "<extra_id_59>",
857
+ "<extra_id_60>",
858
+ "<extra_id_61>",
859
+ "<extra_id_62>",
860
+ "<extra_id_63>",
861
+ "<extra_id_64>",
862
+ "<extra_id_65>",
863
+ "<extra_id_66>",
864
+ "<extra_id_67>",
865
+ "<extra_id_68>",
866
+ "<extra_id_69>",
867
+ "<extra_id_70>",
868
+ "<extra_id_71>",
869
+ "<extra_id_72>",
870
+ "<extra_id_73>",
871
+ "<extra_id_74>",
872
+ "<extra_id_75>",
873
+ "<extra_id_76>",
874
+ "<extra_id_77>",
875
+ "<extra_id_78>",
876
+ "<extra_id_79>",
877
+ "<extra_id_80>",
878
+ "<extra_id_81>",
879
+ "<extra_id_82>",
880
+ "<extra_id_83>",
881
+ "<extra_id_84>",
882
+ "<extra_id_85>",
883
+ "<extra_id_86>",
884
+ "<extra_id_87>",
885
+ "<extra_id_88>",
886
+ "<extra_id_89>",
887
+ "<extra_id_90>",
888
+ "<extra_id_91>",
889
+ "<extra_id_92>",
890
+ "<extra_id_93>",
891
+ "<extra_id_94>",
892
+ "<extra_id_95>"
893
+ ],
894
+ "clean_up_tokenization_spaces": true,
895
+ "eos_token": "</s>",
896
+ "extra_ids": 96,
897
+ "model_max_length": 1000000000000000019884624838656,
898
+ "pad_token": "<pad>",
899
+ "sp_model_kwargs": {},
900
+ "tokenizer_class": "T5Tokenizer",
901
+ "unk_token": "<unk>"
902
+ }
trainer_state.json ADDED
@@ -0,0 +1,909 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 24.91103202846975,
5
+ "eval_steps": 500,
6
+ "global_step": 14000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.89,
13
+ "learning_rate": 1.9288256227758007e-05,
14
+ "loss": 0.7021,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_bp": 0.4478803932550057,
20
+ "eval_counts": [
21
+ 951,
22
+ 851,
23
+ 761,
24
+ 672
25
+ ],
26
+ "eval_loss": 0.1726560890674591,
27
+ "eval_precisions": [
28
+ 95.96367305751765,
29
+ 92.19934994582881,
30
+ 89.00584795321637,
31
+ 85.38754764930114
32
+ ],
33
+ "eval_ref_len": 1787,
34
+ "eval_runtime": 18.1569,
35
+ "eval_samples_per_second": 3.745,
36
+ "eval_score": 40.55776382580726,
37
+ "eval_steps_per_second": 1.873,
38
+ "eval_sys_len": 991,
39
+ "eval_totals": [
40
+ 991,
41
+ 923,
42
+ 855,
43
+ 787
44
+ ],
45
+ "step": 562
46
+ },
47
+ {
48
+ "epoch": 1.78,
49
+ "learning_rate": 1.8576512455516017e-05,
50
+ "loss": 0.2854,
51
+ "step": 1000
52
+ },
53
+ {
54
+ "epoch": 2.0,
55
+ "eval_bp": 0.441355602158059,
56
+ "eval_counts": [
57
+ 962,
58
+ 883,
59
+ 802,
60
+ 721
61
+ ],
62
+ "eval_loss": 0.11405563354492188,
63
+ "eval_precisions": [
64
+ 97.86368260427264,
65
+ 96.50273224043715,
66
+ 94.68713105076742,
67
+ 92.55455712451861
68
+ ],
69
+ "eval_ref_len": 1787,
70
+ "eval_runtime": 16.4762,
71
+ "eval_samples_per_second": 4.127,
72
+ "eval_score": 42.09699789518687,
73
+ "eval_steps_per_second": 2.064,
74
+ "eval_sys_len": 983,
75
+ "eval_totals": [
76
+ 983,
77
+ 915,
78
+ 847,
79
+ 779
80
+ ],
81
+ "step": 1124
82
+ },
83
+ {
84
+ "epoch": 2.67,
85
+ "learning_rate": 1.7864768683274022e-05,
86
+ "loss": 0.1956,
87
+ "step": 1500
88
+ },
89
+ {
90
+ "epoch": 3.0,
91
+ "eval_bp": 0.44380356964488166,
92
+ "eval_counts": [
93
+ 965,
94
+ 886,
95
+ 806,
96
+ 726
97
+ ],
98
+ "eval_loss": 0.10203403234481812,
99
+ "eval_precisions": [
100
+ 97.87018255578093,
101
+ 96.51416122004358,
102
+ 94.82352941176471,
103
+ 92.8388746803069
104
+ ],
105
+ "eval_ref_len": 1787,
106
+ "eval_runtime": 16.5425,
107
+ "eval_samples_per_second": 4.111,
108
+ "eval_score": 42.380165345955355,
109
+ "eval_steps_per_second": 2.055,
110
+ "eval_sys_len": 986,
111
+ "eval_totals": [
112
+ 986,
113
+ 918,
114
+ 850,
115
+ 782
116
+ ],
117
+ "step": 1686
118
+ },
119
+ {
120
+ "epoch": 3.56,
121
+ "learning_rate": 1.715302491103203e-05,
122
+ "loss": 0.1441,
123
+ "step": 2000
124
+ },
125
+ {
126
+ "epoch": 4.0,
127
+ "eval_bp": 0.437272650606809,
128
+ "eval_counts": [
129
+ 966,
130
+ 894,
131
+ 816,
132
+ 739
133
+ ],
134
+ "eval_loss": 0.05576588958501816,
135
+ "eval_precisions": [
136
+ 98.77300613496932,
137
+ 98.24175824175825,
138
+ 96.91211401425178,
139
+ 95.4780361757106
140
+ ],
141
+ "eval_ref_len": 1787,
142
+ "eval_runtime": 16.5385,
143
+ "eval_samples_per_second": 4.112,
144
+ "eval_score": 42.565359021286106,
145
+ "eval_steps_per_second": 2.056,
146
+ "eval_sys_len": 978,
147
+ "eval_totals": [
148
+ 978,
149
+ 910,
150
+ 842,
151
+ 774
152
+ ],
153
+ "step": 2248
154
+ },
155
+ {
156
+ "epoch": 4.45,
157
+ "learning_rate": 1.6441281138790037e-05,
158
+ "loss": 0.1082,
159
+ "step": 2500
160
+ },
161
+ {
162
+ "epoch": 5.0,
163
+ "eval_bp": 0.425821753267709,
164
+ "eval_counts": [
165
+ 956,
166
+ 882,
167
+ 809,
168
+ 736
169
+ ],
170
+ "eval_loss": 0.0341346338391304,
171
+ "eval_precisions": [
172
+ 99.1701244813278,
173
+ 98.4375,
174
+ 97.70531400966183,
175
+ 96.84210526315789
176
+ ],
177
+ "eval_ref_len": 1787,
178
+ "eval_runtime": 16.4383,
179
+ "eval_samples_per_second": 4.137,
180
+ "eval_score": 41.745417030738814,
181
+ "eval_steps_per_second": 2.068,
182
+ "eval_sys_len": 964,
183
+ "eval_totals": [
184
+ 964,
185
+ 896,
186
+ 828,
187
+ 760
188
+ ],
189
+ "step": 2810
190
+ },
191
+ {
192
+ "epoch": 5.34,
193
+ "learning_rate": 1.5729537366548043e-05,
194
+ "loss": 0.0942,
195
+ "step": 3000
196
+ },
197
+ {
198
+ "epoch": 6.0,
199
+ "eval_bp": 0.4356384499188918,
200
+ "eval_counts": [
201
+ 973,
202
+ 899,
203
+ 824,
204
+ 749
205
+ ],
206
+ "eval_loss": 0.05856137350201607,
207
+ "eval_precisions": [
208
+ 99.69262295081967,
209
+ 99.00881057268722,
210
+ 98.0952380952381,
211
+ 97.02072538860104
212
+ ],
213
+ "eval_ref_len": 1787,
214
+ "eval_runtime": 16.3313,
215
+ "eval_samples_per_second": 4.164,
216
+ "eval_score": 42.888270294493864,
217
+ "eval_steps_per_second": 2.082,
218
+ "eval_sys_len": 976,
219
+ "eval_totals": [
220
+ 976,
221
+ 908,
222
+ 840,
223
+ 772
224
+ ],
225
+ "step": 3372
226
+ },
227
+ {
228
+ "epoch": 6.23,
229
+ "learning_rate": 1.5017793594306052e-05,
230
+ "loss": 0.0713,
231
+ "step": 3500
232
+ },
233
+ {
234
+ "epoch": 7.0,
235
+ "eval_bp": 0.42745918009113226,
236
+ "eval_counts": [
237
+ 964,
238
+ 894,
239
+ 824,
240
+ 754
241
+ ],
242
+ "eval_loss": 0.02425399236381054,
243
+ "eval_precisions": [
244
+ 99.79296066252589,
245
+ 99.55456570155901,
246
+ 99.27710843373494,
247
+ 98.9501312335958
248
+ ],
249
+ "eval_ref_len": 1787,
250
+ "eval_runtime": 16.4255,
251
+ "eval_samples_per_second": 4.14,
252
+ "eval_score": 42.486533114975146,
253
+ "eval_steps_per_second": 2.07,
254
+ "eval_sys_len": 966,
255
+ "eval_totals": [
256
+ 966,
257
+ 898,
258
+ 830,
259
+ 762
260
+ ],
261
+ "step": 3934
262
+ },
263
+ {
264
+ "epoch": 7.12,
265
+ "learning_rate": 1.4306049822064058e-05,
266
+ "loss": 0.0599,
267
+ "step": 4000
268
+ },
269
+ {
270
+ "epoch": 8.0,
271
+ "eval_bp": 0.43073249568232586,
272
+ "eval_counts": [
273
+ 961,
274
+ 890,
275
+ 820,
276
+ 751
277
+ ],
278
+ "eval_loss": 0.015419703908264637,
279
+ "eval_precisions": [
280
+ 99.0721649484536,
281
+ 98.66962305986696,
282
+ 98.32134292565948,
283
+ 98.04177545691905
284
+ ],
285
+ "eval_ref_len": 1787,
286
+ "eval_runtime": 16.187,
287
+ "eval_samples_per_second": 4.201,
288
+ "eval_score": 42.438122327030186,
289
+ "eval_steps_per_second": 2.1,
290
+ "eval_sys_len": 970,
291
+ "eval_totals": [
292
+ 970,
293
+ 902,
294
+ 834,
295
+ 766
296
+ ],
297
+ "step": 4496
298
+ },
299
+ {
300
+ "epoch": 8.01,
301
+ "learning_rate": 1.3594306049822066e-05,
302
+ "loss": 0.048,
303
+ "step": 4500
304
+ },
305
+ {
306
+ "epoch": 8.9,
307
+ "learning_rate": 1.2882562277580073e-05,
308
+ "loss": 0.0392,
309
+ "step": 5000
310
+ },
311
+ {
312
+ "epoch": 9.0,
313
+ "eval_bp": 0.4250028527550296,
314
+ "eval_counts": [
315
+ 959,
316
+ 889,
317
+ 818,
318
+ 747
319
+ ],
320
+ "eval_loss": 0.019724518060684204,
321
+ "eval_precisions": [
322
+ 99.5846313603323,
323
+ 99.32960893854748,
324
+ 98.9117291414752,
325
+ 98.41897233201581
326
+ ],
327
+ "eval_ref_len": 1787,
328
+ "eval_runtime": 16.8132,
329
+ "eval_samples_per_second": 4.044,
330
+ "eval_score": 42.10088852964188,
331
+ "eval_steps_per_second": 2.022,
332
+ "eval_sys_len": 963,
333
+ "eval_totals": [
334
+ 963,
335
+ 895,
336
+ 827,
337
+ 759
338
+ ],
339
+ "step": 5058
340
+ },
341
+ {
342
+ "epoch": 9.79,
343
+ "learning_rate": 1.217081850533808e-05,
344
+ "loss": 0.0319,
345
+ "step": 5500
346
+ },
347
+ {
348
+ "epoch": 10.0,
349
+ "eval_bp": 0.42909609813393135,
350
+ "eval_counts": [
351
+ 966,
352
+ 898,
353
+ 830,
354
+ 762
355
+ ],
356
+ "eval_loss": 0.005858541466295719,
357
+ "eval_precisions": [
358
+ 99.79338842975207,
359
+ 99.77777777777777,
360
+ 99.75961538461539,
361
+ 99.73821989528795
362
+ ],
363
+ "eval_ref_len": 1787,
364
+ "eval_runtime": 16.1653,
365
+ "eval_samples_per_second": 4.207,
366
+ "eval_score": 42.809736944779694,
367
+ "eval_steps_per_second": 2.103,
368
+ "eval_sys_len": 968,
369
+ "eval_totals": [
370
+ 968,
371
+ 900,
372
+ 832,
373
+ 764
374
+ ],
375
+ "step": 5620
376
+ },
377
+ {
378
+ "epoch": 10.68,
379
+ "learning_rate": 1.1459074733096086e-05,
380
+ "loss": 0.026,
381
+ "step": 6000
382
+ },
383
+ {
384
+ "epoch": 11.0,
385
+ "eval_bp": 0.42909609813393135,
386
+ "eval_counts": [
387
+ 966,
388
+ 898,
389
+ 829,
390
+ 760
391
+ ],
392
+ "eval_loss": 0.010834704153239727,
393
+ "eval_precisions": [
394
+ 99.79338842975207,
395
+ 99.77777777777777,
396
+ 99.63942307692308,
397
+ 99.47643979057591
398
+ ],
399
+ "eval_ref_len": 1787,
400
+ "eval_runtime": 16.4611,
401
+ "eval_samples_per_second": 4.131,
402
+ "eval_score": 42.768727019910926,
403
+ "eval_steps_per_second": 2.065,
404
+ "eval_sys_len": 968,
405
+ "eval_totals": [
406
+ 968,
407
+ 900,
408
+ 832,
409
+ 764
410
+ ],
411
+ "step": 6182
412
+ },
413
+ {
414
+ "epoch": 11.57,
415
+ "learning_rate": 1.0747330960854094e-05,
416
+ "loss": 0.025,
417
+ "step": 6500
418
+ },
419
+ {
420
+ "epoch": 12.0,
421
+ "eval_bp": 0.42909609813393135,
422
+ "eval_counts": [
423
+ 966,
424
+ 898,
425
+ 830,
426
+ 762
427
+ ],
428
+ "eval_loss": 0.0013562627136707306,
429
+ "eval_precisions": [
430
+ 99.79338842975207,
431
+ 99.77777777777777,
432
+ 99.75961538461539,
433
+ 99.73821989528795
434
+ ],
435
+ "eval_ref_len": 1787,
436
+ "eval_runtime": 16.1168,
437
+ "eval_samples_per_second": 4.219,
438
+ "eval_score": 42.809736944779694,
439
+ "eval_steps_per_second": 2.11,
440
+ "eval_sys_len": 968,
441
+ "eval_totals": [
442
+ 968,
443
+ 900,
444
+ 832,
445
+ 764
446
+ ],
447
+ "step": 6744
448
+ },
449
+ {
450
+ "epoch": 12.46,
451
+ "learning_rate": 1.0035587188612101e-05,
452
+ "loss": 0.0182,
453
+ "step": 7000
454
+ },
455
+ {
456
+ "epoch": 13.0,
457
+ "eval_bp": 0.42909609813393135,
458
+ "eval_counts": [
459
+ 966,
460
+ 898,
461
+ 830,
462
+ 762
463
+ ],
464
+ "eval_loss": 0.0013860436156392097,
465
+ "eval_precisions": [
466
+ 99.79338842975207,
467
+ 99.77777777777777,
468
+ 99.75961538461539,
469
+ 99.73821989528795
470
+ ],
471
+ "eval_ref_len": 1787,
472
+ "eval_runtime": 16.6416,
473
+ "eval_samples_per_second": 4.086,
474
+ "eval_score": 42.809736944779694,
475
+ "eval_steps_per_second": 2.043,
476
+ "eval_sys_len": 968,
477
+ "eval_totals": [
478
+ 968,
479
+ 900,
480
+ 832,
481
+ 764
482
+ ],
483
+ "step": 7306
484
+ },
485
+ {
486
+ "epoch": 13.35,
487
+ "learning_rate": 9.323843416370107e-06,
488
+ "loss": 0.0148,
489
+ "step": 7500
490
+ },
491
+ {
492
+ "epoch": 14.0,
493
+ "eval_bp": 0.4315504956415897,
494
+ "eval_counts": [
495
+ 963,
496
+ 894,
497
+ 825,
498
+ 756
499
+ ],
500
+ "eval_loss": 0.004028095863759518,
501
+ "eval_precisions": [
502
+ 99.17610710607622,
503
+ 99.00332225913621,
504
+ 98.80239520958084,
505
+ 98.56584093872229
506
+ ],
507
+ "eval_ref_len": 1787,
508
+ "eval_runtime": 16.2486,
509
+ "eval_samples_per_second": 4.185,
510
+ "eval_score": 42.674584599098594,
511
+ "eval_steps_per_second": 2.092,
512
+ "eval_sys_len": 971,
513
+ "eval_totals": [
514
+ 971,
515
+ 903,
516
+ 835,
517
+ 767
518
+ ],
519
+ "step": 7868
520
+ },
521
+ {
522
+ "epoch": 14.23,
523
+ "learning_rate": 8.612099644128115e-06,
524
+ "loss": 0.0149,
525
+ "step": 8000
526
+ },
527
+ {
528
+ "epoch": 15.0,
529
+ "eval_bp": 0.4299143626976017,
530
+ "eval_counts": [
531
+ 967,
532
+ 899,
533
+ 830,
534
+ 761
535
+ ],
536
+ "eval_loss": 0.004267631098628044,
537
+ "eval_precisions": [
538
+ 99.79360165118679,
539
+ 99.7780244173141,
540
+ 99.63985594237695,
541
+ 99.47712418300654
542
+ ],
543
+ "eval_ref_len": 1787,
544
+ "eval_runtime": 16.2443,
545
+ "eval_samples_per_second": 4.186,
546
+ "eval_score": 42.85045442963625,
547
+ "eval_steps_per_second": 2.093,
548
+ "eval_sys_len": 969,
549
+ "eval_totals": [
550
+ 969,
551
+ 901,
552
+ 833,
553
+ 765
554
+ ],
555
+ "step": 8430
556
+ },
557
+ {
558
+ "epoch": 15.12,
559
+ "learning_rate": 7.900355871886122e-06,
560
+ "loss": 0.0144,
561
+ "step": 8500
562
+ },
563
+ {
564
+ "epoch": 16.0,
565
+ "eval_bp": 0.42909609813393135,
566
+ "eval_counts": [
567
+ 966,
568
+ 898,
569
+ 830,
570
+ 762
571
+ ],
572
+ "eval_loss": 0.00286501320078969,
573
+ "eval_precisions": [
574
+ 99.79338842975207,
575
+ 99.77777777777777,
576
+ 99.75961538461539,
577
+ 99.73821989528795
578
+ ],
579
+ "eval_ref_len": 1787,
580
+ "eval_runtime": 16.5144,
581
+ "eval_samples_per_second": 4.118,
582
+ "eval_score": 42.809736944779694,
583
+ "eval_steps_per_second": 2.059,
584
+ "eval_sys_len": 968,
585
+ "eval_totals": [
586
+ 968,
587
+ 900,
588
+ 832,
589
+ 764
590
+ ],
591
+ "step": 8992
592
+ },
593
+ {
594
+ "epoch": 16.01,
595
+ "learning_rate": 7.188612099644129e-06,
596
+ "loss": 0.0112,
597
+ "step": 9000
598
+ },
599
+ {
600
+ "epoch": 16.9,
601
+ "learning_rate": 6.476868327402136e-06,
602
+ "loss": 0.0098,
603
+ "step": 9500
604
+ },
605
+ {
606
+ "epoch": 17.0,
607
+ "eval_bp": 0.42909609813393135,
608
+ "eval_counts": [
609
+ 966,
610
+ 898,
611
+ 830,
612
+ 762
613
+ ],
614
+ "eval_loss": 0.0009978804737329483,
615
+ "eval_precisions": [
616
+ 99.79338842975207,
617
+ 99.77777777777777,
618
+ 99.75961538461539,
619
+ 99.73821989528795
620
+ ],
621
+ "eval_ref_len": 1787,
622
+ "eval_runtime": 16.1028,
623
+ "eval_samples_per_second": 4.223,
624
+ "eval_score": 42.809736944779694,
625
+ "eval_steps_per_second": 2.111,
626
+ "eval_sys_len": 968,
627
+ "eval_totals": [
628
+ 968,
629
+ 900,
630
+ 832,
631
+ 764
632
+ ],
633
+ "step": 9554
634
+ },
635
+ {
636
+ "epoch": 17.79,
637
+ "learning_rate": 5.765124555160143e-06,
638
+ "loss": 0.0089,
639
+ "step": 10000
640
+ },
641
+ {
642
+ "epoch": 18.0,
643
+ "eval_bp": 0.42909609813393135,
644
+ "eval_counts": [
645
+ 966,
646
+ 898,
647
+ 830,
648
+ 762
649
+ ],
650
+ "eval_loss": 0.00037646759301424026,
651
+ "eval_precisions": [
652
+ 99.79338842975207,
653
+ 99.77777777777777,
654
+ 99.75961538461539,
655
+ 99.73821989528795
656
+ ],
657
+ "eval_ref_len": 1787,
658
+ "eval_runtime": 16.4684,
659
+ "eval_samples_per_second": 4.129,
660
+ "eval_score": 42.809736944779694,
661
+ "eval_steps_per_second": 2.065,
662
+ "eval_sys_len": 968,
663
+ "eval_totals": [
664
+ 968,
665
+ 900,
666
+ 832,
667
+ 764
668
+ ],
669
+ "step": 10116
670
+ },
671
+ {
672
+ "epoch": 18.68,
673
+ "learning_rate": 5.05338078291815e-06,
674
+ "loss": 0.0075,
675
+ "step": 10500
676
+ },
677
+ {
678
+ "epoch": 19.0,
679
+ "eval_bp": 0.42909609813393135,
680
+ "eval_counts": [
681
+ 966,
682
+ 898,
683
+ 830,
684
+ 762
685
+ ],
686
+ "eval_loss": 0.00018596854351926595,
687
+ "eval_precisions": [
688
+ 99.79338842975207,
689
+ 99.77777777777777,
690
+ 99.75961538461539,
691
+ 99.73821989528795
692
+ ],
693
+ "eval_ref_len": 1787,
694
+ "eval_runtime": 16.3451,
695
+ "eval_samples_per_second": 4.16,
696
+ "eval_score": 42.809736944779694,
697
+ "eval_steps_per_second": 2.08,
698
+ "eval_sys_len": 968,
699
+ "eval_totals": [
700
+ 968,
701
+ 900,
702
+ 832,
703
+ 764
704
+ ],
705
+ "step": 10678
706
+ },
707
+ {
708
+ "epoch": 19.57,
709
+ "learning_rate": 4.341637010676157e-06,
710
+ "loss": 0.0068,
711
+ "step": 11000
712
+ },
713
+ {
714
+ "epoch": 20.0,
715
+ "eval_bp": 0.42909609813393135,
716
+ "eval_counts": [
717
+ 966,
718
+ 898,
719
+ 830,
720
+ 762
721
+ ],
722
+ "eval_loss": 7.006935447861906e-06,
723
+ "eval_precisions": [
724
+ 99.79338842975207,
725
+ 99.77777777777777,
726
+ 99.75961538461539,
727
+ 99.73821989528795
728
+ ],
729
+ "eval_ref_len": 1787,
730
+ "eval_runtime": 16.0905,
731
+ "eval_samples_per_second": 4.226,
732
+ "eval_score": 42.809736944779694,
733
+ "eval_steps_per_second": 2.113,
734
+ "eval_sys_len": 968,
735
+ "eval_totals": [
736
+ 968,
737
+ 900,
738
+ 832,
739
+ 764
740
+ ],
741
+ "step": 11240
742
+ },
743
+ {
744
+ "epoch": 20.46,
745
+ "learning_rate": 3.629893238434164e-06,
746
+ "loss": 0.0056,
747
+ "step": 11500
748
+ },
749
+ {
750
+ "epoch": 21.0,
751
+ "eval_bp": 0.42909609813393135,
752
+ "eval_counts": [
753
+ 966,
754
+ 898,
755
+ 830,
756
+ 762
757
+ ],
758
+ "eval_loss": 1.5906211046967655e-05,
759
+ "eval_precisions": [
760
+ 99.79338842975207,
761
+ 99.77777777777777,
762
+ 99.75961538461539,
763
+ 99.73821989528795
764
+ ],
765
+ "eval_ref_len": 1787,
766
+ "eval_runtime": 16.3937,
767
+ "eval_samples_per_second": 4.148,
768
+ "eval_score": 42.809736944779694,
769
+ "eval_steps_per_second": 2.074,
770
+ "eval_sys_len": 968,
771
+ "eval_totals": [
772
+ 968,
773
+ 900,
774
+ 832,
775
+ 764
776
+ ],
777
+ "step": 11802
778
+ },
779
+ {
780
+ "epoch": 21.35,
781
+ "learning_rate": 2.918149466192171e-06,
782
+ "loss": 0.0041,
783
+ "step": 12000
784
+ },
785
+ {
786
+ "epoch": 22.0,
787
+ "eval_bp": 0.42909609813393135,
788
+ "eval_counts": [
789
+ 966,
790
+ 898,
791
+ 830,
792
+ 762
793
+ ],
794
+ "eval_loss": 1.3131144442013465e-05,
795
+ "eval_precisions": [
796
+ 99.79338842975207,
797
+ 99.77777777777777,
798
+ 99.75961538461539,
799
+ 99.73821989528795
800
+ ],
801
+ "eval_ref_len": 1787,
802
+ "eval_runtime": 16.4474,
803
+ "eval_samples_per_second": 4.134,
804
+ "eval_score": 42.809736944779694,
805
+ "eval_steps_per_second": 2.067,
806
+ "eval_sys_len": 968,
807
+ "eval_totals": [
808
+ 968,
809
+ 900,
810
+ 832,
811
+ 764
812
+ ],
813
+ "step": 12364
814
+ },
815
+ {
816
+ "epoch": 22.24,
817
+ "learning_rate": 2.2064056939501782e-06,
818
+ "loss": 0.0033,
819
+ "step": 12500
820
+ },
821
+ {
822
+ "epoch": 23.0,
823
+ "eval_bp": 0.42909609813393135,
824
+ "eval_counts": [
825
+ 966,
826
+ 898,
827
+ 830,
828
+ 762
829
+ ],
830
+ "eval_loss": 5.197064183448674e-06,
831
+ "eval_precisions": [
832
+ 99.79338842975207,
833
+ 99.77777777777777,
834
+ 99.75961538461539,
835
+ 99.73821989528795
836
+ ],
837
+ "eval_ref_len": 1787,
838
+ "eval_runtime": 16.1321,
839
+ "eval_samples_per_second": 4.215,
840
+ "eval_score": 42.809736944779694,
841
+ "eval_steps_per_second": 2.108,
842
+ "eval_sys_len": 968,
843
+ "eval_totals": [
844
+ 968,
845
+ 900,
846
+ 832,
847
+ 764
848
+ ],
849
+ "step": 12926
850
+ },
851
+ {
852
+ "epoch": 23.13,
853
+ "learning_rate": 1.494661921708185e-06,
854
+ "loss": 0.0033,
855
+ "step": 13000
856
+ },
857
+ {
858
+ "epoch": 24.0,
859
+ "eval_bp": 0.42909609813393135,
860
+ "eval_counts": [
861
+ 966,
862
+ 898,
863
+ 830,
864
+ 762
865
+ ],
866
+ "eval_loss": 2.9162031296436908e-06,
867
+ "eval_precisions": [
868
+ 99.79338842975207,
869
+ 99.77777777777777,
870
+ 99.75961538461539,
871
+ 99.73821989528795
872
+ ],
873
+ "eval_ref_len": 1787,
874
+ "eval_runtime": 16.4335,
875
+ "eval_samples_per_second": 4.138,
876
+ "eval_score": 42.809736944779694,
877
+ "eval_steps_per_second": 2.069,
878
+ "eval_sys_len": 968,
879
+ "eval_totals": [
880
+ 968,
881
+ 900,
882
+ 832,
883
+ 764
884
+ ],
885
+ "step": 13488
886
+ },
887
+ {
888
+ "epoch": 24.02,
889
+ "learning_rate": 7.829181494661923e-07,
890
+ "loss": 0.0025,
891
+ "step": 13500
892
+ },
893
+ {
894
+ "epoch": 24.91,
895
+ "learning_rate": 7.117437722419929e-08,
896
+ "loss": 0.0023,
897
+ "step": 14000
898
+ }
899
+ ],
900
+ "logging_steps": 500,
901
+ "max_steps": 14050,
902
+ "num_input_tokens_seen": 0,
903
+ "num_train_epochs": 25,
904
+ "save_steps": 500,
905
+ "total_flos": 2476170265006080.0,
906
+ "train_batch_size": 2,
907
+ "trial_name": null,
908
+ "trial_params": null
909
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c134f81c994ca2055469594d6e5175cf2da37c84c417b0b683d2fcfce48a0ee0
3
+ size 4856