duyvu8373 commited on
Commit
64b925d
1 Parent(s): 4e52389

Upload 12 files

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "duyvu8373/vit5-base-newformat",
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": true,
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 sha256:4b8d03fa856c5d64d31a525a2f83e77eff70c981b437371a32dce28085f04ee1
3
+ size 903834408
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d30f7feaee41a4f9b5c388cc38559f402dd54a209ad878521a81bdf4b2536934
3
+ size 1807824186
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19d4f0b5cd6717dc7a747c0d2115e48d9f25a9154783d18b643e092c46773f4c
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d7850e60e1d70db02ff34128df1e02e6e90351becfeb0e5c2a59b4a2f875291
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 +1,1473 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 46.51162790697674,
5
+ "eval_steps": 500,
6
+ "global_step": 6000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_bp": 0.9523463051958837,
14
+ "eval_counts": [
15
+ 3593,
16
+ 3028,
17
+ 2503,
18
+ 1978
19
+ ],
20
+ "eval_loss": 0.020566828548908234,
21
+ "eval_precisions": [
22
+ 96.92473698408416,
23
+ 95.19019176359636,
24
+ 94.27495291902072,
25
+ 92.90746829497417
26
+ ],
27
+ "eval_ref_len": 3888,
28
+ "eval_runtime": 15.2582,
29
+ "eval_samples_per_second": 34.473,
30
+ "eval_score": 90.29492610822332,
31
+ "eval_steps_per_second": 1.114,
32
+ "eval_sys_len": 3707,
33
+ "eval_totals": [
34
+ 3707,
35
+ 3181,
36
+ 2655,
37
+ 2129
38
+ ],
39
+ "step": 129
40
+ },
41
+ {
42
+ "epoch": 2.0,
43
+ "eval_bp": 0.9404234170896001,
44
+ "eval_counts": [
45
+ 3612,
46
+ 3070,
47
+ 2543,
48
+ 2017
49
+ ],
50
+ "eval_loss": 0.008390815928578377,
51
+ "eval_precisions": [
52
+ 98.60769860769861,
53
+ 97.86420146636914,
54
+ 97.39563385675986,
55
+ 96.73860911270984
56
+ ],
57
+ "eval_ref_len": 3888,
58
+ "eval_runtime": 12.8658,
59
+ "eval_samples_per_second": 40.883,
60
+ "eval_score": 91.83155461111092,
61
+ "eval_steps_per_second": 1.321,
62
+ "eval_sys_len": 3663,
63
+ "eval_totals": [
64
+ 3663,
65
+ 3137,
66
+ 2611,
67
+ 2085
68
+ ],
69
+ "step": 258
70
+ },
71
+ {
72
+ "epoch": 3.0,
73
+ "eval_bp": 0.9398782656901951,
74
+ "eval_counts": [
75
+ 3630,
76
+ 3102,
77
+ 2576,
78
+ 2050
79
+ ],
80
+ "eval_loss": 0.0058166454546153545,
81
+ "eval_precisions": [
82
+ 99.15323682054084,
83
+ 98.94736842105263,
84
+ 98.73514756611729,
85
+ 98.4157465194431
86
+ ],
87
+ "eval_ref_len": 3888,
88
+ "eval_runtime": 12.6316,
89
+ "eval_samples_per_second": 41.642,
90
+ "eval_score": 92.87171931381575,
91
+ "eval_steps_per_second": 1.346,
92
+ "eval_sys_len": 3661,
93
+ "eval_totals": [
94
+ 3661,
95
+ 3135,
96
+ 2609,
97
+ 2083
98
+ ],
99
+ "step": 387
100
+ },
101
+ {
102
+ "epoch": 3.88,
103
+ "learning_rate": 1.8449612403100777e-05,
104
+ "loss": 0.0629,
105
+ "step": 500
106
+ },
107
+ {
108
+ "epoch": 4.0,
109
+ "eval_bp": 0.9330402574316247,
110
+ "eval_counts": [
111
+ 3610,
112
+ 3078,
113
+ 2553,
114
+ 2028
115
+ ],
116
+ "eval_loss": 0.005211379379034042,
117
+ "eval_precisions": [
118
+ 99.28492849284929,
119
+ 98.97106109324758,
120
+ 98.80030959752322,
121
+ 98.54227405247813
122
+ ],
123
+ "eval_ref_len": 3888,
124
+ "eval_runtime": 12.7405,
125
+ "eval_samples_per_second": 41.286,
126
+ "eval_score": 92.27700542114854,
127
+ "eval_steps_per_second": 1.334,
128
+ "eval_sys_len": 3636,
129
+ "eval_totals": [
130
+ 3636,
131
+ 3110,
132
+ 2584,
133
+ 2058
134
+ ],
135
+ "step": 516
136
+ },
137
+ {
138
+ "epoch": 5.0,
139
+ "eval_bp": 0.9338631315468312,
140
+ "eval_counts": [
141
+ 3627,
142
+ 3095,
143
+ 2565,
144
+ 2036
145
+ ],
146
+ "eval_loss": 0.0038907737471163273,
147
+ "eval_precisions": [
148
+ 99.67023907666942,
149
+ 99.42177963379376,
150
+ 99.14959412446849,
151
+ 98.7869966035905
152
+ ],
153
+ "eval_ref_len": 3888,
154
+ "eval_runtime": 12.6798,
155
+ "eval_samples_per_second": 41.483,
156
+ "eval_score": 92.69208875986402,
157
+ "eval_steps_per_second": 1.341,
158
+ "eval_sys_len": 3639,
159
+ "eval_totals": [
160
+ 3639,
161
+ 3113,
162
+ 2587,
163
+ 2061
164
+ ],
165
+ "step": 645
166
+ },
167
+ {
168
+ "epoch": 6.0,
169
+ "eval_bp": 0.9335889103861881,
170
+ "eval_counts": [
171
+ 3634,
172
+ 3104,
173
+ 2576,
174
+ 2049
175
+ ],
176
+ "eval_loss": 0.002504762727767229,
177
+ "eval_precisions": [
178
+ 99.89004947773502,
179
+ 99.74293059125964,
180
+ 99.61330239752513,
181
+ 99.46601941747574
182
+ ],
183
+ "eval_ref_len": 3888,
184
+ "eval_runtime": 12.7893,
185
+ "eval_samples_per_second": 41.128,
186
+ "eval_score": 93.05823077997785,
187
+ "eval_steps_per_second": 1.329,
188
+ "eval_sys_len": 3638,
189
+ "eval_totals": [
190
+ 3638,
191
+ 3112,
192
+ 2586,
193
+ 2060
194
+ ],
195
+ "step": 774
196
+ },
197
+ {
198
+ "epoch": 7.0,
199
+ "eval_bp": 0.9357807151741461,
200
+ "eval_counts": [
201
+ 3634,
202
+ 3107,
203
+ 2581,
204
+ 2055
205
+ ],
206
+ "eval_loss": 0.0016112308949232101,
207
+ "eval_precisions": [
208
+ 99.67087218869995,
209
+ 99.58333333333333,
210
+ 99.4988434849653,
211
+ 99.37137330754352
212
+ ],
213
+ "eval_ref_len": 3888,
214
+ "eval_runtime": 12.7232,
215
+ "eval_samples_per_second": 41.342,
216
+ "eval_score": 93.13923177834742,
217
+ "eval_steps_per_second": 1.336,
218
+ "eval_sys_len": 3646,
219
+ "eval_totals": [
220
+ 3646,
221
+ 3120,
222
+ 2594,
223
+ 2068
224
+ ],
225
+ "step": 903
226
+ },
227
+ {
228
+ "epoch": 7.75,
229
+ "learning_rate": 1.689922480620155e-05,
230
+ "loss": 0.0146,
231
+ "step": 1000
232
+ },
233
+ {
234
+ "epoch": 8.0,
235
+ "eval_bp": 0.9335889103861881,
236
+ "eval_counts": [
237
+ 3635,
238
+ 3109,
239
+ 2583,
240
+ 2057
241
+ ],
242
+ "eval_loss": 0.0012645127717405558,
243
+ "eval_precisions": [
244
+ 99.91753710830126,
245
+ 99.90359897172236,
246
+ 99.88399071925754,
247
+ 99.85436893203884
248
+ ],
249
+ "eval_ref_len": 3888,
250
+ "eval_runtime": 12.6584,
251
+ "eval_samples_per_second": 41.553,
252
+ "eval_score": 93.25607593613448,
253
+ "eval_steps_per_second": 1.343,
254
+ "eval_sys_len": 3638,
255
+ "eval_totals": [
256
+ 3638,
257
+ 3112,
258
+ 2586,
259
+ 2060
260
+ ],
261
+ "step": 1032
262
+ },
263
+ {
264
+ "epoch": 9.0,
265
+ "eval_bp": 0.9341372825165507,
266
+ "eval_counts": [
267
+ 3633,
268
+ 3105,
269
+ 2580,
270
+ 2055
271
+ ],
272
+ "eval_loss": 0.001253910711966455,
273
+ "eval_precisions": [
274
+ 99.8076923076923,
275
+ 99.71098265895954,
276
+ 99.69088098918084,
277
+ 99.66052376333657
278
+ ],
279
+ "eval_ref_len": 3888,
280
+ "eval_runtime": 12.6869,
281
+ "eval_samples_per_second": 41.46,
282
+ "eval_score": 93.14983888433298,
283
+ "eval_steps_per_second": 1.34,
284
+ "eval_sys_len": 3640,
285
+ "eval_totals": [
286
+ 3640,
287
+ 3114,
288
+ 2588,
289
+ 2062
290
+ ],
291
+ "step": 1161
292
+ },
293
+ {
294
+ "epoch": 10.0,
295
+ "eval_bp": 0.933314619019492,
296
+ "eval_counts": [
297
+ 3634,
298
+ 3108,
299
+ 2582,
300
+ 2056
301
+ ],
302
+ "eval_loss": 0.002512833336368203,
303
+ "eval_precisions": [
304
+ 99.91751443497388,
305
+ 99.90356798457088,
306
+ 99.88394584139265,
307
+ 99.85429820301117
308
+ ],
309
+ "eval_ref_len": 3888,
310
+ "eval_runtime": 12.7666,
311
+ "eval_samples_per_second": 41.201,
312
+ "eval_score": 93.22863750791105,
313
+ "eval_steps_per_second": 1.332,
314
+ "eval_sys_len": 3637,
315
+ "eval_totals": [
316
+ 3637,
317
+ 3111,
318
+ 2585,
319
+ 2059
320
+ ],
321
+ "step": 1290
322
+ },
323
+ {
324
+ "epoch": 11.0,
325
+ "eval_bp": 0.9335889103861881,
326
+ "eval_counts": [
327
+ 3635,
328
+ 3109,
329
+ 2583,
330
+ 2057
331
+ ],
332
+ "eval_loss": 0.0023178395349532366,
333
+ "eval_precisions": [
334
+ 99.91753710830126,
335
+ 99.90359897172236,
336
+ 99.88399071925754,
337
+ 99.85436893203884
338
+ ],
339
+ "eval_ref_len": 3888,
340
+ "eval_runtime": 12.9233,
341
+ "eval_samples_per_second": 40.702,
342
+ "eval_score": 93.25607593613448,
343
+ "eval_steps_per_second": 1.315,
344
+ "eval_sys_len": 3638,
345
+ "eval_totals": [
346
+ 3638,
347
+ 3112,
348
+ 2586,
349
+ 2060
350
+ ],
351
+ "step": 1419
352
+ },
353
+ {
354
+ "epoch": 11.63,
355
+ "learning_rate": 1.5348837209302328e-05,
356
+ "loss": 0.0083,
357
+ "step": 1500
358
+ },
359
+ {
360
+ "epoch": 12.0,
361
+ "eval_bp": 0.9335889103861881,
362
+ "eval_counts": [
363
+ 3634,
364
+ 3107,
365
+ 2580,
366
+ 2053
367
+ ],
368
+ "eval_loss": 0.0019630142487585545,
369
+ "eval_precisions": [
370
+ 99.89004947773502,
371
+ 99.83933161953728,
372
+ 99.76798143851508,
373
+ 99.66019417475728
374
+ ],
375
+ "eval_ref_len": 3888,
376
+ "eval_runtime": 12.6747,
377
+ "eval_samples_per_second": 41.5,
378
+ "eval_score": 93.16223228048803,
379
+ "eval_steps_per_second": 1.341,
380
+ "eval_sys_len": 3638,
381
+ "eval_totals": [
382
+ 3638,
383
+ 3112,
384
+ 2586,
385
+ 2060
386
+ ],
387
+ "step": 1548
388
+ },
389
+ {
390
+ "epoch": 13.0,
391
+ "eval_bp": 0.933314619019492,
392
+ "eval_counts": [
393
+ 3634,
394
+ 3108,
395
+ 2582,
396
+ 2056
397
+ ],
398
+ "eval_loss": 0.0019749533385038376,
399
+ "eval_precisions": [
400
+ 99.91751443497388,
401
+ 99.90356798457088,
402
+ 99.88394584139265,
403
+ 99.85429820301117
404
+ ],
405
+ "eval_ref_len": 3888,
406
+ "eval_runtime": 12.9957,
407
+ "eval_samples_per_second": 40.475,
408
+ "eval_score": 93.22863750791105,
409
+ "eval_steps_per_second": 1.308,
410
+ "eval_sys_len": 3637,
411
+ "eval_totals": [
412
+ 3637,
413
+ 3111,
414
+ 2585,
415
+ 2059
416
+ ],
417
+ "step": 1677
418
+ },
419
+ {
420
+ "epoch": 14.0,
421
+ "eval_bp": 0.9316673956463823,
422
+ "eval_counts": [
423
+ 3624,
424
+ 3098,
425
+ 2573,
426
+ 2048
427
+ ],
428
+ "eval_loss": 0.003918025176972151,
429
+ "eval_precisions": [
430
+ 99.80721564307353,
431
+ 99.77455716586151,
432
+ 99.76735168670027,
433
+ 99.75645396980029
434
+ ],
435
+ "eval_ref_len": 3888,
436
+ "eval_runtime": 12.6294,
437
+ "eval_samples_per_second": 41.649,
438
+ "eval_score": 92.95841204711185,
439
+ "eval_steps_per_second": 1.346,
440
+ "eval_sys_len": 3631,
441
+ "eval_totals": [
442
+ 3631,
443
+ 3105,
444
+ 2579,
445
+ 2053
446
+ ],
447
+ "step": 1806
448
+ },
449
+ {
450
+ "epoch": 15.0,
451
+ "eval_bp": 0.936327965220313,
452
+ "eval_counts": [
453
+ 3633,
454
+ 3105,
455
+ 2580,
456
+ 2055
457
+ ],
458
+ "eval_loss": 0.0004065596731379628,
459
+ "eval_precisions": [
460
+ 99.58881578947368,
461
+ 99.45547725816785,
462
+ 99.38366718027736,
463
+ 99.27536231884058
464
+ ],
465
+ "eval_ref_len": 3888,
466
+ "eval_runtime": 12.9462,
467
+ "eval_samples_per_second": 40.63,
468
+ "eval_score": 93.09512464742835,
469
+ "eval_steps_per_second": 1.313,
470
+ "eval_sys_len": 3648,
471
+ "eval_totals": [
472
+ 3648,
473
+ 3122,
474
+ 2596,
475
+ 2070
476
+ ],
477
+ "step": 1935
478
+ },
479
+ {
480
+ "epoch": 15.5,
481
+ "learning_rate": 1.3798449612403102e-05,
482
+ "loss": 0.0058,
483
+ "step": 2000
484
+ },
485
+ {
486
+ "epoch": 16.0,
487
+ "eval_bp": 0.9335889103861881,
488
+ "eval_counts": [
489
+ 3635,
490
+ 3109,
491
+ 2583,
492
+ 2057
493
+ ],
494
+ "eval_loss": 0.0023909315932542086,
495
+ "eval_precisions": [
496
+ 99.91753710830126,
497
+ 99.90359897172236,
498
+ 99.88399071925754,
499
+ 99.85436893203884
500
+ ],
501
+ "eval_ref_len": 3888,
502
+ "eval_runtime": 12.6508,
503
+ "eval_samples_per_second": 41.578,
504
+ "eval_score": 93.25607593613448,
505
+ "eval_steps_per_second": 1.344,
506
+ "eval_sys_len": 3638,
507
+ "eval_totals": [
508
+ 3638,
509
+ 3112,
510
+ 2586,
511
+ 2060
512
+ ],
513
+ "step": 2064
514
+ },
515
+ {
516
+ "epoch": 17.0,
517
+ "eval_bp": 0.9335889103861881,
518
+ "eval_counts": [
519
+ 3635,
520
+ 3109,
521
+ 2583,
522
+ 2057
523
+ ],
524
+ "eval_loss": 0.0004882567736785859,
525
+ "eval_precisions": [
526
+ 99.91753710830126,
527
+ 99.90359897172236,
528
+ 99.88399071925754,
529
+ 99.85436893203884
530
+ ],
531
+ "eval_ref_len": 3888,
532
+ "eval_runtime": 12.9088,
533
+ "eval_samples_per_second": 40.747,
534
+ "eval_score": 93.25607593613448,
535
+ "eval_steps_per_second": 1.317,
536
+ "eval_sys_len": 3638,
537
+ "eval_totals": [
538
+ 3638,
539
+ 3112,
540
+ 2586,
541
+ 2060
542
+ ],
543
+ "step": 2193
544
+ },
545
+ {
546
+ "epoch": 18.0,
547
+ "eval_bp": 0.9335889103861881,
548
+ "eval_counts": [
549
+ 3635,
550
+ 3109,
551
+ 2583,
552
+ 2057
553
+ ],
554
+ "eval_loss": 0.000274818652542308,
555
+ "eval_precisions": [
556
+ 99.91753710830126,
557
+ 99.90359897172236,
558
+ 99.88399071925754,
559
+ 99.85436893203884
560
+ ],
561
+ "eval_ref_len": 3888,
562
+ "eval_runtime": 12.638,
563
+ "eval_samples_per_second": 41.621,
564
+ "eval_score": 93.25607593613448,
565
+ "eval_steps_per_second": 1.345,
566
+ "eval_sys_len": 3638,
567
+ "eval_totals": [
568
+ 3638,
569
+ 3112,
570
+ 2586,
571
+ 2060
572
+ ],
573
+ "step": 2322
574
+ },
575
+ {
576
+ "epoch": 19.0,
577
+ "eval_bp": 0.9335889103861881,
578
+ "eval_counts": [
579
+ 3635,
580
+ 3109,
581
+ 2583,
582
+ 2057
583
+ ],
584
+ "eval_loss": 0.0001670583733357489,
585
+ "eval_precisions": [
586
+ 99.91753710830126,
587
+ 99.90359897172236,
588
+ 99.88399071925754,
589
+ 99.85436893203884
590
+ ],
591
+ "eval_ref_len": 3888,
592
+ "eval_runtime": 12.6977,
593
+ "eval_samples_per_second": 41.425,
594
+ "eval_score": 93.25607593613448,
595
+ "eval_steps_per_second": 1.339,
596
+ "eval_sys_len": 3638,
597
+ "eval_totals": [
598
+ 3638,
599
+ 3112,
600
+ 2586,
601
+ 2060
602
+ ],
603
+ "step": 2451
604
+ },
605
+ {
606
+ "epoch": 19.38,
607
+ "learning_rate": 1.2248062015503876e-05,
608
+ "loss": 0.0045,
609
+ "step": 2500
610
+ },
611
+ {
612
+ "epoch": 20.0,
613
+ "eval_bp": 0.9335889103861881,
614
+ "eval_counts": [
615
+ 3635,
616
+ 3109,
617
+ 2583,
618
+ 2057
619
+ ],
620
+ "eval_loss": 2.638001569721382e-05,
621
+ "eval_precisions": [
622
+ 99.91753710830126,
623
+ 99.90359897172236,
624
+ 99.88399071925754,
625
+ 99.85436893203884
626
+ ],
627
+ "eval_ref_len": 3888,
628
+ "eval_runtime": 12.6589,
629
+ "eval_samples_per_second": 41.552,
630
+ "eval_score": 93.25607593613448,
631
+ "eval_steps_per_second": 1.343,
632
+ "eval_sys_len": 3638,
633
+ "eval_totals": [
634
+ 3638,
635
+ 3112,
636
+ 2586,
637
+ 2060
638
+ ],
639
+ "step": 2580
640
+ },
641
+ {
642
+ "epoch": 21.0,
643
+ "eval_bp": 0.9335889103861881,
644
+ "eval_counts": [
645
+ 3635,
646
+ 3109,
647
+ 2583,
648
+ 2057
649
+ ],
650
+ "eval_loss": 2.2430480385082774e-05,
651
+ "eval_precisions": [
652
+ 99.91753710830126,
653
+ 99.90359897172236,
654
+ 99.88399071925754,
655
+ 99.85436893203884
656
+ ],
657
+ "eval_ref_len": 3888,
658
+ "eval_runtime": 12.8875,
659
+ "eval_samples_per_second": 40.815,
660
+ "eval_score": 93.25607593613448,
661
+ "eval_steps_per_second": 1.319,
662
+ "eval_sys_len": 3638,
663
+ "eval_totals": [
664
+ 3638,
665
+ 3112,
666
+ 2586,
667
+ 2060
668
+ ],
669
+ "step": 2709
670
+ },
671
+ {
672
+ "epoch": 22.0,
673
+ "eval_bp": 0.9338631315468312,
674
+ "eval_counts": [
675
+ 3635,
676
+ 3109,
677
+ 2582,
678
+ 2055
679
+ ],
680
+ "eval_loss": 0.002159741008654237,
681
+ "eval_precisions": [
682
+ 99.89007969222314,
683
+ 99.8715065852875,
684
+ 99.8067259373792,
685
+ 99.70887918486171
686
+ ],
687
+ "eval_ref_len": 3888,
688
+ "eval_runtime": 12.6238,
689
+ "eval_samples_per_second": 41.667,
690
+ "eval_score": 93.21753858269537,
691
+ "eval_steps_per_second": 1.347,
692
+ "eval_sys_len": 3639,
693
+ "eval_totals": [
694
+ 3639,
695
+ 3113,
696
+ 2587,
697
+ 2061
698
+ ],
699
+ "step": 2838
700
+ },
701
+ {
702
+ "epoch": 23.0,
703
+ "eval_bp": 0.9335889103861881,
704
+ "eval_counts": [
705
+ 3635,
706
+ 3109,
707
+ 2583,
708
+ 2057
709
+ ],
710
+ "eval_loss": 0.00015405841986648738,
711
+ "eval_precisions": [
712
+ 99.91753710830126,
713
+ 99.90359897172236,
714
+ 99.88399071925754,
715
+ 99.85436893203884
716
+ ],
717
+ "eval_ref_len": 3888,
718
+ "eval_runtime": 12.6331,
719
+ "eval_samples_per_second": 41.637,
720
+ "eval_score": 93.25607593613448,
721
+ "eval_steps_per_second": 1.346,
722
+ "eval_sys_len": 3638,
723
+ "eval_totals": [
724
+ 3638,
725
+ 3112,
726
+ 2586,
727
+ 2060
728
+ ],
729
+ "step": 2967
730
+ },
731
+ {
732
+ "epoch": 23.26,
733
+ "learning_rate": 1.0697674418604651e-05,
734
+ "loss": 0.0028,
735
+ "step": 3000
736
+ },
737
+ {
738
+ "epoch": 24.0,
739
+ "eval_bp": 0.9335889103861881,
740
+ "eval_counts": [
741
+ 3635,
742
+ 3109,
743
+ 2583,
744
+ 2057
745
+ ],
746
+ "eval_loss": 2.6909227017313242e-05,
747
+ "eval_precisions": [
748
+ 99.91753710830126,
749
+ 99.90359897172236,
750
+ 99.88399071925754,
751
+ 99.85436893203884
752
+ ],
753
+ "eval_ref_len": 3888,
754
+ "eval_runtime": 12.7937,
755
+ "eval_samples_per_second": 41.114,
756
+ "eval_score": 93.25607593613448,
757
+ "eval_steps_per_second": 1.329,
758
+ "eval_sys_len": 3638,
759
+ "eval_totals": [
760
+ 3638,
761
+ 3112,
762
+ 2586,
763
+ 2060
764
+ ],
765
+ "step": 3096
766
+ },
767
+ {
768
+ "epoch": 25.0,
769
+ "eval_bp": 0.9335889103861881,
770
+ "eval_counts": [
771
+ 3635,
772
+ 3109,
773
+ 2582,
774
+ 2055
775
+ ],
776
+ "eval_loss": 0.0019257767125964165,
777
+ "eval_precisions": [
778
+ 99.91753710830126,
779
+ 99.90359897172236,
780
+ 99.84532095901005,
781
+ 99.75728155339806
782
+ ],
783
+ "eval_ref_len": 3888,
784
+ "eval_runtime": 12.5937,
785
+ "eval_samples_per_second": 41.767,
786
+ "eval_score": 93.2243746232048,
787
+ "eval_steps_per_second": 1.35,
788
+ "eval_sys_len": 3638,
789
+ "eval_totals": [
790
+ 3638,
791
+ 3112,
792
+ 2586,
793
+ 2060
794
+ ],
795
+ "step": 3225
796
+ },
797
+ {
798
+ "epoch": 26.0,
799
+ "eval_bp": 0.9335889103861881,
800
+ "eval_counts": [
801
+ 3635,
802
+ 3109,
803
+ 2583,
804
+ 2057
805
+ ],
806
+ "eval_loss": 2.2932923457119614e-05,
807
+ "eval_precisions": [
808
+ 99.91753710830126,
809
+ 99.90359897172236,
810
+ 99.88399071925754,
811
+ 99.85436893203884
812
+ ],
813
+ "eval_ref_len": 3888,
814
+ "eval_runtime": 12.8177,
815
+ "eval_samples_per_second": 41.037,
816
+ "eval_score": 93.25607593613448,
817
+ "eval_steps_per_second": 1.326,
818
+ "eval_sys_len": 3638,
819
+ "eval_totals": [
820
+ 3638,
821
+ 3112,
822
+ 2586,
823
+ 2060
824
+ ],
825
+ "step": 3354
826
+ },
827
+ {
828
+ "epoch": 27.0,
829
+ "eval_bp": 0.9335889103861881,
830
+ "eval_counts": [
831
+ 3635,
832
+ 3109,
833
+ 2583,
834
+ 2057
835
+ ],
836
+ "eval_loss": 8.50883407110814e-06,
837
+ "eval_precisions": [
838
+ 99.91753710830126,
839
+ 99.90359897172236,
840
+ 99.88399071925754,
841
+ 99.85436893203884
842
+ ],
843
+ "eval_ref_len": 3888,
844
+ "eval_runtime": 12.6361,
845
+ "eval_samples_per_second": 41.627,
846
+ "eval_score": 93.25607593613448,
847
+ "eval_steps_per_second": 1.345,
848
+ "eval_sys_len": 3638,
849
+ "eval_totals": [
850
+ 3638,
851
+ 3112,
852
+ 2586,
853
+ 2060
854
+ ],
855
+ "step": 3483
856
+ },
857
+ {
858
+ "epoch": 27.13,
859
+ "learning_rate": 9.147286821705427e-06,
860
+ "loss": 0.0024,
861
+ "step": 3500
862
+ },
863
+ {
864
+ "epoch": 28.0,
865
+ "eval_bp": 0.9335889103861881,
866
+ "eval_counts": [
867
+ 3635,
868
+ 3109,
869
+ 2583,
870
+ 2057
871
+ ],
872
+ "eval_loss": 4.2664833017624915e-05,
873
+ "eval_precisions": [
874
+ 99.91753710830126,
875
+ 99.90359897172236,
876
+ 99.88399071925754,
877
+ 99.85436893203884
878
+ ],
879
+ "eval_ref_len": 3888,
880
+ "eval_runtime": 12.8206,
881
+ "eval_samples_per_second": 41.028,
882
+ "eval_score": 93.25607593613448,
883
+ "eval_steps_per_second": 1.326,
884
+ "eval_sys_len": 3638,
885
+ "eval_totals": [
886
+ 3638,
887
+ 3112,
888
+ 2586,
889
+ 2060
890
+ ],
891
+ "step": 3612
892
+ },
893
+ {
894
+ "epoch": 29.0,
895
+ "eval_bp": 0.9335889103861881,
896
+ "eval_counts": [
897
+ 3635,
898
+ 3109,
899
+ 2583,
900
+ 2057
901
+ ],
902
+ "eval_loss": 1.0555435437709093e-05,
903
+ "eval_precisions": [
904
+ 99.91753710830126,
905
+ 99.90359897172236,
906
+ 99.88399071925754,
907
+ 99.85436893203884
908
+ ],
909
+ "eval_ref_len": 3888,
910
+ "eval_runtime": 12.6065,
911
+ "eval_samples_per_second": 41.725,
912
+ "eval_score": 93.25607593613448,
913
+ "eval_steps_per_second": 1.349,
914
+ "eval_sys_len": 3638,
915
+ "eval_totals": [
916
+ 3638,
917
+ 3112,
918
+ 2586,
919
+ 2060
920
+ ],
921
+ "step": 3741
922
+ },
923
+ {
924
+ "epoch": 30.0,
925
+ "eval_bp": 0.9335889103861881,
926
+ "eval_counts": [
927
+ 3635,
928
+ 3109,
929
+ 2583,
930
+ 2057
931
+ ],
932
+ "eval_loss": 4.156934210186591e-06,
933
+ "eval_precisions": [
934
+ 99.91753710830126,
935
+ 99.90359897172236,
936
+ 99.88399071925754,
937
+ 99.85436893203884
938
+ ],
939
+ "eval_ref_len": 3888,
940
+ "eval_runtime": 12.9263,
941
+ "eval_samples_per_second": 40.692,
942
+ "eval_score": 93.25607593613448,
943
+ "eval_steps_per_second": 1.315,
944
+ "eval_sys_len": 3638,
945
+ "eval_totals": [
946
+ 3638,
947
+ 3112,
948
+ 2586,
949
+ 2060
950
+ ],
951
+ "step": 3870
952
+ },
953
+ {
954
+ "epoch": 31.0,
955
+ "eval_bp": 0.9335889103861881,
956
+ "eval_counts": [
957
+ 3635,
958
+ 3109,
959
+ 2583,
960
+ 2057
961
+ ],
962
+ "eval_loss": 3.890494554070756e-06,
963
+ "eval_precisions": [
964
+ 99.91753710830126,
965
+ 99.90359897172236,
966
+ 99.88399071925754,
967
+ 99.85436893203884
968
+ ],
969
+ "eval_ref_len": 3888,
970
+ "eval_runtime": 12.67,
971
+ "eval_samples_per_second": 41.515,
972
+ "eval_score": 93.25607593613448,
973
+ "eval_steps_per_second": 1.342,
974
+ "eval_sys_len": 3638,
975
+ "eval_totals": [
976
+ 3638,
977
+ 3112,
978
+ 2586,
979
+ 2060
980
+ ],
981
+ "step": 3999
982
+ },
983
+ {
984
+ "epoch": 31.01,
985
+ "learning_rate": 7.596899224806202e-06,
986
+ "loss": 0.002,
987
+ "step": 4000
988
+ },
989
+ {
990
+ "epoch": 32.0,
991
+ "eval_bp": 0.9335889103861881,
992
+ "eval_counts": [
993
+ 3635,
994
+ 3109,
995
+ 2583,
996
+ 2057
997
+ ],
998
+ "eval_loss": 4.488087142817676e-06,
999
+ "eval_precisions": [
1000
+ 99.91753710830126,
1001
+ 99.90359897172236,
1002
+ 99.88399071925754,
1003
+ 99.85436893203884
1004
+ ],
1005
+ "eval_ref_len": 3888,
1006
+ "eval_runtime": 12.6776,
1007
+ "eval_samples_per_second": 41.491,
1008
+ "eval_score": 93.25607593613448,
1009
+ "eval_steps_per_second": 1.341,
1010
+ "eval_sys_len": 3638,
1011
+ "eval_totals": [
1012
+ 3638,
1013
+ 3112,
1014
+ 2586,
1015
+ 2060
1016
+ ],
1017
+ "step": 4128
1018
+ },
1019
+ {
1020
+ "epoch": 33.0,
1021
+ "eval_bp": 0.9335889103861881,
1022
+ "eval_counts": [
1023
+ 3635,
1024
+ 3109,
1025
+ 2583,
1026
+ 2057
1027
+ ],
1028
+ "eval_loss": 4.070204340678174e-06,
1029
+ "eval_precisions": [
1030
+ 99.91753710830126,
1031
+ 99.90359897172236,
1032
+ 99.88399071925754,
1033
+ 99.85436893203884
1034
+ ],
1035
+ "eval_ref_len": 3888,
1036
+ "eval_runtime": 12.6602,
1037
+ "eval_samples_per_second": 41.547,
1038
+ "eval_score": 93.25607593613448,
1039
+ "eval_steps_per_second": 1.343,
1040
+ "eval_sys_len": 3638,
1041
+ "eval_totals": [
1042
+ 3638,
1043
+ 3112,
1044
+ 2586,
1045
+ 2060
1046
+ ],
1047
+ "step": 4257
1048
+ },
1049
+ {
1050
+ "epoch": 34.0,
1051
+ "eval_bp": 0.9335889103861881,
1052
+ "eval_counts": [
1053
+ 3635,
1054
+ 3109,
1055
+ 2583,
1056
+ 2057
1057
+ ],
1058
+ "eval_loss": 1.0456860763952136e-06,
1059
+ "eval_precisions": [
1060
+ 99.91753710830126,
1061
+ 99.90359897172236,
1062
+ 99.88399071925754,
1063
+ 99.85436893203884
1064
+ ],
1065
+ "eval_ref_len": 3888,
1066
+ "eval_runtime": 12.6435,
1067
+ "eval_samples_per_second": 41.602,
1068
+ "eval_score": 93.25607593613448,
1069
+ "eval_steps_per_second": 1.345,
1070
+ "eval_sys_len": 3638,
1071
+ "eval_totals": [
1072
+ 3638,
1073
+ 3112,
1074
+ 2586,
1075
+ 2060
1076
+ ],
1077
+ "step": 4386
1078
+ },
1079
+ {
1080
+ "epoch": 34.88,
1081
+ "learning_rate": 6.046511627906977e-06,
1082
+ "loss": 0.0015,
1083
+ "step": 4500
1084
+ },
1085
+ {
1086
+ "epoch": 35.0,
1087
+ "eval_bp": 0.9335889103861881,
1088
+ "eval_counts": [
1089
+ 3635,
1090
+ 3109,
1091
+ 2583,
1092
+ 2057
1093
+ ],
1094
+ "eval_loss": 1.005386025099142e-06,
1095
+ "eval_precisions": [
1096
+ 99.91753710830126,
1097
+ 99.90359897172236,
1098
+ 99.88399071925754,
1099
+ 99.85436893203884
1100
+ ],
1101
+ "eval_ref_len": 3888,
1102
+ "eval_runtime": 12.9848,
1103
+ "eval_samples_per_second": 40.509,
1104
+ "eval_score": 93.25607593613448,
1105
+ "eval_steps_per_second": 1.309,
1106
+ "eval_sys_len": 3638,
1107
+ "eval_totals": [
1108
+ 3638,
1109
+ 3112,
1110
+ 2586,
1111
+ 2060
1112
+ ],
1113
+ "step": 4515
1114
+ },
1115
+ {
1116
+ "epoch": 36.0,
1117
+ "eval_bp": 0.9335889103861881,
1118
+ "eval_counts": [
1119
+ 3635,
1120
+ 3109,
1121
+ 2583,
1122
+ 2057
1123
+ ],
1124
+ "eval_loss": 1.019975456983957e-06,
1125
+ "eval_precisions": [
1126
+ 99.91753710830126,
1127
+ 99.90359897172236,
1128
+ 99.88399071925754,
1129
+ 99.85436893203884
1130
+ ],
1131
+ "eval_ref_len": 3888,
1132
+ "eval_runtime": 12.6703,
1133
+ "eval_samples_per_second": 41.515,
1134
+ "eval_score": 93.25607593613448,
1135
+ "eval_steps_per_second": 1.342,
1136
+ "eval_sys_len": 3638,
1137
+ "eval_totals": [
1138
+ 3638,
1139
+ 3112,
1140
+ 2586,
1141
+ 2060
1142
+ ],
1143
+ "step": 4644
1144
+ },
1145
+ {
1146
+ "epoch": 37.0,
1147
+ "eval_bp": 0.9335889103861881,
1148
+ "eval_counts": [
1149
+ 3635,
1150
+ 3109,
1151
+ 2583,
1152
+ 2057
1153
+ ],
1154
+ "eval_loss": 9.417852879778366e-07,
1155
+ "eval_precisions": [
1156
+ 99.91753710830126,
1157
+ 99.90359897172236,
1158
+ 99.88399071925754,
1159
+ 99.85436893203884
1160
+ ],
1161
+ "eval_ref_len": 3888,
1162
+ "eval_runtime": 12.9803,
1163
+ "eval_samples_per_second": 40.523,
1164
+ "eval_score": 93.25607593613448,
1165
+ "eval_steps_per_second": 1.31,
1166
+ "eval_sys_len": 3638,
1167
+ "eval_totals": [
1168
+ 3638,
1169
+ 3112,
1170
+ 2586,
1171
+ 2060
1172
+ ],
1173
+ "step": 4773
1174
+ },
1175
+ {
1176
+ "epoch": 38.0,
1177
+ "eval_bp": 0.9335889103861881,
1178
+ "eval_counts": [
1179
+ 3635,
1180
+ 3109,
1181
+ 2583,
1182
+ 2057
1183
+ ],
1184
+ "eval_loss": 6.607356226595584e-07,
1185
+ "eval_precisions": [
1186
+ 99.91753710830126,
1187
+ 99.90359897172236,
1188
+ 99.88399071925754,
1189
+ 99.85436893203884
1190
+ ],
1191
+ "eval_ref_len": 3888,
1192
+ "eval_runtime": 12.6699,
1193
+ "eval_samples_per_second": 41.516,
1194
+ "eval_score": 93.25607593613448,
1195
+ "eval_steps_per_second": 1.342,
1196
+ "eval_sys_len": 3638,
1197
+ "eval_totals": [
1198
+ 3638,
1199
+ 3112,
1200
+ 2586,
1201
+ 2060
1202
+ ],
1203
+ "step": 4902
1204
+ },
1205
+ {
1206
+ "epoch": 38.76,
1207
+ "learning_rate": 4.4961240310077525e-06,
1208
+ "loss": 0.0013,
1209
+ "step": 5000
1210
+ },
1211
+ {
1212
+ "epoch": 39.0,
1213
+ "eval_bp": 0.9335889103861881,
1214
+ "eval_counts": [
1215
+ 3635,
1216
+ 3109,
1217
+ 2583,
1218
+ 2057
1219
+ ],
1220
+ "eval_loss": 8.30285159736377e-07,
1221
+ "eval_precisions": [
1222
+ 99.91753710830126,
1223
+ 99.90359897172236,
1224
+ 99.88399071925754,
1225
+ 99.85436893203884
1226
+ ],
1227
+ "eval_ref_len": 3888,
1228
+ "eval_runtime": 12.8802,
1229
+ "eval_samples_per_second": 40.838,
1230
+ "eval_score": 93.25607593613448,
1231
+ "eval_steps_per_second": 1.32,
1232
+ "eval_sys_len": 3638,
1233
+ "eval_totals": [
1234
+ 3638,
1235
+ 3112,
1236
+ 2586,
1237
+ 2060
1238
+ ],
1239
+ "step": 5031
1240
+ },
1241
+ {
1242
+ "epoch": 40.0,
1243
+ "eval_bp": 0.9335889103861881,
1244
+ "eval_counts": [
1245
+ 3635,
1246
+ 3109,
1247
+ 2583,
1248
+ 2057
1249
+ ],
1250
+ "eval_loss": 6.291656404755486e-07,
1251
+ "eval_precisions": [
1252
+ 99.91753710830126,
1253
+ 99.90359897172236,
1254
+ 99.88399071925754,
1255
+ 99.85436893203884
1256
+ ],
1257
+ "eval_ref_len": 3888,
1258
+ "eval_runtime": 12.7302,
1259
+ "eval_samples_per_second": 41.319,
1260
+ "eval_score": 93.25607593613448,
1261
+ "eval_steps_per_second": 1.335,
1262
+ "eval_sys_len": 3638,
1263
+ "eval_totals": [
1264
+ 3638,
1265
+ 3112,
1266
+ 2586,
1267
+ 2060
1268
+ ],
1269
+ "step": 5160
1270
+ },
1271
+ {
1272
+ "epoch": 41.0,
1273
+ "eval_bp": 0.9335889103861881,
1274
+ "eval_counts": [
1275
+ 3635,
1276
+ 3109,
1277
+ 2583,
1278
+ 2057
1279
+ ],
1280
+ "eval_loss": 6.857289918116294e-07,
1281
+ "eval_precisions": [
1282
+ 99.91753710830126,
1283
+ 99.90359897172236,
1284
+ 99.88399071925754,
1285
+ 99.85436893203884
1286
+ ],
1287
+ "eval_ref_len": 3888,
1288
+ "eval_runtime": 12.6807,
1289
+ "eval_samples_per_second": 41.48,
1290
+ "eval_score": 93.25607593613448,
1291
+ "eval_steps_per_second": 1.341,
1292
+ "eval_sys_len": 3638,
1293
+ "eval_totals": [
1294
+ 3638,
1295
+ 3112,
1296
+ 2586,
1297
+ 2060
1298
+ ],
1299
+ "step": 5289
1300
+ },
1301
+ {
1302
+ "epoch": 42.0,
1303
+ "eval_bp": 0.9335889103861881,
1304
+ "eval_counts": [
1305
+ 3635,
1306
+ 3109,
1307
+ 2583,
1308
+ 2057
1309
+ ],
1310
+ "eval_loss": 5.779653520221473e-07,
1311
+ "eval_precisions": [
1312
+ 99.91753710830126,
1313
+ 99.90359897172236,
1314
+ 99.88399071925754,
1315
+ 99.85436893203884
1316
+ ],
1317
+ "eval_ref_len": 3888,
1318
+ "eval_runtime": 12.935,
1319
+ "eval_samples_per_second": 40.665,
1320
+ "eval_score": 93.25607593613448,
1321
+ "eval_steps_per_second": 1.314,
1322
+ "eval_sys_len": 3638,
1323
+ "eval_totals": [
1324
+ 3638,
1325
+ 3112,
1326
+ 2586,
1327
+ 2060
1328
+ ],
1329
+ "step": 5418
1330
+ },
1331
+ {
1332
+ "epoch": 42.64,
1333
+ "learning_rate": 2.9457364341085276e-06,
1334
+ "loss": 0.001,
1335
+ "step": 5500
1336
+ },
1337
+ {
1338
+ "epoch": 43.0,
1339
+ "eval_bp": 0.9335889103861881,
1340
+ "eval_counts": [
1341
+ 3635,
1342
+ 3109,
1343
+ 2583,
1344
+ 2057
1345
+ ],
1346
+ "eval_loss": 4.883366386820853e-07,
1347
+ "eval_precisions": [
1348
+ 99.91753710830126,
1349
+ 99.90359897172236,
1350
+ 99.88399071925754,
1351
+ 99.85436893203884
1352
+ ],
1353
+ "eval_ref_len": 3888,
1354
+ "eval_runtime": 12.5557,
1355
+ "eval_samples_per_second": 41.893,
1356
+ "eval_score": 93.25607593613448,
1357
+ "eval_steps_per_second": 1.354,
1358
+ "eval_sys_len": 3638,
1359
+ "eval_totals": [
1360
+ 3638,
1361
+ 3112,
1362
+ 2586,
1363
+ 2060
1364
+ ],
1365
+ "step": 5547
1366
+ },
1367
+ {
1368
+ "epoch": 44.0,
1369
+ "eval_bp": 0.9335889103861881,
1370
+ "eval_counts": [
1371
+ 3635,
1372
+ 3109,
1373
+ 2583,
1374
+ 2057
1375
+ ],
1376
+ "eval_loss": 4.574254433009628e-07,
1377
+ "eval_precisions": [
1378
+ 99.91753710830126,
1379
+ 99.90359897172236,
1380
+ 99.88399071925754,
1381
+ 99.85436893203884
1382
+ ],
1383
+ "eval_ref_len": 3888,
1384
+ "eval_runtime": 12.9614,
1385
+ "eval_samples_per_second": 40.582,
1386
+ "eval_score": 93.25607593613448,
1387
+ "eval_steps_per_second": 1.312,
1388
+ "eval_sys_len": 3638,
1389
+ "eval_totals": [
1390
+ 3638,
1391
+ 3112,
1392
+ 2586,
1393
+ 2060
1394
+ ],
1395
+ "step": 5676
1396
+ },
1397
+ {
1398
+ "epoch": 45.0,
1399
+ "eval_bp": 0.9335889103861881,
1400
+ "eval_counts": [
1401
+ 3635,
1402
+ 3109,
1403
+ 2583,
1404
+ 2057
1405
+ ],
1406
+ "eval_loss": 5.373989324652939e-07,
1407
+ "eval_precisions": [
1408
+ 99.91753710830126,
1409
+ 99.90359897172236,
1410
+ 99.88399071925754,
1411
+ 99.85436893203884
1412
+ ],
1413
+ "eval_ref_len": 3888,
1414
+ "eval_runtime": 12.641,
1415
+ "eval_samples_per_second": 41.611,
1416
+ "eval_score": 93.25607593613448,
1417
+ "eval_steps_per_second": 1.345,
1418
+ "eval_sys_len": 3638,
1419
+ "eval_totals": [
1420
+ 3638,
1421
+ 3112,
1422
+ 2586,
1423
+ 2060
1424
+ ],
1425
+ "step": 5805
1426
+ },
1427
+ {
1428
+ "epoch": 46.0,
1429
+ "eval_bp": 0.9335889103861881,
1430
+ "eval_counts": [
1431
+ 3635,
1432
+ 3109,
1433
+ 2583,
1434
+ 2057
1435
+ ],
1436
+ "eval_loss": 4.2050155002471e-07,
1437
+ "eval_precisions": [
1438
+ 99.91753710830126,
1439
+ 99.90359897172236,
1440
+ 99.88399071925754,
1441
+ 99.85436893203884
1442
+ ],
1443
+ "eval_ref_len": 3888,
1444
+ "eval_runtime": 12.9508,
1445
+ "eval_samples_per_second": 40.615,
1446
+ "eval_score": 93.25607593613448,
1447
+ "eval_steps_per_second": 1.313,
1448
+ "eval_sys_len": 3638,
1449
+ "eval_totals": [
1450
+ 3638,
1451
+ 3112,
1452
+ 2586,
1453
+ 2060
1454
+ ],
1455
+ "step": 5934
1456
+ },
1457
+ {
1458
+ "epoch": 46.51,
1459
+ "learning_rate": 1.3953488372093025e-06,
1460
+ "loss": 0.0007,
1461
+ "step": 6000
1462
+ }
1463
+ ],
1464
+ "logging_steps": 500,
1465
+ "max_steps": 6450,
1466
+ "num_input_tokens_seen": 0,
1467
+ "num_train_epochs": 50,
1468
+ "save_steps": 500,
1469
+ "total_flos": 2.0486735002368e+16,
1470
+ "train_batch_size": 32,
1471
+ "trial_name": null,
1472
+ "trial_params": null
1473
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a21ba4c3e1a448be45c882e3ac85afadb6467dd79e956054400475b6a2c7d49
3
+ size 4856