combe4259 commited on
Commit
aab8c7a
·
verified ·
1 Parent(s): f9ecf14

Upload 12 files

Browse files
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "dtype": "float32",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "transformers_version": "4.56.1",
29
+ "use_cache": true,
30
+ "vocab_size": 50258
31
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": [
5
+ 1
6
+ ],
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.56.1"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d533b40a5edd2786242a21125079e4325cca634679cc520db272b1476396aea
3
+ size 1101735784
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59107a5257da863197b3380f2bfb20c722e79a1ea6fb28d6a886a2258cce758a
3
+ size 2203646219
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f86e858d8107e2c88e030322fa3fdef49366c64a5f17e57b67f0426070728ed
3
+ size 14645
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52af23f532408e159531da812d6fa783fee6e0b24f03c75f4e9a133c637f1b27
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b19690c6c954e2b4360c99a157782ccb300a4657de9f228794ac3185771e0c5
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<pad>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,935 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<extra_id_0>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<extra_id_1>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50260": {
37
+ "content": "<extra_id_2>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50261": {
45
+ "content": "<extra_id_3>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50262": {
53
+ "content": "<extra_id_4>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "50263": {
61
+ "content": "<extra_id_5>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "50264": {
69
+ "content": "<extra_id_6>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "50265": {
77
+ "content": "<extra_id_7>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "50266": {
85
+ "content": "<extra_id_8>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "50267": {
93
+ "content": "<extra_id_9>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "50268": {
101
+ "content": "<extra_id_10>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "50269": {
109
+ "content": "<extra_id_11>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "50270": {
117
+ "content": "<extra_id_12>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "50271": {
125
+ "content": "<extra_id_13>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "50272": {
133
+ "content": "<extra_id_14>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "50273": {
141
+ "content": "<extra_id_15>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "50274": {
149
+ "content": "<extra_id_16>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "50275": {
157
+ "content": "<extra_id_17>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "50276": {
165
+ "content": "<extra_id_18>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "50277": {
173
+ "content": "<extra_id_19>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "50278": {
181
+ "content": "<extra_id_20>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "50279": {
189
+ "content": "<extra_id_21>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "50280": {
197
+ "content": "<extra_id_22>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "50281": {
205
+ "content": "<extra_id_23>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "50282": {
213
+ "content": "<extra_id_24>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "50283": {
221
+ "content": "<extra_id_25>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "50284": {
229
+ "content": "<extra_id_26>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "50285": {
237
+ "content": "<extra_id_27>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "50286": {
245
+ "content": "<extra_id_28>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "50287": {
253
+ "content": "<extra_id_29>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "50288": {
261
+ "content": "<extra_id_30>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "50289": {
269
+ "content": "<extra_id_31>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "50290": {
277
+ "content": "<extra_id_32>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "50291": {
285
+ "content": "<extra_id_33>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "50292": {
293
+ "content": "<extra_id_34>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "50293": {
301
+ "content": "<extra_id_35>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "50294": {
309
+ "content": "<extra_id_36>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "50295": {
317
+ "content": "<extra_id_37>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "50296": {
325
+ "content": "<extra_id_38>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "50297": {
333
+ "content": "<extra_id_39>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "50298": {
341
+ "content": "<extra_id_40>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "50299": {
349
+ "content": "<extra_id_41>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "50300": {
357
+ "content": "<extra_id_42>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "50301": {
365
+ "content": "<extra_id_43>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "50302": {
373
+ "content": "<extra_id_44>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "50303": {
381
+ "content": "<extra_id_45>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "50304": {
389
+ "content": "<extra_id_46>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "50305": {
397
+ "content": "<extra_id_47>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "50306": {
405
+ "content": "<extra_id_48>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "50307": {
413
+ "content": "<extra_id_49>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "50308": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "50309": {
429
+ "content": "<extra_id_51>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "50310": {
437
+ "content": "<extra_id_52>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "50311": {
445
+ "content": "<extra_id_53>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "50312": {
453
+ "content": "<extra_id_54>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "50313": {
461
+ "content": "<extra_id_55>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "50314": {
469
+ "content": "<extra_id_56>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "50315": {
477
+ "content": "<extra_id_57>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "50316": {
485
+ "content": "<extra_id_58>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "50317": {
493
+ "content": "<extra_id_59>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "50318": {
501
+ "content": "<extra_id_60>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "50319": {
509
+ "content": "<extra_id_61>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "50320": {
517
+ "content": "<extra_id_62>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "50321": {
525
+ "content": "<extra_id_63>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "50322": {
533
+ "content": "<extra_id_64>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "50323": {
541
+ "content": "<extra_id_65>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "50324": {
549
+ "content": "<extra_id_66>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "50325": {
557
+ "content": "<extra_id_67>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "50326": {
565
+ "content": "<extra_id_68>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "50327": {
573
+ "content": "<extra_id_69>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "50328": {
581
+ "content": "<extra_id_70>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "50329": {
589
+ "content": "<extra_id_71>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "50330": {
597
+ "content": "<extra_id_72>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "50331": {
605
+ "content": "<extra_id_73>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "50332": {
613
+ "content": "<extra_id_74>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "50333": {
621
+ "content": "<extra_id_75>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "50334": {
629
+ "content": "<extra_id_76>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "50335": {
637
+ "content": "<extra_id_77>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "50336": {
645
+ "content": "<extra_id_78>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "50337": {
653
+ "content": "<extra_id_79>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "50338": {
661
+ "content": "<extra_id_80>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "50339": {
669
+ "content": "<extra_id_81>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "50340": {
677
+ "content": "<extra_id_82>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "50341": {
685
+ "content": "<extra_id_83>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "50342": {
693
+ "content": "<extra_id_84>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "50343": {
701
+ "content": "<extra_id_85>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "50344": {
709
+ "content": "<extra_id_86>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "50345": {
717
+ "content": "<extra_id_87>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "50346": {
725
+ "content": "<extra_id_88>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "50347": {
733
+ "content": "<extra_id_89>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "50348": {
741
+ "content": "<extra_id_90>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "50349": {
749
+ "content": "<extra_id_91>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "50350": {
757
+ "content": "<extra_id_92>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "50351": {
765
+ "content": "<extra_id_93>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "50352": {
773
+ "content": "<extra_id_94>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "50353": {
781
+ "content": "<extra_id_95>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "50354": {
789
+ "content": "<extra_id_96>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "50355": {
797
+ "content": "<extra_id_97>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "50356": {
805
+ "content": "<extra_id_98>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "50357": {
813
+ "content": "<extra_id_99>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ }
820
+ },
821
+ "additional_special_tokens": [
822
+ "<extra_id_0>",
823
+ "<extra_id_1>",
824
+ "<extra_id_2>",
825
+ "<extra_id_3>",
826
+ "<extra_id_4>",
827
+ "<extra_id_5>",
828
+ "<extra_id_6>",
829
+ "<extra_id_7>",
830
+ "<extra_id_8>",
831
+ "<extra_id_9>",
832
+ "<extra_id_10>",
833
+ "<extra_id_11>",
834
+ "<extra_id_12>",
835
+ "<extra_id_13>",
836
+ "<extra_id_14>",
837
+ "<extra_id_15>",
838
+ "<extra_id_16>",
839
+ "<extra_id_17>",
840
+ "<extra_id_18>",
841
+ "<extra_id_19>",
842
+ "<extra_id_20>",
843
+ "<extra_id_21>",
844
+ "<extra_id_22>",
845
+ "<extra_id_23>",
846
+ "<extra_id_24>",
847
+ "<extra_id_25>",
848
+ "<extra_id_26>",
849
+ "<extra_id_27>",
850
+ "<extra_id_28>",
851
+ "<extra_id_29>",
852
+ "<extra_id_30>",
853
+ "<extra_id_31>",
854
+ "<extra_id_32>",
855
+ "<extra_id_33>",
856
+ "<extra_id_34>",
857
+ "<extra_id_35>",
858
+ "<extra_id_36>",
859
+ "<extra_id_37>",
860
+ "<extra_id_38>",
861
+ "<extra_id_39>",
862
+ "<extra_id_40>",
863
+ "<extra_id_41>",
864
+ "<extra_id_42>",
865
+ "<extra_id_43>",
866
+ "<extra_id_44>",
867
+ "<extra_id_45>",
868
+ "<extra_id_46>",
869
+ "<extra_id_47>",
870
+ "<extra_id_48>",
871
+ "<extra_id_49>",
872
+ "<extra_id_50>",
873
+ "<extra_id_51>",
874
+ "<extra_id_52>",
875
+ "<extra_id_53>",
876
+ "<extra_id_54>",
877
+ "<extra_id_55>",
878
+ "<extra_id_56>",
879
+ "<extra_id_57>",
880
+ "<extra_id_58>",
881
+ "<extra_id_59>",
882
+ "<extra_id_60>",
883
+ "<extra_id_61>",
884
+ "<extra_id_62>",
885
+ "<extra_id_63>",
886
+ "<extra_id_64>",
887
+ "<extra_id_65>",
888
+ "<extra_id_66>",
889
+ "<extra_id_67>",
890
+ "<extra_id_68>",
891
+ "<extra_id_69>",
892
+ "<extra_id_70>",
893
+ "<extra_id_71>",
894
+ "<extra_id_72>",
895
+ "<extra_id_73>",
896
+ "<extra_id_74>",
897
+ "<extra_id_75>",
898
+ "<extra_id_76>",
899
+ "<extra_id_77>",
900
+ "<extra_id_78>",
901
+ "<extra_id_79>",
902
+ "<extra_id_80>",
903
+ "<extra_id_81>",
904
+ "<extra_id_82>",
905
+ "<extra_id_83>",
906
+ "<extra_id_84>",
907
+ "<extra_id_85>",
908
+ "<extra_id_86>",
909
+ "<extra_id_87>",
910
+ "<extra_id_88>",
911
+ "<extra_id_89>",
912
+ "<extra_id_90>",
913
+ "<extra_id_91>",
914
+ "<extra_id_92>",
915
+ "<extra_id_93>",
916
+ "<extra_id_94>",
917
+ "<extra_id_95>",
918
+ "<extra_id_96>",
919
+ "<extra_id_97>",
920
+ "<extra_id_98>",
921
+ "<extra_id_99>"
922
+ ],
923
+ "clean_up_tokenization_spaces": false,
924
+ "eos_token": "</s>",
925
+ "extra_ids": 100,
926
+ "extra_special_tokens": {},
927
+ "max_length": null,
928
+ "model_max_length": 1000000000000000019884624838656,
929
+ "pad_to_multiple_of": null,
930
+ "pad_token": "<pad>",
931
+ "pad_token_type_id": 0,
932
+ "padding_side": "right",
933
+ "tokenizer_class": "T5TokenizerFast",
934
+ "unk_token": "<pad>"
935
+ }
trainer_state.json ADDED
@@ -0,0 +1,185 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 2000,
7
+ "global_step": 8340,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0003597769382982551,
14
+ "grad_norm": 43.59233474731445,
15
+ "learning_rate": 0.0,
16
+ "loss": 4.6611,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.17988846914912754,
21
+ "grad_norm": 0.34114521741867065,
22
+ "learning_rate": 4.816339066339067e-05,
23
+ "loss": 0.4796,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 0.3597769382982551,
28
+ "grad_norm": 0.40485045313835144,
29
+ "learning_rate": 4.5092137592137595e-05,
30
+ "loss": 0.1239,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 0.5396654074473827,
35
+ "grad_norm": 0.26643964648246765,
36
+ "learning_rate": 4.202088452088452e-05,
37
+ "loss": 0.0915,
38
+ "step": 1500
39
+ },
40
+ {
41
+ "epoch": 0.7195538765965102,
42
+ "grad_norm": 0.2876332998275757,
43
+ "learning_rate": 3.894963144963145e-05,
44
+ "loss": 0.074,
45
+ "step": 2000
46
+ },
47
+ {
48
+ "epoch": 0.7195538765965102,
49
+ "eval_loss": 0.051152389496564865,
50
+ "eval_runtime": 73.981,
51
+ "eval_samples_per_second": 149.038,
52
+ "eval_steps_per_second": 18.64,
53
+ "step": 2000
54
+ },
55
+ {
56
+ "epoch": 0.8994423457456378,
57
+ "grad_norm": 0.27155473828315735,
58
+ "learning_rate": 3.587837837837838e-05,
59
+ "loss": 0.0643,
60
+ "step": 2500
61
+ },
62
+ {
63
+ "epoch": 1.079150926425616,
64
+ "grad_norm": 0.257112592458725,
65
+ "learning_rate": 3.2807125307125305e-05,
66
+ "loss": 0.0573,
67
+ "step": 3000
68
+ },
69
+ {
70
+ "epoch": 1.2590393955747436,
71
+ "grad_norm": 0.1687777042388916,
72
+ "learning_rate": 2.9735872235872236e-05,
73
+ "loss": 0.0521,
74
+ "step": 3500
75
+ },
76
+ {
77
+ "epoch": 1.4389278647238712,
78
+ "grad_norm": 0.2531055212020874,
79
+ "learning_rate": 2.6664619164619163e-05,
80
+ "loss": 0.0492,
81
+ "step": 4000
82
+ },
83
+ {
84
+ "epoch": 1.4389278647238712,
85
+ "eval_loss": 0.037362292408943176,
86
+ "eval_runtime": 73.4788,
87
+ "eval_samples_per_second": 150.057,
88
+ "eval_steps_per_second": 18.767,
89
+ "step": 4000
90
+ },
91
+ {
92
+ "epoch": 1.6188163338729988,
93
+ "grad_norm": 0.2625373899936676,
94
+ "learning_rate": 2.3593366093366094e-05,
95
+ "loss": 0.0471,
96
+ "step": 4500
97
+ },
98
+ {
99
+ "epoch": 1.7987048030221264,
100
+ "grad_norm": 0.20707161724567413,
101
+ "learning_rate": 2.0522113022113025e-05,
102
+ "loss": 0.0443,
103
+ "step": 5000
104
+ },
105
+ {
106
+ "epoch": 1.9785932721712538,
107
+ "grad_norm": 0.37195566296577454,
108
+ "learning_rate": 1.7450859950859953e-05,
109
+ "loss": 0.0431,
110
+ "step": 5500
111
+ },
112
+ {
113
+ "epoch": 2.158301852851232,
114
+ "grad_norm": 0.2803611755371094,
115
+ "learning_rate": 1.437960687960688e-05,
116
+ "loss": 0.04,
117
+ "step": 6000
118
+ },
119
+ {
120
+ "epoch": 2.158301852851232,
121
+ "eval_loss": 0.032591212540864944,
122
+ "eval_runtime": 73.1424,
123
+ "eval_samples_per_second": 150.747,
124
+ "eval_steps_per_second": 18.854,
125
+ "step": 6000
126
+ },
127
+ {
128
+ "epoch": 2.3381903220003597,
129
+ "grad_norm": 0.26601219177246094,
130
+ "learning_rate": 1.130835380835381e-05,
131
+ "loss": 0.0383,
132
+ "step": 6500
133
+ },
134
+ {
135
+ "epoch": 2.5180787911494873,
136
+ "grad_norm": 0.18378710746765137,
137
+ "learning_rate": 8.237100737100738e-06,
138
+ "loss": 0.0386,
139
+ "step": 7000
140
+ },
141
+ {
142
+ "epoch": 2.697967260298615,
143
+ "grad_norm": 0.2807880938053131,
144
+ "learning_rate": 5.165847665847666e-06,
145
+ "loss": 0.0382,
146
+ "step": 7500
147
+ },
148
+ {
149
+ "epoch": 2.8778557294477425,
150
+ "grad_norm": 0.22750866413116455,
151
+ "learning_rate": 2.094594594594595e-06,
152
+ "loss": 0.0368,
153
+ "step": 8000
154
+ },
155
+ {
156
+ "epoch": 2.8778557294477425,
157
+ "eval_loss": 0.03069758228957653,
158
+ "eval_runtime": 74.1126,
159
+ "eval_samples_per_second": 148.774,
160
+ "eval_steps_per_second": 18.607,
161
+ "step": 8000
162
+ }
163
+ ],
164
+ "logging_steps": 500,
165
+ "max_steps": 8340,
166
+ "num_input_tokens_seen": 0,
167
+ "num_train_epochs": 3,
168
+ "save_steps": 4000,
169
+ "stateful_callbacks": {
170
+ "TrainerControl": {
171
+ "args": {
172
+ "should_epoch_stop": false,
173
+ "should_evaluate": false,
174
+ "should_log": false,
175
+ "should_save": true,
176
+ "should_training_stop": true
177
+ },
178
+ "attributes": {}
179
+ }
180
+ },
181
+ "total_flos": 1.941286555704361e+17,
182
+ "train_batch_size": 16,
183
+ "trial_name": null,
184
+ "trial_params": null
185
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16769ac9874539d0f1bd78d471412563ff70840479297e3c0610dc9e247521d1
3
+ size 5969