Toshiiiii1 commited on
Commit
a4e2dc1
1 Parent(s): c247f30

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/kaggle/input/vit5-modell",
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 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.37.0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2218f7201847b7e781b0513fc6df5973878e1cdb276bc2ca5bafa16d57ba3fe
3
+ size 903834408
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8985a156acd3dcbfb374791b63b5d5267f233797fa0da7b08f4dd1513a6023e1
3
+ size 1807824186
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38a7293bd35b75887d83a6bedce62ef9d8d6955b31408e19318083abd105bc31
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a695d02b332472deffe5c2ac5eaf79d10f61708451f7d1a734bbcd5bbc0e4a0f
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
+ }
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 +1,735 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.995418771290967,
5
+ "eval_steps": 500,
6
+ "global_step": 25500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06,
13
+ "learning_rate": 5.873140172278778e-05,
14
+ "loss": 0.0966,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.06,
19
+ "eval_loss": 0.03481524437665939,
20
+ "eval_runtime": 123.2077,
21
+ "eval_samples_per_second": 53.097,
22
+ "eval_steps_per_second": 6.639,
23
+ "step": 500
24
+ },
25
+ {
26
+ "epoch": 0.12,
27
+ "learning_rate": 0.00011746280344557555,
28
+ "loss": 0.0446,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 0.12,
33
+ "eval_loss": 0.038774896413087845,
34
+ "eval_runtime": 123.3038,
35
+ "eval_samples_per_second": 53.056,
36
+ "eval_steps_per_second": 6.634,
37
+ "step": 1000
38
+ },
39
+ {
40
+ "epoch": 0.18,
41
+ "learning_rate": 0.00017619420516836332,
42
+ "loss": 0.063,
43
+ "step": 1500
44
+ },
45
+ {
46
+ "epoch": 0.18,
47
+ "eval_loss": 0.06299161165952682,
48
+ "eval_runtime": 123.374,
49
+ "eval_samples_per_second": 53.026,
50
+ "eval_steps_per_second": 6.63,
51
+ "step": 1500
52
+ },
53
+ {
54
+ "epoch": 0.23,
55
+ "learning_rate": 0.0002349256068911511,
56
+ "loss": 0.0938,
57
+ "step": 2000
58
+ },
59
+ {
60
+ "epoch": 0.23,
61
+ "eval_loss": 0.07528574019670486,
62
+ "eval_runtime": 123.3537,
63
+ "eval_samples_per_second": 53.034,
64
+ "eval_steps_per_second": 6.631,
65
+ "step": 2000
66
+ },
67
+ {
68
+ "epoch": 0.29,
69
+ "learning_rate": 0.0002936570086139389,
70
+ "loss": 0.1281,
71
+ "step": 2500
72
+ },
73
+ {
74
+ "epoch": 0.29,
75
+ "eval_loss": 0.10252855718135834,
76
+ "eval_runtime": 123.3622,
77
+ "eval_samples_per_second": 53.031,
78
+ "eval_steps_per_second": 6.631,
79
+ "step": 2500
80
+ },
81
+ {
82
+ "epoch": 0.35,
83
+ "learning_rate": 0.00029417881226887095,
84
+ "loss": 0.1452,
85
+ "step": 3000
86
+ },
87
+ {
88
+ "epoch": 0.35,
89
+ "eval_loss": 0.12126505374908447,
90
+ "eval_runtime": 123.2879,
91
+ "eval_samples_per_second": 53.063,
92
+ "eval_steps_per_second": 6.635,
93
+ "step": 3000
94
+ },
95
+ {
96
+ "epoch": 0.41,
97
+ "learning_rate": 0.0002876528170546008,
98
+ "loss": 0.1393,
99
+ "step": 3500
100
+ },
101
+ {
102
+ "epoch": 0.41,
103
+ "eval_loss": 0.0877891555428505,
104
+ "eval_runtime": 123.3134,
105
+ "eval_samples_per_second": 53.052,
106
+ "eval_steps_per_second": 6.634,
107
+ "step": 3500
108
+ },
109
+ {
110
+ "epoch": 0.47,
111
+ "learning_rate": 0.00028112682184033063,
112
+ "loss": 0.1278,
113
+ "step": 4000
114
+ },
115
+ {
116
+ "epoch": 0.47,
117
+ "eval_loss": 0.08643390238285065,
118
+ "eval_runtime": 123.5525,
119
+ "eval_samples_per_second": 52.949,
120
+ "eval_steps_per_second": 6.621,
121
+ "step": 4000
122
+ },
123
+ {
124
+ "epoch": 0.53,
125
+ "learning_rate": 0.00027460082662606047,
126
+ "loss": 0.121,
127
+ "step": 4500
128
+ },
129
+ {
130
+ "epoch": 0.53,
131
+ "eval_loss": 0.07961534708738327,
132
+ "eval_runtime": 123.4172,
133
+ "eval_samples_per_second": 53.007,
134
+ "eval_steps_per_second": 6.628,
135
+ "step": 4500
136
+ },
137
+ {
138
+ "epoch": 0.59,
139
+ "learning_rate": 0.00026807483141179025,
140
+ "loss": 0.115,
141
+ "step": 5000
142
+ },
143
+ {
144
+ "epoch": 0.59,
145
+ "eval_loss": 0.07281593233346939,
146
+ "eval_runtime": 123.3851,
147
+ "eval_samples_per_second": 53.021,
148
+ "eval_steps_per_second": 6.63,
149
+ "step": 5000
150
+ },
151
+ {
152
+ "epoch": 0.65,
153
+ "learning_rate": 0.0002615488361975201,
154
+ "loss": 0.1105,
155
+ "step": 5500
156
+ },
157
+ {
158
+ "epoch": 0.65,
159
+ "eval_loss": 0.06985253840684891,
160
+ "eval_runtime": 123.3894,
161
+ "eval_samples_per_second": 53.019,
162
+ "eval_steps_per_second": 6.629,
163
+ "step": 5500
164
+ },
165
+ {
166
+ "epoch": 0.7,
167
+ "learning_rate": 0.00025502284098324993,
168
+ "loss": 0.109,
169
+ "step": 6000
170
+ },
171
+ {
172
+ "epoch": 0.7,
173
+ "eval_loss": 0.0665203332901001,
174
+ "eval_runtime": 123.2402,
175
+ "eval_samples_per_second": 53.083,
176
+ "eval_steps_per_second": 6.637,
177
+ "step": 6000
178
+ },
179
+ {
180
+ "epoch": 0.76,
181
+ "learning_rate": 0.00024849684576897977,
182
+ "loss": 0.0989,
183
+ "step": 6500
184
+ },
185
+ {
186
+ "epoch": 0.76,
187
+ "eval_loss": 0.06210066005587578,
188
+ "eval_runtime": 123.1909,
189
+ "eval_samples_per_second": 53.105,
190
+ "eval_steps_per_second": 6.64,
191
+ "step": 6500
192
+ },
193
+ {
194
+ "epoch": 0.82,
195
+ "learning_rate": 0.00024197085055470958,
196
+ "loss": 0.0981,
197
+ "step": 7000
198
+ },
199
+ {
200
+ "epoch": 0.82,
201
+ "eval_loss": 0.06805345416069031,
202
+ "eval_runtime": 123.2672,
203
+ "eval_samples_per_second": 53.072,
204
+ "eval_steps_per_second": 6.636,
205
+ "step": 7000
206
+ },
207
+ {
208
+ "epoch": 0.88,
209
+ "learning_rate": 0.0002354448553404394,
210
+ "loss": 0.0913,
211
+ "step": 7500
212
+ },
213
+ {
214
+ "epoch": 0.88,
215
+ "eval_loss": 0.05965917557477951,
216
+ "eval_runtime": 123.3122,
217
+ "eval_samples_per_second": 53.052,
218
+ "eval_steps_per_second": 6.634,
219
+ "step": 7500
220
+ },
221
+ {
222
+ "epoch": 0.94,
223
+ "learning_rate": 0.00022891886012616923,
224
+ "loss": 0.0878,
225
+ "step": 8000
226
+ },
227
+ {
228
+ "epoch": 0.94,
229
+ "eval_loss": 0.05600811913609505,
230
+ "eval_runtime": 123.3189,
231
+ "eval_samples_per_second": 53.049,
232
+ "eval_steps_per_second": 6.633,
233
+ "step": 8000
234
+ },
235
+ {
236
+ "epoch": 1.0,
237
+ "learning_rate": 0.00022239286491189904,
238
+ "loss": 0.0852,
239
+ "step": 8500
240
+ },
241
+ {
242
+ "epoch": 1.0,
243
+ "eval_loss": 0.05495968833565712,
244
+ "eval_runtime": 123.3222,
245
+ "eval_samples_per_second": 53.048,
246
+ "eval_steps_per_second": 6.633,
247
+ "step": 8500
248
+ },
249
+ {
250
+ "epoch": 1.06,
251
+ "learning_rate": 0.00021586686969762888,
252
+ "loss": 0.0708,
253
+ "step": 9000
254
+ },
255
+ {
256
+ "epoch": 1.06,
257
+ "eval_loss": 0.05065647512674332,
258
+ "eval_runtime": 123.1018,
259
+ "eval_samples_per_second": 53.143,
260
+ "eval_steps_per_second": 6.645,
261
+ "step": 9000
262
+ },
263
+ {
264
+ "epoch": 1.12,
265
+ "learning_rate": 0.0002093408744833587,
266
+ "loss": 0.0669,
267
+ "step": 9500
268
+ },
269
+ {
270
+ "epoch": 1.12,
271
+ "eval_loss": 0.05243635177612305,
272
+ "eval_runtime": 123.1404,
273
+ "eval_samples_per_second": 53.126,
274
+ "eval_steps_per_second": 6.643,
275
+ "step": 9500
276
+ },
277
+ {
278
+ "epoch": 1.17,
279
+ "learning_rate": 0.00020281487926908853,
280
+ "loss": 0.0657,
281
+ "step": 10000
282
+ },
283
+ {
284
+ "epoch": 1.17,
285
+ "eval_loss": 0.04499243199825287,
286
+ "eval_runtime": 123.3227,
287
+ "eval_samples_per_second": 53.048,
288
+ "eval_steps_per_second": 6.633,
289
+ "step": 10000
290
+ },
291
+ {
292
+ "epoch": 1.23,
293
+ "learning_rate": 0.00019628888405481834,
294
+ "loss": 0.0636,
295
+ "step": 10500
296
+ },
297
+ {
298
+ "epoch": 1.23,
299
+ "eval_loss": 0.04722798988223076,
300
+ "eval_runtime": 123.4099,
301
+ "eval_samples_per_second": 53.01,
302
+ "eval_steps_per_second": 6.628,
303
+ "step": 10500
304
+ },
305
+ {
306
+ "epoch": 1.29,
307
+ "learning_rate": 0.00018976288884054818,
308
+ "loss": 0.0623,
309
+ "step": 11000
310
+ },
311
+ {
312
+ "epoch": 1.29,
313
+ "eval_loss": 0.042462971061468124,
314
+ "eval_runtime": 123.343,
315
+ "eval_samples_per_second": 53.039,
316
+ "eval_steps_per_second": 6.632,
317
+ "step": 11000
318
+ },
319
+ {
320
+ "epoch": 1.35,
321
+ "learning_rate": 0.00018323689362627802,
322
+ "loss": 0.0596,
323
+ "step": 11500
324
+ },
325
+ {
326
+ "epoch": 1.35,
327
+ "eval_loss": 0.04393870010972023,
328
+ "eval_runtime": 123.1794,
329
+ "eval_samples_per_second": 53.11,
330
+ "eval_steps_per_second": 6.641,
331
+ "step": 11500
332
+ },
333
+ {
334
+ "epoch": 1.41,
335
+ "learning_rate": 0.00017671089841200783,
336
+ "loss": 0.0612,
337
+ "step": 12000
338
+ },
339
+ {
340
+ "epoch": 1.41,
341
+ "eval_loss": 0.03987164422869682,
342
+ "eval_runtime": 123.4328,
343
+ "eval_samples_per_second": 53.001,
344
+ "eval_steps_per_second": 6.627,
345
+ "step": 12000
346
+ },
347
+ {
348
+ "epoch": 1.47,
349
+ "learning_rate": 0.00017018490319773767,
350
+ "loss": 0.0553,
351
+ "step": 12500
352
+ },
353
+ {
354
+ "epoch": 1.47,
355
+ "eval_loss": 0.04043687880039215,
356
+ "eval_runtime": 123.5215,
357
+ "eval_samples_per_second": 52.962,
358
+ "eval_steps_per_second": 6.622,
359
+ "step": 12500
360
+ },
361
+ {
362
+ "epoch": 1.53,
363
+ "learning_rate": 0.00016365890798346748,
364
+ "loss": 0.0565,
365
+ "step": 13000
366
+ },
367
+ {
368
+ "epoch": 1.53,
369
+ "eval_loss": 0.04023285582661629,
370
+ "eval_runtime": 123.3607,
371
+ "eval_samples_per_second": 53.031,
372
+ "eval_steps_per_second": 6.631,
373
+ "step": 13000
374
+ },
375
+ {
376
+ "epoch": 1.59,
377
+ "learning_rate": 0.00015713291276919726,
378
+ "loss": 0.0541,
379
+ "step": 13500
380
+ },
381
+ {
382
+ "epoch": 1.59,
383
+ "eval_loss": 0.03617456555366516,
384
+ "eval_runtime": 123.7139,
385
+ "eval_samples_per_second": 52.88,
386
+ "eval_steps_per_second": 6.612,
387
+ "step": 13500
388
+ },
389
+ {
390
+ "epoch": 1.64,
391
+ "learning_rate": 0.0001506069175549271,
392
+ "loss": 0.0527,
393
+ "step": 14000
394
+ },
395
+ {
396
+ "epoch": 1.64,
397
+ "eval_loss": 0.036614831537008286,
398
+ "eval_runtime": 123.4987,
399
+ "eval_samples_per_second": 52.972,
400
+ "eval_steps_per_second": 6.624,
401
+ "step": 14000
402
+ },
403
+ {
404
+ "epoch": 1.7,
405
+ "learning_rate": 0.00014408092234065694,
406
+ "loss": 0.0485,
407
+ "step": 14500
408
+ },
409
+ {
410
+ "epoch": 1.7,
411
+ "eval_loss": 0.03705143555998802,
412
+ "eval_runtime": 123.4413,
413
+ "eval_samples_per_second": 52.997,
414
+ "eval_steps_per_second": 6.627,
415
+ "step": 14500
416
+ },
417
+ {
418
+ "epoch": 1.76,
419
+ "learning_rate": 0.00013755492712638678,
420
+ "loss": 0.0502,
421
+ "step": 15000
422
+ },
423
+ {
424
+ "epoch": 1.76,
425
+ "eval_loss": 0.03249647840857506,
426
+ "eval_runtime": 123.5764,
427
+ "eval_samples_per_second": 52.939,
428
+ "eval_steps_per_second": 6.619,
429
+ "step": 15000
430
+ },
431
+ {
432
+ "epoch": 1.82,
433
+ "learning_rate": 0.0001310289319121166,
434
+ "loss": 0.0485,
435
+ "step": 15500
436
+ },
437
+ {
438
+ "epoch": 1.82,
439
+ "eval_loss": 0.03329641371965408,
440
+ "eval_runtime": 123.7232,
441
+ "eval_samples_per_second": 52.876,
442
+ "eval_steps_per_second": 6.612,
443
+ "step": 15500
444
+ },
445
+ {
446
+ "epoch": 1.88,
447
+ "learning_rate": 0.00012450293669784643,
448
+ "loss": 0.0459,
449
+ "step": 16000
450
+ },
451
+ {
452
+ "epoch": 1.88,
453
+ "eval_loss": 0.03429277986288071,
454
+ "eval_runtime": 123.8157,
455
+ "eval_samples_per_second": 52.837,
456
+ "eval_steps_per_second": 6.607,
457
+ "step": 16000
458
+ },
459
+ {
460
+ "epoch": 1.94,
461
+ "learning_rate": 0.00011797694148357624,
462
+ "loss": 0.0461,
463
+ "step": 16500
464
+ },
465
+ {
466
+ "epoch": 1.94,
467
+ "eval_loss": 0.02981030009686947,
468
+ "eval_runtime": 123.4645,
469
+ "eval_samples_per_second": 52.987,
470
+ "eval_steps_per_second": 6.625,
471
+ "step": 16500
472
+ },
473
+ {
474
+ "epoch": 2.0,
475
+ "learning_rate": 0.00011145094626930605,
476
+ "loss": 0.0423,
477
+ "step": 17000
478
+ },
479
+ {
480
+ "epoch": 2.0,
481
+ "eval_loss": 0.029031969606876373,
482
+ "eval_runtime": 123.8223,
483
+ "eval_samples_per_second": 52.834,
484
+ "eval_steps_per_second": 6.606,
485
+ "step": 17000
486
+ },
487
+ {
488
+ "epoch": 2.06,
489
+ "learning_rate": 0.00010492495105503587,
490
+ "loss": 0.0304,
491
+ "step": 17500
492
+ },
493
+ {
494
+ "epoch": 2.06,
495
+ "eval_loss": 0.029610687866806984,
496
+ "eval_runtime": 123.3939,
497
+ "eval_samples_per_second": 53.017,
498
+ "eval_steps_per_second": 6.629,
499
+ "step": 17500
500
+ },
501
+ {
502
+ "epoch": 2.11,
503
+ "learning_rate": 9.83989558407657e-05,
504
+ "loss": 0.0286,
505
+ "step": 18000
506
+ },
507
+ {
508
+ "epoch": 2.11,
509
+ "eval_loss": 0.029453950002789497,
510
+ "eval_runtime": 123.7963,
511
+ "eval_samples_per_second": 52.845,
512
+ "eval_steps_per_second": 6.608,
513
+ "step": 18000
514
+ },
515
+ {
516
+ "epoch": 2.17,
517
+ "learning_rate": 9.187296062649552e-05,
518
+ "loss": 0.0294,
519
+ "step": 18500
520
+ },
521
+ {
522
+ "epoch": 2.17,
523
+ "eval_loss": 0.028666863217949867,
524
+ "eval_runtime": 123.5343,
525
+ "eval_samples_per_second": 52.957,
526
+ "eval_steps_per_second": 6.622,
527
+ "step": 18500
528
+ },
529
+ {
530
+ "epoch": 2.23,
531
+ "learning_rate": 8.534696541222536e-05,
532
+ "loss": 0.0271,
533
+ "step": 19000
534
+ },
535
+ {
536
+ "epoch": 2.23,
537
+ "eval_loss": 0.029929010197520256,
538
+ "eval_runtime": 123.4149,
539
+ "eval_samples_per_second": 53.008,
540
+ "eval_steps_per_second": 6.628,
541
+ "step": 19000
542
+ },
543
+ {
544
+ "epoch": 2.29,
545
+ "learning_rate": 7.882097019795519e-05,
546
+ "loss": 0.0256,
547
+ "step": 19500
548
+ },
549
+ {
550
+ "epoch": 2.29,
551
+ "eval_loss": 0.027137087658047676,
552
+ "eval_runtime": 123.7129,
553
+ "eval_samples_per_second": 52.88,
554
+ "eval_steps_per_second": 6.612,
555
+ "step": 19500
556
+ },
557
+ {
558
+ "epoch": 2.35,
559
+ "learning_rate": 7.229497498368501e-05,
560
+ "loss": 0.0256,
561
+ "step": 20000
562
+ },
563
+ {
564
+ "epoch": 2.35,
565
+ "eval_loss": 0.027056274935603142,
566
+ "eval_runtime": 123.4616,
567
+ "eval_samples_per_second": 52.988,
568
+ "eval_steps_per_second": 6.626,
569
+ "step": 20000
570
+ },
571
+ {
572
+ "epoch": 2.41,
573
+ "learning_rate": 6.576897976941483e-05,
574
+ "loss": 0.0231,
575
+ "step": 20500
576
+ },
577
+ {
578
+ "epoch": 2.41,
579
+ "eval_loss": 0.02597939409315586,
580
+ "eval_runtime": 123.5327,
581
+ "eval_samples_per_second": 52.958,
582
+ "eval_steps_per_second": 6.622,
583
+ "step": 20500
584
+ },
585
+ {
586
+ "epoch": 2.47,
587
+ "learning_rate": 5.924298455514466e-05,
588
+ "loss": 0.0246,
589
+ "step": 21000
590
+ },
591
+ {
592
+ "epoch": 2.47,
593
+ "eval_loss": 0.025122959166765213,
594
+ "eval_runtime": 123.806,
595
+ "eval_samples_per_second": 52.841,
596
+ "eval_steps_per_second": 6.607,
597
+ "step": 21000
598
+ },
599
+ {
600
+ "epoch": 2.53,
601
+ "learning_rate": 5.2716989340874485e-05,
602
+ "loss": 0.0235,
603
+ "step": 21500
604
+ },
605
+ {
606
+ "epoch": 2.53,
607
+ "eval_loss": 0.024449240416288376,
608
+ "eval_runtime": 123.6218,
609
+ "eval_samples_per_second": 52.919,
610
+ "eval_steps_per_second": 6.617,
611
+ "step": 21500
612
+ },
613
+ {
614
+ "epoch": 2.58,
615
+ "learning_rate": 4.61909941266043e-05,
616
+ "loss": 0.0234,
617
+ "step": 22000
618
+ },
619
+ {
620
+ "epoch": 2.58,
621
+ "eval_loss": 0.024168582633137703,
622
+ "eval_runtime": 123.8732,
623
+ "eval_samples_per_second": 52.812,
624
+ "eval_steps_per_second": 6.604,
625
+ "step": 22000
626
+ },
627
+ {
628
+ "epoch": 2.64,
629
+ "learning_rate": 3.966499891233413e-05,
630
+ "loss": 0.0224,
631
+ "step": 22500
632
+ },
633
+ {
634
+ "epoch": 2.64,
635
+ "eval_loss": 0.023941034451127052,
636
+ "eval_runtime": 123.519,
637
+ "eval_samples_per_second": 52.963,
638
+ "eval_steps_per_second": 6.622,
639
+ "step": 22500
640
+ },
641
+ {
642
+ "epoch": 2.7,
643
+ "learning_rate": 3.313900369806395e-05,
644
+ "loss": 0.0214,
645
+ "step": 23000
646
+ },
647
+ {
648
+ "epoch": 2.7,
649
+ "eval_loss": 0.02283557504415512,
650
+ "eval_runtime": 123.5762,
651
+ "eval_samples_per_second": 52.939,
652
+ "eval_steps_per_second": 6.619,
653
+ "step": 23000
654
+ },
655
+ {
656
+ "epoch": 2.76,
657
+ "learning_rate": 2.6613008483793777e-05,
658
+ "loss": 0.0213,
659
+ "step": 23500
660
+ },
661
+ {
662
+ "epoch": 2.76,
663
+ "eval_loss": 0.0223745945841074,
664
+ "eval_runtime": 123.8829,
665
+ "eval_samples_per_second": 52.808,
666
+ "eval_steps_per_second": 6.603,
667
+ "step": 23500
668
+ },
669
+ {
670
+ "epoch": 2.82,
671
+ "learning_rate": 2.0087013269523602e-05,
672
+ "loss": 0.0196,
673
+ "step": 24000
674
+ },
675
+ {
676
+ "epoch": 2.82,
677
+ "eval_loss": 0.02261008322238922,
678
+ "eval_runtime": 123.6333,
679
+ "eval_samples_per_second": 52.915,
680
+ "eval_steps_per_second": 6.616,
681
+ "step": 24000
682
+ },
683
+ {
684
+ "epoch": 2.88,
685
+ "learning_rate": 1.3561018055253423e-05,
686
+ "loss": 0.0194,
687
+ "step": 24500
688
+ },
689
+ {
690
+ "epoch": 2.88,
691
+ "eval_loss": 0.021464873105287552,
692
+ "eval_runtime": 124.0332,
693
+ "eval_samples_per_second": 52.744,
694
+ "eval_steps_per_second": 6.595,
695
+ "step": 24500
696
+ },
697
+ {
698
+ "epoch": 2.94,
699
+ "learning_rate": 7.03502284098325e-06,
700
+ "loss": 0.0191,
701
+ "step": 25000
702
+ },
703
+ {
704
+ "epoch": 2.94,
705
+ "eval_loss": 0.021281694993376732,
706
+ "eval_runtime": 123.6857,
707
+ "eval_samples_per_second": 52.892,
708
+ "eval_steps_per_second": 6.614,
709
+ "step": 25000
710
+ },
711
+ {
712
+ "epoch": 3.0,
713
+ "learning_rate": 5.090276267130737e-07,
714
+ "loss": 0.0197,
715
+ "step": 25500
716
+ },
717
+ {
718
+ "epoch": 3.0,
719
+ "eval_loss": 0.0211211945861578,
720
+ "eval_runtime": 123.7008,
721
+ "eval_samples_per_second": 52.886,
722
+ "eval_steps_per_second": 6.613,
723
+ "step": 25500
724
+ }
725
+ ],
726
+ "logging_steps": 500,
727
+ "max_steps": 25539,
728
+ "num_input_tokens_seen": 0,
729
+ "num_train_epochs": 3,
730
+ "save_steps": 500,
731
+ "total_flos": 2.428545951977472e+16,
732
+ "train_batch_size": 18,
733
+ "trial_name": null,
734
+ "trial_params": null
735
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6129448b796c356b6b8a9e37fb8560bdf806cfc7af672e5c9912ed37ee092f0f
3
+ size 4792