Hugging Face's logo

marksverdhei
/
t5-deshuffle

Text2Text Generation
Transformers
PyTorch
Safetensors
English
t5
text-generation-inference
Inference Endpoints
Model card Files Community
1
marksverdhei commited on
Commit
babc7bb
•
1 Parent(s): 81be0c6

add model

Browse files
Files changed (11) hide show
  1. config.json +58 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +1 -0
  7. spiece.model +3 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +1 -0
  10. trainer_state.json +388 -0
  11. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "n_positions": 512,
18
+ "num_decoder_layers": 12,
19
+ "num_heads": 12,
20
+ "num_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "relative_attention_max_distance": 128,
24
+ "relative_attention_num_buckets": 32,
25
+ "task_specific_params": {
26
+ "summarization": {
27
+ "early_stopping": true,
28
+ "length_penalty": 2.0,
29
+ "max_length": 200,
30
+ "min_length": 30,
31
+ "no_repeat_ngram_size": 3,
32
+ "num_beams": 4,
33
+ "prefix": "summarize: "
34
+ },
35
+ "translation_en_to_de": {
36
+ "early_stopping": true,
37
+ "max_length": 300,
38
+ "num_beams": 4,
39
+ "prefix": "translate English to German: "
40
+ },
41
+ "translation_en_to_fr": {
42
+ "early_stopping": true,
43
+ "max_length": 300,
44
+ "num_beams": 4,
45
+ "prefix": "translate English to French: "
46
+ },
47
+ "translation_en_to_ro": {
48
+ "early_stopping": true,
49
+ "max_length": 300,
50
+ "num_beams": 4,
51
+ "prefix": "translate English to Romanian: "
52
+ }
53
+ },
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.19.0.dev0",
56
+ "use_cache": true,
57
+ "vocab_size": 32128
58
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eace4749e94c1691a5105e81c93b08756578752606a401704b8409c9a605fbb
3
+ size 2140803
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e134dee48d68e6f4458fe03aecef1927fe63c1e649f9d230d71a982cfbbd3eb
3
+ size 891700799
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af781986f95bc8572fc3e807fafacf69d3b0789e59f8b426e1b471ae5859e497
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ccc0f3a7041d00ed367e64cf35a83cb5d1d46aadc2f0d9fcb1b5926b693388e
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-base", "tokenizer_class": "T5Tokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,388 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.5397371053695679,
3
+ "best_model_checkpoint": "./results/t5-bow-decoder-base\\checkpoint-13500",
4
+ "epoch": 6.0,
5
+ "global_step": 13500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.11,
12
+ "learning_rate": 5e-05,
13
+ "loss": 4.0305,
14
+ "step": 250
15
+ },
16
+ {
17
+ "epoch": 0.22,
18
+ "learning_rate": 0.0001,
19
+ "loss": 2.3805,
20
+ "step": 500
21
+ },
22
+ {
23
+ "epoch": 0.33,
24
+ "learning_rate": 9.943820224719102e-05,
25
+ "loss": 2.1631,
26
+ "step": 750
27
+ },
28
+ {
29
+ "epoch": 0.44,
30
+ "learning_rate": 9.887640449438202e-05,
31
+ "loss": 2.0932,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 0.56,
36
+ "learning_rate": 9.831460674157303e-05,
37
+ "loss": 1.9341,
38
+ "step": 1250
39
+ },
40
+ {
41
+ "epoch": 0.67,
42
+ "learning_rate": 9.775280898876405e-05,
43
+ "loss": 1.9336,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 0.78,
48
+ "learning_rate": 9.719101123595506e-05,
49
+ "loss": 1.8884,
50
+ "step": 1750
51
+ },
52
+ {
53
+ "epoch": 0.89,
54
+ "learning_rate": 9.662921348314608e-05,
55
+ "loss": 1.899,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 1.0,
60
+ "learning_rate": 9.606741573033708e-05,
61
+ "loss": 1.867,
62
+ "step": 2250
63
+ },
64
+ {
65
+ "epoch": 1.0,
66
+ "eval_loss": 1.7203162908554077,
67
+ "eval_runtime": 17.6762,
68
+ "eval_samples_per_second": 56.573,
69
+ "eval_steps_per_second": 3.564,
70
+ "step": 2250
71
+ },
72
+ {
73
+ "epoch": 1.11,
74
+ "learning_rate": 9.550561797752809e-05,
75
+ "loss": 1.8113,
76
+ "step": 2500
77
+ },
78
+ {
79
+ "epoch": 1.22,
80
+ "learning_rate": 9.49438202247191e-05,
81
+ "loss": 1.8082,
82
+ "step": 2750
83
+ },
84
+ {
85
+ "epoch": 1.33,
86
+ "learning_rate": 9.438202247191012e-05,
87
+ "loss": 1.8161,
88
+ "step": 3000
89
+ },
90
+ {
91
+ "epoch": 1.44,
92
+ "learning_rate": 9.382022471910112e-05,
93
+ "loss": 1.7548,
94
+ "step": 3250
95
+ },
96
+ {
97
+ "epoch": 1.56,
98
+ "learning_rate": 9.325842696629214e-05,
99
+ "loss": 1.7057,
100
+ "step": 3500
101
+ },
102
+ {
103
+ "epoch": 1.67,
104
+ "learning_rate": 9.269662921348315e-05,
105
+ "loss": 1.7636,
106
+ "step": 3750
107
+ },
108
+ {
109
+ "epoch": 1.78,
110
+ "learning_rate": 9.213483146067416e-05,
111
+ "loss": 1.7652,
112
+ "step": 4000
113
+ },
114
+ {
115
+ "epoch": 1.89,
116
+ "learning_rate": 9.157303370786518e-05,
117
+ "loss": 1.693,
118
+ "step": 4250
119
+ },
120
+ {
121
+ "epoch": 2.0,
122
+ "learning_rate": 9.101123595505618e-05,
123
+ "loss": 1.7073,
124
+ "step": 4500
125
+ },
126
+ {
127
+ "epoch": 2.0,
128
+ "eval_loss": 1.624514102935791,
129
+ "eval_runtime": 17.0363,
130
+ "eval_samples_per_second": 58.698,
131
+ "eval_steps_per_second": 3.698,
132
+ "step": 4500
133
+ },
134
+ {
135
+ "epoch": 2.11,
136
+ "learning_rate": 9.04494382022472e-05,
137
+ "loss": 1.668,
138
+ "step": 4750
139
+ },
140
+ {
141
+ "epoch": 2.22,
142
+ "learning_rate": 8.988764044943821e-05,
143
+ "loss": 1.6579,
144
+ "step": 5000
145
+ },
146
+ {
147
+ "epoch": 2.33,
148
+ "learning_rate": 8.932584269662921e-05,
149
+ "loss": 1.6282,
150
+ "step": 5250
151
+ },
152
+ {
153
+ "epoch": 2.44,
154
+ "learning_rate": 8.876404494382022e-05,
155
+ "loss": 1.6937,
156
+ "step": 5500
157
+ },
158
+ {
159
+ "epoch": 2.56,
160
+ "learning_rate": 8.820224719101124e-05,
161
+ "loss": 1.6562,
162
+ "step": 5750
163
+ },
164
+ {
165
+ "epoch": 2.67,
166
+ "learning_rate": 8.764044943820225e-05,
167
+ "loss": 1.61,
168
+ "step": 6000
169
+ },
170
+ {
171
+ "epoch": 2.78,
172
+ "learning_rate": 8.707865168539327e-05,
173
+ "loss": 1.6144,
174
+ "step": 6250
175
+ },
176
+ {
177
+ "epoch": 2.89,
178
+ "learning_rate": 8.651685393258427e-05,
179
+ "loss": 1.5554,
180
+ "step": 6500
181
+ },
182
+ {
183
+ "epoch": 3.0,
184
+ "learning_rate": 8.595505617977528e-05,
185
+ "loss": 1.6599,
186
+ "step": 6750
187
+ },
188
+ {
189
+ "epoch": 3.0,
190
+ "eval_loss": 1.593631386756897,
191
+ "eval_runtime": 19.1501,
192
+ "eval_samples_per_second": 52.219,
193
+ "eval_steps_per_second": 3.29,
194
+ "step": 6750
195
+ },
196
+ {
197
+ "epoch": 3.11,
198
+ "learning_rate": 8.53932584269663e-05,
199
+ "loss": 1.5611,
200
+ "step": 7000
201
+ },
202
+ {
203
+ "epoch": 3.22,
204
+ "learning_rate": 8.483146067415731e-05,
205
+ "loss": 1.5177,
206
+ "step": 7250
207
+ },
208
+ {
209
+ "epoch": 3.33,
210
+ "learning_rate": 8.426966292134831e-05,
211
+ "loss": 1.5332,
212
+ "step": 7500
213
+ },
214
+ {
215
+ "epoch": 3.44,
216
+ "learning_rate": 8.370786516853934e-05,
217
+ "loss": 1.6529,
218
+ "step": 7750
219
+ },
220
+ {
221
+ "epoch": 3.56,
222
+ "learning_rate": 8.314606741573034e-05,
223
+ "loss": 1.5575,
224
+ "step": 8000
225
+ },
226
+ {
227
+ "epoch": 3.67,
228
+ "learning_rate": 8.258426966292135e-05,
229
+ "loss": 1.5424,
230
+ "step": 8250
231
+ },
232
+ {
233
+ "epoch": 3.78,
234
+ "learning_rate": 8.202247191011237e-05,
235
+ "loss": 1.5496,
236
+ "step": 8500
237
+ },
238
+ {
239
+ "epoch": 3.89,
240
+ "learning_rate": 8.146067415730337e-05,
241
+ "loss": 1.5465,
242
+ "step": 8750
243
+ },
244
+ {
245
+ "epoch": 4.0,
246
+ "learning_rate": 8.089887640449438e-05,
247
+ "loss": 1.5903,
248
+ "step": 9000
249
+ },
250
+ {
251
+ "epoch": 4.0,
252
+ "eval_loss": 1.5624333620071411,
253
+ "eval_runtime": 19.0571,
254
+ "eval_samples_per_second": 52.474,
255
+ "eval_steps_per_second": 3.306,
256
+ "step": 9000
257
+ },
258
+ {
259
+ "epoch": 4.11,
260
+ "learning_rate": 8.03370786516854e-05,
261
+ "loss": 1.4976,
262
+ "step": 9250
263
+ },
264
+ {
265
+ "epoch": 4.22,
266
+ "learning_rate": 7.97752808988764e-05,
267
+ "loss": 1.4719,
268
+ "step": 9500
269
+ },
270
+ {
271
+ "epoch": 4.33,
272
+ "learning_rate": 7.921348314606743e-05,
273
+ "loss": 1.4781,
274
+ "step": 9750
275
+ },
276
+ {
277
+ "epoch": 4.44,
278
+ "learning_rate": 7.865168539325843e-05,
279
+ "loss": 1.4652,
280
+ "step": 10000
281
+ },
282
+ {
283
+ "epoch": 4.56,
284
+ "learning_rate": 7.808988764044944e-05,
285
+ "loss": 1.4997,
286
+ "step": 10250
287
+ },
288
+ {
289
+ "epoch": 4.67,
290
+ "learning_rate": 7.752808988764046e-05,
291
+ "loss": 1.5537,
292
+ "step": 10500
293
+ },
294
+ {
295
+ "epoch": 4.78,
296
+ "learning_rate": 7.696629213483147e-05,
297
+ "loss": 1.5558,
298
+ "step": 10750
299
+ },
300
+ {
301
+ "epoch": 4.89,
302
+ "learning_rate": 7.640449438202247e-05,
303
+ "loss": 1.4763,
304
+ "step": 11000
305
+ },
306
+ {
307
+ "epoch": 5.0,
308
+ "learning_rate": 7.584269662921349e-05,
309
+ "loss": 1.5011,
310
+ "step": 11250
311
+ },
312
+ {
313
+ "epoch": 5.0,
314
+ "eval_loss": 1.5619711875915527,
315
+ "eval_runtime": 19.201,
316
+ "eval_samples_per_second": 52.081,
317
+ "eval_steps_per_second": 3.281,
318
+ "step": 11250
319
+ },
320
+ {
321
+ "epoch": 5.11,
322
+ "learning_rate": 7.52808988764045e-05,
323
+ "loss": 1.4501,
324
+ "step": 11500
325
+ },
326
+ {
327
+ "epoch": 5.22,
328
+ "learning_rate": 7.471910112359551e-05,
329
+ "loss": 1.434,
330
+ "step": 11750
331
+ },
332
+ {
333
+ "epoch": 5.33,
334
+ "learning_rate": 7.415730337078653e-05,
335
+ "loss": 1.3839,
336
+ "step": 12000
337
+ },
338
+ {
339
+ "epoch": 5.44,
340
+ "learning_rate": 7.359550561797753e-05,
341
+ "loss": 1.4426,
342
+ "step": 12250
343
+ },
344
+ {
345
+ "epoch": 5.56,
346
+ "learning_rate": 7.303370786516854e-05,
347
+ "loss": 1.4481,
348
+ "step": 12500
349
+ },
350
+ {
351
+ "epoch": 5.67,
352
+ "learning_rate": 7.247191011235956e-05,
353
+ "loss": 1.452,
354
+ "step": 12750
355
+ },
356
+ {
357
+ "epoch": 5.78,
358
+ "learning_rate": 7.191011235955056e-05,
359
+ "loss": 1.485,
360
+ "step": 13000
361
+ },
362
+ {
363
+ "epoch": 5.89,
364
+ "learning_rate": 7.134831460674157e-05,
365
+ "loss": 1.5027,
366
+ "step": 13250
367
+ },
368
+ {
369
+ "epoch": 6.0,
370
+ "learning_rate": 7.078651685393259e-05,
371
+ "loss": 1.4556,
372
+ "step": 13500
373
+ },
374
+ {
375
+ "epoch": 6.0,
376
+ "eval_loss": 1.5397371053695679,
377
+ "eval_runtime": 22.8085,
378
+ "eval_samples_per_second": 43.843,
379
+ "eval_steps_per_second": 2.762,
380
+ "step": 13500
381
+ }
382
+ ],
383
+ "max_steps": 45000,
384
+ "num_train_epochs": 20,
385
+ "total_flos": 3.288372609024e+16,
386
+ "trial_name": null,
387
+ "trial_params": null
388
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ce237e25f8b732a629e19ab53cc5eefa8e06dca68c10167ded74b63d9864aec
3
+ size 3247