Hugging Face's logo

Wikidepia
/
byt5-sentfix

Transformers
PyTorch
t5
text2text-generation
text-generation-inference
Model card Files
xet
Community
1
Wikidepia commited on
Commit
de5f1a8
·
1 Parent(s): ee1dc5d

Initial commit

Browse files
Files changed (8) hide show
  1. config.json +30 -0
  2. pytorch_model.bin +3 -0
  3. rng_state.pth +3 -0
  4. scheduler.pt +3 -0
  5. special_tokens_map.json +1 -0
  6. tokenizer_config.json +1 -0
  7. trainer_state.json +280 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/byt5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3584,
7
+ "d_kv": 64,
8
+ "d_model": 1472,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "gradient_checkpointing": false,
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "layer_norm_epsilon": 1e-06,
17
+ "model_type": "t5",
18
+ "num_decoder_layers": 4,
19
+ "num_heads": 6,
20
+ "num_layers": 12,
21
+ "pad_token_id": 0,
22
+ "relative_attention_max_distance": 128,
23
+ "relative_attention_num_buckets": 32,
24
+ "tie_word_embeddings": false,
25
+ "tokenizer_class": "ByT5Tokenizer",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.19.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 384
30
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6441062b402882ccf653f62d19a51da7fd429e2725e8fa76768d0b04fa773b06
3
+ size 1198608045
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c367c4e27d4b5ab81258c499bfceffee4b73e0e0a98bbef45134f805273c6f5
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add80cc6f6ce2beee63291761d515aaf1d129a2f5eebc131dd26448d741ee929
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "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>", "<extra_id_100>", "<extra_id_101>", "<extra_id_102>", "<extra_id_103>", "<extra_id_104>", "<extra_id_105>", "<extra_id_106>", "<extra_id_107>", "<extra_id_108>", "<extra_id_109>", "<extra_id_110>", "<extra_id_111>", "<extra_id_112>", "<extra_id_113>", "<extra_id_114>", "<extra_id_115>", "<extra_id_116>", "<extra_id_117>", "<extra_id_118>", "<extra_id_119>", "<extra_id_120>", "<extra_id_121>", "<extra_id_122>", "<extra_id_123>", "<extra_id_124>"]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "extra_ids": 125, "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>", "<extra_id_100>", "<extra_id_101>", "<extra_id_102>", "<extra_id_103>", "<extra_id_104>", "<extra_id_105>", "<extra_id_106>", "<extra_id_107>", "<extra_id_108>", "<extra_id_109>", "<extra_id_110>", "<extra_id_111>", "<extra_id_112>", "<extra_id_113>", "<extra_id_114>", "<extra_id_115>", "<extra_id_116>", "<extra_id_117>", "<extra_id_118>", "<extra_id_119>", "<extra_id_120>", "<extra_id_121>", "<extra_id_122>", "<extra_id_123>", "<extra_id_124>"], "special_tokens_map_file": "/root/.cache/huggingface/transformers/3715c3de7f5eda8f5c9274c55ea8e8632fe6e4cdfdf8e9066ae173b956cd9b80.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109", "name_or_path": "google/byt5-small", "tokenizer_class": "ByT5Tokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,280 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.362265145153057,
5
+ "global_step": 22000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 4.958833506232608e-05,
13
+ "loss": 0.3018,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 4.9176670124652144e-05,
19
+ "loss": 0.1198,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 4.876500518697822e-05,
25
+ "loss": 0.1041,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.03,
30
+ "learning_rate": 4.835334024930429e-05,
31
+ "loss": 0.0934,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.04,
36
+ "learning_rate": 4.794167531163036e-05,
37
+ "loss": 0.0893,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.05,
42
+ "learning_rate": 4.753001037395643e-05,
43
+ "loss": 0.0827,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.06,
48
+ "learning_rate": 4.71183454362825e-05,
49
+ "loss": 0.0794,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.07,
54
+ "learning_rate": 4.670668049860858e-05,
55
+ "loss": 0.0773,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.07,
60
+ "learning_rate": 4.6295015560934644e-05,
61
+ "loss": 0.0761,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.08,
66
+ "learning_rate": 4.588335062326072e-05,
67
+ "loss": 0.0719,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.09,
72
+ "learning_rate": 4.547168568558679e-05,
73
+ "loss": 0.0702,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.1,
78
+ "learning_rate": 4.506002074791286e-05,
79
+ "loss": 0.0681,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.11,
84
+ "learning_rate": 4.4648355810238935e-05,
85
+ "loss": 0.0684,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.12,
90
+ "learning_rate": 4.423669087256501e-05,
91
+ "loss": 0.0651,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.12,
96
+ "learning_rate": 4.382502593489107e-05,
97
+ "loss": 0.0642,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.13,
102
+ "learning_rate": 4.3413360997217144e-05,
103
+ "loss": 0.0651,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.14,
108
+ "learning_rate": 4.300169605954322e-05,
109
+ "loss": 0.064,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.15,
114
+ "learning_rate": 4.2590031121869286e-05,
115
+ "loss": 0.061,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.16,
120
+ "learning_rate": 4.217836618419536e-05,
121
+ "loss": 0.0623,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.16,
126
+ "learning_rate": 4.1766701246521435e-05,
127
+ "loss": 0.0589,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.17,
132
+ "learning_rate": 4.13550363088475e-05,
133
+ "loss": 0.058,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.18,
138
+ "learning_rate": 4.094337137117358e-05,
139
+ "loss": 0.0581,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.19,
144
+ "learning_rate": 4.053170643349965e-05,
145
+ "loss": 0.0574,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.2,
150
+ "learning_rate": 4.012004149582572e-05,
151
+ "loss": 0.0582,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.21,
156
+ "learning_rate": 3.9708376558151786e-05,
157
+ "loss": 0.0561,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.21,
162
+ "learning_rate": 3.929671162047786e-05,
163
+ "loss": 0.0557,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.22,
168
+ "learning_rate": 3.8885046682803935e-05,
169
+ "loss": 0.0549,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.23,
174
+ "learning_rate": 3.847338174513e-05,
175
+ "loss": 0.0556,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.24,
180
+ "learning_rate": 3.806171680745608e-05,
181
+ "loss": 0.0535,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.25,
186
+ "learning_rate": 3.765005186978215e-05,
187
+ "loss": 0.0539,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.26,
192
+ "learning_rate": 3.723838693210822e-05,
193
+ "loss": 0.0544,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.26,
198
+ "learning_rate": 3.682672199443429e-05,
199
+ "loss": 0.0532,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.27,
204
+ "learning_rate": 3.641505705676037e-05,
205
+ "loss": 0.0541,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.28,
210
+ "learning_rate": 3.6003392119086435e-05,
211
+ "loss": 0.0523,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.29,
216
+ "learning_rate": 3.55917271814125e-05,
217
+ "loss": 0.0518,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.3,
222
+ "learning_rate": 3.518006224373858e-05,
223
+ "loss": 0.0518,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.3,
228
+ "learning_rate": 3.476839730606465e-05,
229
+ "loss": 0.0508,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.31,
234
+ "learning_rate": 3.435673236839072e-05,
235
+ "loss": 0.0522,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.32,
240
+ "learning_rate": 3.3945067430716793e-05,
241
+ "loss": 0.0518,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.33,
246
+ "learning_rate": 3.353340249304287e-05,
247
+ "loss": 0.0506,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.34,
252
+ "learning_rate": 3.3121737555368935e-05,
253
+ "loss": 0.0503,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.35,
258
+ "learning_rate": 3.271007261769501e-05,
259
+ "loss": 0.0502,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.35,
264
+ "learning_rate": 3.2298407680021084e-05,
265
+ "loss": 0.0497,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.36,
270
+ "learning_rate": 3.1886742742347145e-05,
271
+ "loss": 0.051,
272
+ "step": 22000
273
+ }
274
+ ],
275
+ "max_steps": 60729,
276
+ "num_train_epochs": 1,
277
+ "total_flos": 8.854507190040883e+16,
278
+ "trial_name": null,
279
+ "trial_params": null
280
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a8dc7723ae38f891836e2f95ea12cab48f86df73a5295410769aebd18371dc6
3
+ size 3183