Amir Kargaran
commited on
Commit
·
5ef3c94
1
Parent(s):
37bc035
add T5R
Browse files- README.md +8 -9
- config.json +9 -30
- generation_config.json +0 -6
- pytorch_model.bin +2 -2
- spiece.model +3 -0
- tokenizer.json +206 -206
- tokenizer_config.json +2 -1
- trainer_state.json +690 -100
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -5,33 +5,32 @@ datasets:
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
-
- name:
|
| 9 |
results: []
|
| 10 |
pipeline_tag: text-generation
|
| 11 |
language:
|
| 12 |
- en
|
| 13 |
widget:
|
| 14 |
- text: >-
|
| 15 |
-
|
| 16 |
raised near Linz. He lived in Vienna later in the first decade of the
|
| 17 |
1900s and moved to Germany in 1913. He was decorated during his service in
|
| 18 |
the German Army in World War I. In 1919, he joined the German Workers'
|
| 19 |
Party (DAP), the precursor of the Nazi Party, and was appointed leader of
|
| 20 |
the Nazi Party in 1921. In 1923, he attempted to seize governmental power
|
| 21 |
in a failed coup in Munich and was imprisoned with a sentence of five
|
| 22 |
-
years
|
| 23 |
-
input:
|
| 24 |
example_title: Example 1
|
| 25 |
- text: >-
|
| 26 |
-
|
| 27 |
-
lots of fruit and veg 3
|
| 28 |
-
|
| 29 |
example_title: Example 2
|
| 30 |
---
|
| 31 |
|
| 32 |
|
| 33 |
-
#
|
| 34 |
|
| 35 |
This model can generate prompts (instruction) for any text!
|
| 36 |
|
| 37 |
-
This model is
|
|
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
+
- name: T5R
|
| 9 |
results: []
|
| 10 |
pipeline_tag: text-generation
|
| 11 |
language:
|
| 12 |
- en
|
| 13 |
widget:
|
| 14 |
- text: >-
|
| 15 |
+
Instruction: X\nOutput: Hitler was born in Braunau am Inn in Austria-Hungary and was
|
| 16 |
raised near Linz. He lived in Vienna later in the first decade of the
|
| 17 |
1900s and moved to Germany in 1913. He was decorated during his service in
|
| 18 |
the German Army in World War I. In 1919, he joined the German Workers'
|
| 19 |
Party (DAP), the precursor of the Nazi Party, and was appointed leader of
|
| 20 |
the Nazi Party in 1921. In 1923, he attempted to seize governmental power
|
| 21 |
in a failed coup in Munich and was imprisoned with a sentence of five
|
| 22 |
+
years.\nWhat kind of instruction could this be the answer to?\nX:
|
|
|
|
| 23 |
example_title: Example 1
|
| 24 |
- text: >-
|
| 25 |
+
Instruction: X\nOutput: 1- Base your meals on higher fibre starchy carbohydrates. 2- Eat
|
| 26 |
+
lots of fruit and veg. 3- Eat more fish, including a portion of oily fish.\nWhat kind of instruction could
|
| 27 |
+
this be the answer to?\nX:
|
| 28 |
example_title: Example 2
|
| 29 |
---
|
| 30 |
|
| 31 |
|
| 32 |
+
# T5-Reverse (T5R)
|
| 33 |
|
| 34 |
This model can generate prompts (instruction) for any text!
|
| 35 |
|
| 36 |
+
This model is an instruction-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on [alpaca dataset](https://huggingface.co/datasets/tatsu-lab/alpaca) but in **reverse format**!
|
config.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
| 6 |
-
"d_ff":
|
| 7 |
"d_kv": 64,
|
| 8 |
-
"d_model":
|
| 9 |
"decoder_start_token_id": 0,
|
| 10 |
"dense_act_fn": "gelu_new",
|
| 11 |
"dropout_rate": 0.1,
|
|
@@ -17,45 +17,24 @@
|
|
| 17 |
"layer_norm_epsilon": 1e-06,
|
| 18 |
"model_type": "t5",
|
| 19 |
"n_positions": 512,
|
| 20 |
-
"num_decoder_layers":
|
| 21 |
-
"num_heads":
|
| 22 |
-
"num_layers":
|
| 23 |
"output_past": true,
|
| 24 |
"pad_token_id": 0,
|
| 25 |
"relative_attention_max_distance": 128,
|
| 26 |
"relative_attention_num_buckets": 32,
|
| 27 |
"task_specific_params": {
|
| 28 |
-
"
|
| 29 |
-
"early_stopping": true,
|
| 30 |
-
"length_penalty": 2.0,
|
| 31 |
-
"max_length": 200,
|
| 32 |
-
"min_length": 30,
|
| 33 |
-
"no_repeat_ngram_size": 3,
|
| 34 |
-
"num_beams": 4,
|
| 35 |
-
"prefix": "summarize: "
|
| 36 |
-
},
|
| 37 |
-
"translation_en_to_de": {
|
| 38 |
-
"early_stopping": true,
|
| 39 |
-
"max_length": 300,
|
| 40 |
-
"num_beams": 4,
|
| 41 |
-
"prefix": "translate English to German: "
|
| 42 |
-
},
|
| 43 |
-
"translation_en_to_fr": {
|
| 44 |
-
"early_stopping": true,
|
| 45 |
-
"max_length": 300,
|
| 46 |
-
"num_beams": 4,
|
| 47 |
-
"prefix": "translate English to French: "
|
| 48 |
-
},
|
| 49 |
-
"translation_en_to_ro": {
|
| 50 |
"early_stopping": true,
|
| 51 |
"max_length": 300,
|
| 52 |
"num_beams": 4,
|
| 53 |
-
"prefix": "
|
| 54 |
}
|
| 55 |
},
|
| 56 |
"tie_word_embeddings": false,
|
| 57 |
"torch_dtype": "float32",
|
| 58 |
-
"transformers_version": "4.
|
| 59 |
"use_cache": true,
|
| 60 |
"vocab_size": 32128
|
| 61 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "kargaranamir/T5R",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
| 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,
|
|
|
|
| 17 |
"layer_norm_epsilon": 1e-06,
|
| 18 |
"model_type": "t5",
|
| 19 |
"n_positions": 512,
|
| 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 |
"task_specific_params": {
|
| 28 |
+
"reverse-gen": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"early_stopping": true,
|
| 30 |
"max_length": 300,
|
| 31 |
"num_beams": 4,
|
| 32 |
+
"prefix": "Instruction: X"
|
| 33 |
}
|
| 34 |
},
|
| 35 |
"tie_word_embeddings": false,
|
| 36 |
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.24.0",
|
| 38 |
"use_cache": true,
|
| 39 |
"vocab_size": 32128
|
| 40 |
}
|
generation_config.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"decoder_start_token_id": 0,
|
| 3 |
-
"eos_token_id": 1,
|
| 4 |
-
"pad_token_id": 0,
|
| 5 |
-
"transformers_version": "4.29.1"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f08bda4a51ec276efc98bb0cd0c994f5b493465386b0aef79409b69a851774c
|
| 3 |
+
size 990406605
|
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
CHANGED
|
@@ -19,930 +19,930 @@
|
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 22 |
"content": "<pad>",
|
| 23 |
"single_word": false,
|
| 24 |
"lstrip": false,
|
| 25 |
"rstrip": false,
|
| 26 |
-
"normalized": false
|
| 27 |
-
"special": true
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"id": 1,
|
|
|
|
| 31 |
"content": "</s>",
|
| 32 |
"single_word": false,
|
| 33 |
"lstrip": false,
|
| 34 |
"rstrip": false,
|
| 35 |
-
"normalized": false
|
| 36 |
-
"special": true
|
| 37 |
},
|
| 38 |
{
|
| 39 |
"id": 2,
|
|
|
|
| 40 |
"content": "<unk>",
|
| 41 |
"single_word": false,
|
| 42 |
"lstrip": false,
|
| 43 |
"rstrip": false,
|
| 44 |
-
"normalized": false
|
| 45 |
-
"special": true
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"id": 32000,
|
|
|
|
| 49 |
"content": "<extra_id_99>",
|
| 50 |
"single_word": false,
|
| 51 |
"lstrip": false,
|
| 52 |
"rstrip": false,
|
| 53 |
-
"normalized": false
|
| 54 |
-
"special": true
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"id": 32001,
|
|
|
|
| 58 |
"content": "<extra_id_98>",
|
| 59 |
"single_word": false,
|
| 60 |
"lstrip": false,
|
| 61 |
"rstrip": false,
|
| 62 |
-
"normalized": false
|
| 63 |
-
"special": true
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"id": 32002,
|
|
|
|
| 67 |
"content": "<extra_id_97>",
|
| 68 |
"single_word": false,
|
| 69 |
"lstrip": false,
|
| 70 |
"rstrip": false,
|
| 71 |
-
"normalized": false
|
| 72 |
-
"special": true
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"id": 32003,
|
|
|
|
| 76 |
"content": "<extra_id_96>",
|
| 77 |
"single_word": false,
|
| 78 |
"lstrip": false,
|
| 79 |
"rstrip": false,
|
| 80 |
-
"normalized": false
|
| 81 |
-
"special": true
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"id": 32004,
|
|
|
|
| 85 |
"content": "<extra_id_95>",
|
| 86 |
"single_word": false,
|
| 87 |
"lstrip": false,
|
| 88 |
"rstrip": false,
|
| 89 |
-
"normalized": false
|
| 90 |
-
"special": true
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"id": 32005,
|
|
|
|
| 94 |
"content": "<extra_id_94>",
|
| 95 |
"single_word": false,
|
| 96 |
"lstrip": false,
|
| 97 |
"rstrip": false,
|
| 98 |
-
"normalized": false
|
| 99 |
-
"special": true
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"id": 32006,
|
|
|
|
| 103 |
"content": "<extra_id_93>",
|
| 104 |
"single_word": false,
|
| 105 |
"lstrip": false,
|
| 106 |
"rstrip": false,
|
| 107 |
-
"normalized": false
|
| 108 |
-
"special": true
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"id": 32007,
|
|
|
|
| 112 |
"content": "<extra_id_92>",
|
| 113 |
"single_word": false,
|
| 114 |
"lstrip": false,
|
| 115 |
"rstrip": false,
|
| 116 |
-
"normalized": false
|
| 117 |
-
"special": true
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"id": 32008,
|
|
|
|
| 121 |
"content": "<extra_id_91>",
|
| 122 |
"single_word": false,
|
| 123 |
"lstrip": false,
|
| 124 |
"rstrip": false,
|
| 125 |
-
"normalized": false
|
| 126 |
-
"special": true
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"id": 32009,
|
|
|
|
| 130 |
"content": "<extra_id_90>",
|
| 131 |
"single_word": false,
|
| 132 |
"lstrip": false,
|
| 133 |
"rstrip": false,
|
| 134 |
-
"normalized": false
|
| 135 |
-
"special": true
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"id": 32010,
|
|
|
|
| 139 |
"content": "<extra_id_89>",
|
| 140 |
"single_word": false,
|
| 141 |
"lstrip": false,
|
| 142 |
"rstrip": false,
|
| 143 |
-
"normalized": false
|
| 144 |
-
"special": true
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"id": 32011,
|
|
|
|
| 148 |
"content": "<extra_id_88>",
|
| 149 |
"single_word": false,
|
| 150 |
"lstrip": false,
|
| 151 |
"rstrip": false,
|
| 152 |
-
"normalized": false
|
| 153 |
-
"special": true
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"id": 32012,
|
|
|
|
| 157 |
"content": "<extra_id_87>",
|
| 158 |
"single_word": false,
|
| 159 |
"lstrip": false,
|
| 160 |
"rstrip": false,
|
| 161 |
-
"normalized": false
|
| 162 |
-
"special": true
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"id": 32013,
|
|
|
|
| 166 |
"content": "<extra_id_86>",
|
| 167 |
"single_word": false,
|
| 168 |
"lstrip": false,
|
| 169 |
"rstrip": false,
|
| 170 |
-
"normalized": false
|
| 171 |
-
"special": true
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"id": 32014,
|
|
|
|
| 175 |
"content": "<extra_id_85>",
|
| 176 |
"single_word": false,
|
| 177 |
"lstrip": false,
|
| 178 |
"rstrip": false,
|
| 179 |
-
"normalized": false
|
| 180 |
-
"special": true
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"id": 32015,
|
|
|
|
| 184 |
"content": "<extra_id_84>",
|
| 185 |
"single_word": false,
|
| 186 |
"lstrip": false,
|
| 187 |
"rstrip": false,
|
| 188 |
-
"normalized": false
|
| 189 |
-
"special": true
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"id": 32016,
|
|
|
|
| 193 |
"content": "<extra_id_83>",
|
| 194 |
"single_word": false,
|
| 195 |
"lstrip": false,
|
| 196 |
"rstrip": false,
|
| 197 |
-
"normalized": false
|
| 198 |
-
"special": true
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"id": 32017,
|
|
|
|
| 202 |
"content": "<extra_id_82>",
|
| 203 |
"single_word": false,
|
| 204 |
"lstrip": false,
|
| 205 |
"rstrip": false,
|
| 206 |
-
"normalized": false
|
| 207 |
-
"special": true
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"id": 32018,
|
|
|
|
| 211 |
"content": "<extra_id_81>",
|
| 212 |
"single_word": false,
|
| 213 |
"lstrip": false,
|
| 214 |
"rstrip": false,
|
| 215 |
-
"normalized": false
|
| 216 |
-
"special": true
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"id": 32019,
|
|
|
|
| 220 |
"content": "<extra_id_80>",
|
| 221 |
"single_word": false,
|
| 222 |
"lstrip": false,
|
| 223 |
"rstrip": false,
|
| 224 |
-
"normalized": false
|
| 225 |
-
"special": true
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"id": 32020,
|
|
|
|
| 229 |
"content": "<extra_id_79>",
|
| 230 |
"single_word": false,
|
| 231 |
"lstrip": false,
|
| 232 |
"rstrip": false,
|
| 233 |
-
"normalized": false
|
| 234 |
-
"special": true
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"id": 32021,
|
|
|
|
| 238 |
"content": "<extra_id_78>",
|
| 239 |
"single_word": false,
|
| 240 |
"lstrip": false,
|
| 241 |
"rstrip": false,
|
| 242 |
-
"normalized": false
|
| 243 |
-
"special": true
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"id": 32022,
|
|
|
|
| 247 |
"content": "<extra_id_77>",
|
| 248 |
"single_word": false,
|
| 249 |
"lstrip": false,
|
| 250 |
"rstrip": false,
|
| 251 |
-
"normalized": false
|
| 252 |
-
"special": true
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"id": 32023,
|
|
|
|
| 256 |
"content": "<extra_id_76>",
|
| 257 |
"single_word": false,
|
| 258 |
"lstrip": false,
|
| 259 |
"rstrip": false,
|
| 260 |
-
"normalized": false
|
| 261 |
-
"special": true
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"id": 32024,
|
|
|
|
| 265 |
"content": "<extra_id_75>",
|
| 266 |
"single_word": false,
|
| 267 |
"lstrip": false,
|
| 268 |
"rstrip": false,
|
| 269 |
-
"normalized": false
|
| 270 |
-
"special": true
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"id": 32025,
|
|
|
|
| 274 |
"content": "<extra_id_74>",
|
| 275 |
"single_word": false,
|
| 276 |
"lstrip": false,
|
| 277 |
"rstrip": false,
|
| 278 |
-
"normalized": false
|
| 279 |
-
"special": true
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"id": 32026,
|
|
|
|
| 283 |
"content": "<extra_id_73>",
|
| 284 |
"single_word": false,
|
| 285 |
"lstrip": false,
|
| 286 |
"rstrip": false,
|
| 287 |
-
"normalized": false
|
| 288 |
-
"special": true
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"id": 32027,
|
|
|
|
| 292 |
"content": "<extra_id_72>",
|
| 293 |
"single_word": false,
|
| 294 |
"lstrip": false,
|
| 295 |
"rstrip": false,
|
| 296 |
-
"normalized": false
|
| 297 |
-
"special": true
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"id": 32028,
|
|
|
|
| 301 |
"content": "<extra_id_71>",
|
| 302 |
"single_word": false,
|
| 303 |
"lstrip": false,
|
| 304 |
"rstrip": false,
|
| 305 |
-
"normalized": false
|
| 306 |
-
"special": true
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"id": 32029,
|
|
|
|
| 310 |
"content": "<extra_id_70>",
|
| 311 |
"single_word": false,
|
| 312 |
"lstrip": false,
|
| 313 |
"rstrip": false,
|
| 314 |
-
"normalized": false
|
| 315 |
-
"special": true
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"id": 32030,
|
|
|
|
| 319 |
"content": "<extra_id_69>",
|
| 320 |
"single_word": false,
|
| 321 |
"lstrip": false,
|
| 322 |
"rstrip": false,
|
| 323 |
-
"normalized": false
|
| 324 |
-
"special": true
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"id": 32031,
|
|
|
|
| 328 |
"content": "<extra_id_68>",
|
| 329 |
"single_word": false,
|
| 330 |
"lstrip": false,
|
| 331 |
"rstrip": false,
|
| 332 |
-
"normalized": false
|
| 333 |
-
"special": true
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"id": 32032,
|
|
|
|
| 337 |
"content": "<extra_id_67>",
|
| 338 |
"single_word": false,
|
| 339 |
"lstrip": false,
|
| 340 |
"rstrip": false,
|
| 341 |
-
"normalized": false
|
| 342 |
-
"special": true
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"id": 32033,
|
|
|
|
| 346 |
"content": "<extra_id_66>",
|
| 347 |
"single_word": false,
|
| 348 |
"lstrip": false,
|
| 349 |
"rstrip": false,
|
| 350 |
-
"normalized": false
|
| 351 |
-
"special": true
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"id": 32034,
|
|
|
|
| 355 |
"content": "<extra_id_65>",
|
| 356 |
"single_word": false,
|
| 357 |
"lstrip": false,
|
| 358 |
"rstrip": false,
|
| 359 |
-
"normalized": false
|
| 360 |
-
"special": true
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"id": 32035,
|
|
|
|
| 364 |
"content": "<extra_id_64>",
|
| 365 |
"single_word": false,
|
| 366 |
"lstrip": false,
|
| 367 |
"rstrip": false,
|
| 368 |
-
"normalized": false
|
| 369 |
-
"special": true
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"id": 32036,
|
|
|
|
| 373 |
"content": "<extra_id_63>",
|
| 374 |
"single_word": false,
|
| 375 |
"lstrip": false,
|
| 376 |
"rstrip": false,
|
| 377 |
-
"normalized": false
|
| 378 |
-
"special": true
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"id": 32037,
|
|
|
|
| 382 |
"content": "<extra_id_62>",
|
| 383 |
"single_word": false,
|
| 384 |
"lstrip": false,
|
| 385 |
"rstrip": false,
|
| 386 |
-
"normalized": false
|
| 387 |
-
"special": true
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"id": 32038,
|
|
|
|
| 391 |
"content": "<extra_id_61>",
|
| 392 |
"single_word": false,
|
| 393 |
"lstrip": false,
|
| 394 |
"rstrip": false,
|
| 395 |
-
"normalized": false
|
| 396 |
-
"special": true
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"id": 32039,
|
|
|
|
| 400 |
"content": "<extra_id_60>",
|
| 401 |
"single_word": false,
|
| 402 |
"lstrip": false,
|
| 403 |
"rstrip": false,
|
| 404 |
-
"normalized": false
|
| 405 |
-
"special": true
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"id": 32040,
|
|
|
|
| 409 |
"content": "<extra_id_59>",
|
| 410 |
"single_word": false,
|
| 411 |
"lstrip": false,
|
| 412 |
"rstrip": false,
|
| 413 |
-
"normalized": false
|
| 414 |
-
"special": true
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"id": 32041,
|
|
|
|
| 418 |
"content": "<extra_id_58>",
|
| 419 |
"single_word": false,
|
| 420 |
"lstrip": false,
|
| 421 |
"rstrip": false,
|
| 422 |
-
"normalized": false
|
| 423 |
-
"special": true
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"id": 32042,
|
|
|
|
| 427 |
"content": "<extra_id_57>",
|
| 428 |
"single_word": false,
|
| 429 |
"lstrip": false,
|
| 430 |
"rstrip": false,
|
| 431 |
-
"normalized": false
|
| 432 |
-
"special": true
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"id": 32043,
|
|
|
|
| 436 |
"content": "<extra_id_56>",
|
| 437 |
"single_word": false,
|
| 438 |
"lstrip": false,
|
| 439 |
"rstrip": false,
|
| 440 |
-
"normalized": false
|
| 441 |
-
"special": true
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"id": 32044,
|
|
|
|
| 445 |
"content": "<extra_id_55>",
|
| 446 |
"single_word": false,
|
| 447 |
"lstrip": false,
|
| 448 |
"rstrip": false,
|
| 449 |
-
"normalized": false
|
| 450 |
-
"special": true
|
| 451 |
},
|
| 452 |
{
|
| 453 |
"id": 32045,
|
|
|
|
| 454 |
"content": "<extra_id_54>",
|
| 455 |
"single_word": false,
|
| 456 |
"lstrip": false,
|
| 457 |
"rstrip": false,
|
| 458 |
-
"normalized": false
|
| 459 |
-
"special": true
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"id": 32046,
|
|
|
|
| 463 |
"content": "<extra_id_53>",
|
| 464 |
"single_word": false,
|
| 465 |
"lstrip": false,
|
| 466 |
"rstrip": false,
|
| 467 |
-
"normalized": false
|
| 468 |
-
"special": true
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"id": 32047,
|
|
|
|
| 472 |
"content": "<extra_id_52>",
|
| 473 |
"single_word": false,
|
| 474 |
"lstrip": false,
|
| 475 |
"rstrip": false,
|
| 476 |
-
"normalized": false
|
| 477 |
-
"special": true
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"id": 32048,
|
|
|
|
| 481 |
"content": "<extra_id_51>",
|
| 482 |
"single_word": false,
|
| 483 |
"lstrip": false,
|
| 484 |
"rstrip": false,
|
| 485 |
-
"normalized": false
|
| 486 |
-
"special": true
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"id": 32049,
|
|
|
|
| 490 |
"content": "<extra_id_50>",
|
| 491 |
"single_word": false,
|
| 492 |
"lstrip": false,
|
| 493 |
"rstrip": false,
|
| 494 |
-
"normalized": false
|
| 495 |
-
"special": true
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"id": 32050,
|
|
|
|
| 499 |
"content": "<extra_id_49>",
|
| 500 |
"single_word": false,
|
| 501 |
"lstrip": false,
|
| 502 |
"rstrip": false,
|
| 503 |
-
"normalized": false
|
| 504 |
-
"special": true
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"id": 32051,
|
|
|
|
| 508 |
"content": "<extra_id_48>",
|
| 509 |
"single_word": false,
|
| 510 |
"lstrip": false,
|
| 511 |
"rstrip": false,
|
| 512 |
-
"normalized": false
|
| 513 |
-
"special": true
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"id": 32052,
|
|
|
|
| 517 |
"content": "<extra_id_47>",
|
| 518 |
"single_word": false,
|
| 519 |
"lstrip": false,
|
| 520 |
"rstrip": false,
|
| 521 |
-
"normalized": false
|
| 522 |
-
"special": true
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"id": 32053,
|
|
|
|
| 526 |
"content": "<extra_id_46>",
|
| 527 |
"single_word": false,
|
| 528 |
"lstrip": false,
|
| 529 |
"rstrip": false,
|
| 530 |
-
"normalized": false
|
| 531 |
-
"special": true
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"id": 32054,
|
|
|
|
| 535 |
"content": "<extra_id_45>",
|
| 536 |
"single_word": false,
|
| 537 |
"lstrip": false,
|
| 538 |
"rstrip": false,
|
| 539 |
-
"normalized": false
|
| 540 |
-
"special": true
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"id": 32055,
|
|
|
|
| 544 |
"content": "<extra_id_44>",
|
| 545 |
"single_word": false,
|
| 546 |
"lstrip": false,
|
| 547 |
"rstrip": false,
|
| 548 |
-
"normalized": false
|
| 549 |
-
"special": true
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"id": 32056,
|
|
|
|
| 553 |
"content": "<extra_id_43>",
|
| 554 |
"single_word": false,
|
| 555 |
"lstrip": false,
|
| 556 |
"rstrip": false,
|
| 557 |
-
"normalized": false
|
| 558 |
-
"special": true
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"id": 32057,
|
|
|
|
| 562 |
"content": "<extra_id_42>",
|
| 563 |
"single_word": false,
|
| 564 |
"lstrip": false,
|
| 565 |
"rstrip": false,
|
| 566 |
-
"normalized": false
|
| 567 |
-
"special": true
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"id": 32058,
|
|
|
|
| 571 |
"content": "<extra_id_41>",
|
| 572 |
"single_word": false,
|
| 573 |
"lstrip": false,
|
| 574 |
"rstrip": false,
|
| 575 |
-
"normalized": false
|
| 576 |
-
"special": true
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"id": 32059,
|
|
|
|
| 580 |
"content": "<extra_id_40>",
|
| 581 |
"single_word": false,
|
| 582 |
"lstrip": false,
|
| 583 |
"rstrip": false,
|
| 584 |
-
"normalized": false
|
| 585 |
-
"special": true
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"id": 32060,
|
|
|
|
| 589 |
"content": "<extra_id_39>",
|
| 590 |
"single_word": false,
|
| 591 |
"lstrip": false,
|
| 592 |
"rstrip": false,
|
| 593 |
-
"normalized": false
|
| 594 |
-
"special": true
|
| 595 |
},
|
| 596 |
{
|
| 597 |
"id": 32061,
|
|
|
|
| 598 |
"content": "<extra_id_38>",
|
| 599 |
"single_word": false,
|
| 600 |
"lstrip": false,
|
| 601 |
"rstrip": false,
|
| 602 |
-
"normalized": false
|
| 603 |
-
"special": true
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"id": 32062,
|
|
|
|
| 607 |
"content": "<extra_id_37>",
|
| 608 |
"single_word": false,
|
| 609 |
"lstrip": false,
|
| 610 |
"rstrip": false,
|
| 611 |
-
"normalized": false
|
| 612 |
-
"special": true
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"id": 32063,
|
|
|
|
| 616 |
"content": "<extra_id_36>",
|
| 617 |
"single_word": false,
|
| 618 |
"lstrip": false,
|
| 619 |
"rstrip": false,
|
| 620 |
-
"normalized": false
|
| 621 |
-
"special": true
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"id": 32064,
|
|
|
|
| 625 |
"content": "<extra_id_35>",
|
| 626 |
"single_word": false,
|
| 627 |
"lstrip": false,
|
| 628 |
"rstrip": false,
|
| 629 |
-
"normalized": false
|
| 630 |
-
"special": true
|
| 631 |
},
|
| 632 |
{
|
| 633 |
"id": 32065,
|
|
|
|
| 634 |
"content": "<extra_id_34>",
|
| 635 |
"single_word": false,
|
| 636 |
"lstrip": false,
|
| 637 |
"rstrip": false,
|
| 638 |
-
"normalized": false
|
| 639 |
-
"special": true
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"id": 32066,
|
|
|
|
| 643 |
"content": "<extra_id_33>",
|
| 644 |
"single_word": false,
|
| 645 |
"lstrip": false,
|
| 646 |
"rstrip": false,
|
| 647 |
-
"normalized": false
|
| 648 |
-
"special": true
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"id": 32067,
|
|
|
|
| 652 |
"content": "<extra_id_32>",
|
| 653 |
"single_word": false,
|
| 654 |
"lstrip": false,
|
| 655 |
"rstrip": false,
|
| 656 |
-
"normalized": false
|
| 657 |
-
"special": true
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"id": 32068,
|
|
|
|
| 661 |
"content": "<extra_id_31>",
|
| 662 |
"single_word": false,
|
| 663 |
"lstrip": false,
|
| 664 |
"rstrip": false,
|
| 665 |
-
"normalized": false
|
| 666 |
-
"special": true
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"id": 32069,
|
|
|
|
| 670 |
"content": "<extra_id_30>",
|
| 671 |
"single_word": false,
|
| 672 |
"lstrip": false,
|
| 673 |
"rstrip": false,
|
| 674 |
-
"normalized": false
|
| 675 |
-
"special": true
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"id": 32070,
|
|
|
|
| 679 |
"content": "<extra_id_29>",
|
| 680 |
"single_word": false,
|
| 681 |
"lstrip": false,
|
| 682 |
"rstrip": false,
|
| 683 |
-
"normalized": false
|
| 684 |
-
"special": true
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"id": 32071,
|
|
|
|
| 688 |
"content": "<extra_id_28>",
|
| 689 |
"single_word": false,
|
| 690 |
"lstrip": false,
|
| 691 |
"rstrip": false,
|
| 692 |
-
"normalized": false
|
| 693 |
-
"special": true
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"id": 32072,
|
|
|
|
| 697 |
"content": "<extra_id_27>",
|
| 698 |
"single_word": false,
|
| 699 |
"lstrip": false,
|
| 700 |
"rstrip": false,
|
| 701 |
-
"normalized": false
|
| 702 |
-
"special": true
|
| 703 |
},
|
| 704 |
{
|
| 705 |
"id": 32073,
|
|
|
|
| 706 |
"content": "<extra_id_26>",
|
| 707 |
"single_word": false,
|
| 708 |
"lstrip": false,
|
| 709 |
"rstrip": false,
|
| 710 |
-
"normalized": false
|
| 711 |
-
"special": true
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"id": 32074,
|
|
|
|
| 715 |
"content": "<extra_id_25>",
|
| 716 |
"single_word": false,
|
| 717 |
"lstrip": false,
|
| 718 |
"rstrip": false,
|
| 719 |
-
"normalized": false
|
| 720 |
-
"special": true
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"id": 32075,
|
|
|
|
| 724 |
"content": "<extra_id_24>",
|
| 725 |
"single_word": false,
|
| 726 |
"lstrip": false,
|
| 727 |
"rstrip": false,
|
| 728 |
-
"normalized": false
|
| 729 |
-
"special": true
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"id": 32076,
|
|
|
|
| 733 |
"content": "<extra_id_23>",
|
| 734 |
"single_word": false,
|
| 735 |
"lstrip": false,
|
| 736 |
"rstrip": false,
|
| 737 |
-
"normalized": false
|
| 738 |
-
"special": true
|
| 739 |
},
|
| 740 |
{
|
| 741 |
"id": 32077,
|
|
|
|
| 742 |
"content": "<extra_id_22>",
|
| 743 |
"single_word": false,
|
| 744 |
"lstrip": false,
|
| 745 |
"rstrip": false,
|
| 746 |
-
"normalized": false
|
| 747 |
-
"special": true
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"id": 32078,
|
|
|
|
| 751 |
"content": "<extra_id_21>",
|
| 752 |
"single_word": false,
|
| 753 |
"lstrip": false,
|
| 754 |
"rstrip": false,
|
| 755 |
-
"normalized": false
|
| 756 |
-
"special": true
|
| 757 |
},
|
| 758 |
{
|
| 759 |
"id": 32079,
|
|
|
|
| 760 |
"content": "<extra_id_20>",
|
| 761 |
"single_word": false,
|
| 762 |
"lstrip": false,
|
| 763 |
"rstrip": false,
|
| 764 |
-
"normalized": false
|
| 765 |
-
"special": true
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"id": 32080,
|
|
|
|
| 769 |
"content": "<extra_id_19>",
|
| 770 |
"single_word": false,
|
| 771 |
"lstrip": false,
|
| 772 |
"rstrip": false,
|
| 773 |
-
"normalized": false
|
| 774 |
-
"special": true
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"id": 32081,
|
|
|
|
| 778 |
"content": "<extra_id_18>",
|
| 779 |
"single_word": false,
|
| 780 |
"lstrip": false,
|
| 781 |
"rstrip": false,
|
| 782 |
-
"normalized": false
|
| 783 |
-
"special": true
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"id": 32082,
|
|
|
|
| 787 |
"content": "<extra_id_17>",
|
| 788 |
"single_word": false,
|
| 789 |
"lstrip": false,
|
| 790 |
"rstrip": false,
|
| 791 |
-
"normalized": false
|
| 792 |
-
"special": true
|
| 793 |
},
|
| 794 |
{
|
| 795 |
"id": 32083,
|
|
|
|
| 796 |
"content": "<extra_id_16>",
|
| 797 |
"single_word": false,
|
| 798 |
"lstrip": false,
|
| 799 |
"rstrip": false,
|
| 800 |
-
"normalized": false
|
| 801 |
-
"special": true
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"id": 32084,
|
|
|
|
| 805 |
"content": "<extra_id_15>",
|
| 806 |
"single_word": false,
|
| 807 |
"lstrip": false,
|
| 808 |
"rstrip": false,
|
| 809 |
-
"normalized": false
|
| 810 |
-
"special": true
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"id": 32085,
|
|
|
|
| 814 |
"content": "<extra_id_14>",
|
| 815 |
"single_word": false,
|
| 816 |
"lstrip": false,
|
| 817 |
"rstrip": false,
|
| 818 |
-
"normalized": false
|
| 819 |
-
"special": true
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"id": 32086,
|
|
|
|
| 823 |
"content": "<extra_id_13>",
|
| 824 |
"single_word": false,
|
| 825 |
"lstrip": false,
|
| 826 |
"rstrip": false,
|
| 827 |
-
"normalized": false
|
| 828 |
-
"special": true
|
| 829 |
},
|
| 830 |
{
|
| 831 |
"id": 32087,
|
|
|
|
| 832 |
"content": "<extra_id_12>",
|
| 833 |
"single_word": false,
|
| 834 |
"lstrip": false,
|
| 835 |
"rstrip": false,
|
| 836 |
-
"normalized": false
|
| 837 |
-
"special": true
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"id": 32088,
|
|
|
|
| 841 |
"content": "<extra_id_11>",
|
| 842 |
"single_word": false,
|
| 843 |
"lstrip": false,
|
| 844 |
"rstrip": false,
|
| 845 |
-
"normalized": false
|
| 846 |
-
"special": true
|
| 847 |
},
|
| 848 |
{
|
| 849 |
"id": 32089,
|
|
|
|
| 850 |
"content": "<extra_id_10>",
|
| 851 |
"single_word": false,
|
| 852 |
"lstrip": false,
|
| 853 |
"rstrip": false,
|
| 854 |
-
"normalized": false
|
| 855 |
-
"special": true
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"id": 32090,
|
|
|
|
| 859 |
"content": "<extra_id_9>",
|
| 860 |
"single_word": false,
|
| 861 |
"lstrip": false,
|
| 862 |
"rstrip": false,
|
| 863 |
-
"normalized": false
|
| 864 |
-
"special": true
|
| 865 |
},
|
| 866 |
{
|
| 867 |
"id": 32091,
|
|
|
|
| 868 |
"content": "<extra_id_8>",
|
| 869 |
"single_word": false,
|
| 870 |
"lstrip": false,
|
| 871 |
"rstrip": false,
|
| 872 |
-
"normalized": false
|
| 873 |
-
"special": true
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"id": 32092,
|
|
|
|
| 877 |
"content": "<extra_id_7>",
|
| 878 |
"single_word": false,
|
| 879 |
"lstrip": false,
|
| 880 |
"rstrip": false,
|
| 881 |
-
"normalized": false
|
| 882 |
-
"special": true
|
| 883 |
},
|
| 884 |
{
|
| 885 |
"id": 32093,
|
|
|
|
| 886 |
"content": "<extra_id_6>",
|
| 887 |
"single_word": false,
|
| 888 |
"lstrip": false,
|
| 889 |
"rstrip": false,
|
| 890 |
-
"normalized": false
|
| 891 |
-
"special": true
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"id": 32094,
|
|
|
|
| 895 |
"content": "<extra_id_5>",
|
| 896 |
"single_word": false,
|
| 897 |
"lstrip": false,
|
| 898 |
"rstrip": false,
|
| 899 |
-
"normalized": false
|
| 900 |
-
"special": true
|
| 901 |
},
|
| 902 |
{
|
| 903 |
"id": 32095,
|
|
|
|
| 904 |
"content": "<extra_id_4>",
|
| 905 |
"single_word": false,
|
| 906 |
"lstrip": false,
|
| 907 |
"rstrip": false,
|
| 908 |
-
"normalized": false
|
| 909 |
-
"special": true
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"id": 32096,
|
|
|
|
| 913 |
"content": "<extra_id_3>",
|
| 914 |
"single_word": false,
|
| 915 |
"lstrip": false,
|
| 916 |
"rstrip": false,
|
| 917 |
-
"normalized": false
|
| 918 |
-
"special": true
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"id": 32097,
|
|
|
|
| 922 |
"content": "<extra_id_2>",
|
| 923 |
"single_word": false,
|
| 924 |
"lstrip": false,
|
| 925 |
"rstrip": false,
|
| 926 |
-
"normalized": false
|
| 927 |
-
"special": true
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"id": 32098,
|
|
|
|
| 931 |
"content": "<extra_id_1>",
|
| 932 |
"single_word": false,
|
| 933 |
"lstrip": false,
|
| 934 |
"rstrip": false,
|
| 935 |
-
"normalized": false
|
| 936 |
-
"special": true
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"id": 32099,
|
|
|
|
| 940 |
"content": "<extra_id_0>",
|
| 941 |
"single_word": false,
|
| 942 |
"lstrip": false,
|
| 943 |
"rstrip": false,
|
| 944 |
-
"normalized": false
|
| 945 |
-
"special": true
|
| 946 |
}
|
| 947 |
],
|
| 948 |
"normalizer": {
|
|
|
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
| 22 |
+
"special": true,
|
| 23 |
"content": "<pad>",
|
| 24 |
"single_word": false,
|
| 25 |
"lstrip": false,
|
| 26 |
"rstrip": false,
|
| 27 |
+
"normalized": false
|
|
|
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"id": 1,
|
| 31 |
+
"special": true,
|
| 32 |
"content": "</s>",
|
| 33 |
"single_word": false,
|
| 34 |
"lstrip": false,
|
| 35 |
"rstrip": false,
|
| 36 |
+
"normalized": false
|
|
|
|
| 37 |
},
|
| 38 |
{
|
| 39 |
"id": 2,
|
| 40 |
+
"special": true,
|
| 41 |
"content": "<unk>",
|
| 42 |
"single_word": false,
|
| 43 |
"lstrip": false,
|
| 44 |
"rstrip": false,
|
| 45 |
+
"normalized": false
|
|
|
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"id": 32000,
|
| 49 |
+
"special": true,
|
| 50 |
"content": "<extra_id_99>",
|
| 51 |
"single_word": false,
|
| 52 |
"lstrip": false,
|
| 53 |
"rstrip": false,
|
| 54 |
+
"normalized": false
|
|
|
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"id": 32001,
|
| 58 |
+
"special": true,
|
| 59 |
"content": "<extra_id_98>",
|
| 60 |
"single_word": false,
|
| 61 |
"lstrip": false,
|
| 62 |
"rstrip": false,
|
| 63 |
+
"normalized": false
|
|
|
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"id": 32002,
|
| 67 |
+
"special": true,
|
| 68 |
"content": "<extra_id_97>",
|
| 69 |
"single_word": false,
|
| 70 |
"lstrip": false,
|
| 71 |
"rstrip": false,
|
| 72 |
+
"normalized": false
|
|
|
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"id": 32003,
|
| 76 |
+
"special": true,
|
| 77 |
"content": "<extra_id_96>",
|
| 78 |
"single_word": false,
|
| 79 |
"lstrip": false,
|
| 80 |
"rstrip": false,
|
| 81 |
+
"normalized": false
|
|
|
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"id": 32004,
|
| 85 |
+
"special": true,
|
| 86 |
"content": "<extra_id_95>",
|
| 87 |
"single_word": false,
|
| 88 |
"lstrip": false,
|
| 89 |
"rstrip": false,
|
| 90 |
+
"normalized": false
|
|
|
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"id": 32005,
|
| 94 |
+
"special": true,
|
| 95 |
"content": "<extra_id_94>",
|
| 96 |
"single_word": false,
|
| 97 |
"lstrip": false,
|
| 98 |
"rstrip": false,
|
| 99 |
+
"normalized": false
|
|
|
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"id": 32006,
|
| 103 |
+
"special": true,
|
| 104 |
"content": "<extra_id_93>",
|
| 105 |
"single_word": false,
|
| 106 |
"lstrip": false,
|
| 107 |
"rstrip": false,
|
| 108 |
+
"normalized": false
|
|
|
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"id": 32007,
|
| 112 |
+
"special": true,
|
| 113 |
"content": "<extra_id_92>",
|
| 114 |
"single_word": false,
|
| 115 |
"lstrip": false,
|
| 116 |
"rstrip": false,
|
| 117 |
+
"normalized": false
|
|
|
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"id": 32008,
|
| 121 |
+
"special": true,
|
| 122 |
"content": "<extra_id_91>",
|
| 123 |
"single_word": false,
|
| 124 |
"lstrip": false,
|
| 125 |
"rstrip": false,
|
| 126 |
+
"normalized": false
|
|
|
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"id": 32009,
|
| 130 |
+
"special": true,
|
| 131 |
"content": "<extra_id_90>",
|
| 132 |
"single_word": false,
|
| 133 |
"lstrip": false,
|
| 134 |
"rstrip": false,
|
| 135 |
+
"normalized": false
|
|
|
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"id": 32010,
|
| 139 |
+
"special": true,
|
| 140 |
"content": "<extra_id_89>",
|
| 141 |
"single_word": false,
|
| 142 |
"lstrip": false,
|
| 143 |
"rstrip": false,
|
| 144 |
+
"normalized": false
|
|
|
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"id": 32011,
|
| 148 |
+
"special": true,
|
| 149 |
"content": "<extra_id_88>",
|
| 150 |
"single_word": false,
|
| 151 |
"lstrip": false,
|
| 152 |
"rstrip": false,
|
| 153 |
+
"normalized": false
|
|
|
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"id": 32012,
|
| 157 |
+
"special": true,
|
| 158 |
"content": "<extra_id_87>",
|
| 159 |
"single_word": false,
|
| 160 |
"lstrip": false,
|
| 161 |
"rstrip": false,
|
| 162 |
+
"normalized": false
|
|
|
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"id": 32013,
|
| 166 |
+
"special": true,
|
| 167 |
"content": "<extra_id_86>",
|
| 168 |
"single_word": false,
|
| 169 |
"lstrip": false,
|
| 170 |
"rstrip": false,
|
| 171 |
+
"normalized": false
|
|
|
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"id": 32014,
|
| 175 |
+
"special": true,
|
| 176 |
"content": "<extra_id_85>",
|
| 177 |
"single_word": false,
|
| 178 |
"lstrip": false,
|
| 179 |
"rstrip": false,
|
| 180 |
+
"normalized": false
|
|
|
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"id": 32015,
|
| 184 |
+
"special": true,
|
| 185 |
"content": "<extra_id_84>",
|
| 186 |
"single_word": false,
|
| 187 |
"lstrip": false,
|
| 188 |
"rstrip": false,
|
| 189 |
+
"normalized": false
|
|
|
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"id": 32016,
|
| 193 |
+
"special": true,
|
| 194 |
"content": "<extra_id_83>",
|
| 195 |
"single_word": false,
|
| 196 |
"lstrip": false,
|
| 197 |
"rstrip": false,
|
| 198 |
+
"normalized": false
|
|
|
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"id": 32017,
|
| 202 |
+
"special": true,
|
| 203 |
"content": "<extra_id_82>",
|
| 204 |
"single_word": false,
|
| 205 |
"lstrip": false,
|
| 206 |
"rstrip": false,
|
| 207 |
+
"normalized": false
|
|
|
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"id": 32018,
|
| 211 |
+
"special": true,
|
| 212 |
"content": "<extra_id_81>",
|
| 213 |
"single_word": false,
|
| 214 |
"lstrip": false,
|
| 215 |
"rstrip": false,
|
| 216 |
+
"normalized": false
|
|
|
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"id": 32019,
|
| 220 |
+
"special": true,
|
| 221 |
"content": "<extra_id_80>",
|
| 222 |
"single_word": false,
|
| 223 |
"lstrip": false,
|
| 224 |
"rstrip": false,
|
| 225 |
+
"normalized": false
|
|
|
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"id": 32020,
|
| 229 |
+
"special": true,
|
| 230 |
"content": "<extra_id_79>",
|
| 231 |
"single_word": false,
|
| 232 |
"lstrip": false,
|
| 233 |
"rstrip": false,
|
| 234 |
+
"normalized": false
|
|
|
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"id": 32021,
|
| 238 |
+
"special": true,
|
| 239 |
"content": "<extra_id_78>",
|
| 240 |
"single_word": false,
|
| 241 |
"lstrip": false,
|
| 242 |
"rstrip": false,
|
| 243 |
+
"normalized": false
|
|
|
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"id": 32022,
|
| 247 |
+
"special": true,
|
| 248 |
"content": "<extra_id_77>",
|
| 249 |
"single_word": false,
|
| 250 |
"lstrip": false,
|
| 251 |
"rstrip": false,
|
| 252 |
+
"normalized": false
|
|
|
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"id": 32023,
|
| 256 |
+
"special": true,
|
| 257 |
"content": "<extra_id_76>",
|
| 258 |
"single_word": false,
|
| 259 |
"lstrip": false,
|
| 260 |
"rstrip": false,
|
| 261 |
+
"normalized": false
|
|
|
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"id": 32024,
|
| 265 |
+
"special": true,
|
| 266 |
"content": "<extra_id_75>",
|
| 267 |
"single_word": false,
|
| 268 |
"lstrip": false,
|
| 269 |
"rstrip": false,
|
| 270 |
+
"normalized": false
|
|
|
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"id": 32025,
|
| 274 |
+
"special": true,
|
| 275 |
"content": "<extra_id_74>",
|
| 276 |
"single_word": false,
|
| 277 |
"lstrip": false,
|
| 278 |
"rstrip": false,
|
| 279 |
+
"normalized": false
|
|
|
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"id": 32026,
|
| 283 |
+
"special": true,
|
| 284 |
"content": "<extra_id_73>",
|
| 285 |
"single_word": false,
|
| 286 |
"lstrip": false,
|
| 287 |
"rstrip": false,
|
| 288 |
+
"normalized": false
|
|
|
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"id": 32027,
|
| 292 |
+
"special": true,
|
| 293 |
"content": "<extra_id_72>",
|
| 294 |
"single_word": false,
|
| 295 |
"lstrip": false,
|
| 296 |
"rstrip": false,
|
| 297 |
+
"normalized": false
|
|
|
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"id": 32028,
|
| 301 |
+
"special": true,
|
| 302 |
"content": "<extra_id_71>",
|
| 303 |
"single_word": false,
|
| 304 |
"lstrip": false,
|
| 305 |
"rstrip": false,
|
| 306 |
+
"normalized": false
|
|
|
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"id": 32029,
|
| 310 |
+
"special": true,
|
| 311 |
"content": "<extra_id_70>",
|
| 312 |
"single_word": false,
|
| 313 |
"lstrip": false,
|
| 314 |
"rstrip": false,
|
| 315 |
+
"normalized": false
|
|
|
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"id": 32030,
|
| 319 |
+
"special": true,
|
| 320 |
"content": "<extra_id_69>",
|
| 321 |
"single_word": false,
|
| 322 |
"lstrip": false,
|
| 323 |
"rstrip": false,
|
| 324 |
+
"normalized": false
|
|
|
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"id": 32031,
|
| 328 |
+
"special": true,
|
| 329 |
"content": "<extra_id_68>",
|
| 330 |
"single_word": false,
|
| 331 |
"lstrip": false,
|
| 332 |
"rstrip": false,
|
| 333 |
+
"normalized": false
|
|
|
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"id": 32032,
|
| 337 |
+
"special": true,
|
| 338 |
"content": "<extra_id_67>",
|
| 339 |
"single_word": false,
|
| 340 |
"lstrip": false,
|
| 341 |
"rstrip": false,
|
| 342 |
+
"normalized": false
|
|
|
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"id": 32033,
|
| 346 |
+
"special": true,
|
| 347 |
"content": "<extra_id_66>",
|
| 348 |
"single_word": false,
|
| 349 |
"lstrip": false,
|
| 350 |
"rstrip": false,
|
| 351 |
+
"normalized": false
|
|
|
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"id": 32034,
|
| 355 |
+
"special": true,
|
| 356 |
"content": "<extra_id_65>",
|
| 357 |
"single_word": false,
|
| 358 |
"lstrip": false,
|
| 359 |
"rstrip": false,
|
| 360 |
+
"normalized": false
|
|
|
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"id": 32035,
|
| 364 |
+
"special": true,
|
| 365 |
"content": "<extra_id_64>",
|
| 366 |
"single_word": false,
|
| 367 |
"lstrip": false,
|
| 368 |
"rstrip": false,
|
| 369 |
+
"normalized": false
|
|
|
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"id": 32036,
|
| 373 |
+
"special": true,
|
| 374 |
"content": "<extra_id_63>",
|
| 375 |
"single_word": false,
|
| 376 |
"lstrip": false,
|
| 377 |
"rstrip": false,
|
| 378 |
+
"normalized": false
|
|
|
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"id": 32037,
|
| 382 |
+
"special": true,
|
| 383 |
"content": "<extra_id_62>",
|
| 384 |
"single_word": false,
|
| 385 |
"lstrip": false,
|
| 386 |
"rstrip": false,
|
| 387 |
+
"normalized": false
|
|
|
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"id": 32038,
|
| 391 |
+
"special": true,
|
| 392 |
"content": "<extra_id_61>",
|
| 393 |
"single_word": false,
|
| 394 |
"lstrip": false,
|
| 395 |
"rstrip": false,
|
| 396 |
+
"normalized": false
|
|
|
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"id": 32039,
|
| 400 |
+
"special": true,
|
| 401 |
"content": "<extra_id_60>",
|
| 402 |
"single_word": false,
|
| 403 |
"lstrip": false,
|
| 404 |
"rstrip": false,
|
| 405 |
+
"normalized": false
|
|
|
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"id": 32040,
|
| 409 |
+
"special": true,
|
| 410 |
"content": "<extra_id_59>",
|
| 411 |
"single_word": false,
|
| 412 |
"lstrip": false,
|
| 413 |
"rstrip": false,
|
| 414 |
+
"normalized": false
|
|
|
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"id": 32041,
|
| 418 |
+
"special": true,
|
| 419 |
"content": "<extra_id_58>",
|
| 420 |
"single_word": false,
|
| 421 |
"lstrip": false,
|
| 422 |
"rstrip": false,
|
| 423 |
+
"normalized": false
|
|
|
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"id": 32042,
|
| 427 |
+
"special": true,
|
| 428 |
"content": "<extra_id_57>",
|
| 429 |
"single_word": false,
|
| 430 |
"lstrip": false,
|
| 431 |
"rstrip": false,
|
| 432 |
+
"normalized": false
|
|
|
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"id": 32043,
|
| 436 |
+
"special": true,
|
| 437 |
"content": "<extra_id_56>",
|
| 438 |
"single_word": false,
|
| 439 |
"lstrip": false,
|
| 440 |
"rstrip": false,
|
| 441 |
+
"normalized": false
|
|
|
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"id": 32044,
|
| 445 |
+
"special": true,
|
| 446 |
"content": "<extra_id_55>",
|
| 447 |
"single_word": false,
|
| 448 |
"lstrip": false,
|
| 449 |
"rstrip": false,
|
| 450 |
+
"normalized": false
|
|
|
|
| 451 |
},
|
| 452 |
{
|
| 453 |
"id": 32045,
|
| 454 |
+
"special": true,
|
| 455 |
"content": "<extra_id_54>",
|
| 456 |
"single_word": false,
|
| 457 |
"lstrip": false,
|
| 458 |
"rstrip": false,
|
| 459 |
+
"normalized": false
|
|
|
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"id": 32046,
|
| 463 |
+
"special": true,
|
| 464 |
"content": "<extra_id_53>",
|
| 465 |
"single_word": false,
|
| 466 |
"lstrip": false,
|
| 467 |
"rstrip": false,
|
| 468 |
+
"normalized": false
|
|
|
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"id": 32047,
|
| 472 |
+
"special": true,
|
| 473 |
"content": "<extra_id_52>",
|
| 474 |
"single_word": false,
|
| 475 |
"lstrip": false,
|
| 476 |
"rstrip": false,
|
| 477 |
+
"normalized": false
|
|
|
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"id": 32048,
|
| 481 |
+
"special": true,
|
| 482 |
"content": "<extra_id_51>",
|
| 483 |
"single_word": false,
|
| 484 |
"lstrip": false,
|
| 485 |
"rstrip": false,
|
| 486 |
+
"normalized": false
|
|
|
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"id": 32049,
|
| 490 |
+
"special": true,
|
| 491 |
"content": "<extra_id_50>",
|
| 492 |
"single_word": false,
|
| 493 |
"lstrip": false,
|
| 494 |
"rstrip": false,
|
| 495 |
+
"normalized": false
|
|
|
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"id": 32050,
|
| 499 |
+
"special": true,
|
| 500 |
"content": "<extra_id_49>",
|
| 501 |
"single_word": false,
|
| 502 |
"lstrip": false,
|
| 503 |
"rstrip": false,
|
| 504 |
+
"normalized": false
|
|
|
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"id": 32051,
|
| 508 |
+
"special": true,
|
| 509 |
"content": "<extra_id_48>",
|
| 510 |
"single_word": false,
|
| 511 |
"lstrip": false,
|
| 512 |
"rstrip": false,
|
| 513 |
+
"normalized": false
|
|
|
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"id": 32052,
|
| 517 |
+
"special": true,
|
| 518 |
"content": "<extra_id_47>",
|
| 519 |
"single_word": false,
|
| 520 |
"lstrip": false,
|
| 521 |
"rstrip": false,
|
| 522 |
+
"normalized": false
|
|
|
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"id": 32053,
|
| 526 |
+
"special": true,
|
| 527 |
"content": "<extra_id_46>",
|
| 528 |
"single_word": false,
|
| 529 |
"lstrip": false,
|
| 530 |
"rstrip": false,
|
| 531 |
+
"normalized": false
|
|
|
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"id": 32054,
|
| 535 |
+
"special": true,
|
| 536 |
"content": "<extra_id_45>",
|
| 537 |
"single_word": false,
|
| 538 |
"lstrip": false,
|
| 539 |
"rstrip": false,
|
| 540 |
+
"normalized": false
|
|
|
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"id": 32055,
|
| 544 |
+
"special": true,
|
| 545 |
"content": "<extra_id_44>",
|
| 546 |
"single_word": false,
|
| 547 |
"lstrip": false,
|
| 548 |
"rstrip": false,
|
| 549 |
+
"normalized": false
|
|
|
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"id": 32056,
|
| 553 |
+
"special": true,
|
| 554 |
"content": "<extra_id_43>",
|
| 555 |
"single_word": false,
|
| 556 |
"lstrip": false,
|
| 557 |
"rstrip": false,
|
| 558 |
+
"normalized": false
|
|
|
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"id": 32057,
|
| 562 |
+
"special": true,
|
| 563 |
"content": "<extra_id_42>",
|
| 564 |
"single_word": false,
|
| 565 |
"lstrip": false,
|
| 566 |
"rstrip": false,
|
| 567 |
+
"normalized": false
|
|
|
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"id": 32058,
|
| 571 |
+
"special": true,
|
| 572 |
"content": "<extra_id_41>",
|
| 573 |
"single_word": false,
|
| 574 |
"lstrip": false,
|
| 575 |
"rstrip": false,
|
| 576 |
+
"normalized": false
|
|
|
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"id": 32059,
|
| 580 |
+
"special": true,
|
| 581 |
"content": "<extra_id_40>",
|
| 582 |
"single_word": false,
|
| 583 |
"lstrip": false,
|
| 584 |
"rstrip": false,
|
| 585 |
+
"normalized": false
|
|
|
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"id": 32060,
|
| 589 |
+
"special": true,
|
| 590 |
"content": "<extra_id_39>",
|
| 591 |
"single_word": false,
|
| 592 |
"lstrip": false,
|
| 593 |
"rstrip": false,
|
| 594 |
+
"normalized": false
|
|
|
|
| 595 |
},
|
| 596 |
{
|
| 597 |
"id": 32061,
|
| 598 |
+
"special": true,
|
| 599 |
"content": "<extra_id_38>",
|
| 600 |
"single_word": false,
|
| 601 |
"lstrip": false,
|
| 602 |
"rstrip": false,
|
| 603 |
+
"normalized": false
|
|
|
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"id": 32062,
|
| 607 |
+
"special": true,
|
| 608 |
"content": "<extra_id_37>",
|
| 609 |
"single_word": false,
|
| 610 |
"lstrip": false,
|
| 611 |
"rstrip": false,
|
| 612 |
+
"normalized": false
|
|
|
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"id": 32063,
|
| 616 |
+
"special": true,
|
| 617 |
"content": "<extra_id_36>",
|
| 618 |
"single_word": false,
|
| 619 |
"lstrip": false,
|
| 620 |
"rstrip": false,
|
| 621 |
+
"normalized": false
|
|
|
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"id": 32064,
|
| 625 |
+
"special": true,
|
| 626 |
"content": "<extra_id_35>",
|
| 627 |
"single_word": false,
|
| 628 |
"lstrip": false,
|
| 629 |
"rstrip": false,
|
| 630 |
+
"normalized": false
|
|
|
|
| 631 |
},
|
| 632 |
{
|
| 633 |
"id": 32065,
|
| 634 |
+
"special": true,
|
| 635 |
"content": "<extra_id_34>",
|
| 636 |
"single_word": false,
|
| 637 |
"lstrip": false,
|
| 638 |
"rstrip": false,
|
| 639 |
+
"normalized": false
|
|
|
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"id": 32066,
|
| 643 |
+
"special": true,
|
| 644 |
"content": "<extra_id_33>",
|
| 645 |
"single_word": false,
|
| 646 |
"lstrip": false,
|
| 647 |
"rstrip": false,
|
| 648 |
+
"normalized": false
|
|
|
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"id": 32067,
|
| 652 |
+
"special": true,
|
| 653 |
"content": "<extra_id_32>",
|
| 654 |
"single_word": false,
|
| 655 |
"lstrip": false,
|
| 656 |
"rstrip": false,
|
| 657 |
+
"normalized": false
|
|
|
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"id": 32068,
|
| 661 |
+
"special": true,
|
| 662 |
"content": "<extra_id_31>",
|
| 663 |
"single_word": false,
|
| 664 |
"lstrip": false,
|
| 665 |
"rstrip": false,
|
| 666 |
+
"normalized": false
|
|
|
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"id": 32069,
|
| 670 |
+
"special": true,
|
| 671 |
"content": "<extra_id_30>",
|
| 672 |
"single_word": false,
|
| 673 |
"lstrip": false,
|
| 674 |
"rstrip": false,
|
| 675 |
+
"normalized": false
|
|
|
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"id": 32070,
|
| 679 |
+
"special": true,
|
| 680 |
"content": "<extra_id_29>",
|
| 681 |
"single_word": false,
|
| 682 |
"lstrip": false,
|
| 683 |
"rstrip": false,
|
| 684 |
+
"normalized": false
|
|
|
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"id": 32071,
|
| 688 |
+
"special": true,
|
| 689 |
"content": "<extra_id_28>",
|
| 690 |
"single_word": false,
|
| 691 |
"lstrip": false,
|
| 692 |
"rstrip": false,
|
| 693 |
+
"normalized": false
|
|
|
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"id": 32072,
|
| 697 |
+
"special": true,
|
| 698 |
"content": "<extra_id_27>",
|
| 699 |
"single_word": false,
|
| 700 |
"lstrip": false,
|
| 701 |
"rstrip": false,
|
| 702 |
+
"normalized": false
|
|
|
|
| 703 |
},
|
| 704 |
{
|
| 705 |
"id": 32073,
|
| 706 |
+
"special": true,
|
| 707 |
"content": "<extra_id_26>",
|
| 708 |
"single_word": false,
|
| 709 |
"lstrip": false,
|
| 710 |
"rstrip": false,
|
| 711 |
+
"normalized": false
|
|
|
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"id": 32074,
|
| 715 |
+
"special": true,
|
| 716 |
"content": "<extra_id_25>",
|
| 717 |
"single_word": false,
|
| 718 |
"lstrip": false,
|
| 719 |
"rstrip": false,
|
| 720 |
+
"normalized": false
|
|
|
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"id": 32075,
|
| 724 |
+
"special": true,
|
| 725 |
"content": "<extra_id_24>",
|
| 726 |
"single_word": false,
|
| 727 |
"lstrip": false,
|
| 728 |
"rstrip": false,
|
| 729 |
+
"normalized": false
|
|
|
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"id": 32076,
|
| 733 |
+
"special": true,
|
| 734 |
"content": "<extra_id_23>",
|
| 735 |
"single_word": false,
|
| 736 |
"lstrip": false,
|
| 737 |
"rstrip": false,
|
| 738 |
+
"normalized": false
|
|
|
|
| 739 |
},
|
| 740 |
{
|
| 741 |
"id": 32077,
|
| 742 |
+
"special": true,
|
| 743 |
"content": "<extra_id_22>",
|
| 744 |
"single_word": false,
|
| 745 |
"lstrip": false,
|
| 746 |
"rstrip": false,
|
| 747 |
+
"normalized": false
|
|
|
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"id": 32078,
|
| 751 |
+
"special": true,
|
| 752 |
"content": "<extra_id_21>",
|
| 753 |
"single_word": false,
|
| 754 |
"lstrip": false,
|
| 755 |
"rstrip": false,
|
| 756 |
+
"normalized": false
|
|
|
|
| 757 |
},
|
| 758 |
{
|
| 759 |
"id": 32079,
|
| 760 |
+
"special": true,
|
| 761 |
"content": "<extra_id_20>",
|
| 762 |
"single_word": false,
|
| 763 |
"lstrip": false,
|
| 764 |
"rstrip": false,
|
| 765 |
+
"normalized": false
|
|
|
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"id": 32080,
|
| 769 |
+
"special": true,
|
| 770 |
"content": "<extra_id_19>",
|
| 771 |
"single_word": false,
|
| 772 |
"lstrip": false,
|
| 773 |
"rstrip": false,
|
| 774 |
+
"normalized": false
|
|
|
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"id": 32081,
|
| 778 |
+
"special": true,
|
| 779 |
"content": "<extra_id_18>",
|
| 780 |
"single_word": false,
|
| 781 |
"lstrip": false,
|
| 782 |
"rstrip": false,
|
| 783 |
+
"normalized": false
|
|
|
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"id": 32082,
|
| 787 |
+
"special": true,
|
| 788 |
"content": "<extra_id_17>",
|
| 789 |
"single_word": false,
|
| 790 |
"lstrip": false,
|
| 791 |
"rstrip": false,
|
| 792 |
+
"normalized": false
|
|
|
|
| 793 |
},
|
| 794 |
{
|
| 795 |
"id": 32083,
|
| 796 |
+
"special": true,
|
| 797 |
"content": "<extra_id_16>",
|
| 798 |
"single_word": false,
|
| 799 |
"lstrip": false,
|
| 800 |
"rstrip": false,
|
| 801 |
+
"normalized": false
|
|
|
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"id": 32084,
|
| 805 |
+
"special": true,
|
| 806 |
"content": "<extra_id_15>",
|
| 807 |
"single_word": false,
|
| 808 |
"lstrip": false,
|
| 809 |
"rstrip": false,
|
| 810 |
+
"normalized": false
|
|
|
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"id": 32085,
|
| 814 |
+
"special": true,
|
| 815 |
"content": "<extra_id_14>",
|
| 816 |
"single_word": false,
|
| 817 |
"lstrip": false,
|
| 818 |
"rstrip": false,
|
| 819 |
+
"normalized": false
|
|
|
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"id": 32086,
|
| 823 |
+
"special": true,
|
| 824 |
"content": "<extra_id_13>",
|
| 825 |
"single_word": false,
|
| 826 |
"lstrip": false,
|
| 827 |
"rstrip": false,
|
| 828 |
+
"normalized": false
|
|
|
|
| 829 |
},
|
| 830 |
{
|
| 831 |
"id": 32087,
|
| 832 |
+
"special": true,
|
| 833 |
"content": "<extra_id_12>",
|
| 834 |
"single_word": false,
|
| 835 |
"lstrip": false,
|
| 836 |
"rstrip": false,
|
| 837 |
+
"normalized": false
|
|
|
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"id": 32088,
|
| 841 |
+
"special": true,
|
| 842 |
"content": "<extra_id_11>",
|
| 843 |
"single_word": false,
|
| 844 |
"lstrip": false,
|
| 845 |
"rstrip": false,
|
| 846 |
+
"normalized": false
|
|
|
|
| 847 |
},
|
| 848 |
{
|
| 849 |
"id": 32089,
|
| 850 |
+
"special": true,
|
| 851 |
"content": "<extra_id_10>",
|
| 852 |
"single_word": false,
|
| 853 |
"lstrip": false,
|
| 854 |
"rstrip": false,
|
| 855 |
+
"normalized": false
|
|
|
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"id": 32090,
|
| 859 |
+
"special": true,
|
| 860 |
"content": "<extra_id_9>",
|
| 861 |
"single_word": false,
|
| 862 |
"lstrip": false,
|
| 863 |
"rstrip": false,
|
| 864 |
+
"normalized": false
|
|
|
|
| 865 |
},
|
| 866 |
{
|
| 867 |
"id": 32091,
|
| 868 |
+
"special": true,
|
| 869 |
"content": "<extra_id_8>",
|
| 870 |
"single_word": false,
|
| 871 |
"lstrip": false,
|
| 872 |
"rstrip": false,
|
| 873 |
+
"normalized": false
|
|
|
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"id": 32092,
|
| 877 |
+
"special": true,
|
| 878 |
"content": "<extra_id_7>",
|
| 879 |
"single_word": false,
|
| 880 |
"lstrip": false,
|
| 881 |
"rstrip": false,
|
| 882 |
+
"normalized": false
|
|
|
|
| 883 |
},
|
| 884 |
{
|
| 885 |
"id": 32093,
|
| 886 |
+
"special": true,
|
| 887 |
"content": "<extra_id_6>",
|
| 888 |
"single_word": false,
|
| 889 |
"lstrip": false,
|
| 890 |
"rstrip": false,
|
| 891 |
+
"normalized": false
|
|
|
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"id": 32094,
|
| 895 |
+
"special": true,
|
| 896 |
"content": "<extra_id_5>",
|
| 897 |
"single_word": false,
|
| 898 |
"lstrip": false,
|
| 899 |
"rstrip": false,
|
| 900 |
+
"normalized": false
|
|
|
|
| 901 |
},
|
| 902 |
{
|
| 903 |
"id": 32095,
|
| 904 |
+
"special": true,
|
| 905 |
"content": "<extra_id_4>",
|
| 906 |
"single_word": false,
|
| 907 |
"lstrip": false,
|
| 908 |
"rstrip": false,
|
| 909 |
+
"normalized": false
|
|
|
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"id": 32096,
|
| 913 |
+
"special": true,
|
| 914 |
"content": "<extra_id_3>",
|
| 915 |
"single_word": false,
|
| 916 |
"lstrip": false,
|
| 917 |
"rstrip": false,
|
| 918 |
+
"normalized": false
|
|
|
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"id": 32097,
|
| 922 |
+
"special": true,
|
| 923 |
"content": "<extra_id_2>",
|
| 924 |
"single_word": false,
|
| 925 |
"lstrip": false,
|
| 926 |
"rstrip": false,
|
| 927 |
+
"normalized": false
|
|
|
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"id": 32098,
|
| 931 |
+
"special": true,
|
| 932 |
"content": "<extra_id_1>",
|
| 933 |
"single_word": false,
|
| 934 |
"lstrip": false,
|
| 935 |
"rstrip": false,
|
| 936 |
+
"normalized": false
|
|
|
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"id": 32099,
|
| 940 |
+
"special": true,
|
| 941 |
"content": "<extra_id_0>",
|
| 942 |
"single_word": false,
|
| 943 |
"lstrip": false,
|
| 944 |
"rstrip": false,
|
| 945 |
+
"normalized": false
|
|
|
|
| 946 |
}
|
| 947 |
],
|
| 948 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -101,12 +101,13 @@
|
|
| 101 |
"<extra_id_98>",
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
| 104 |
-
"clean_up_tokenization_spaces": true,
|
| 105 |
"eos_token": "</s>",
|
| 106 |
"extra_ids": 100,
|
| 107 |
"model_max_length": 512,
|
|
|
|
| 108 |
"pad_token": "<pad>",
|
| 109 |
"sp_model_kwargs": {},
|
|
|
|
| 110 |
"tokenizer_class": "T5Tokenizer",
|
| 111 |
"unk_token": "<unk>"
|
| 112 |
}
|
|
|
|
| 101 |
"<extra_id_98>",
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
|
|
|
| 104 |
"eos_token": "</s>",
|
| 105 |
"extra_ids": 100,
|
| 106 |
"model_max_length": 512,
|
| 107 |
+
"name_or_path": "google/flan-t5-base",
|
| 108 |
"pad_token": "<pad>",
|
| 109 |
"sp_model_kwargs": {},
|
| 110 |
+
"special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-base/snapshots/650d7745bf1e502d6949b22cc19155cd656d3d4e/special_tokens_map.json",
|
| 111 |
"tokenizer_class": "T5Tokenizer",
|
| 112 |
"unk_token": "<unk>"
|
| 113 |
}
|
trainer_state.json
CHANGED
|
@@ -1,180 +1,770 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "flan-t5-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 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.
|
| 12 |
-
"learning_rate": 4.
|
| 13 |
-
"loss": 2.
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate": 4.
|
| 19 |
-
"loss": 1.
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate": 4.
|
| 25 |
-
"loss": 1.
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate": 4.
|
| 31 |
-
"loss": 1.
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate": 4.
|
| 37 |
-
"loss": 1.
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate": 4.
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"learning_rate": 4.
|
| 49 |
-
"loss": 1.
|
| 50 |
"step": 3500
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch": 0.
|
| 54 |
-
"learning_rate": 4.
|
| 55 |
-
"loss": 1.
|
| 56 |
"step": 4000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch": 0.
|
| 60 |
-
"learning_rate": 4.
|
| 61 |
-
"loss": 1.
|
| 62 |
"step": 4500
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch": 0.
|
| 66 |
-
"learning_rate": 4.
|
| 67 |
-
"loss": 1.
|
| 68 |
"step": 5000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch": 0
|
| 72 |
-
"
|
| 73 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
"step": 5500
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch": 1.
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"eval_rouge1": 52.0316,
|
| 81 |
-
"eval_rouge2": 33.7896,
|
| 82 |
-
"eval_rougeL": 49.2826,
|
| 83 |
-
"eval_rougeLsum": 49.8238,
|
| 84 |
-
"eval_runtime": 375.6869,
|
| 85 |
-
"eval_samples_per_second": 13.841,
|
| 86 |
-
"eval_steps_per_second": 1.73,
|
| 87 |
-
"step": 5851
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 1.03,
|
| 91 |
-
"learning_rate": 3.9745342676465566e-05,
|
| 92 |
-
"loss": 1.6711,
|
| 93 |
"step": 6000
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 1.
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"loss": 1.
|
| 99 |
"step": 6500
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 1.
|
| 103 |
-
"learning_rate":
|
| 104 |
-
"loss": 1.
|
| 105 |
"step": 7000
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 1.
|
| 109 |
-
"learning_rate":
|
| 110 |
-
"loss": 1.
|
| 111 |
"step": 7500
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch": 1.
|
| 115 |
-
"learning_rate":
|
| 116 |
-
"loss": 1.
|
| 117 |
"step": 8000
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch": 1.
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 1.
|
| 123 |
"step": 8500
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 1.
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss": 1.
|
| 129 |
"step": 9000
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 1.
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 1.
|
| 135 |
"step": 9500
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 1.
|
| 139 |
-
"learning_rate":
|
| 140 |
-
"loss": 1.
|
| 141 |
"step": 10000
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch":
|
| 145 |
-
"
|
| 146 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 147 |
"step": 10500
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch":
|
| 151 |
-
"learning_rate": 3.
|
| 152 |
-
"loss": 1.
|
| 153 |
"step": 11000
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch":
|
| 157 |
-
"learning_rate": 3.
|
| 158 |
-
"loss": 1.
|
| 159 |
"step": 11500
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 2.
|
| 163 |
-
"
|
| 164 |
-
"
|
| 165 |
-
"
|
| 166 |
-
|
| 167 |
-
|
| 168 |
-
"
|
| 169 |
-
"
|
| 170 |
-
"
|
| 171 |
-
"
|
| 172 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 173 |
}
|
| 174 |
],
|
| 175 |
-
"max_steps":
|
| 176 |
-
"num_train_epochs":
|
| 177 |
-
"total_flos":
|
| 178 |
"trial_name": null,
|
| 179 |
"trial_params": null
|
| 180 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.341736078262329,
|
| 3 |
+
"best_model_checkpoint": "./dual/flan-t5-base-dual/checkpoint-52010",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 52010,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 4.951932320707556e-05,
|
| 13 |
+
"loss": 2.0525,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.19,
|
| 18 |
+
"learning_rate": 4.903864641415113e-05,
|
| 19 |
+
"loss": 1.9359,
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.29,
|
| 24 |
+
"learning_rate": 4.855796962122669e-05,
|
| 25 |
+
"loss": 1.892,
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.38,
|
| 30 |
+
"learning_rate": 4.807729282830225e-05,
|
| 31 |
+
"loss": 1.8455,
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.48,
|
| 36 |
+
"learning_rate": 4.7596616035377816e-05,
|
| 37 |
+
"loss": 1.8273,
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.58,
|
| 42 |
+
"learning_rate": 4.7115939242453377e-05,
|
| 43 |
+
"loss": 1.8317,
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.67,
|
| 48 |
+
"learning_rate": 4.663526244952894e-05,
|
| 49 |
+
"loss": 1.8103,
|
| 50 |
"step": 3500
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.77,
|
| 54 |
+
"learning_rate": 4.61545856566045e-05,
|
| 55 |
+
"loss": 1.8032,
|
| 56 |
"step": 4000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 0.87,
|
| 60 |
+
"learning_rate": 4.5673908863680064e-05,
|
| 61 |
+
"loss": 1.7842,
|
| 62 |
"step": 4500
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 0.96,
|
| 66 |
+
"learning_rate": 4.5193232070755624e-05,
|
| 67 |
+
"loss": 1.7674,
|
| 68 |
"step": 5000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 1.0,
|
| 72 |
+
"eval_gen_len": 16.8,
|
| 73 |
+
"eval_loss": 1.4587862491607666,
|
| 74 |
+
"eval_rouge1": 43.5356,
|
| 75 |
+
"eval_rouge2": 25.8338,
|
| 76 |
+
"eval_rougeL": 41.1764,
|
| 77 |
+
"eval_rougeLsum": 41.816,
|
| 78 |
+
"eval_runtime": 629.4032,
|
| 79 |
+
"eval_samples_per_second": 16.524,
|
| 80 |
+
"eval_steps_per_second": 1.033,
|
| 81 |
+
"step": 5201
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.06,
|
| 85 |
+
"learning_rate": 4.4712555277831184e-05,
|
| 86 |
+
"loss": 1.7405,
|
| 87 |
"step": 5500
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 1.15,
|
| 91 |
+
"learning_rate": 4.423187848490675e-05,
|
| 92 |
+
"loss": 1.7135,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
"step": 6000
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 1.25,
|
| 97 |
+
"learning_rate": 4.375120169198231e-05,
|
| 98 |
+
"loss": 1.7161,
|
| 99 |
"step": 6500
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 1.35,
|
| 103 |
+
"learning_rate": 4.327052489905787e-05,
|
| 104 |
+
"loss": 1.7208,
|
| 105 |
"step": 7000
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 1.44,
|
| 109 |
+
"learning_rate": 4.278984810613344e-05,
|
| 110 |
+
"loss": 1.6999,
|
| 111 |
"step": 7500
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 1.54,
|
| 115 |
+
"learning_rate": 4.2309171313209e-05,
|
| 116 |
+
"loss": 1.694,
|
| 117 |
"step": 8000
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 1.63,
|
| 121 |
+
"learning_rate": 4.182849452028456e-05,
|
| 122 |
+
"loss": 1.6837,
|
| 123 |
"step": 8500
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 1.73,
|
| 127 |
+
"learning_rate": 4.1347817727360125e-05,
|
| 128 |
+
"loss": 1.6892,
|
| 129 |
"step": 9000
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 1.83,
|
| 133 |
+
"learning_rate": 4.0867140934435685e-05,
|
| 134 |
+
"loss": 1.6811,
|
| 135 |
"step": 9500
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 1.92,
|
| 139 |
+
"learning_rate": 4.038646414151125e-05,
|
| 140 |
+
"loss": 1.7004,
|
| 141 |
"step": 10000
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 2.0,
|
| 145 |
+
"eval_gen_len": 16.87192307692308,
|
| 146 |
+
"eval_loss": 1.4108598232269287,
|
| 147 |
+
"eval_rouge1": 44.1953,
|
| 148 |
+
"eval_rouge2": 26.6443,
|
| 149 |
+
"eval_rougeL": 41.7387,
|
| 150 |
+
"eval_rougeLsum": 42.3745,
|
| 151 |
+
"eval_runtime": 674.3077,
|
| 152 |
+
"eval_samples_per_second": 15.423,
|
| 153 |
+
"eval_steps_per_second": 0.964,
|
| 154 |
+
"step": 10402
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.02,
|
| 158 |
+
"learning_rate": 3.990578734858681e-05,
|
| 159 |
+
"loss": 1.6572,
|
| 160 |
"step": 10500
|
| 161 |
},
|
| 162 |
{
|
| 163 |
+
"epoch": 2.11,
|
| 164 |
+
"learning_rate": 3.942511055566238e-05,
|
| 165 |
+
"loss": 1.6449,
|
| 166 |
"step": 11000
|
| 167 |
},
|
| 168 |
{
|
| 169 |
+
"epoch": 2.21,
|
| 170 |
+
"learning_rate": 3.894443376273794e-05,
|
| 171 |
+
"loss": 1.6235,
|
| 172 |
"step": 11500
|
| 173 |
},
|
| 174 |
{
|
| 175 |
+
"epoch": 2.31,
|
| 176 |
+
"learning_rate": 3.84637569698135e-05,
|
| 177 |
+
"loss": 1.6573,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.4,
|
| 182 |
+
"learning_rate": 3.7983080176889066e-05,
|
| 183 |
+
"loss": 1.6262,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.5,
|
| 188 |
+
"learning_rate": 3.7502403383964626e-05,
|
| 189 |
+
"loss": 1.6377,
|
| 190 |
+
"step": 13000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.6,
|
| 194 |
+
"learning_rate": 3.7021726591040186e-05,
|
| 195 |
+
"loss": 1.6407,
|
| 196 |
+
"step": 13500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.69,
|
| 200 |
+
"learning_rate": 3.654104979811575e-05,
|
| 201 |
+
"loss": 1.6343,
|
| 202 |
+
"step": 14000
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.79,
|
| 206 |
+
"learning_rate": 3.606037300519131e-05,
|
| 207 |
+
"loss": 1.6221,
|
| 208 |
+
"step": 14500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.88,
|
| 212 |
+
"learning_rate": 3.557969621226687e-05,
|
| 213 |
+
"loss": 1.6127,
|
| 214 |
+
"step": 15000
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 2.98,
|
| 218 |
+
"learning_rate": 3.509901941934244e-05,
|
| 219 |
+
"loss": 1.622,
|
| 220 |
+
"step": 15500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.0,
|
| 224 |
+
"eval_gen_len": 16.911923076923078,
|
| 225 |
+
"eval_loss": 1.387160301208496,
|
| 226 |
+
"eval_rouge1": 44.6617,
|
| 227 |
+
"eval_rouge2": 27.2456,
|
| 228 |
+
"eval_rougeL": 42.2185,
|
| 229 |
+
"eval_rougeLsum": 42.8309,
|
| 230 |
+
"eval_runtime": 678.3822,
|
| 231 |
+
"eval_samples_per_second": 15.331,
|
| 232 |
+
"eval_steps_per_second": 0.958,
|
| 233 |
+
"step": 15603
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.08,
|
| 237 |
+
"learning_rate": 3.4618342626418e-05,
|
| 238 |
+
"loss": 1.5886,
|
| 239 |
+
"step": 16000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.17,
|
| 243 |
+
"learning_rate": 3.413766583349356e-05,
|
| 244 |
+
"loss": 1.5913,
|
| 245 |
+
"step": 16500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.27,
|
| 249 |
+
"learning_rate": 3.365698904056912e-05,
|
| 250 |
+
"loss": 1.5693,
|
| 251 |
+
"step": 17000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.36,
|
| 255 |
+
"learning_rate": 3.317631224764469e-05,
|
| 256 |
+
"loss": 1.5781,
|
| 257 |
+
"step": 17500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.46,
|
| 261 |
+
"learning_rate": 3.269563545472025e-05,
|
| 262 |
+
"loss": 1.5944,
|
| 263 |
+
"step": 18000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.56,
|
| 267 |
+
"learning_rate": 3.221495866179581e-05,
|
| 268 |
+
"loss": 1.5671,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.65,
|
| 273 |
+
"learning_rate": 3.1734281868871374e-05,
|
| 274 |
+
"loss": 1.5979,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.75,
|
| 279 |
+
"learning_rate": 3.1253605075946935e-05,
|
| 280 |
+
"loss": 1.6014,
|
| 281 |
+
"step": 19500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.85,
|
| 285 |
+
"learning_rate": 3.0772928283022495e-05,
|
| 286 |
+
"loss": 1.5929,
|
| 287 |
+
"step": 20000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.94,
|
| 291 |
+
"learning_rate": 3.029225149009806e-05,
|
| 292 |
+
"loss": 1.5822,
|
| 293 |
+
"step": 20500
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 4.0,
|
| 297 |
+
"eval_gen_len": 16.976153846153846,
|
| 298 |
+
"eval_loss": 1.3675929307937622,
|
| 299 |
+
"eval_rouge1": 44.7885,
|
| 300 |
+
"eval_rouge2": 27.4914,
|
| 301 |
+
"eval_rougeL": 42.3527,
|
| 302 |
+
"eval_rougeLsum": 42.9959,
|
| 303 |
+
"eval_runtime": 672.7849,
|
| 304 |
+
"eval_samples_per_second": 15.458,
|
| 305 |
+
"eval_steps_per_second": 0.966,
|
| 306 |
+
"step": 20804
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 4.04,
|
| 310 |
+
"learning_rate": 2.981157469717362e-05,
|
| 311 |
+
"loss": 1.5658,
|
| 312 |
+
"step": 21000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 4.13,
|
| 316 |
+
"learning_rate": 2.9330897904249182e-05,
|
| 317 |
+
"loss": 1.5656,
|
| 318 |
+
"step": 21500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 4.23,
|
| 322 |
+
"learning_rate": 2.885022111132475e-05,
|
| 323 |
+
"loss": 1.5643,
|
| 324 |
+
"step": 22000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.33,
|
| 328 |
+
"learning_rate": 2.836954431840031e-05,
|
| 329 |
+
"loss": 1.5484,
|
| 330 |
+
"step": 22500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 4.42,
|
| 334 |
+
"learning_rate": 2.788886752547587e-05,
|
| 335 |
+
"loss": 1.5504,
|
| 336 |
+
"step": 23000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 4.52,
|
| 340 |
+
"learning_rate": 2.7408190732551436e-05,
|
| 341 |
+
"loss": 1.5546,
|
| 342 |
+
"step": 23500
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 4.61,
|
| 346 |
+
"learning_rate": 2.6927513939626996e-05,
|
| 347 |
+
"loss": 1.556,
|
| 348 |
+
"step": 24000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 4.71,
|
| 352 |
+
"learning_rate": 2.644683714670256e-05,
|
| 353 |
+
"loss": 1.5448,
|
| 354 |
+
"step": 24500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 4.81,
|
| 358 |
+
"learning_rate": 2.596616035377812e-05,
|
| 359 |
+
"loss": 1.5519,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.9,
|
| 364 |
+
"learning_rate": 2.5485483560853686e-05,
|
| 365 |
+
"loss": 1.5606,
|
| 366 |
+
"step": 25500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 5.0,
|
| 370 |
+
"learning_rate": 2.5004806767929246e-05,
|
| 371 |
+
"loss": 1.5541,
|
| 372 |
+
"step": 26000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 5.0,
|
| 376 |
+
"eval_gen_len": 17.028846153846153,
|
| 377 |
+
"eval_loss": 1.3574897050857544,
|
| 378 |
+
"eval_rouge1": 44.7589,
|
| 379 |
+
"eval_rouge2": 27.4697,
|
| 380 |
+
"eval_rougeL": 42.3549,
|
| 381 |
+
"eval_rougeLsum": 42.9704,
|
| 382 |
+
"eval_runtime": 665.8005,
|
| 383 |
+
"eval_samples_per_second": 15.62,
|
| 384 |
+
"eval_steps_per_second": 0.976,
|
| 385 |
+
"step": 26005
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 5.1,
|
| 389 |
+
"learning_rate": 2.452412997500481e-05,
|
| 390 |
+
"loss": 1.5154,
|
| 391 |
+
"step": 26500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 5.19,
|
| 395 |
+
"learning_rate": 2.404345318208037e-05,
|
| 396 |
+
"loss": 1.5163,
|
| 397 |
+
"step": 27000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 5.29,
|
| 401 |
+
"learning_rate": 2.3562776389155933e-05,
|
| 402 |
+
"loss": 1.5176,
|
| 403 |
+
"step": 27500
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 5.38,
|
| 407 |
+
"learning_rate": 2.3082099596231497e-05,
|
| 408 |
+
"loss": 1.5293,
|
| 409 |
+
"step": 28000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 5.48,
|
| 413 |
+
"learning_rate": 2.2601422803307057e-05,
|
| 414 |
+
"loss": 1.5237,
|
| 415 |
+
"step": 28500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 5.58,
|
| 419 |
+
"learning_rate": 2.212074601038262e-05,
|
| 420 |
+
"loss": 1.5422,
|
| 421 |
+
"step": 29000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 5.67,
|
| 425 |
+
"learning_rate": 2.164006921745818e-05,
|
| 426 |
+
"loss": 1.5309,
|
| 427 |
+
"step": 29500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 5.77,
|
| 431 |
+
"learning_rate": 2.1159392424533744e-05,
|
| 432 |
+
"loss": 1.5296,
|
| 433 |
+
"step": 30000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 5.86,
|
| 437 |
+
"learning_rate": 2.0678715631609308e-05,
|
| 438 |
+
"loss": 1.5137,
|
| 439 |
+
"step": 30500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 5.96,
|
| 443 |
+
"learning_rate": 2.0198038838684868e-05,
|
| 444 |
+
"loss": 1.5116,
|
| 445 |
+
"step": 31000
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 6.0,
|
| 449 |
+
"eval_gen_len": 16.991923076923076,
|
| 450 |
+
"eval_loss": 1.3511042594909668,
|
| 451 |
+
"eval_rouge1": 45.0017,
|
| 452 |
+
"eval_rouge2": 27.6906,
|
| 453 |
+
"eval_rougeL": 42.5834,
|
| 454 |
+
"eval_rougeLsum": 43.2073,
|
| 455 |
+
"eval_runtime": 658.0426,
|
| 456 |
+
"eval_samples_per_second": 15.804,
|
| 457 |
+
"eval_steps_per_second": 0.988,
|
| 458 |
+
"step": 31206
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 6.06,
|
| 462 |
+
"learning_rate": 1.971736204576043e-05,
|
| 463 |
+
"loss": 1.5018,
|
| 464 |
+
"step": 31500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 6.15,
|
| 468 |
+
"learning_rate": 1.9236685252835995e-05,
|
| 469 |
+
"loss": 1.5037,
|
| 470 |
+
"step": 32000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 6.25,
|
| 474 |
+
"learning_rate": 1.8756008459911555e-05,
|
| 475 |
+
"loss": 1.4991,
|
| 476 |
+
"step": 32500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 6.34,
|
| 480 |
+
"learning_rate": 1.8275331666987118e-05,
|
| 481 |
+
"loss": 1.4977,
|
| 482 |
+
"step": 33000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 6.44,
|
| 486 |
+
"learning_rate": 1.779465487406268e-05,
|
| 487 |
+
"loss": 1.5024,
|
| 488 |
+
"step": 33500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 6.54,
|
| 492 |
+
"learning_rate": 1.7313978081138242e-05,
|
| 493 |
+
"loss": 1.5043,
|
| 494 |
+
"step": 34000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 6.63,
|
| 498 |
+
"learning_rate": 1.6833301288213805e-05,
|
| 499 |
+
"loss": 1.506,
|
| 500 |
+
"step": 34500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 6.73,
|
| 504 |
+
"learning_rate": 1.635262449528937e-05,
|
| 505 |
+
"loss": 1.497,
|
| 506 |
+
"step": 35000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 6.83,
|
| 510 |
+
"learning_rate": 1.5871947702364932e-05,
|
| 511 |
+
"loss": 1.5132,
|
| 512 |
+
"step": 35500
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 6.92,
|
| 516 |
+
"learning_rate": 1.5391270909440492e-05,
|
| 517 |
+
"loss": 1.5079,
|
| 518 |
+
"step": 36000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 7.0,
|
| 522 |
+
"eval_gen_len": 16.982019230769232,
|
| 523 |
+
"eval_loss": 1.347075343132019,
|
| 524 |
+
"eval_rouge1": 44.9759,
|
| 525 |
+
"eval_rouge2": 27.7179,
|
| 526 |
+
"eval_rougeL": 42.5719,
|
| 527 |
+
"eval_rougeLsum": 43.1803,
|
| 528 |
+
"eval_runtime": 667.8543,
|
| 529 |
+
"eval_samples_per_second": 15.572,
|
| 530 |
+
"eval_steps_per_second": 0.973,
|
| 531 |
+
"step": 36407
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 7.02,
|
| 535 |
+
"learning_rate": 1.4910594116516054e-05,
|
| 536 |
+
"loss": 1.5017,
|
| 537 |
+
"step": 36500
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 7.11,
|
| 541 |
+
"learning_rate": 1.4429917323591618e-05,
|
| 542 |
+
"loss": 1.4946,
|
| 543 |
+
"step": 37000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 7.21,
|
| 547 |
+
"learning_rate": 1.394924053066718e-05,
|
| 548 |
+
"loss": 1.4941,
|
| 549 |
+
"step": 37500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 7.31,
|
| 553 |
+
"learning_rate": 1.3468563737742743e-05,
|
| 554 |
+
"loss": 1.5029,
|
| 555 |
+
"step": 38000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 7.4,
|
| 559 |
+
"learning_rate": 1.2987886944818307e-05,
|
| 560 |
+
"loss": 1.4855,
|
| 561 |
+
"step": 38500
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 7.5,
|
| 565 |
+
"learning_rate": 1.2507210151893867e-05,
|
| 566 |
+
"loss": 1.4726,
|
| 567 |
+
"step": 39000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 7.59,
|
| 571 |
+
"learning_rate": 1.202653335896943e-05,
|
| 572 |
+
"loss": 1.4687,
|
| 573 |
+
"step": 39500
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 7.69,
|
| 577 |
+
"learning_rate": 1.1545856566044992e-05,
|
| 578 |
+
"loss": 1.4915,
|
| 579 |
+
"step": 40000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 7.79,
|
| 583 |
+
"learning_rate": 1.1065179773120554e-05,
|
| 584 |
+
"loss": 1.4793,
|
| 585 |
+
"step": 40500
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 7.88,
|
| 589 |
+
"learning_rate": 1.0584502980196116e-05,
|
| 590 |
+
"loss": 1.4818,
|
| 591 |
+
"step": 41000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 7.98,
|
| 595 |
+
"learning_rate": 1.0103826187271679e-05,
|
| 596 |
+
"loss": 1.4771,
|
| 597 |
+
"step": 41500
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 8.0,
|
| 601 |
+
"eval_gen_len": 16.986923076923077,
|
| 602 |
+
"eval_loss": 1.3443900346755981,
|
| 603 |
+
"eval_rouge1": 45.2057,
|
| 604 |
+
"eval_rouge2": 27.9779,
|
| 605 |
+
"eval_rougeL": 42.7648,
|
| 606 |
+
"eval_rougeLsum": 43.3885,
|
| 607 |
+
"eval_runtime": 559.194,
|
| 608 |
+
"eval_samples_per_second": 18.598,
|
| 609 |
+
"eval_steps_per_second": 1.162,
|
| 610 |
+
"step": 41608
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 8.08,
|
| 614 |
+
"learning_rate": 9.623149394347242e-06,
|
| 615 |
+
"loss": 1.4658,
|
| 616 |
+
"step": 42000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 8.17,
|
| 620 |
+
"learning_rate": 9.142472601422804e-06,
|
| 621 |
+
"loss": 1.469,
|
| 622 |
+
"step": 42500
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 8.27,
|
| 626 |
+
"learning_rate": 8.661795808498366e-06,
|
| 627 |
+
"loss": 1.4966,
|
| 628 |
+
"step": 43000
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 8.36,
|
| 632 |
+
"learning_rate": 8.181119015573928e-06,
|
| 633 |
+
"loss": 1.4691,
|
| 634 |
+
"step": 43500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 8.46,
|
| 638 |
+
"learning_rate": 7.700442222649491e-06,
|
| 639 |
+
"loss": 1.4767,
|
| 640 |
+
"step": 44000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 8.56,
|
| 644 |
+
"learning_rate": 7.219765429725053e-06,
|
| 645 |
+
"loss": 1.4875,
|
| 646 |
+
"step": 44500
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 8.65,
|
| 650 |
+
"learning_rate": 6.739088636800615e-06,
|
| 651 |
+
"loss": 1.473,
|
| 652 |
+
"step": 45000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 8.75,
|
| 656 |
+
"learning_rate": 6.258411843876178e-06,
|
| 657 |
+
"loss": 1.4826,
|
| 658 |
+
"step": 45500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 8.84,
|
| 662 |
+
"learning_rate": 5.77773505095174e-06,
|
| 663 |
+
"loss": 1.4683,
|
| 664 |
+
"step": 46000
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 8.94,
|
| 668 |
+
"learning_rate": 5.297058258027303e-06,
|
| 669 |
+
"loss": 1.4691,
|
| 670 |
+
"step": 46500
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 9.0,
|
| 674 |
+
"eval_gen_len": 16.951634615384616,
|
| 675 |
+
"eval_loss": 1.3431836366653442,
|
| 676 |
+
"eval_rouge1": 45.197,
|
| 677 |
+
"eval_rouge2": 27.8923,
|
| 678 |
+
"eval_rougeL": 42.7387,
|
| 679 |
+
"eval_rougeLsum": 43.3577,
|
| 680 |
+
"eval_runtime": 562.3582,
|
| 681 |
+
"eval_samples_per_second": 18.494,
|
| 682 |
+
"eval_steps_per_second": 1.156,
|
| 683 |
+
"step": 46809
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 9.04,
|
| 687 |
+
"learning_rate": 4.816381465102865e-06,
|
| 688 |
+
"loss": 1.4663,
|
| 689 |
+
"step": 47000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 9.13,
|
| 693 |
+
"learning_rate": 4.335704672178427e-06,
|
| 694 |
+
"loss": 1.4658,
|
| 695 |
+
"step": 47500
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 9.23,
|
| 699 |
+
"learning_rate": 3.85502787925399e-06,
|
| 700 |
+
"loss": 1.4679,
|
| 701 |
+
"step": 48000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 9.33,
|
| 705 |
+
"learning_rate": 3.3743510863295526e-06,
|
| 706 |
+
"loss": 1.4573,
|
| 707 |
+
"step": 48500
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 9.42,
|
| 711 |
+
"learning_rate": 2.8936742934051144e-06,
|
| 712 |
+
"loss": 1.465,
|
| 713 |
+
"step": 49000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 9.52,
|
| 717 |
+
"learning_rate": 2.412997500480677e-06,
|
| 718 |
+
"loss": 1.4582,
|
| 719 |
+
"step": 49500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 9.61,
|
| 723 |
+
"learning_rate": 1.9323207075562393e-06,
|
| 724 |
+
"loss": 1.4736,
|
| 725 |
+
"step": 50000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 9.71,
|
| 729 |
+
"learning_rate": 1.4516439146318017e-06,
|
| 730 |
+
"loss": 1.4768,
|
| 731 |
+
"step": 50500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 9.81,
|
| 735 |
+
"learning_rate": 9.70967121707364e-07,
|
| 736 |
+
"loss": 1.4634,
|
| 737 |
+
"step": 51000
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 9.9,
|
| 741 |
+
"learning_rate": 4.902903287829264e-07,
|
| 742 |
+
"loss": 1.4832,
|
| 743 |
+
"step": 51500
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 10.0,
|
| 747 |
+
"learning_rate": 9.613535858488752e-09,
|
| 748 |
+
"loss": 1.4719,
|
| 749 |
+
"step": 52000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 10.0,
|
| 753 |
+
"eval_gen_len": 16.988557692307694,
|
| 754 |
+
"eval_loss": 1.341736078262329,
|
| 755 |
+
"eval_rouge1": 45.2143,
|
| 756 |
+
"eval_rouge2": 27.9673,
|
| 757 |
+
"eval_rougeL": 42.7712,
|
| 758 |
+
"eval_rougeLsum": 43.3892,
|
| 759 |
+
"eval_runtime": 603.039,
|
| 760 |
+
"eval_samples_per_second": 17.246,
|
| 761 |
+
"eval_steps_per_second": 1.078,
|
| 762 |
+
"step": 52010
|
| 763 |
}
|
| 764 |
],
|
| 765 |
+
"max_steps": 52010,
|
| 766 |
+
"num_train_epochs": 10,
|
| 767 |
+
"total_flos": 5.697455075308339e+17,
|
| 768 |
"trial_name": null,
|
| 769 |
"trial_params": null
|
| 770 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0329604d8f92dab1fae265c51697fbf1309edc89ed828f2774dd8a76c9fa7dad
|
| 3 |
+
size 3567
|