riken01 commited on
Commit
b121009
1 Parent(s): 91c5dc4

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - text2text-generation
6
+ base_model: google/flan-t5-base
7
+ widget:
8
+ - text: "I love AutoTrain"
9
+ ---
10
+
11
+ # Model Trained Using AutoTrain
12
+
13
+ - Problem type: Seq2Seq
14
+
15
+ ## Validation Metrics
16
+ loss: nan
17
+
18
+ rouge1: 13.2945
19
+
20
+ rouge2: 3.5623
21
+
22
+ rougeL: 12.4291
23
+
24
+ rougeLsum: 12.5471
25
+
26
+ gen_len: 12.915
27
+
28
+ runtime: 123.248
29
+
30
+ samples_per_second: 9.063
31
+
32
+ steps_per_second: 2.272
33
+
34
+ : 3.0
checkpoint-4469/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "tie_word_embeddings": false,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.41.0",
60
+ "use_cache": false,
61
+ "vocab_size": 32128
62
+ }
checkpoint-4469/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.41.0"
6
+ }
checkpoint-4469/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197b346658905cda50c1a71fe0eb77a4d79306adaeb5d7a3c0e9208c91022d45
3
+ size 990345064
checkpoint-4469/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eb2f6ff914c04e2e49919f9e6c838d22c1af95bb4f466a355c1debcff48d57c
3
+ size 1832
checkpoint-4469/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0717baaab0d0ec27adf7c58f830af2339fb55c668299e867c44596ed945586ed
3
+ size 14244
checkpoint-4469/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0198810671b0700993e71dcd3ab8f6012bbc4e3080ccb33efdc560594fe4262d
3
+ size 1064
checkpoint-4469/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
checkpoint-4469/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-4469/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4469/tokenizer_config.json ADDED
@@ -0,0 +1,938 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<extra_id_99>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<extra_id_98>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "<extra_id_97>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "<extra_id_96>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32004": {
60
+ "content": "<extra_id_95>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32005": {
68
+ "content": "<extra_id_94>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32006": {
76
+ "content": "<extra_id_93>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "32007": {
84
+ "content": "<extra_id_92>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "32008": {
92
+ "content": "<extra_id_91>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "32009": {
100
+ "content": "<extra_id_90>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "32010": {
108
+ "content": "<extra_id_89>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "32011": {
116
+ "content": "<extra_id_88>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "32012": {
124
+ "content": "<extra_id_87>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "32013": {
132
+ "content": "<extra_id_86>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "32014": {
140
+ "content": "<extra_id_85>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "32015": {
148
+ "content": "<extra_id_84>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "32016": {
156
+ "content": "<extra_id_83>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "32017": {
164
+ "content": "<extra_id_82>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "32018": {
172
+ "content": "<extra_id_81>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "32019": {
180
+ "content": "<extra_id_80>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "32020": {
188
+ "content": "<extra_id_79>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "32021": {
196
+ "content": "<extra_id_78>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "32022": {
204
+ "content": "<extra_id_77>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "32023": {
212
+ "content": "<extra_id_76>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "32024": {
220
+ "content": "<extra_id_75>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "32025": {
228
+ "content": "<extra_id_74>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "32026": {
236
+ "content": "<extra_id_73>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32027": {
244
+ "content": "<extra_id_72>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "32028": {
252
+ "content": "<extra_id_71>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32029": {
260
+ "content": "<extra_id_70>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "32030": {
268
+ "content": "<extra_id_69>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "32031": {
276
+ "content": "<extra_id_68>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "32032": {
284
+ "content": "<extra_id_67>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "32033": {
292
+ "content": "<extra_id_66>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "32034": {
300
+ "content": "<extra_id_65>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "32035": {
308
+ "content": "<extra_id_64>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "32036": {
316
+ "content": "<extra_id_63>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "32037": {
324
+ "content": "<extra_id_62>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "32038": {
332
+ "content": "<extra_id_61>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "32039": {
340
+ "content": "<extra_id_60>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "32040": {
348
+ "content": "<extra_id_59>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "32041": {
356
+ "content": "<extra_id_58>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "32042": {
364
+ "content": "<extra_id_57>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "32043": {
372
+ "content": "<extra_id_56>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "32044": {
380
+ "content": "<extra_id_55>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "32045": {
388
+ "content": "<extra_id_54>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "32046": {
396
+ "content": "<extra_id_53>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "32047": {
404
+ "content": "<extra_id_52>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "32048": {
412
+ "content": "<extra_id_51>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "32049": {
420
+ "content": "<extra_id_50>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "32050": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "32051": {
436
+ "content": "<extra_id_48>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "32052": {
444
+ "content": "<extra_id_47>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "32053": {
452
+ "content": "<extra_id_46>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "32054": {
460
+ "content": "<extra_id_45>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "32055": {
468
+ "content": "<extra_id_44>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "32056": {
476
+ "content": "<extra_id_43>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "32057": {
484
+ "content": "<extra_id_42>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "32058": {
492
+ "content": "<extra_id_41>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "32059": {
500
+ "content": "<extra_id_40>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "32060": {
508
+ "content": "<extra_id_39>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "32061": {
516
+ "content": "<extra_id_38>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "32062": {
524
+ "content": "<extra_id_37>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "32063": {
532
+ "content": "<extra_id_36>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "32064": {
540
+ "content": "<extra_id_35>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "32065": {
548
+ "content": "<extra_id_34>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "32066": {
556
+ "content": "<extra_id_33>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "32067": {
564
+ "content": "<extra_id_32>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "32068": {
572
+ "content": "<extra_id_31>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "32069": {
580
+ "content": "<extra_id_30>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "32070": {
588
+ "content": "<extra_id_29>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "32071": {
596
+ "content": "<extra_id_28>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "32072": {
604
+ "content": "<extra_id_27>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "32073": {
612
+ "content": "<extra_id_26>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "32074": {
620
+ "content": "<extra_id_25>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "32075": {
628
+ "content": "<extra_id_24>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "32076": {
636
+ "content": "<extra_id_23>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "32077": {
644
+ "content": "<extra_id_22>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "32078": {
652
+ "content": "<extra_id_21>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "32079": {
660
+ "content": "<extra_id_20>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "32080": {
668
+ "content": "<extra_id_19>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "32081": {
676
+ "content": "<extra_id_18>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "32082": {
684
+ "content": "<extra_id_17>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "32083": {
692
+ "content": "<extra_id_16>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "32084": {
700
+ "content": "<extra_id_15>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "32085": {
708
+ "content": "<extra_id_14>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "32086": {
716
+ "content": "<extra_id_13>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "32087": {
724
+ "content": "<extra_id_12>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "32088": {
732
+ "content": "<extra_id_11>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "32089": {
740
+ "content": "<extra_id_10>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "32090": {
748
+ "content": "<extra_id_9>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "32091": {
756
+ "content": "<extra_id_8>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "32092": {
764
+ "content": "<extra_id_7>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "32093": {
772
+ "content": "<extra_id_6>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "32094": {
780
+ "content": "<extra_id_5>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "32095": {
788
+ "content": "<extra_id_4>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "32096": {
796
+ "content": "<extra_id_3>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "32097": {
804
+ "content": "<extra_id_2>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "32098": {
812
+ "content": "<extra_id_1>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "32099": {
820
+ "content": "<extra_id_0>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ }
827
+ },
828
+ "additional_special_tokens": [
829
+ "<extra_id_0>",
830
+ "<extra_id_1>",
831
+ "<extra_id_2>",
832
+ "<extra_id_3>",
833
+ "<extra_id_4>",
834
+ "<extra_id_5>",
835
+ "<extra_id_6>",
836
+ "<extra_id_7>",
837
+ "<extra_id_8>",
838
+ "<extra_id_9>",
839
+ "<extra_id_10>",
840
+ "<extra_id_11>",
841
+ "<extra_id_12>",
842
+ "<extra_id_13>",
843
+ "<extra_id_14>",
844
+ "<extra_id_15>",
845
+ "<extra_id_16>",
846
+ "<extra_id_17>",
847
+ "<extra_id_18>",
848
+ "<extra_id_19>",
849
+ "<extra_id_20>",
850
+ "<extra_id_21>",
851
+ "<extra_id_22>",
852
+ "<extra_id_23>",
853
+ "<extra_id_24>",
854
+ "<extra_id_25>",
855
+ "<extra_id_26>",
856
+ "<extra_id_27>",
857
+ "<extra_id_28>",
858
+ "<extra_id_29>",
859
+ "<extra_id_30>",
860
+ "<extra_id_31>",
861
+ "<extra_id_32>",
862
+ "<extra_id_33>",
863
+ "<extra_id_34>",
864
+ "<extra_id_35>",
865
+ "<extra_id_36>",
866
+ "<extra_id_37>",
867
+ "<extra_id_38>",
868
+ "<extra_id_39>",
869
+ "<extra_id_40>",
870
+ "<extra_id_41>",
871
+ "<extra_id_42>",
872
+ "<extra_id_43>",
873
+ "<extra_id_44>",
874
+ "<extra_id_45>",
875
+ "<extra_id_46>",
876
+ "<extra_id_47>",
877
+ "<extra_id_48>",
878
+ "<extra_id_49>",
879
+ "<extra_id_50>",
880
+ "<extra_id_51>",
881
+ "<extra_id_52>",
882
+ "<extra_id_53>",
883
+ "<extra_id_54>",
884
+ "<extra_id_55>",
885
+ "<extra_id_56>",
886
+ "<extra_id_57>",
887
+ "<extra_id_58>",
888
+ "<extra_id_59>",
889
+ "<extra_id_60>",
890
+ "<extra_id_61>",
891
+ "<extra_id_62>",
892
+ "<extra_id_63>",
893
+ "<extra_id_64>",
894
+ "<extra_id_65>",
895
+ "<extra_id_66>",
896
+ "<extra_id_67>",
897
+ "<extra_id_68>",
898
+ "<extra_id_69>",
899
+ "<extra_id_70>",
900
+ "<extra_id_71>",
901
+ "<extra_id_72>",
902
+ "<extra_id_73>",
903
+ "<extra_id_74>",
904
+ "<extra_id_75>",
905
+ "<extra_id_76>",
906
+ "<extra_id_77>",
907
+ "<extra_id_78>",
908
+ "<extra_id_79>",
909
+ "<extra_id_80>",
910
+ "<extra_id_81>",
911
+ "<extra_id_82>",
912
+ "<extra_id_83>",
913
+ "<extra_id_84>",
914
+ "<extra_id_85>",
915
+ "<extra_id_86>",
916
+ "<extra_id_87>",
917
+ "<extra_id_88>",
918
+ "<extra_id_89>",
919
+ "<extra_id_90>",
920
+ "<extra_id_91>",
921
+ "<extra_id_92>",
922
+ "<extra_id_93>",
923
+ "<extra_id_94>",
924
+ "<extra_id_95>",
925
+ "<extra_id_96>",
926
+ "<extra_id_97>",
927
+ "<extra_id_98>",
928
+ "<extra_id_99>"
929
+ ],
930
+ "clean_up_tokenization_spaces": true,
931
+ "eos_token": "</s>",
932
+ "extra_ids": 100,
933
+ "model_max_length": 512,
934
+ "pad_token": "<pad>",
935
+ "sp_model_kwargs": {},
936
+ "tokenizer_class": "T5Tokenizer",
937
+ "unk_token": "<unk>"
938
+ }
checkpoint-4469/trainer_state.json ADDED
@@ -0,0 +1,1301 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": NaN,
3
+ "best_model_checkpoint": "autotrain-q48dd-y2s6a/checkpoint-4469",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4469,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.005594092638174088,
13
+ "grad_norm": NaN,
14
+ "learning_rate": 0.0,
15
+ "loss": 0.0,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.011188185276348177,
20
+ "grad_norm": NaN,
21
+ "learning_rate": 0.0,
22
+ "loss": 0.0,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.016782277914522265,
27
+ "grad_norm": NaN,
28
+ "learning_rate": 0.0,
29
+ "loss": 0.0,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.022376370552696354,
34
+ "grad_norm": NaN,
35
+ "learning_rate": 0.0,
36
+ "loss": 0.0,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.027970463190870442,
41
+ "grad_norm": NaN,
42
+ "learning_rate": 0.0,
43
+ "loss": 0.0,
44
+ "step": 125
45
+ },
46
+ {
47
+ "epoch": 0.03356455582904453,
48
+ "grad_norm": NaN,
49
+ "learning_rate": 0.0,
50
+ "loss": 0.0,
51
+ "step": 150
52
+ },
53
+ {
54
+ "epoch": 0.039158648467218615,
55
+ "grad_norm": NaN,
56
+ "learning_rate": 0.0,
57
+ "loss": 0.0,
58
+ "step": 175
59
+ },
60
+ {
61
+ "epoch": 0.04475274110539271,
62
+ "grad_norm": NaN,
63
+ "learning_rate": 0.0,
64
+ "loss": 0.0,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.05034683374356679,
69
+ "grad_norm": NaN,
70
+ "learning_rate": 0.0,
71
+ "loss": 0.0,
72
+ "step": 225
73
+ },
74
+ {
75
+ "epoch": 0.055940926381740884,
76
+ "grad_norm": NaN,
77
+ "learning_rate": 0.0,
78
+ "loss": 0.0,
79
+ "step": 250
80
+ },
81
+ {
82
+ "epoch": 0.06153501901991497,
83
+ "grad_norm": NaN,
84
+ "learning_rate": 0.0,
85
+ "loss": 0.0,
86
+ "step": 275
87
+ },
88
+ {
89
+ "epoch": 0.06712911165808906,
90
+ "grad_norm": NaN,
91
+ "learning_rate": 0.0,
92
+ "loss": 0.0,
93
+ "step": 300
94
+ },
95
+ {
96
+ "epoch": 0.07272320429626315,
97
+ "grad_norm": NaN,
98
+ "learning_rate": 0.0,
99
+ "loss": 0.0,
100
+ "step": 325
101
+ },
102
+ {
103
+ "epoch": 0.07831729693443723,
104
+ "grad_norm": NaN,
105
+ "learning_rate": 0.0,
106
+ "loss": 0.0,
107
+ "step": 350
108
+ },
109
+ {
110
+ "epoch": 0.08391138957261132,
111
+ "grad_norm": NaN,
112
+ "learning_rate": 0.0,
113
+ "loss": 0.0,
114
+ "step": 375
115
+ },
116
+ {
117
+ "epoch": 0.08950548221078541,
118
+ "grad_norm": NaN,
119
+ "learning_rate": 0.0,
120
+ "loss": 0.0,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.09509957484895949,
125
+ "grad_norm": NaN,
126
+ "learning_rate": 0.0,
127
+ "loss": 0.0,
128
+ "step": 425
129
+ },
130
+ {
131
+ "epoch": 0.10069366748713358,
132
+ "grad_norm": NaN,
133
+ "learning_rate": 0.0,
134
+ "loss": 0.0,
135
+ "step": 450
136
+ },
137
+ {
138
+ "epoch": 0.10628776012530768,
139
+ "grad_norm": NaN,
140
+ "learning_rate": 0.0,
141
+ "loss": 0.0,
142
+ "step": 475
143
+ },
144
+ {
145
+ "epoch": 0.11188185276348177,
146
+ "grad_norm": NaN,
147
+ "learning_rate": 0.0,
148
+ "loss": 0.0,
149
+ "step": 500
150
+ },
151
+ {
152
+ "epoch": 0.11747594540165585,
153
+ "grad_norm": NaN,
154
+ "learning_rate": 0.0,
155
+ "loss": 0.0,
156
+ "step": 525
157
+ },
158
+ {
159
+ "epoch": 0.12307003803982994,
160
+ "grad_norm": NaN,
161
+ "learning_rate": 0.0,
162
+ "loss": 0.0,
163
+ "step": 550
164
+ },
165
+ {
166
+ "epoch": 0.12866413067800403,
167
+ "grad_norm": NaN,
168
+ "learning_rate": 0.0,
169
+ "loss": 0.0,
170
+ "step": 575
171
+ },
172
+ {
173
+ "epoch": 0.13425822331617812,
174
+ "grad_norm": NaN,
175
+ "learning_rate": 0.0,
176
+ "loss": 0.0,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.1398523159543522,
181
+ "grad_norm": NaN,
182
+ "learning_rate": 0.0,
183
+ "loss": 0.0,
184
+ "step": 625
185
+ },
186
+ {
187
+ "epoch": 0.1454464085925263,
188
+ "grad_norm": NaN,
189
+ "learning_rate": 0.0,
190
+ "loss": 0.0,
191
+ "step": 650
192
+ },
193
+ {
194
+ "epoch": 0.15104050123070037,
195
+ "grad_norm": NaN,
196
+ "learning_rate": 0.0,
197
+ "loss": 0.0,
198
+ "step": 675
199
+ },
200
+ {
201
+ "epoch": 0.15663459386887446,
202
+ "grad_norm": NaN,
203
+ "learning_rate": 0.0,
204
+ "loss": 0.0,
205
+ "step": 700
206
+ },
207
+ {
208
+ "epoch": 0.16222868650704855,
209
+ "grad_norm": NaN,
210
+ "learning_rate": 0.0,
211
+ "loss": 0.0,
212
+ "step": 725
213
+ },
214
+ {
215
+ "epoch": 0.16782277914522264,
216
+ "grad_norm": NaN,
217
+ "learning_rate": 0.0,
218
+ "loss": 0.0,
219
+ "step": 750
220
+ },
221
+ {
222
+ "epoch": 0.17341687178339674,
223
+ "grad_norm": NaN,
224
+ "learning_rate": 0.0,
225
+ "loss": 0.0,
226
+ "step": 775
227
+ },
228
+ {
229
+ "epoch": 0.17901096442157083,
230
+ "grad_norm": NaN,
231
+ "learning_rate": 0.0,
232
+ "loss": 0.0,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.18460505705974492,
237
+ "grad_norm": NaN,
238
+ "learning_rate": 0.0,
239
+ "loss": 0.0,
240
+ "step": 825
241
+ },
242
+ {
243
+ "epoch": 0.19019914969791898,
244
+ "grad_norm": NaN,
245
+ "learning_rate": 0.0,
246
+ "loss": 0.0,
247
+ "step": 850
248
+ },
249
+ {
250
+ "epoch": 0.19579324233609308,
251
+ "grad_norm": NaN,
252
+ "learning_rate": 0.0,
253
+ "loss": 0.0,
254
+ "step": 875
255
+ },
256
+ {
257
+ "epoch": 0.20138733497426717,
258
+ "grad_norm": NaN,
259
+ "learning_rate": 0.0,
260
+ "loss": 0.0,
261
+ "step": 900
262
+ },
263
+ {
264
+ "epoch": 0.20698142761244126,
265
+ "grad_norm": NaN,
266
+ "learning_rate": 0.0,
267
+ "loss": 0.0,
268
+ "step": 925
269
+ },
270
+ {
271
+ "epoch": 0.21257552025061535,
272
+ "grad_norm": NaN,
273
+ "learning_rate": 0.0,
274
+ "loss": 0.0,
275
+ "step": 950
276
+ },
277
+ {
278
+ "epoch": 0.21816961288878944,
279
+ "grad_norm": NaN,
280
+ "learning_rate": 0.0,
281
+ "loss": 0.0,
282
+ "step": 975
283
+ },
284
+ {
285
+ "epoch": 0.22376370552696354,
286
+ "grad_norm": NaN,
287
+ "learning_rate": 0.0,
288
+ "loss": 0.0,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 0.22935779816513763,
293
+ "grad_norm": NaN,
294
+ "learning_rate": 0.0,
295
+ "loss": 0.0,
296
+ "step": 1025
297
+ },
298
+ {
299
+ "epoch": 0.2349518908033117,
300
+ "grad_norm": NaN,
301
+ "learning_rate": 0.0,
302
+ "loss": 0.0,
303
+ "step": 1050
304
+ },
305
+ {
306
+ "epoch": 0.24054598344148578,
307
+ "grad_norm": NaN,
308
+ "learning_rate": 0.0,
309
+ "loss": 0.0,
310
+ "step": 1075
311
+ },
312
+ {
313
+ "epoch": 0.24614007607965988,
314
+ "grad_norm": NaN,
315
+ "learning_rate": 0.0,
316
+ "loss": 0.0,
317
+ "step": 1100
318
+ },
319
+ {
320
+ "epoch": 0.251734168717834,
321
+ "grad_norm": NaN,
322
+ "learning_rate": 0.0,
323
+ "loss": 0.0,
324
+ "step": 1125
325
+ },
326
+ {
327
+ "epoch": 0.25732826135600806,
328
+ "grad_norm": NaN,
329
+ "learning_rate": 0.0,
330
+ "loss": 0.0,
331
+ "step": 1150
332
+ },
333
+ {
334
+ "epoch": 0.2629223539941821,
335
+ "grad_norm": NaN,
336
+ "learning_rate": 0.0,
337
+ "loss": 0.0,
338
+ "step": 1175
339
+ },
340
+ {
341
+ "epoch": 0.26851644663235624,
342
+ "grad_norm": NaN,
343
+ "learning_rate": 0.0,
344
+ "loss": 0.0,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 0.2741105392705303,
349
+ "grad_norm": NaN,
350
+ "learning_rate": 0.0,
351
+ "loss": 0.0,
352
+ "step": 1225
353
+ },
354
+ {
355
+ "epoch": 0.2797046319087044,
356
+ "grad_norm": NaN,
357
+ "learning_rate": 0.0,
358
+ "loss": 0.0,
359
+ "step": 1250
360
+ },
361
+ {
362
+ "epoch": 0.2852987245468785,
363
+ "grad_norm": NaN,
364
+ "learning_rate": 0.0,
365
+ "loss": 0.0,
366
+ "step": 1275
367
+ },
368
+ {
369
+ "epoch": 0.2908928171850526,
370
+ "grad_norm": NaN,
371
+ "learning_rate": 0.0,
372
+ "loss": 0.0,
373
+ "step": 1300
374
+ },
375
+ {
376
+ "epoch": 0.2964869098232267,
377
+ "grad_norm": NaN,
378
+ "learning_rate": 0.0,
379
+ "loss": 0.0,
380
+ "step": 1325
381
+ },
382
+ {
383
+ "epoch": 0.30208100246140074,
384
+ "grad_norm": NaN,
385
+ "learning_rate": 0.0,
386
+ "loss": 0.0,
387
+ "step": 1350
388
+ },
389
+ {
390
+ "epoch": 0.30767509509957486,
391
+ "grad_norm": NaN,
392
+ "learning_rate": 0.0,
393
+ "loss": 0.0,
394
+ "step": 1375
395
+ },
396
+ {
397
+ "epoch": 0.3132691877377489,
398
+ "grad_norm": NaN,
399
+ "learning_rate": 0.0,
400
+ "loss": 0.0,
401
+ "step": 1400
402
+ },
403
+ {
404
+ "epoch": 0.31886328037592304,
405
+ "grad_norm": NaN,
406
+ "learning_rate": 0.0,
407
+ "loss": 0.0,
408
+ "step": 1425
409
+ },
410
+ {
411
+ "epoch": 0.3244573730140971,
412
+ "grad_norm": NaN,
413
+ "learning_rate": 0.0,
414
+ "loss": 0.0,
415
+ "step": 1450
416
+ },
417
+ {
418
+ "epoch": 0.3300514656522712,
419
+ "grad_norm": NaN,
420
+ "learning_rate": 0.0,
421
+ "loss": 0.0,
422
+ "step": 1475
423
+ },
424
+ {
425
+ "epoch": 0.3356455582904453,
426
+ "grad_norm": NaN,
427
+ "learning_rate": 0.0,
428
+ "loss": 0.0,
429
+ "step": 1500
430
+ },
431
+ {
432
+ "epoch": 0.34123965092861935,
433
+ "grad_norm": NaN,
434
+ "learning_rate": 0.0,
435
+ "loss": 0.0,
436
+ "step": 1525
437
+ },
438
+ {
439
+ "epoch": 0.3468337435667935,
440
+ "grad_norm": NaN,
441
+ "learning_rate": 0.0,
442
+ "loss": 0.0,
443
+ "step": 1550
444
+ },
445
+ {
446
+ "epoch": 0.35242783620496754,
447
+ "grad_norm": NaN,
448
+ "learning_rate": 0.0,
449
+ "loss": 0.0,
450
+ "step": 1575
451
+ },
452
+ {
453
+ "epoch": 0.35802192884314166,
454
+ "grad_norm": NaN,
455
+ "learning_rate": 0.0,
456
+ "loss": 0.0,
457
+ "step": 1600
458
+ },
459
+ {
460
+ "epoch": 0.3636160214813157,
461
+ "grad_norm": NaN,
462
+ "learning_rate": 0.0,
463
+ "loss": 0.0,
464
+ "step": 1625
465
+ },
466
+ {
467
+ "epoch": 0.36921011411948984,
468
+ "grad_norm": NaN,
469
+ "learning_rate": 0.0,
470
+ "loss": 0.0,
471
+ "step": 1650
472
+ },
473
+ {
474
+ "epoch": 0.3748042067576639,
475
+ "grad_norm": NaN,
476
+ "learning_rate": 0.0,
477
+ "loss": 0.0,
478
+ "step": 1675
479
+ },
480
+ {
481
+ "epoch": 0.38039829939583797,
482
+ "grad_norm": NaN,
483
+ "learning_rate": 0.0,
484
+ "loss": 0.0,
485
+ "step": 1700
486
+ },
487
+ {
488
+ "epoch": 0.3859923920340121,
489
+ "grad_norm": NaN,
490
+ "learning_rate": 0.0,
491
+ "loss": 0.0,
492
+ "step": 1725
493
+ },
494
+ {
495
+ "epoch": 0.39158648467218615,
496
+ "grad_norm": NaN,
497
+ "learning_rate": 0.0,
498
+ "loss": 0.0,
499
+ "step": 1750
500
+ },
501
+ {
502
+ "epoch": 0.39718057731036027,
503
+ "grad_norm": NaN,
504
+ "learning_rate": 0.0,
505
+ "loss": 0.0,
506
+ "step": 1775
507
+ },
508
+ {
509
+ "epoch": 0.40277466994853434,
510
+ "grad_norm": NaN,
511
+ "learning_rate": 0.0,
512
+ "loss": 0.0,
513
+ "step": 1800
514
+ },
515
+ {
516
+ "epoch": 0.40836876258670846,
517
+ "grad_norm": NaN,
518
+ "learning_rate": 0.0,
519
+ "loss": 0.0,
520
+ "step": 1825
521
+ },
522
+ {
523
+ "epoch": 0.4139628552248825,
524
+ "grad_norm": NaN,
525
+ "learning_rate": 0.0,
526
+ "loss": 0.0,
527
+ "step": 1850
528
+ },
529
+ {
530
+ "epoch": 0.41955694786305664,
531
+ "grad_norm": NaN,
532
+ "learning_rate": 0.0,
533
+ "loss": 0.0,
534
+ "step": 1875
535
+ },
536
+ {
537
+ "epoch": 0.4251510405012307,
538
+ "grad_norm": NaN,
539
+ "learning_rate": 0.0,
540
+ "loss": 0.0,
541
+ "step": 1900
542
+ },
543
+ {
544
+ "epoch": 0.43074513313940477,
545
+ "grad_norm": NaN,
546
+ "learning_rate": 0.0,
547
+ "loss": 0.0,
548
+ "step": 1925
549
+ },
550
+ {
551
+ "epoch": 0.4363392257775789,
552
+ "grad_norm": NaN,
553
+ "learning_rate": 0.0,
554
+ "loss": 0.0,
555
+ "step": 1950
556
+ },
557
+ {
558
+ "epoch": 0.44193331841575295,
559
+ "grad_norm": NaN,
560
+ "learning_rate": 0.0,
561
+ "loss": 0.0,
562
+ "step": 1975
563
+ },
564
+ {
565
+ "epoch": 0.44752741105392707,
566
+ "grad_norm": NaN,
567
+ "learning_rate": 0.0,
568
+ "loss": 0.0,
569
+ "step": 2000
570
+ },
571
+ {
572
+ "epoch": 0.45312150369210114,
573
+ "grad_norm": NaN,
574
+ "learning_rate": 0.0,
575
+ "loss": 0.0,
576
+ "step": 2025
577
+ },
578
+ {
579
+ "epoch": 0.45871559633027525,
580
+ "grad_norm": NaN,
581
+ "learning_rate": 0.0,
582
+ "loss": 0.0,
583
+ "step": 2050
584
+ },
585
+ {
586
+ "epoch": 0.4643096889684493,
587
+ "grad_norm": NaN,
588
+ "learning_rate": 0.0,
589
+ "loss": 0.0,
590
+ "step": 2075
591
+ },
592
+ {
593
+ "epoch": 0.4699037816066234,
594
+ "grad_norm": NaN,
595
+ "learning_rate": 0.0,
596
+ "loss": 0.0,
597
+ "step": 2100
598
+ },
599
+ {
600
+ "epoch": 0.4754978742447975,
601
+ "grad_norm": NaN,
602
+ "learning_rate": 0.0,
603
+ "loss": 0.0,
604
+ "step": 2125
605
+ },
606
+ {
607
+ "epoch": 0.48109196688297157,
608
+ "grad_norm": NaN,
609
+ "learning_rate": 0.0,
610
+ "loss": 0.0,
611
+ "step": 2150
612
+ },
613
+ {
614
+ "epoch": 0.4866860595211457,
615
+ "grad_norm": NaN,
616
+ "learning_rate": 0.0,
617
+ "loss": 0.0,
618
+ "step": 2175
619
+ },
620
+ {
621
+ "epoch": 0.49228015215931975,
622
+ "grad_norm": NaN,
623
+ "learning_rate": 0.0,
624
+ "loss": 0.0,
625
+ "step": 2200
626
+ },
627
+ {
628
+ "epoch": 0.49787424479749387,
629
+ "grad_norm": NaN,
630
+ "learning_rate": 0.0,
631
+ "loss": 0.0,
632
+ "step": 2225
633
+ },
634
+ {
635
+ "epoch": 0.503468337435668,
636
+ "grad_norm": NaN,
637
+ "learning_rate": 0.0,
638
+ "loss": 0.0,
639
+ "step": 2250
640
+ },
641
+ {
642
+ "epoch": 0.509062430073842,
643
+ "grad_norm": NaN,
644
+ "learning_rate": 0.0,
645
+ "loss": 0.0,
646
+ "step": 2275
647
+ },
648
+ {
649
+ "epoch": 0.5146565227120161,
650
+ "grad_norm": NaN,
651
+ "learning_rate": 0.0,
652
+ "loss": 0.0,
653
+ "step": 2300
654
+ },
655
+ {
656
+ "epoch": 0.5202506153501902,
657
+ "grad_norm": NaN,
658
+ "learning_rate": 0.0,
659
+ "loss": 0.0,
660
+ "step": 2325
661
+ },
662
+ {
663
+ "epoch": 0.5258447079883642,
664
+ "grad_norm": NaN,
665
+ "learning_rate": 0.0,
666
+ "loss": 0.0,
667
+ "step": 2350
668
+ },
669
+ {
670
+ "epoch": 0.5314388006265384,
671
+ "grad_norm": NaN,
672
+ "learning_rate": 0.0,
673
+ "loss": 0.0,
674
+ "step": 2375
675
+ },
676
+ {
677
+ "epoch": 0.5370328932647125,
678
+ "grad_norm": NaN,
679
+ "learning_rate": 0.0,
680
+ "loss": 0.0,
681
+ "step": 2400
682
+ },
683
+ {
684
+ "epoch": 0.5426269859028866,
685
+ "grad_norm": NaN,
686
+ "learning_rate": 0.0,
687
+ "loss": 0.0,
688
+ "step": 2425
689
+ },
690
+ {
691
+ "epoch": 0.5482210785410606,
692
+ "grad_norm": NaN,
693
+ "learning_rate": 0.0,
694
+ "loss": 0.0,
695
+ "step": 2450
696
+ },
697
+ {
698
+ "epoch": 0.5538151711792347,
699
+ "grad_norm": NaN,
700
+ "learning_rate": 0.0,
701
+ "loss": 0.0,
702
+ "step": 2475
703
+ },
704
+ {
705
+ "epoch": 0.5594092638174089,
706
+ "grad_norm": NaN,
707
+ "learning_rate": 0.0,
708
+ "loss": 0.0,
709
+ "step": 2500
710
+ },
711
+ {
712
+ "epoch": 0.5650033564555829,
713
+ "grad_norm": NaN,
714
+ "learning_rate": 0.0,
715
+ "loss": 0.0,
716
+ "step": 2525
717
+ },
718
+ {
719
+ "epoch": 0.570597449093757,
720
+ "grad_norm": NaN,
721
+ "learning_rate": 0.0,
722
+ "loss": 0.0,
723
+ "step": 2550
724
+ },
725
+ {
726
+ "epoch": 0.5761915417319311,
727
+ "grad_norm": NaN,
728
+ "learning_rate": 0.0,
729
+ "loss": 0.0,
730
+ "step": 2575
731
+ },
732
+ {
733
+ "epoch": 0.5817856343701052,
734
+ "grad_norm": NaN,
735
+ "learning_rate": 0.0,
736
+ "loss": 0.0,
737
+ "step": 2600
738
+ },
739
+ {
740
+ "epoch": 0.5873797270082792,
741
+ "grad_norm": NaN,
742
+ "learning_rate": 0.0,
743
+ "loss": 0.0,
744
+ "step": 2625
745
+ },
746
+ {
747
+ "epoch": 0.5929738196464533,
748
+ "grad_norm": NaN,
749
+ "learning_rate": 0.0,
750
+ "loss": 0.0,
751
+ "step": 2650
752
+ },
753
+ {
754
+ "epoch": 0.5985679122846275,
755
+ "grad_norm": NaN,
756
+ "learning_rate": 0.0,
757
+ "loss": 0.0,
758
+ "step": 2675
759
+ },
760
+ {
761
+ "epoch": 0.6041620049228015,
762
+ "grad_norm": NaN,
763
+ "learning_rate": 0.0,
764
+ "loss": 0.0,
765
+ "step": 2700
766
+ },
767
+ {
768
+ "epoch": 0.6097560975609756,
769
+ "grad_norm": NaN,
770
+ "learning_rate": 0.0,
771
+ "loss": 0.0,
772
+ "step": 2725
773
+ },
774
+ {
775
+ "epoch": 0.6153501901991497,
776
+ "grad_norm": NaN,
777
+ "learning_rate": 0.0,
778
+ "loss": 0.0,
779
+ "step": 2750
780
+ },
781
+ {
782
+ "epoch": 0.6209442828373238,
783
+ "grad_norm": NaN,
784
+ "learning_rate": 0.0,
785
+ "loss": 0.0,
786
+ "step": 2775
787
+ },
788
+ {
789
+ "epoch": 0.6265383754754978,
790
+ "grad_norm": NaN,
791
+ "learning_rate": 0.0,
792
+ "loss": 0.0,
793
+ "step": 2800
794
+ },
795
+ {
796
+ "epoch": 0.632132468113672,
797
+ "grad_norm": NaN,
798
+ "learning_rate": 0.0,
799
+ "loss": 0.0,
800
+ "step": 2825
801
+ },
802
+ {
803
+ "epoch": 0.6377265607518461,
804
+ "grad_norm": NaN,
805
+ "learning_rate": 0.0,
806
+ "loss": 0.0,
807
+ "step": 2850
808
+ },
809
+ {
810
+ "epoch": 0.6433206533900201,
811
+ "grad_norm": NaN,
812
+ "learning_rate": 0.0,
813
+ "loss": 0.0,
814
+ "step": 2875
815
+ },
816
+ {
817
+ "epoch": 0.6489147460281942,
818
+ "grad_norm": NaN,
819
+ "learning_rate": 0.0,
820
+ "loss": 0.0,
821
+ "step": 2900
822
+ },
823
+ {
824
+ "epoch": 0.6545088386663683,
825
+ "grad_norm": NaN,
826
+ "learning_rate": 0.0,
827
+ "loss": 0.0,
828
+ "step": 2925
829
+ },
830
+ {
831
+ "epoch": 0.6601029313045425,
832
+ "grad_norm": NaN,
833
+ "learning_rate": 0.0,
834
+ "loss": 0.0,
835
+ "step": 2950
836
+ },
837
+ {
838
+ "epoch": 0.6656970239427165,
839
+ "grad_norm": NaN,
840
+ "learning_rate": 0.0,
841
+ "loss": 0.0,
842
+ "step": 2975
843
+ },
844
+ {
845
+ "epoch": 0.6712911165808906,
846
+ "grad_norm": NaN,
847
+ "learning_rate": 0.0,
848
+ "loss": 0.0,
849
+ "step": 3000
850
+ },
851
+ {
852
+ "epoch": 0.6768852092190647,
853
+ "grad_norm": NaN,
854
+ "learning_rate": 0.0,
855
+ "loss": 0.0,
856
+ "step": 3025
857
+ },
858
+ {
859
+ "epoch": 0.6824793018572387,
860
+ "grad_norm": NaN,
861
+ "learning_rate": 0.0,
862
+ "loss": 0.0,
863
+ "step": 3050
864
+ },
865
+ {
866
+ "epoch": 0.6880733944954128,
867
+ "grad_norm": NaN,
868
+ "learning_rate": 0.0,
869
+ "loss": 0.0,
870
+ "step": 3075
871
+ },
872
+ {
873
+ "epoch": 0.693667487133587,
874
+ "grad_norm": NaN,
875
+ "learning_rate": 0.0,
876
+ "loss": 0.0,
877
+ "step": 3100
878
+ },
879
+ {
880
+ "epoch": 0.6992615797717611,
881
+ "grad_norm": NaN,
882
+ "learning_rate": 0.0,
883
+ "loss": 0.0,
884
+ "step": 3125
885
+ },
886
+ {
887
+ "epoch": 0.7048556724099351,
888
+ "grad_norm": NaN,
889
+ "learning_rate": 0.0,
890
+ "loss": 0.0,
891
+ "step": 3150
892
+ },
893
+ {
894
+ "epoch": 0.7104497650481092,
895
+ "grad_norm": NaN,
896
+ "learning_rate": 0.0,
897
+ "loss": 0.0,
898
+ "step": 3175
899
+ },
900
+ {
901
+ "epoch": 0.7160438576862833,
902
+ "grad_norm": NaN,
903
+ "learning_rate": 0.0,
904
+ "loss": 0.0,
905
+ "step": 3200
906
+ },
907
+ {
908
+ "epoch": 0.7216379503244573,
909
+ "grad_norm": NaN,
910
+ "learning_rate": 0.0,
911
+ "loss": 0.0,
912
+ "step": 3225
913
+ },
914
+ {
915
+ "epoch": 0.7272320429626314,
916
+ "grad_norm": NaN,
917
+ "learning_rate": 0.0,
918
+ "loss": 0.0,
919
+ "step": 3250
920
+ },
921
+ {
922
+ "epoch": 0.7328261356008056,
923
+ "grad_norm": NaN,
924
+ "learning_rate": 0.0,
925
+ "loss": 0.0,
926
+ "step": 3275
927
+ },
928
+ {
929
+ "epoch": 0.7384202282389797,
930
+ "grad_norm": NaN,
931
+ "learning_rate": 0.0,
932
+ "loss": 0.0,
933
+ "step": 3300
934
+ },
935
+ {
936
+ "epoch": 0.7440143208771537,
937
+ "grad_norm": NaN,
938
+ "learning_rate": 0.0,
939
+ "loss": 0.0,
940
+ "step": 3325
941
+ },
942
+ {
943
+ "epoch": 0.7496084135153278,
944
+ "grad_norm": NaN,
945
+ "learning_rate": 0.0,
946
+ "loss": 0.0,
947
+ "step": 3350
948
+ },
949
+ {
950
+ "epoch": 0.7552025061535019,
951
+ "grad_norm": NaN,
952
+ "learning_rate": 0.0,
953
+ "loss": 0.0,
954
+ "step": 3375
955
+ },
956
+ {
957
+ "epoch": 0.7607965987916759,
958
+ "grad_norm": NaN,
959
+ "learning_rate": 0.0,
960
+ "loss": 0.0,
961
+ "step": 3400
962
+ },
963
+ {
964
+ "epoch": 0.7663906914298501,
965
+ "grad_norm": NaN,
966
+ "learning_rate": 0.0,
967
+ "loss": 0.0,
968
+ "step": 3425
969
+ },
970
+ {
971
+ "epoch": 0.7719847840680242,
972
+ "grad_norm": NaN,
973
+ "learning_rate": 0.0,
974
+ "loss": 0.0,
975
+ "step": 3450
976
+ },
977
+ {
978
+ "epoch": 0.7775788767061983,
979
+ "grad_norm": NaN,
980
+ "learning_rate": 0.0,
981
+ "loss": 0.0,
982
+ "step": 3475
983
+ },
984
+ {
985
+ "epoch": 0.7831729693443723,
986
+ "grad_norm": NaN,
987
+ "learning_rate": 0.0,
988
+ "loss": 0.0,
989
+ "step": 3500
990
+ },
991
+ {
992
+ "epoch": 0.7887670619825464,
993
+ "grad_norm": NaN,
994
+ "learning_rate": 0.0,
995
+ "loss": 0.0,
996
+ "step": 3525
997
+ },
998
+ {
999
+ "epoch": 0.7943611546207205,
1000
+ "grad_norm": NaN,
1001
+ "learning_rate": 0.0,
1002
+ "loss": 0.0,
1003
+ "step": 3550
1004
+ },
1005
+ {
1006
+ "epoch": 0.7999552472588946,
1007
+ "grad_norm": NaN,
1008
+ "learning_rate": 0.0,
1009
+ "loss": 0.0,
1010
+ "step": 3575
1011
+ },
1012
+ {
1013
+ "epoch": 0.8055493398970687,
1014
+ "grad_norm": NaN,
1015
+ "learning_rate": 0.0,
1016
+ "loss": 0.0,
1017
+ "step": 3600
1018
+ },
1019
+ {
1020
+ "epoch": 0.8111434325352428,
1021
+ "grad_norm": NaN,
1022
+ "learning_rate": 0.0,
1023
+ "loss": 0.0,
1024
+ "step": 3625
1025
+ },
1026
+ {
1027
+ "epoch": 0.8167375251734169,
1028
+ "grad_norm": NaN,
1029
+ "learning_rate": 0.0,
1030
+ "loss": 0.0,
1031
+ "step": 3650
1032
+ },
1033
+ {
1034
+ "epoch": 0.8223316178115909,
1035
+ "grad_norm": NaN,
1036
+ "learning_rate": 0.0,
1037
+ "loss": 0.0,
1038
+ "step": 3675
1039
+ },
1040
+ {
1041
+ "epoch": 0.827925710449765,
1042
+ "grad_norm": NaN,
1043
+ "learning_rate": 0.0,
1044
+ "loss": 0.0,
1045
+ "step": 3700
1046
+ },
1047
+ {
1048
+ "epoch": 0.8335198030879392,
1049
+ "grad_norm": NaN,
1050
+ "learning_rate": 0.0,
1051
+ "loss": 0.0,
1052
+ "step": 3725
1053
+ },
1054
+ {
1055
+ "epoch": 0.8391138957261133,
1056
+ "grad_norm": NaN,
1057
+ "learning_rate": 0.0,
1058
+ "loss": 0.0,
1059
+ "step": 3750
1060
+ },
1061
+ {
1062
+ "epoch": 0.8447079883642873,
1063
+ "grad_norm": NaN,
1064
+ "learning_rate": 0.0,
1065
+ "loss": 0.0,
1066
+ "step": 3775
1067
+ },
1068
+ {
1069
+ "epoch": 0.8503020810024614,
1070
+ "grad_norm": NaN,
1071
+ "learning_rate": 0.0,
1072
+ "loss": 0.0,
1073
+ "step": 3800
1074
+ },
1075
+ {
1076
+ "epoch": 0.8558961736406355,
1077
+ "grad_norm": NaN,
1078
+ "learning_rate": 0.0,
1079
+ "loss": 0.0,
1080
+ "step": 3825
1081
+ },
1082
+ {
1083
+ "epoch": 0.8614902662788095,
1084
+ "grad_norm": NaN,
1085
+ "learning_rate": 0.0,
1086
+ "loss": 0.0,
1087
+ "step": 3850
1088
+ },
1089
+ {
1090
+ "epoch": 0.8670843589169837,
1091
+ "grad_norm": NaN,
1092
+ "learning_rate": 0.0,
1093
+ "loss": 0.0,
1094
+ "step": 3875
1095
+ },
1096
+ {
1097
+ "epoch": 0.8726784515551578,
1098
+ "grad_norm": NaN,
1099
+ "learning_rate": 0.0,
1100
+ "loss": 0.0,
1101
+ "step": 3900
1102
+ },
1103
+ {
1104
+ "epoch": 0.8782725441933319,
1105
+ "grad_norm": NaN,
1106
+ "learning_rate": 0.0,
1107
+ "loss": 0.0,
1108
+ "step": 3925
1109
+ },
1110
+ {
1111
+ "epoch": 0.8838666368315059,
1112
+ "grad_norm": NaN,
1113
+ "learning_rate": 0.0,
1114
+ "loss": 0.0,
1115
+ "step": 3950
1116
+ },
1117
+ {
1118
+ "epoch": 0.88946072946968,
1119
+ "grad_norm": NaN,
1120
+ "learning_rate": 0.0,
1121
+ "loss": 0.0,
1122
+ "step": 3975
1123
+ },
1124
+ {
1125
+ "epoch": 0.8950548221078541,
1126
+ "grad_norm": NaN,
1127
+ "learning_rate": 0.0,
1128
+ "loss": 0.0,
1129
+ "step": 4000
1130
+ },
1131
+ {
1132
+ "epoch": 0.9006489147460282,
1133
+ "grad_norm": NaN,
1134
+ "learning_rate": 0.0,
1135
+ "loss": 0.0,
1136
+ "step": 4025
1137
+ },
1138
+ {
1139
+ "epoch": 0.9062430073842023,
1140
+ "grad_norm": NaN,
1141
+ "learning_rate": 0.0,
1142
+ "loss": 0.0,
1143
+ "step": 4050
1144
+ },
1145
+ {
1146
+ "epoch": 0.9118371000223764,
1147
+ "grad_norm": NaN,
1148
+ "learning_rate": 0.0,
1149
+ "loss": 0.0,
1150
+ "step": 4075
1151
+ },
1152
+ {
1153
+ "epoch": 0.9174311926605505,
1154
+ "grad_norm": NaN,
1155
+ "learning_rate": 0.0,
1156
+ "loss": 0.0,
1157
+ "step": 4100
1158
+ },
1159
+ {
1160
+ "epoch": 0.9230252852987245,
1161
+ "grad_norm": NaN,
1162
+ "learning_rate": 0.0,
1163
+ "loss": 0.0,
1164
+ "step": 4125
1165
+ },
1166
+ {
1167
+ "epoch": 0.9286193779368986,
1168
+ "grad_norm": NaN,
1169
+ "learning_rate": 0.0,
1170
+ "loss": 0.0,
1171
+ "step": 4150
1172
+ },
1173
+ {
1174
+ "epoch": 0.9342134705750728,
1175
+ "grad_norm": NaN,
1176
+ "learning_rate": 0.0,
1177
+ "loss": 0.0,
1178
+ "step": 4175
1179
+ },
1180
+ {
1181
+ "epoch": 0.9398075632132468,
1182
+ "grad_norm": NaN,
1183
+ "learning_rate": 0.0,
1184
+ "loss": 0.0,
1185
+ "step": 4200
1186
+ },
1187
+ {
1188
+ "epoch": 0.9454016558514209,
1189
+ "grad_norm": NaN,
1190
+ "learning_rate": 0.0,
1191
+ "loss": 0.0,
1192
+ "step": 4225
1193
+ },
1194
+ {
1195
+ "epoch": 0.950995748489595,
1196
+ "grad_norm": NaN,
1197
+ "learning_rate": 0.0,
1198
+ "loss": 0.0,
1199
+ "step": 4250
1200
+ },
1201
+ {
1202
+ "epoch": 0.9565898411277691,
1203
+ "grad_norm": NaN,
1204
+ "learning_rate": 0.0,
1205
+ "loss": 0.0,
1206
+ "step": 4275
1207
+ },
1208
+ {
1209
+ "epoch": 0.9621839337659431,
1210
+ "grad_norm": NaN,
1211
+ "learning_rate": 0.0,
1212
+ "loss": 0.0,
1213
+ "step": 4300
1214
+ },
1215
+ {
1216
+ "epoch": 0.9677780264041173,
1217
+ "grad_norm": NaN,
1218
+ "learning_rate": 0.0,
1219
+ "loss": 0.0,
1220
+ "step": 4325
1221
+ },
1222
+ {
1223
+ "epoch": 0.9733721190422914,
1224
+ "grad_norm": NaN,
1225
+ "learning_rate": 0.0,
1226
+ "loss": 0.0,
1227
+ "step": 4350
1228
+ },
1229
+ {
1230
+ "epoch": 0.9789662116804654,
1231
+ "grad_norm": NaN,
1232
+ "learning_rate": 0.0,
1233
+ "loss": 0.0,
1234
+ "step": 4375
1235
+ },
1236
+ {
1237
+ "epoch": 0.9845603043186395,
1238
+ "grad_norm": NaN,
1239
+ "learning_rate": 0.0,
1240
+ "loss": 0.0,
1241
+ "step": 4400
1242
+ },
1243
+ {
1244
+ "epoch": 0.9901543969568136,
1245
+ "grad_norm": NaN,
1246
+ "learning_rate": 0.0,
1247
+ "loss": 0.0,
1248
+ "step": 4425
1249
+ },
1250
+ {
1251
+ "epoch": 0.9957484895949877,
1252
+ "grad_norm": NaN,
1253
+ "learning_rate": 0.0,
1254
+ "loss": 0.0,
1255
+ "step": 4450
1256
+ },
1257
+ {
1258
+ "epoch": 1.0,
1259
+ "eval_gen_len": 12.915,
1260
+ "eval_loss": NaN,
1261
+ "eval_rouge1": 13.2945,
1262
+ "eval_rouge2": 3.5623,
1263
+ "eval_rougeL": 12.4291,
1264
+ "eval_rougeLsum": 12.5471,
1265
+ "eval_runtime": 125.0743,
1266
+ "eval_samples_per_second": 8.931,
1267
+ "eval_steps_per_second": 2.239,
1268
+ "step": 4469
1269
+ }
1270
+ ],
1271
+ "logging_steps": 25,
1272
+ "max_steps": 13407,
1273
+ "num_input_tokens_seen": 0,
1274
+ "num_train_epochs": 3,
1275
+ "save_steps": 500,
1276
+ "stateful_callbacks": {
1277
+ "EarlyStoppingCallback": {
1278
+ "args": {
1279
+ "early_stopping_patience": 5,
1280
+ "early_stopping_threshold": 0.01
1281
+ },
1282
+ "attributes": {
1283
+ "early_stopping_patience_counter": 0
1284
+ }
1285
+ },
1286
+ "TrainerControl": {
1287
+ "args": {
1288
+ "should_epoch_stop": false,
1289
+ "should_evaluate": false,
1290
+ "should_log": false,
1291
+ "should_save": true,
1292
+ "should_training_stop": false
1293
+ },
1294
+ "attributes": {}
1295
+ }
1296
+ },
1297
+ "total_flos": 434735324135424.0,
1298
+ "train_batch_size": 2,
1299
+ "trial_name": null,
1300
+ "trial_params": null
1301
+ }
checkpoint-4469/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e30dde2c07c719efc923a44bbf2d30ec916ea87a9c98e81e071b989e7dcb7fda
3
+ size 5304
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "tie_word_embeddings": false,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.41.0",
60
+ "use_cache": true,
61
+ "vocab_size": 32128
62
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.41.0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197b346658905cda50c1a71fe0eb77a4d79306adaeb5d7a3c0e9208c91022d45
3
+ size 990345064
runs/Jun11_08-20-01_r-riken01-flan-t5-base-k40gibpq-dbd37-gzci3/events.out.tfevents.1718094007.r-riken01-flan-t5-base-k40gibpq-dbd37-gzci3.85.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54bd9d956ef01b11323e7070bc57638b93d78f8120310314c4c5b73a7bf46f3a
3
- size 114110
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:778134a0c07d9485b97921bb4ea9ce93b9ba916b72264448442de36039c0af16
3
+ size 120897
runs/Jun11_08-20-01_r-riken01-flan-t5-base-k40gibpq-dbd37-gzci3/events.out.tfevents.1718096791.r-riken01-flan-t5-base-k40gibpq-dbd37-gzci3.85.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee81d3ad83fc523180afd9caeb9b1c325258a0331a56fcecb68b515297e7f23
3
+ size 613
special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,938 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<extra_id_99>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<extra_id_98>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "<extra_id_97>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "<extra_id_96>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32004": {
60
+ "content": "<extra_id_95>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32005": {
68
+ "content": "<extra_id_94>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32006": {
76
+ "content": "<extra_id_93>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "32007": {
84
+ "content": "<extra_id_92>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "32008": {
92
+ "content": "<extra_id_91>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "32009": {
100
+ "content": "<extra_id_90>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "32010": {
108
+ "content": "<extra_id_89>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "32011": {
116
+ "content": "<extra_id_88>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "32012": {
124
+ "content": "<extra_id_87>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "32013": {
132
+ "content": "<extra_id_86>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "32014": {
140
+ "content": "<extra_id_85>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "32015": {
148
+ "content": "<extra_id_84>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "32016": {
156
+ "content": "<extra_id_83>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "32017": {
164
+ "content": "<extra_id_82>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "32018": {
172
+ "content": "<extra_id_81>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "32019": {
180
+ "content": "<extra_id_80>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "32020": {
188
+ "content": "<extra_id_79>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "32021": {
196
+ "content": "<extra_id_78>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "32022": {
204
+ "content": "<extra_id_77>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "32023": {
212
+ "content": "<extra_id_76>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "32024": {
220
+ "content": "<extra_id_75>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "32025": {
228
+ "content": "<extra_id_74>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "32026": {
236
+ "content": "<extra_id_73>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32027": {
244
+ "content": "<extra_id_72>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "32028": {
252
+ "content": "<extra_id_71>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32029": {
260
+ "content": "<extra_id_70>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "32030": {
268
+ "content": "<extra_id_69>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "32031": {
276
+ "content": "<extra_id_68>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "32032": {
284
+ "content": "<extra_id_67>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "32033": {
292
+ "content": "<extra_id_66>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "32034": {
300
+ "content": "<extra_id_65>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "32035": {
308
+ "content": "<extra_id_64>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "32036": {
316
+ "content": "<extra_id_63>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "32037": {
324
+ "content": "<extra_id_62>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "32038": {
332
+ "content": "<extra_id_61>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "32039": {
340
+ "content": "<extra_id_60>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "32040": {
348
+ "content": "<extra_id_59>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "32041": {
356
+ "content": "<extra_id_58>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "32042": {
364
+ "content": "<extra_id_57>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "32043": {
372
+ "content": "<extra_id_56>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "32044": {
380
+ "content": "<extra_id_55>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "32045": {
388
+ "content": "<extra_id_54>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "32046": {
396
+ "content": "<extra_id_53>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "32047": {
404
+ "content": "<extra_id_52>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "32048": {
412
+ "content": "<extra_id_51>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "32049": {
420
+ "content": "<extra_id_50>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "32050": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "32051": {
436
+ "content": "<extra_id_48>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "32052": {
444
+ "content": "<extra_id_47>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "32053": {
452
+ "content": "<extra_id_46>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "32054": {
460
+ "content": "<extra_id_45>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "32055": {
468
+ "content": "<extra_id_44>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "32056": {
476
+ "content": "<extra_id_43>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "32057": {
484
+ "content": "<extra_id_42>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "32058": {
492
+ "content": "<extra_id_41>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "32059": {
500
+ "content": "<extra_id_40>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "32060": {
508
+ "content": "<extra_id_39>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "32061": {
516
+ "content": "<extra_id_38>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "32062": {
524
+ "content": "<extra_id_37>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "32063": {
532
+ "content": "<extra_id_36>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "32064": {
540
+ "content": "<extra_id_35>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "32065": {
548
+ "content": "<extra_id_34>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "32066": {
556
+ "content": "<extra_id_33>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "32067": {
564
+ "content": "<extra_id_32>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "32068": {
572
+ "content": "<extra_id_31>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "32069": {
580
+ "content": "<extra_id_30>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "32070": {
588
+ "content": "<extra_id_29>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "32071": {
596
+ "content": "<extra_id_28>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "32072": {
604
+ "content": "<extra_id_27>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "32073": {
612
+ "content": "<extra_id_26>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "32074": {
620
+ "content": "<extra_id_25>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "32075": {
628
+ "content": "<extra_id_24>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "32076": {
636
+ "content": "<extra_id_23>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "32077": {
644
+ "content": "<extra_id_22>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "32078": {
652
+ "content": "<extra_id_21>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "32079": {
660
+ "content": "<extra_id_20>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "32080": {
668
+ "content": "<extra_id_19>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "32081": {
676
+ "content": "<extra_id_18>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "32082": {
684
+ "content": "<extra_id_17>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "32083": {
692
+ "content": "<extra_id_16>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "32084": {
700
+ "content": "<extra_id_15>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "32085": {
708
+ "content": "<extra_id_14>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "32086": {
716
+ "content": "<extra_id_13>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "32087": {
724
+ "content": "<extra_id_12>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "32088": {
732
+ "content": "<extra_id_11>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "32089": {
740
+ "content": "<extra_id_10>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "32090": {
748
+ "content": "<extra_id_9>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "32091": {
756
+ "content": "<extra_id_8>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "32092": {
764
+ "content": "<extra_id_7>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "32093": {
772
+ "content": "<extra_id_6>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "32094": {
780
+ "content": "<extra_id_5>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "32095": {
788
+ "content": "<extra_id_4>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "32096": {
796
+ "content": "<extra_id_3>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "32097": {
804
+ "content": "<extra_id_2>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "32098": {
812
+ "content": "<extra_id_1>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "32099": {
820
+ "content": "<extra_id_0>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ }
827
+ },
828
+ "additional_special_tokens": [
829
+ "<extra_id_0>",
830
+ "<extra_id_1>",
831
+ "<extra_id_2>",
832
+ "<extra_id_3>",
833
+ "<extra_id_4>",
834
+ "<extra_id_5>",
835
+ "<extra_id_6>",
836
+ "<extra_id_7>",
837
+ "<extra_id_8>",
838
+ "<extra_id_9>",
839
+ "<extra_id_10>",
840
+ "<extra_id_11>",
841
+ "<extra_id_12>",
842
+ "<extra_id_13>",
843
+ "<extra_id_14>",
844
+ "<extra_id_15>",
845
+ "<extra_id_16>",
846
+ "<extra_id_17>",
847
+ "<extra_id_18>",
848
+ "<extra_id_19>",
849
+ "<extra_id_20>",
850
+ "<extra_id_21>",
851
+ "<extra_id_22>",
852
+ "<extra_id_23>",
853
+ "<extra_id_24>",
854
+ "<extra_id_25>",
855
+ "<extra_id_26>",
856
+ "<extra_id_27>",
857
+ "<extra_id_28>",
858
+ "<extra_id_29>",
859
+ "<extra_id_30>",
860
+ "<extra_id_31>",
861
+ "<extra_id_32>",
862
+ "<extra_id_33>",
863
+ "<extra_id_34>",
864
+ "<extra_id_35>",
865
+ "<extra_id_36>",
866
+ "<extra_id_37>",
867
+ "<extra_id_38>",
868
+ "<extra_id_39>",
869
+ "<extra_id_40>",
870
+ "<extra_id_41>",
871
+ "<extra_id_42>",
872
+ "<extra_id_43>",
873
+ "<extra_id_44>",
874
+ "<extra_id_45>",
875
+ "<extra_id_46>",
876
+ "<extra_id_47>",
877
+ "<extra_id_48>",
878
+ "<extra_id_49>",
879
+ "<extra_id_50>",
880
+ "<extra_id_51>",
881
+ "<extra_id_52>",
882
+ "<extra_id_53>",
883
+ "<extra_id_54>",
884
+ "<extra_id_55>",
885
+ "<extra_id_56>",
886
+ "<extra_id_57>",
887
+ "<extra_id_58>",
888
+ "<extra_id_59>",
889
+ "<extra_id_60>",
890
+ "<extra_id_61>",
891
+ "<extra_id_62>",
892
+ "<extra_id_63>",
893
+ "<extra_id_64>",
894
+ "<extra_id_65>",
895
+ "<extra_id_66>",
896
+ "<extra_id_67>",
897
+ "<extra_id_68>",
898
+ "<extra_id_69>",
899
+ "<extra_id_70>",
900
+ "<extra_id_71>",
901
+ "<extra_id_72>",
902
+ "<extra_id_73>",
903
+ "<extra_id_74>",
904
+ "<extra_id_75>",
905
+ "<extra_id_76>",
906
+ "<extra_id_77>",
907
+ "<extra_id_78>",
908
+ "<extra_id_79>",
909
+ "<extra_id_80>",
910
+ "<extra_id_81>",
911
+ "<extra_id_82>",
912
+ "<extra_id_83>",
913
+ "<extra_id_84>",
914
+ "<extra_id_85>",
915
+ "<extra_id_86>",
916
+ "<extra_id_87>",
917
+ "<extra_id_88>",
918
+ "<extra_id_89>",
919
+ "<extra_id_90>",
920
+ "<extra_id_91>",
921
+ "<extra_id_92>",
922
+ "<extra_id_93>",
923
+ "<extra_id_94>",
924
+ "<extra_id_95>",
925
+ "<extra_id_96>",
926
+ "<extra_id_97>",
927
+ "<extra_id_98>",
928
+ "<extra_id_99>"
929
+ ],
930
+ "clean_up_tokenization_spaces": true,
931
+ "eos_token": "</s>",
932
+ "extra_ids": 100,
933
+ "model_max_length": 512,
934
+ "pad_token": "<pad>",
935
+ "sp_model_kwargs": {},
936
+ "tokenizer_class": "T5Tokenizer",
937
+ "unk_token": "<unk>"
938
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e30dde2c07c719efc923a44bbf2d30ec916ea87a9c98e81e071b989e7dcb7fda
3
+ size 5304
training_params.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-q48dd-y2s6a/autotrain-data",
3
+ "model": "google/flan-t5-base",
4
+ "username": "riken01",
5
+ "seed": 42,
6
+ "train_split": "train",
7
+ "valid_split": "validation",
8
+ "project_name": "autotrain-q48dd-y2s6a",
9
+ "push_to_hub": true,
10
+ "text_column": "autotrain_text",
11
+ "target_column": "autotrain_label",
12
+ "lr": 1e-06,
13
+ "epochs": 3,
14
+ "max_seq_length": 128,
15
+ "max_target_length": 128,
16
+ "batch_size": 2,
17
+ "warmup_ratio": 0.1,
18
+ "gradient_accumulation": 1,
19
+ "optimizer": "adamw_torch",
20
+ "scheduler": "cosine",
21
+ "weight_decay": 0.0,
22
+ "max_grad_norm": 1.0,
23
+ "logging_steps": -1,
24
+ "evaluation_strategy": "epoch",
25
+ "auto_find_batch_size": false,
26
+ "mixed_precision": "fp16",
27
+ "save_total_limit": 1,
28
+ "peft": false,
29
+ "quantization": "int4",
30
+ "lora_r": 16,
31
+ "lora_alpha": 32,
32
+ "lora_dropout": 0.05,
33
+ "target_modules": "all-linear",
34
+ "log": "tensorboard",
35
+ "early_stopping_patience": 5,
36
+ "early_stopping_threshold": 0.01
37
+ }