pittawat commited on
Commit
2c4d912
1 Parent(s): 450cb7f

init: initialize commit

Browse files
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": "4.36.2",
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": "4.36.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00d42e62ccaa568ac092c7eed6ba3523ae279c97ca8474aec451856505e5591a
3
+ size 990345064
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:526795962624f2835f1833cf7319dc3a927c012d04eeb3de6702a147422b23d3
3
+ size 1980860410
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:179526e81a13ec651a30db73b901766eb81661b9f200dd29f3ee8a248db50967
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04c72869181363c7c0dcffb7a71857fd6a7c81a93e70aff2985fc26363295969
3
+ size 1064
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,939 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "return_tensors": "pt",
936
+ "sp_model_kwargs": {},
937
+ "tokenizer_class": "T5Tokenizer",
938
+ "unk_token": "<unk>"
939
+ }
trainer_state.json ADDED
@@ -0,0 +1,606 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.88888888888889,
5
+ "eval_steps": 256,
6
+ "global_step": 10000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 4.872000000000001e-05,
14
+ "loss": 0.8173,
15
+ "step": 256
16
+ },
17
+ {
18
+ "epoch": 0.23,
19
+ "eval_test_accuracy": 0.09690721649484536,
20
+ "eval_test_loss": 0.4266754984855652,
21
+ "eval_test_runtime": 233.5115,
22
+ "eval_test_samples_per_second": 10.385,
23
+ "eval_test_steps_per_second": 1.302,
24
+ "step": 256
25
+ },
26
+ {
27
+ "epoch": 0.46,
28
+ "learning_rate": 4.744e-05,
29
+ "loss": 0.441,
30
+ "step": 512
31
+ },
32
+ {
33
+ "epoch": 0.46,
34
+ "eval_test_accuracy": 0.16742268041237113,
35
+ "eval_test_loss": 0.36029067635536194,
36
+ "eval_test_runtime": 232.4589,
37
+ "eval_test_samples_per_second": 10.432,
38
+ "eval_test_steps_per_second": 1.308,
39
+ "step": 512
40
+ },
41
+ {
42
+ "epoch": 0.68,
43
+ "learning_rate": 4.6160000000000005e-05,
44
+ "loss": 0.397,
45
+ "step": 768
46
+ },
47
+ {
48
+ "epoch": 0.68,
49
+ "eval_test_accuracy": 0.17649484536082474,
50
+ "eval_test_loss": 0.3348633348941803,
51
+ "eval_test_runtime": 227.1069,
52
+ "eval_test_samples_per_second": 10.678,
53
+ "eval_test_steps_per_second": 1.339,
54
+ "step": 768
55
+ },
56
+ {
57
+ "epoch": 0.91,
58
+ "learning_rate": 4.488e-05,
59
+ "loss": 0.3611,
60
+ "step": 1024
61
+ },
62
+ {
63
+ "epoch": 0.91,
64
+ "eval_test_accuracy": 0.23010309278350516,
65
+ "eval_test_loss": 0.3209882974624634,
66
+ "eval_test_runtime": 226.4132,
67
+ "eval_test_samples_per_second": 10.711,
68
+ "eval_test_steps_per_second": 1.343,
69
+ "step": 1024
70
+ },
71
+ {
72
+ "epoch": 1.14,
73
+ "learning_rate": 4.36e-05,
74
+ "loss": 0.3469,
75
+ "step": 1280
76
+ },
77
+ {
78
+ "epoch": 1.14,
79
+ "eval_test_accuracy": 0.19505154639175257,
80
+ "eval_test_loss": 0.31938230991363525,
81
+ "eval_test_runtime": 227.1405,
82
+ "eval_test_samples_per_second": 10.676,
83
+ "eval_test_steps_per_second": 1.338,
84
+ "step": 1280
85
+ },
86
+ {
87
+ "epoch": 1.37,
88
+ "learning_rate": 4.232e-05,
89
+ "loss": 0.3301,
90
+ "step": 1536
91
+ },
92
+ {
93
+ "epoch": 1.37,
94
+ "eval_test_accuracy": 0.21608247422680413,
95
+ "eval_test_loss": 0.3045227825641632,
96
+ "eval_test_runtime": 229.033,
97
+ "eval_test_samples_per_second": 10.588,
98
+ "eval_test_steps_per_second": 1.327,
99
+ "step": 1536
100
+ },
101
+ {
102
+ "epoch": 1.59,
103
+ "learning_rate": 4.104e-05,
104
+ "loss": 0.3194,
105
+ "step": 1792
106
+ },
107
+ {
108
+ "epoch": 1.59,
109
+ "eval_test_accuracy": 0.2354639175257732,
110
+ "eval_test_loss": 0.2938610017299652,
111
+ "eval_test_runtime": 225.016,
112
+ "eval_test_samples_per_second": 10.777,
113
+ "eval_test_steps_per_second": 1.351,
114
+ "step": 1792
115
+ },
116
+ {
117
+ "epoch": 1.82,
118
+ "learning_rate": 3.9760000000000006e-05,
119
+ "loss": 0.3189,
120
+ "step": 2048
121
+ },
122
+ {
123
+ "epoch": 1.82,
124
+ "eval_test_accuracy": 0.23876288659793815,
125
+ "eval_test_loss": 0.2826090455055237,
126
+ "eval_test_runtime": 235.6637,
127
+ "eval_test_samples_per_second": 10.29,
128
+ "eval_test_steps_per_second": 1.29,
129
+ "step": 2048
130
+ },
131
+ {
132
+ "epoch": 2.05,
133
+ "learning_rate": 3.848e-05,
134
+ "loss": 0.3031,
135
+ "step": 2304
136
+ },
137
+ {
138
+ "epoch": 2.05,
139
+ "eval_test_accuracy": 0.23752577319587628,
140
+ "eval_test_loss": 0.276397705078125,
141
+ "eval_test_runtime": 228.4566,
142
+ "eval_test_samples_per_second": 10.615,
143
+ "eval_test_steps_per_second": 1.331,
144
+ "step": 2304
145
+ },
146
+ {
147
+ "epoch": 2.28,
148
+ "learning_rate": 3.72e-05,
149
+ "loss": 0.3008,
150
+ "step": 2560
151
+ },
152
+ {
153
+ "epoch": 2.28,
154
+ "eval_test_accuracy": 0.231340206185567,
155
+ "eval_test_loss": 0.27680695056915283,
156
+ "eval_test_runtime": 232.6253,
157
+ "eval_test_samples_per_second": 10.424,
158
+ "eval_test_steps_per_second": 1.307,
159
+ "step": 2560
160
+ },
161
+ {
162
+ "epoch": 2.5,
163
+ "learning_rate": 3.592e-05,
164
+ "loss": 0.2941,
165
+ "step": 2816
166
+ },
167
+ {
168
+ "epoch": 2.5,
169
+ "eval_test_accuracy": 0.24082474226804124,
170
+ "eval_test_loss": 0.27100667357444763,
171
+ "eval_test_runtime": 234.9203,
172
+ "eval_test_samples_per_second": 10.323,
173
+ "eval_test_steps_per_second": 1.294,
174
+ "step": 2816
175
+ },
176
+ {
177
+ "epoch": 2.73,
178
+ "learning_rate": 3.464e-05,
179
+ "loss": 0.2855,
180
+ "step": 3072
181
+ },
182
+ {
183
+ "epoch": 2.73,
184
+ "eval_test_accuracy": 0.2552577319587629,
185
+ "eval_test_loss": 0.26808857917785645,
186
+ "eval_test_runtime": 233.699,
187
+ "eval_test_samples_per_second": 10.377,
188
+ "eval_test_steps_per_second": 1.301,
189
+ "step": 3072
190
+ },
191
+ {
192
+ "epoch": 2.96,
193
+ "learning_rate": 3.336e-05,
194
+ "loss": 0.2827,
195
+ "step": 3328
196
+ },
197
+ {
198
+ "epoch": 2.96,
199
+ "eval_test_accuracy": 0.23876288659793815,
200
+ "eval_test_loss": 0.26740676164627075,
201
+ "eval_test_runtime": 232.615,
202
+ "eval_test_samples_per_second": 10.425,
203
+ "eval_test_steps_per_second": 1.307,
204
+ "step": 3328
205
+ },
206
+ {
207
+ "epoch": 3.19,
208
+ "learning_rate": 3.208e-05,
209
+ "loss": 0.2824,
210
+ "step": 3584
211
+ },
212
+ {
213
+ "epoch": 3.19,
214
+ "eval_test_accuracy": 0.23670103092783504,
215
+ "eval_test_loss": 0.26493921875953674,
216
+ "eval_test_runtime": 234.3958,
217
+ "eval_test_samples_per_second": 10.346,
218
+ "eval_test_steps_per_second": 1.297,
219
+ "step": 3584
220
+ },
221
+ {
222
+ "epoch": 3.41,
223
+ "learning_rate": 3.08e-05,
224
+ "loss": 0.2699,
225
+ "step": 3840
226
+ },
227
+ {
228
+ "epoch": 3.41,
229
+ "eval_test_accuracy": 0.24082474226804124,
230
+ "eval_test_loss": 0.2653910517692566,
231
+ "eval_test_runtime": 236.6454,
232
+ "eval_test_samples_per_second": 10.247,
233
+ "eval_test_steps_per_second": 1.285,
234
+ "step": 3840
235
+ },
236
+ {
237
+ "epoch": 3.64,
238
+ "learning_rate": 2.9520000000000002e-05,
239
+ "loss": 0.2744,
240
+ "step": 4096
241
+ },
242
+ {
243
+ "epoch": 3.64,
244
+ "eval_test_accuracy": 0.2503092783505155,
245
+ "eval_test_loss": 0.25940871238708496,
246
+ "eval_test_runtime": 230.5104,
247
+ "eval_test_samples_per_second": 10.52,
248
+ "eval_test_steps_per_second": 1.319,
249
+ "step": 4096
250
+ },
251
+ {
252
+ "epoch": 3.87,
253
+ "learning_rate": 2.824e-05,
254
+ "loss": 0.2679,
255
+ "step": 4352
256
+ },
257
+ {
258
+ "epoch": 3.87,
259
+ "eval_test_accuracy": 0.24824742268041236,
260
+ "eval_test_loss": 0.25839442014694214,
261
+ "eval_test_runtime": 279.8888,
262
+ "eval_test_samples_per_second": 8.664,
263
+ "eval_test_steps_per_second": 1.086,
264
+ "step": 4352
265
+ },
266
+ {
267
+ "epoch": 4.1,
268
+ "learning_rate": 2.6960000000000003e-05,
269
+ "loss": 0.27,
270
+ "step": 4608
271
+ },
272
+ {
273
+ "epoch": 4.1,
274
+ "eval_test_accuracy": 0.2465979381443299,
275
+ "eval_test_loss": 0.25590091943740845,
276
+ "eval_test_runtime": 229.037,
277
+ "eval_test_samples_per_second": 10.588,
278
+ "eval_test_steps_per_second": 1.327,
279
+ "step": 4608
280
+ },
281
+ {
282
+ "epoch": 4.32,
283
+ "learning_rate": 2.5679999999999998e-05,
284
+ "loss": 0.2644,
285
+ "step": 4864
286
+ },
287
+ {
288
+ "epoch": 4.32,
289
+ "eval_test_accuracy": 0.23835051546391753,
290
+ "eval_test_loss": 0.25387293100357056,
291
+ "eval_test_runtime": 231.73,
292
+ "eval_test_samples_per_second": 10.465,
293
+ "eval_test_steps_per_second": 1.312,
294
+ "step": 4864
295
+ },
296
+ {
297
+ "epoch": 4.55,
298
+ "learning_rate": 2.44e-05,
299
+ "loss": 0.2664,
300
+ "step": 5120
301
+ },
302
+ {
303
+ "epoch": 4.55,
304
+ "eval_test_accuracy": 0.24783505154639177,
305
+ "eval_test_loss": 0.2522536516189575,
306
+ "eval_test_runtime": 233.9019,
307
+ "eval_test_samples_per_second": 10.368,
308
+ "eval_test_steps_per_second": 1.3,
309
+ "step": 5120
310
+ },
311
+ {
312
+ "epoch": 4.78,
313
+ "learning_rate": 2.312e-05,
314
+ "loss": 0.2557,
315
+ "step": 5376
316
+ },
317
+ {
318
+ "epoch": 4.78,
319
+ "eval_test_accuracy": 0.23628865979381444,
320
+ "eval_test_loss": 0.2543907165527344,
321
+ "eval_test_runtime": 230.6139,
322
+ "eval_test_samples_per_second": 10.515,
323
+ "eval_test_steps_per_second": 1.318,
324
+ "step": 5376
325
+ },
326
+ {
327
+ "epoch": 5.01,
328
+ "learning_rate": 2.184e-05,
329
+ "loss": 0.2544,
330
+ "step": 5632
331
+ },
332
+ {
333
+ "epoch": 5.01,
334
+ "eval_test_accuracy": 0.2445360824742268,
335
+ "eval_test_loss": 0.24817436933517456,
336
+ "eval_test_runtime": 231.9449,
337
+ "eval_test_samples_per_second": 10.455,
338
+ "eval_test_steps_per_second": 1.311,
339
+ "step": 5632
340
+ },
341
+ {
342
+ "epoch": 5.23,
343
+ "learning_rate": 2.0560000000000003e-05,
344
+ "loss": 0.2549,
345
+ "step": 5888
346
+ },
347
+ {
348
+ "epoch": 5.23,
349
+ "eval_test_accuracy": 0.24618556701030928,
350
+ "eval_test_loss": 0.24915936589241028,
351
+ "eval_test_runtime": 226.5831,
352
+ "eval_test_samples_per_second": 10.702,
353
+ "eval_test_steps_per_second": 1.342,
354
+ "step": 5888
355
+ },
356
+ {
357
+ "epoch": 5.46,
358
+ "learning_rate": 1.9280000000000002e-05,
359
+ "loss": 0.2545,
360
+ "step": 6144
361
+ },
362
+ {
363
+ "epoch": 5.46,
364
+ "eval_test_accuracy": 0.2465979381443299,
365
+ "eval_test_loss": 0.2478923350572586,
366
+ "eval_test_runtime": 233.3756,
367
+ "eval_test_samples_per_second": 10.391,
368
+ "eval_test_steps_per_second": 1.303,
369
+ "step": 6144
370
+ },
371
+ {
372
+ "epoch": 5.69,
373
+ "learning_rate": 1.8e-05,
374
+ "loss": 0.2539,
375
+ "step": 6400
376
+ },
377
+ {
378
+ "epoch": 5.69,
379
+ "eval_test_accuracy": 0.24989690721649485,
380
+ "eval_test_loss": 0.24747271835803986,
381
+ "eval_test_runtime": 231.4653,
382
+ "eval_test_samples_per_second": 10.477,
383
+ "eval_test_steps_per_second": 1.313,
384
+ "step": 6400
385
+ },
386
+ {
387
+ "epoch": 5.92,
388
+ "learning_rate": 1.672e-05,
389
+ "loss": 0.2466,
390
+ "step": 6656
391
+ },
392
+ {
393
+ "epoch": 5.92,
394
+ "eval_test_accuracy": 0.24329896907216494,
395
+ "eval_test_loss": 0.24743035435676575,
396
+ "eval_test_runtime": 233.3396,
397
+ "eval_test_samples_per_second": 10.393,
398
+ "eval_test_steps_per_second": 1.303,
399
+ "step": 6656
400
+ },
401
+ {
402
+ "epoch": 6.14,
403
+ "learning_rate": 1.544e-05,
404
+ "loss": 0.2507,
405
+ "step": 6912
406
+ },
407
+ {
408
+ "epoch": 6.14,
409
+ "eval_test_accuracy": 0.25237113402061856,
410
+ "eval_test_loss": 0.24656306207180023,
411
+ "eval_test_runtime": 228.6153,
412
+ "eval_test_samples_per_second": 10.607,
413
+ "eval_test_steps_per_second": 1.33,
414
+ "step": 6912
415
+ },
416
+ {
417
+ "epoch": 6.37,
418
+ "learning_rate": 1.4160000000000002e-05,
419
+ "loss": 0.2456,
420
+ "step": 7168
421
+ },
422
+ {
423
+ "epoch": 6.37,
424
+ "eval_test_accuracy": 0.24701030927835052,
425
+ "eval_test_loss": 0.24853350222110748,
426
+ "eval_test_runtime": 228.5698,
427
+ "eval_test_samples_per_second": 10.609,
428
+ "eval_test_steps_per_second": 1.33,
429
+ "step": 7168
430
+ },
431
+ {
432
+ "epoch": 6.6,
433
+ "learning_rate": 1.288e-05,
434
+ "loss": 0.241,
435
+ "step": 7424
436
+ },
437
+ {
438
+ "epoch": 6.6,
439
+ "eval_test_accuracy": 0.2490721649484536,
440
+ "eval_test_loss": 0.2469691038131714,
441
+ "eval_test_runtime": 225.5172,
442
+ "eval_test_samples_per_second": 10.753,
443
+ "eval_test_steps_per_second": 1.348,
444
+ "step": 7424
445
+ },
446
+ {
447
+ "epoch": 6.83,
448
+ "learning_rate": 1.16e-05,
449
+ "loss": 0.2443,
450
+ "step": 7680
451
+ },
452
+ {
453
+ "epoch": 6.83,
454
+ "eval_test_accuracy": 0.24824742268041236,
455
+ "eval_test_loss": 0.24246640503406525,
456
+ "eval_test_runtime": 226.9617,
457
+ "eval_test_samples_per_second": 10.685,
458
+ "eval_test_steps_per_second": 1.339,
459
+ "step": 7680
460
+ },
461
+ {
462
+ "epoch": 7.05,
463
+ "learning_rate": 1.0320000000000001e-05,
464
+ "loss": 0.2429,
465
+ "step": 7936
466
+ },
467
+ {
468
+ "epoch": 7.05,
469
+ "eval_test_accuracy": 0.2515463917525773,
470
+ "eval_test_loss": 0.24250201880931854,
471
+ "eval_test_runtime": 228.9785,
472
+ "eval_test_samples_per_second": 10.591,
473
+ "eval_test_steps_per_second": 1.328,
474
+ "step": 7936
475
+ },
476
+ {
477
+ "epoch": 7.28,
478
+ "learning_rate": 9.04e-06,
479
+ "loss": 0.241,
480
+ "step": 8192
481
+ },
482
+ {
483
+ "epoch": 7.28,
484
+ "eval_test_accuracy": 0.25195876288659796,
485
+ "eval_test_loss": 0.24321790039539337,
486
+ "eval_test_runtime": 228.3774,
487
+ "eval_test_samples_per_second": 10.618,
488
+ "eval_test_steps_per_second": 1.331,
489
+ "step": 8192
490
+ },
491
+ {
492
+ "epoch": 7.51,
493
+ "learning_rate": 7.76e-06,
494
+ "loss": 0.2418,
495
+ "step": 8448
496
+ },
497
+ {
498
+ "epoch": 7.51,
499
+ "eval_test_accuracy": 0.2490721649484536,
500
+ "eval_test_loss": 0.24221281707286835,
501
+ "eval_test_runtime": 228.7396,
502
+ "eval_test_samples_per_second": 10.602,
503
+ "eval_test_steps_per_second": 1.329,
504
+ "step": 8448
505
+ },
506
+ {
507
+ "epoch": 7.74,
508
+ "learning_rate": 6.48e-06,
509
+ "loss": 0.2378,
510
+ "step": 8704
511
+ },
512
+ {
513
+ "epoch": 7.74,
514
+ "eval_test_accuracy": 0.2465979381443299,
515
+ "eval_test_loss": 0.24190692603588104,
516
+ "eval_test_runtime": 228.3602,
517
+ "eval_test_samples_per_second": 10.619,
518
+ "eval_test_steps_per_second": 1.331,
519
+ "step": 8704
520
+ },
521
+ {
522
+ "epoch": 7.96,
523
+ "learning_rate": 5.2e-06,
524
+ "loss": 0.2388,
525
+ "step": 8960
526
+ },
527
+ {
528
+ "epoch": 7.96,
529
+ "eval_test_accuracy": 0.25237113402061856,
530
+ "eval_test_loss": 0.24081237614154816,
531
+ "eval_test_runtime": 228.954,
532
+ "eval_test_samples_per_second": 10.592,
533
+ "eval_test_steps_per_second": 1.328,
534
+ "step": 8960
535
+ },
536
+ {
537
+ "epoch": 8.19,
538
+ "learning_rate": 3.92e-06,
539
+ "loss": 0.2304,
540
+ "step": 9216
541
+ },
542
+ {
543
+ "epoch": 8.19,
544
+ "eval_test_accuracy": 0.257319587628866,
545
+ "eval_test_loss": 0.24084854125976562,
546
+ "eval_test_runtime": 227.9624,
547
+ "eval_test_samples_per_second": 10.638,
548
+ "eval_test_steps_per_second": 1.334,
549
+ "step": 9216
550
+ },
551
+ {
552
+ "epoch": 8.42,
553
+ "learning_rate": 2.64e-06,
554
+ "loss": 0.2423,
555
+ "step": 9472
556
+ },
557
+ {
558
+ "epoch": 8.42,
559
+ "eval_test_accuracy": 0.2556701030927835,
560
+ "eval_test_loss": 0.2404756098985672,
561
+ "eval_test_runtime": 228.8532,
562
+ "eval_test_samples_per_second": 10.596,
563
+ "eval_test_steps_per_second": 1.328,
564
+ "step": 9472
565
+ },
566
+ {
567
+ "epoch": 8.65,
568
+ "learning_rate": 1.36e-06,
569
+ "loss": 0.2366,
570
+ "step": 9728
571
+ },
572
+ {
573
+ "epoch": 8.65,
574
+ "eval_test_accuracy": 0.2556701030927835,
575
+ "eval_test_loss": 0.24009202420711517,
576
+ "eval_test_runtime": 229.0313,
577
+ "eval_test_samples_per_second": 10.588,
578
+ "eval_test_steps_per_second": 1.327,
579
+ "step": 9728
580
+ },
581
+ {
582
+ "epoch": 8.87,
583
+ "learning_rate": 8e-08,
584
+ "loss": 0.2321,
585
+ "step": 9984
586
+ },
587
+ {
588
+ "epoch": 8.87,
589
+ "eval_test_accuracy": 0.25278350515463915,
590
+ "eval_test_loss": 0.23984022438526154,
591
+ "eval_test_runtime": 231.7368,
592
+ "eval_test_samples_per_second": 10.464,
593
+ "eval_test_steps_per_second": 1.312,
594
+ "step": 9984
595
+ }
596
+ ],
597
+ "logging_steps": 256,
598
+ "max_steps": 10000,
599
+ "num_input_tokens_seen": 0,
600
+ "num_train_epochs": 9,
601
+ "save_steps": 256,
602
+ "total_flos": 0.0,
603
+ "train_batch_size": 8,
604
+ "trial_name": null,
605
+ "trial_params": null
606
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:277fa10f3beb4b4af2fb7b41392e120048b1598d9ddde517c7b5e947389b9443
3
+ size 4792