sandernotenbaert commited on
Commit
95c4cfd
·
verified ·
1 Parent(s): 0d9f9bb

Training in progress, step 500, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 512,
7
+ "d_kv": 64,
8
+ "d_model": 256,
9
+ "decoder_start_token_id": 1,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 4,
13
+ "feed_forward_proj": "gated-relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "max_position_embeddings": 8192,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 4,
21
+ "num_heads": 4,
22
+ "num_layers": 4,
23
+ "pad_token_id": 1,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.55.0",
28
+ "use_cache": false,
29
+ "vocab_size": 4896
30
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 1,
4
+ "eos_token_id": 4,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.55.0",
7
+ "use_cache": false
8
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e447500378fc2c31e344f6b0b4d97498178b8702113b638240f8d1ff9e5e7a
3
+ size 30214176
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a094cbe7a93565622627f7811dd85637ed7deef92f17e79e5c30b891b35853c2
3
+ size 291962
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb27e78899a7d798ea1705451f6c636a3c5c66c6987acb138f3d8eafcdfb390d
3
+ size 14244
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0e4da17c87e63c6a2b472653f2feb250c4e9e4af8dbe0562d27004625132d42
3
+ size 988
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a40ecfa3f3fd838108dc1603326181f7cc7fa9cd66a24dab20698df0575be28
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": {
105
+ "content": "[START]",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "eos_token": {
112
+ "content": "[END]",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "mask_token": {
119
+ "content": "[MASK]",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "pad_token": {
126
+ "content": "[PAD]",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false
131
+ },
132
+ "unk_token": {
133
+ "content": "[UNK]",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false
138
+ }
139
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,957 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[UNK]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[PAD]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[MASK]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[START]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[END]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "4796": {
45
+ "content": "<extra_id_0>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "4797": {
53
+ "content": "<extra_id_1>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "4798": {
61
+ "content": "<extra_id_2>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "4799": {
69
+ "content": "<extra_id_3>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "4800": {
77
+ "content": "<extra_id_4>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "4801": {
85
+ "content": "<extra_id_5>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "4802": {
93
+ "content": "<extra_id_6>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "4803": {
101
+ "content": "<extra_id_7>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "4804": {
109
+ "content": "<extra_id_8>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "4805": {
117
+ "content": "<extra_id_9>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "4806": {
125
+ "content": "<extra_id_10>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "4807": {
133
+ "content": "<extra_id_11>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "4808": {
141
+ "content": "<extra_id_12>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "4809": {
149
+ "content": "<extra_id_13>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "4810": {
157
+ "content": "<extra_id_14>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "4811": {
165
+ "content": "<extra_id_15>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "4812": {
173
+ "content": "<extra_id_16>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "4813": {
181
+ "content": "<extra_id_17>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "4814": {
189
+ "content": "<extra_id_18>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "4815": {
197
+ "content": "<extra_id_19>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "4816": {
205
+ "content": "<extra_id_20>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "4817": {
213
+ "content": "<extra_id_21>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "4818": {
221
+ "content": "<extra_id_22>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "4819": {
229
+ "content": "<extra_id_23>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "4820": {
237
+ "content": "<extra_id_24>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "4821": {
245
+ "content": "<extra_id_25>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "4822": {
253
+ "content": "<extra_id_26>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "4823": {
261
+ "content": "<extra_id_27>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "4824": {
269
+ "content": "<extra_id_28>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "4825": {
277
+ "content": "<extra_id_29>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "4826": {
285
+ "content": "<extra_id_30>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "4827": {
293
+ "content": "<extra_id_31>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "4828": {
301
+ "content": "<extra_id_32>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "4829": {
309
+ "content": "<extra_id_33>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "4830": {
317
+ "content": "<extra_id_34>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "4831": {
325
+ "content": "<extra_id_35>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "4832": {
333
+ "content": "<extra_id_36>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "4833": {
341
+ "content": "<extra_id_37>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "4834": {
349
+ "content": "<extra_id_38>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "4835": {
357
+ "content": "<extra_id_39>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "4836": {
365
+ "content": "<extra_id_40>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "4837": {
373
+ "content": "<extra_id_41>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "4838": {
381
+ "content": "<extra_id_42>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "4839": {
389
+ "content": "<extra_id_43>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "4840": {
397
+ "content": "<extra_id_44>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "4841": {
405
+ "content": "<extra_id_45>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "4842": {
413
+ "content": "<extra_id_46>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "4843": {
421
+ "content": "<extra_id_47>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "4844": {
429
+ "content": "<extra_id_48>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "4845": {
437
+ "content": "<extra_id_49>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "4846": {
445
+ "content": "<extra_id_50>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "4847": {
453
+ "content": "<extra_id_51>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "4848": {
461
+ "content": "<extra_id_52>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "4849": {
469
+ "content": "<extra_id_53>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "4850": {
477
+ "content": "<extra_id_54>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "4851": {
485
+ "content": "<extra_id_55>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "4852": {
493
+ "content": "<extra_id_56>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "4853": {
501
+ "content": "<extra_id_57>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "4854": {
509
+ "content": "<extra_id_58>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "4855": {
517
+ "content": "<extra_id_59>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "4856": {
525
+ "content": "<extra_id_60>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "4857": {
533
+ "content": "<extra_id_61>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "4858": {
541
+ "content": "<extra_id_62>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "4859": {
549
+ "content": "<extra_id_63>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "4860": {
557
+ "content": "<extra_id_64>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "4861": {
565
+ "content": "<extra_id_65>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "4862": {
573
+ "content": "<extra_id_66>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "4863": {
581
+ "content": "<extra_id_67>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "4864": {
589
+ "content": "<extra_id_68>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "4865": {
597
+ "content": "<extra_id_69>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "4866": {
605
+ "content": "<extra_id_70>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "4867": {
613
+ "content": "<extra_id_71>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "4868": {
621
+ "content": "<extra_id_72>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "4869": {
629
+ "content": "<extra_id_73>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "4870": {
637
+ "content": "<extra_id_74>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "4871": {
645
+ "content": "<extra_id_75>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "4872": {
653
+ "content": "<extra_id_76>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "4873": {
661
+ "content": "<extra_id_77>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "4874": {
669
+ "content": "<extra_id_78>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "4875": {
677
+ "content": "<extra_id_79>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "4876": {
685
+ "content": "<extra_id_80>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "4877": {
693
+ "content": "<extra_id_81>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "4878": {
701
+ "content": "<extra_id_82>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "4879": {
709
+ "content": "<extra_id_83>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "4880": {
717
+ "content": "<extra_id_84>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "4881": {
725
+ "content": "<extra_id_85>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "4882": {
733
+ "content": "<extra_id_86>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "4883": {
741
+ "content": "<extra_id_87>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "4884": {
749
+ "content": "<extra_id_88>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "4885": {
757
+ "content": "<extra_id_89>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "4886": {
765
+ "content": "<extra_id_90>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "4887": {
773
+ "content": "<extra_id_91>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "4888": {
781
+ "content": "<extra_id_92>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "4889": {
789
+ "content": "<extra_id_93>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "4890": {
797
+ "content": "<extra_id_94>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "4891": {
805
+ "content": "<extra_id_95>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "4892": {
813
+ "content": "<extra_id_96>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "4893": {
821
+ "content": "<extra_id_97>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "4894": {
829
+ "content": "<extra_id_98>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "4895": {
837
+ "content": "<extra_id_99>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ }
844
+ },
845
+ "additional_special_tokens": [
846
+ "<extra_id_0>",
847
+ "<extra_id_1>",
848
+ "<extra_id_2>",
849
+ "<extra_id_3>",
850
+ "<extra_id_4>",
851
+ "<extra_id_5>",
852
+ "<extra_id_6>",
853
+ "<extra_id_7>",
854
+ "<extra_id_8>",
855
+ "<extra_id_9>",
856
+ "<extra_id_10>",
857
+ "<extra_id_11>",
858
+ "<extra_id_12>",
859
+ "<extra_id_13>",
860
+ "<extra_id_14>",
861
+ "<extra_id_15>",
862
+ "<extra_id_16>",
863
+ "<extra_id_17>",
864
+ "<extra_id_18>",
865
+ "<extra_id_19>",
866
+ "<extra_id_20>",
867
+ "<extra_id_21>",
868
+ "<extra_id_22>",
869
+ "<extra_id_23>",
870
+ "<extra_id_24>",
871
+ "<extra_id_25>",
872
+ "<extra_id_26>",
873
+ "<extra_id_27>",
874
+ "<extra_id_28>",
875
+ "<extra_id_29>",
876
+ "<extra_id_30>",
877
+ "<extra_id_31>",
878
+ "<extra_id_32>",
879
+ "<extra_id_33>",
880
+ "<extra_id_34>",
881
+ "<extra_id_35>",
882
+ "<extra_id_36>",
883
+ "<extra_id_37>",
884
+ "<extra_id_38>",
885
+ "<extra_id_39>",
886
+ "<extra_id_40>",
887
+ "<extra_id_41>",
888
+ "<extra_id_42>",
889
+ "<extra_id_43>",
890
+ "<extra_id_44>",
891
+ "<extra_id_45>",
892
+ "<extra_id_46>",
893
+ "<extra_id_47>",
894
+ "<extra_id_48>",
895
+ "<extra_id_49>",
896
+ "<extra_id_50>",
897
+ "<extra_id_51>",
898
+ "<extra_id_52>",
899
+ "<extra_id_53>",
900
+ "<extra_id_54>",
901
+ "<extra_id_55>",
902
+ "<extra_id_56>",
903
+ "<extra_id_57>",
904
+ "<extra_id_58>",
905
+ "<extra_id_59>",
906
+ "<extra_id_60>",
907
+ "<extra_id_61>",
908
+ "<extra_id_62>",
909
+ "<extra_id_63>",
910
+ "<extra_id_64>",
911
+ "<extra_id_65>",
912
+ "<extra_id_66>",
913
+ "<extra_id_67>",
914
+ "<extra_id_68>",
915
+ "<extra_id_69>",
916
+ "<extra_id_70>",
917
+ "<extra_id_71>",
918
+ "<extra_id_72>",
919
+ "<extra_id_73>",
920
+ "<extra_id_74>",
921
+ "<extra_id_75>",
922
+ "<extra_id_76>",
923
+ "<extra_id_77>",
924
+ "<extra_id_78>",
925
+ "<extra_id_79>",
926
+ "<extra_id_80>",
927
+ "<extra_id_81>",
928
+ "<extra_id_82>",
929
+ "<extra_id_83>",
930
+ "<extra_id_84>",
931
+ "<extra_id_85>",
932
+ "<extra_id_86>",
933
+ "<extra_id_87>",
934
+ "<extra_id_88>",
935
+ "<extra_id_89>",
936
+ "<extra_id_90>",
937
+ "<extra_id_91>",
938
+ "<extra_id_92>",
939
+ "<extra_id_93>",
940
+ "<extra_id_94>",
941
+ "<extra_id_95>",
942
+ "<extra_id_96>",
943
+ "<extra_id_97>",
944
+ "<extra_id_98>",
945
+ "<extra_id_99>"
946
+ ],
947
+ "bos_token": "[START]",
948
+ "clean_up_tokenization_spaces": false,
949
+ "eos_token": "[END]",
950
+ "extra_ids": 100,
951
+ "extra_special_tokens": {},
952
+ "mask_token": "[MASK]",
953
+ "model_max_length": 1000000000000000019884624838656,
954
+ "pad_token": "[PAD]",
955
+ "tokenizer_class": "T5TokenizerFast",
956
+ "unk_token": "[UNK]"
957
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 500,
3
+ "best_metric": 1.6513175964355469,
4
+ "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-500",
5
+ "epoch": 0.2226241825518297,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.022262418255182968,
14
+ "grad_norm": 0.8790799975395203,
15
+ "learning_rate": 1.088888888888889e-05,
16
+ "loss": 1.7866,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.044524836510365935,
21
+ "grad_norm": 0.8580410480499268,
22
+ "learning_rate": 2.2000000000000003e-05,
23
+ "loss": 1.7931,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.0667872547655489,
28
+ "grad_norm": 1.150437355041504,
29
+ "learning_rate": 3.311111111111112e-05,
30
+ "loss": 1.7747,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.08904967302073187,
35
+ "grad_norm": 1.1797043085098267,
36
+ "learning_rate": 4.422222222222222e-05,
37
+ "loss": 1.7777,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.11131209127591485,
42
+ "grad_norm": 1.1714961528778076,
43
+ "learning_rate": 5e-05,
44
+ "loss": 1.7833,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.1335745095310978,
49
+ "grad_norm": 1.29172682762146,
50
+ "learning_rate": 5e-05,
51
+ "loss": 1.7813,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.15583692778628078,
56
+ "grad_norm": 1.0865519046783447,
57
+ "learning_rate": 5e-05,
58
+ "loss": 1.7737,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.17809934604146374,
63
+ "grad_norm": 1.1579242944717407,
64
+ "learning_rate": 5e-05,
65
+ "loss": 1.7716,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.20036176429664673,
70
+ "grad_norm": 1.1099216938018799,
71
+ "learning_rate": 5e-05,
72
+ "loss": 1.7877,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.2226241825518297,
77
+ "grad_norm": 1.1747430562973022,
78
+ "learning_rate": 5e-05,
79
+ "loss": 1.7839,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.2226241825518297,
84
+ "eval_loss": 1.6513175964355469,
85
+ "eval_runtime": 41.1785,
86
+ "eval_samples_per_second": 387.848,
87
+ "eval_steps_per_second": 48.496,
88
+ "step": 500
89
+ }
90
+ ],
91
+ "logging_steps": 50,
92
+ "max_steps": 11230,
93
+ "num_input_tokens_seen": 0,
94
+ "num_train_epochs": 5,
95
+ "save_steps": 500,
96
+ "stateful_callbacks": {
97
+ "EarlyStoppingCallback": {
98
+ "args": {
99
+ "early_stopping_patience": 3,
100
+ "early_stopping_threshold": 0.0
101
+ },
102
+ "attributes": {
103
+ "early_stopping_patience_counter": 0
104
+ }
105
+ },
106
+ "TrainerControl": {
107
+ "args": {
108
+ "should_epoch_stop": false,
109
+ "should_evaluate": false,
110
+ "should_log": false,
111
+ "should_save": true,
112
+ "should_training_stop": false
113
+ },
114
+ "attributes": {}
115
+ }
116
+ },
117
+ "total_flos": 482648218902528.0,
118
+ "train_batch_size": 4,
119
+ "trial_name": null,
120
+ "trial_params": null
121
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02aa50af5025c9f0ca029c8bf84c80140d605447e8fbdf2b3d4a1f55708551a3
3
+ size 5624