Hugging Face's logo

ratishsp
/
Centrum-Large

Text2Text Generation
Transformers
PyTorch
led
Generated from Trainer
Inference Endpoints
Model card Files Community
Ratish Puduppully commited on
Commit
edd0ba2
•
1 Parent(s): 60ee64b

initial commit

Browse files
Files changed (14) hide show
  1. README.md +262 -0
  2. added_tokens.json +3 -0
  3. all_results.json +13 -0
  4. config.json +63 -0
  5. eval_results.json +8 -0
  6. merges.txt +0 -0
  7. pytorch_model.bin +3 -0
  8. special_tokens_map.json +51 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +65 -0
  11. train_results.json +8 -0
  12. trainer_state.json +0 -0
  13. training_args.bin +3 -0
  14. vocab.json +0 -0
README.md CHANGED
@@ -1,3 +1,265 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - ratishsp/newshead
7
+ model-index:
8
+ - name: Centrum
9
+ results: []
10
  ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # Centrum
16
+
17
+ Centrum is a pretrained model for multi-document summarization, trained with centroid-based pretraining objective on the NewSHead dataset. It is initialized from allenai/led-large-16384. The details of the approach are mentioned in the ACL 2023 Multi-Document Summarization with Centroid-Based Pretraining (Ratish Puduppully, Parag Jain, Nancy F. Chen and Mark Steedman). It achieves the following results on the evaluation set:
18
+
19
+ - Loss: 3.3292
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 3e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 4
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 16
46
+ - total_eval_batch_size: 16
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 10000
50
+ - training_steps: 100000
51
+ - mixed_precision_training: Native AMP
52
+ - label_smoothing_factor: 0.1
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:-----:|:------:|:---------------:|
58
+ | 3.7884 | 0.05 | 500 | 3.7054 |
59
+ | 3.6593 | 0.09 | 1000 | 3.6245 |
60
+ | 3.6425 | 0.14 | 1500 | 3.5841 |
61
+ | 3.6008 | 0.19 | 2000 | 3.5561 |
62
+ | 3.5645 | 0.23 | 2500 | 3.5372 |
63
+ | 3.568 | 0.28 | 3000 | 3.5187 |
64
+ | 3.5408 | 0.32 | 3500 | 3.5045 |
65
+ | 3.5447 | 0.37 | 4000 | 3.4951 |
66
+ | 3.5324 | 0.42 | 4500 | 3.4845 |
67
+ | 3.5192 | 0.46 | 5000 | 3.4739 |
68
+ | 3.4841 | 0.51 | 5500 | 3.4684 |
69
+ | 3.4703 | 0.56 | 6000 | 3.4604 |
70
+ | 3.4759 | 0.6 | 6500 | 3.4534 |
71
+ | 3.4647 | 0.65 | 7000 | 3.4476 |
72
+ | 3.4726 | 0.7 | 7500 | 3.4399 |
73
+ | 3.4522 | 0.74 | 8000 | 3.4332 |
74
+ | 3.4454 | 0.79 | 8500 | 3.4277 |
75
+ | 3.4281 | 0.83 | 9000 | 3.4229 |
76
+ | 3.4341 | 0.88 | 9500 | 3.4173 |
77
+ | 3.4563 | 0.93 | 10000 | 3.4161 |
78
+ | 3.4188 | 0.97 | 10500 | 3.4094 |
79
+ | 3.3967 | 1.02 | 11000 | 3.4123 |
80
+ | 3.3647 | 1.07 | 11500 | 3.4061 |
81
+ | 3.3604 | 1.11 | 12000 | 3.4011 |
82
+ | 3.3662 | 1.16 | 12500 | 3.4011 |
83
+ | 3.3698 | 1.21 | 13000 | 3.3918 |
84
+ | 3.3558 | 1.25 | 13500 | 3.3910 |
85
+ | 3.3421 | 1.3 | 14000 | 3.3891 |
86
+ | 3.3468 | 1.34 | 14500 | 3.3894 |
87
+ | 3.3333 | 1.39 | 15000 | 3.3817 |
88
+ | 3.3545 | 1.44 | 15500 | 3.3803 |
89
+ | 3.3411 | 1.48 | 16000 | 3.3784 |
90
+ | 3.3338 | 1.53 | 16500 | 3.3782 |
91
+ | 3.3354 | 1.58 | 17000 | 3.3749 |
92
+ | 3.3341 | 1.62 | 17500 | 3.3714 |
93
+ | 3.3302 | 1.67 | 18000 | 3.3677 |
94
+ | 3.3179 | 1.71 | 18500 | 3.3659 |
95
+ | 3.3381 | 1.76 | 19000 | 3.3645 |
96
+ | 3.3223 | 1.81 | 19500 | 3.3619 |
97
+ | 3.3079 | 1.85 | 20000 | 3.3593 |
98
+ | 3.3156 | 1.9 | 20500 | 3.3576 |
99
+ | 3.3056 | 1.95 | 21000 | 3.3582 |
100
+ | 3.3117 | 1.99 | 21500 | 3.3552 |
101
+ | 3.2522 | 2.04 | 22000 | 3.3550 |
102
+ | 3.2522 | 2.09 | 22500 | 3.3586 |
103
+ | 3.2386 | 2.13 | 23000 | 3.3548 |
104
+ | 3.2574 | 2.18 | 23500 | 3.3544 |
105
+ | 3.239 | 2.22 | 24000 | 3.3566 |
106
+ | 3.2468 | 2.27 | 24500 | 3.3528 |
107
+ | 3.2264 | 2.32 | 25000 | 3.3511 |
108
+ | 3.2501 | 2.36 | 25500 | 3.3482 |
109
+ | 3.2204 | 2.41 | 26000 | 3.3506 |
110
+ | 3.2302 | 2.46 | 26500 | 3.3526 |
111
+ | 3.2353 | 2.5 | 27000 | 3.3492 |
112
+ | 3.2494 | 2.55 | 27500 | 3.3452 |
113
+ | 3.2423 | 2.6 | 28000 | 3.3455 |
114
+ | 3.2233 | 2.64 | 28500 | 3.3447 |
115
+ | 3.2498 | 2.69 | 29000 | 3.3420 |
116
+ | 3.2175 | 2.73 | 29500 | 3.3457 |
117
+ | 3.2398 | 2.78 | 30000 | 3.3402 |
118
+ | 3.2242 | 2.83 | 30500 | 3.3421 |
119
+ | 3.2185 | 2.87 | 31000 | 3.3457 |
120
+ | 3.2274 | 2.92 | 31500 | 3.3419 |
121
+ | 3.2251 | 2.97 | 32000 | 3.3449 |
122
+ | 3.1507 | 3.01 | 32500 | 3.3518 |
123
+ | 3.165 | 3.06 | 33000 | 3.3462 |
124
+ | 3.1512 | 3.11 | 33500 | 3.3434 |
125
+ | 3.1598 | 3.15 | 34000 | 3.3433 |
126
+ | 3.1728 | 3.2 | 34500 | 3.3445 |
127
+ | 3.1838 | 3.24 | 35000 | 3.3456 |
128
+ | 3.1649 | 3.29 | 35500 | 3.3442 |
129
+ | 3.1684 | 3.34 | 36000 | 3.3404 |
130
+ | 3.1587 | 3.38 | 36500 | 3.3406 |
131
+ | 3.1586 | 3.43 | 37000 | 3.3442 |
132
+ | 3.1545 | 3.48 | 37500 | 3.3381 |
133
+ | 3.1674 | 3.52 | 38000 | 3.3436 |
134
+ | 3.1717 | 3.57 | 38500 | 3.3373 |
135
+ | 3.147 | 3.62 | 39000 | 3.3408 |
136
+ | 3.1462 | 3.66 | 39500 | 3.3374 |
137
+ | 3.156 | 3.71 | 40000 | 3.3382 |
138
+ | 3.1354 | 3.75 | 40500 | 3.3366 |
139
+ | 3.1613 | 3.8 | 41000 | 3.3317 |
140
+ | 3.143 | 3.85 | 41500 | 3.3347 |
141
+ | 3.1667 | 3.89 | 42000 | 3.3353 |
142
+ | 3.1597 | 3.94 | 42500 | 3.3341 |
143
+ | 3.1566 | 3.99 | 43000 | 3.3357 |
144
+ | 3.124 | 4.03 | 43500 | 3.3410 |
145
+ | 3.1035 | 4.08 | 44000 | 3.3434 |
146
+ | 3.0881 | 4.12 | 44500 | 3.3411 |
147
+ | 3.1131 | 4.17 | 45000 | 3.3379 |
148
+ | 3.1191 | 4.22 | 45500 | 3.3468 |
149
+ | 3.1119 | 4.26 | 46000 | 3.3356 |
150
+ | 3.0957 | 4.31 | 46500 | 3.3417 |
151
+ | 3.1024 | 4.36 | 47000 | 3.3380 |
152
+ | 3.1141 | 4.4 | 47500 | 3.3472 |
153
+ | 3.0851 | 4.45 | 48000 | 3.3513 |
154
+ | 3.1252 | 4.5 | 48500 | 3.3351 |
155
+ | 3.1125 | 4.54 | 49000 | 3.3423 |
156
+ | 3.1019 | 4.59 | 49500 | 3.3396 |
157
+ | 3.1185 | 4.63 | 50000 | 3.3349 |
158
+ | 3.1042 | 4.68 | 50500 | 3.3350 |
159
+ | 3.1153 | 4.73 | 51000 | 3.3345 |
160
+ | 3.1289 | 4.77 | 51500 | 3.3356 |
161
+ | 3.1075 | 4.82 | 52000 | 3.3335 |
162
+ | 3.1151 | 4.87 | 52500 | 3.3385 |
163
+ | 3.094 | 4.91 | 53000 | 3.3292 |
164
+ | 3.1272 | 4.96 | 53500 | 3.3349 |
165
+ | 3.0847 | 5.01 | 54000 | 3.3407 |
166
+ | 3.0662 | 5.05 | 54500 | 3.3378 |
167
+ | 3.0345 | 5.1 | 55000 | 3.3481 |
168
+ | 3.0611 | 5.14 | 55500 | 3.3410 |
169
+ | 3.0566 | 5.19 | 56000 | 3.3424 |
170
+ | 3.0413 | 5.24 | 56500 | 3.3466 |
171
+ | 3.0291 | 5.28 | 57000 | 3.3453 |
172
+ | 3.0569 | 5.33 | 57500 | 3.3491 |
173
+ | 3.0645 | 5.38 | 58000 | 3.3378 |
174
+ | 3.0646 | 5.42 | 58500 | 3.3434 |
175
+ | 3.045 | 5.47 | 59000 | 3.3418 |
176
+ | 3.0551 | 5.52 | 59500 | 3.3426 |
177
+ | 3.0706 | 5.56 | 60000 | 3.3378 |
178
+ | 3.0556 | 5.61 | 60500 | 3.3407 |
179
+ | 3.0743 | 5.65 | 61000 | 3.3520 |
180
+ | 3.0764 | 5.7 | 61500 | 3.3320 |
181
+ | 3.0723 | 5.75 | 62000 | 3.3352 |
182
+ | 3.0716 | 5.79 | 62500 | 3.3327 |
183
+ | 3.0618 | 5.84 | 63000 | 3.3447 |
184
+ | 3.0662 | 5.89 | 63500 | 3.3312 |
185
+ | 3.0758 | 5.93 | 64000 | 3.3323 |
186
+ | 3.0501 | 5.98 | 64500 | 3.3400 |
187
+ | 2.978 | 6.03 | 65000 | 3.3473 |
188
+ | 3.0131 | 6.07 | 65500 | 3.3440 |
189
+ | 3.0212 | 6.12 | 66000 | 3.3401 |
190
+ | 3.0095 | 6.16 | 66500 | 3.3361 |
191
+ | 3.0118 | 6.21 | 67000 | 3.3352 |
192
+ | 3.0249 | 6.26 | 67500 | 3.3398 |
193
+ | 3.0107 | 6.3 | 68000 | 3.3444 |
194
+ | 3.0175 | 6.35 | 68500 | 3.3490 |
195
+ | 3.0241 | 6.4 | 69000 | 3.3402 |
196
+ | 3.0094 | 6.44 | 69500 | 3.3437 |
197
+ | 3.0286 | 6.49 | 70000 | 3.3355 |
198
+ | 3.0391 | 6.54 | 70500 | 3.3385 |
199
+ | 3.0243 | 6.58 | 71000 | 3.3395 |
200
+ | 3.0232 | 6.63 | 71500 | 3.3370 |
201
+ | 3.0168 | 6.67 | 72000 | 3.3458 |
202
+ | 3.0432 | 6.72 | 72500 | 3.3400 |
203
+ | 3.0121 | 6.77 | 73000 | 3.3420 |
204
+ | 3.0137 | 6.81 | 73500 | 3.3436 |
205
+ | 3.0333 | 6.86 | 74000 | 3.3362 |
206
+ | 3.0194 | 6.91 | 74500 | 3.3355 |
207
+ | 3.0198 | 6.95 | 75000 | 3.3434 |
208
+ | 3.0105 | 7.0 | 75500 | 3.3346 |
209
+ | 2.9833 | 7.04 | 76000 | 3.3492 |
210
+ | 2.9876 | 7.09 | 76500 | 3.3351 |
211
+ | 2.9918 | 7.14 | 77000 | 3.3466 |
212
+ | 2.9983 | 7.18 | 77500 | 3.3422 |
213
+ | 2.9893 | 7.23 | 78000 | 3.3364 |
214
+ | 2.9946 | 7.28 | 78500 | 3.3365 |
215
+ | 2.9851 | 7.32 | 79000 | 3.3402 |
216
+ | 2.9797 | 7.37 | 79500 | 3.3450 |
217
+ | 2.9888 | 7.42 | 80000 | 3.3423 |
218
+ | 3.0182 | 7.46 | 80500 | 3.3429 |
219
+ | 2.983 | 7.51 | 81000 | 3.3345 |
220
+ | 2.9959 | 7.55 | 81500 | 3.3397 |
221
+ | 2.9935 | 7.6 | 82000 | 3.3389 |
222
+ | 3.0008 | 7.65 | 82500 | 3.3442 |
223
+ | 2.9898 | 7.69 | 83000 | 3.3418 |
224
+ | 2.9989 | 7.74 | 83500 | 3.3387 |
225
+ | 2.985 | 7.79 | 84000 | 3.3482 |
226
+ | 2.963 | 7.83 | 84500 | 3.3369 |
227
+ | 3.0009 | 7.88 | 85000 | 3.3355 |
228
+ | 2.9925 | 7.93 | 85500 | 3.3434 |
229
+ | 2.9616 | 7.97 | 86000 | 3.3346 |
230
+ | 2.9769 | 8.02 | 86500 | 3.3430 |
231
+ | 2.9663 | 8.06 | 87000 | 3.3407 |
232
+ | 2.9872 | 8.11 | 87500 | 3.3448 |
233
+ | 2.9892 | 8.16 | 88000 | 3.3354 |
234
+ | 2.9526 | 8.2 | 88500 | 3.3445 |
235
+ | 2.9426 | 8.25 | 89000 | 3.3405 |
236
+ | 2.9528 | 8.3 | 89500 | 3.3466 |
237
+ | 2.9541 | 8.34 | 90000 | 3.3434 |
238
+ | 2.9643 | 8.39 | 90500 | 3.3475 |
239
+ | 2.9893 | 8.44 | 91000 | 3.3434 |
240
+ | 2.9655 | 8.48 | 91500 | 3.3433 |
241
+ | 2.9735 | 8.53 | 92000 | 3.3416 |
242
+ | 2.9722 | 8.57 | 92500 | 3.3443 |
243
+ | 2.9639 | 8.62 | 93000 | 3.3410 |
244
+ | 2.972 | 8.67 | 93500 | 3.3407 |
245
+ | 2.9586 | 8.71 | 94000 | 3.3393 |
246
+ | 2.9591 | 8.76 | 94500 | 3.3412 |
247
+ | 2.9523 | 8.81 | 95000 | 3.3411 |
248
+ | 2.9572 | 8.85 | 95500 | 3.3393 |
249
+ | 2.9435 | 8.9 | 96000 | 3.3414 |
250
+ | 2.9667 | 8.95 | 96500 | 3.3392 |
251
+ | 2.9824 | 8.99 | 97000 | 3.3428 |
252
+ | 2.9265 | 9.04 | 97500 | 3.3417 |
253
+ | 2.9409 | 9.08 | 98000 | 3.3435 |
254
+ | 2.9387 | 9.13 | 98500 | 3.3425 |
255
+ | 2.9635 | 9.18 | 99000 | 3.3420 |
256
+ | 2.9527 | 9.22 | 99500 | 3.3421 |
257
+ | 2.9755 | 9.27 | 100000 | 3.3430 |
258
+
259
+
260
+ ### Framework versions
261
+
262
+ - Transformers 4.23.0.dev0
263
+ - Pytorch 1.12.1
264
+ - Datasets 2.6.1
265
+ - Tokenizers 0.13.1
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<doc-sep>": 50265
3
+ }
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.27,
3
+ "eval_loss": 3.329162836074829,
4
+ "eval_runtime": 58.6716,
5
+ "eval_samples": 2522,
6
+ "eval_samples_per_second": 42.985,
7
+ "eval_steps_per_second": 2.693,
8
+ "train_loss": 0.653541208190918,
9
+ "train_runtime": 35450.0434,
10
+ "train_samples": 172615,
11
+ "train_samples_per_second": 45.134,
12
+ "train_steps_per_second": 2.821
13
+ }
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/led-large-16384",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "architectures": [
7
+ "LEDForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "attention_window": [
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512
23
+ ],
24
+ "bos_token_id": 0,
25
+ "classif_dropout": 0.0,
26
+ "classifier_dropout": 0.0,
27
+ "d_model": 1024,
28
+ "decoder_attention_heads": 16,
29
+ "decoder_ffn_dim": 4096,
30
+ "decoder_layerdrop": 0.0,
31
+ "decoder_layers": 12,
32
+ "decoder_start_token_id": 2,
33
+ "dropout": 0.1,
34
+ "encoder_attention_heads": 16,
35
+ "encoder_ffn_dim": 4096,
36
+ "encoder_layerdrop": 0.0,
37
+ "encoder_layers": 12,
38
+ "eos_token_id": 2,
39
+ "gradient_checkpointing": false,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1",
43
+ "2": "LABEL_2"
44
+ },
45
+ "init_std": 0.02,
46
+ "is_encoder_decoder": true,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1,
50
+ "LABEL_2": 2
51
+ },
52
+ "max_decoder_position_embeddings": 1024,
53
+ "max_encoder_position_embeddings": 4096,
54
+ "model_type": "led",
55
+ "num_hidden_layers": 12,
56
+ "output_past": false,
57
+ "pad_token_id": 1,
58
+ "prefix": " ",
59
+ "torch_dtype": "float32",
60
+ "transformers_version": "4.23.0.dev0",
61
+ "use_cache": true,
62
+ "vocab_size": 50266
63
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.27,
3
+ "eval_loss": 3.329162836074829,
4
+ "eval_runtime": 58.6716,
5
+ "eval_samples": 2522,
6
+ "eval_samples_per_second": 42.985,
7
+ "eval_steps_per_second": 2.693
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95ddb4ef9e51bc6de78c2c9c7ac0d92951df8d0c1b18c8ac5aa1352b7e052ddb
3
+ size 1789277169
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 16384,
37
+ "name_or_path": "allenai/led-large-16384",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": "/home/co-jai1/.cache/huggingface/hub/models--allenai--led-large-16384/snapshots/04472a9a5d3af2efe700dda11da6063c68cd27a4/special_tokens_map.json",
55
+ "tokenizer_class": "LEDTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.27,
3
+ "train_loss": 0.653541208190918,
4
+ "train_runtime": 35450.0434,
5
+ "train_samples": 172615,
6
+ "train_samples_per_second": 45.134,
7
+ "train_steps_per_second": 2.821
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2cff5695acf51d4ce3eb7ca0ce822bec1f88009d90b7fa93d343f5b83056199
3
+ size 3759
vocab.json ADDED
The diff for this file is too large to render. See raw diff