Hugging Face's logo

dq158
/
morbing

Text2Text Generation
Transformers
PyTorch
t5
text-generation-inference
Inference Endpoints
Model card Files Community
dq158 commited on
Commit
19413b6
•
1 Parent(s): 4e7c8ba

Upload 8 files

Browse files
Files changed (8) hide show
  1. last-checkpoint/config.json +62 -0
  2. last-checkpoint/generation_config.json +6 -0
  3. last-checkpoint/optimizer.pt +3 -0
  4. last-checkpoint/pytorch_model.bin +3 -0
  5. last-checkpoint/rng_state.pth +3 -0
  6. last-checkpoint/scheduler.pt +3 -0
  7. last-checkpoint/trainer_state.json +429 -0
  8. last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "morbius",
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": "4.34.1",
60
+ "use_cache": true,
61
+ "vocab_size": 32128
62
+ }
last-checkpoint/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": "4.34.1"
6
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc5f7966ab751e227a273a7acdbf9909b12ac56502470ca806ef6c19af692daa
3
+ size 1832
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:459187e110db4e0fb7a78cfb68b5e2e416fc7bc717e4748019446f5cdf973209
3
+ size 990409330
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:590ca6cf7a51bd34cebcce091bf7b19ed8c4800b52fae63fdebbcb234b0e6d1d
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1860c7c6ca1e473d03a7cae1a98bbfbcae9f1a1ba246b538abe04ba78364f93
3
+ size 1064
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,429 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": NaN,
3
+ "best_model_checkpoint": "dq158/morbius/checkpoint-144",
4
+ "epoch": 19.913569576490925,
5
+ "eval_steps": 500,
6
+ "global_step": 2880,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_bleu": 1.0,
14
+ "eval_brevity_penalty": 1.0,
15
+ "eval_length_ratio": 1.0,
16
+ "eval_loss": NaN,
17
+ "eval_precisions": [
18
+ 1.0,
19
+ 1.0,
20
+ 1.0,
21
+ 1.0
22
+ ],
23
+ "eval_reference_length": 18771,
24
+ "eval_runtime": 122.4923,
25
+ "eval_samples_per_second": 8.392,
26
+ "eval_steps_per_second": 1.053,
27
+ "eval_translation_length": 18771,
28
+ "step": 144
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_bleu": 1.0,
33
+ "eval_brevity_penalty": 1.0,
34
+ "eval_length_ratio": 1.0,
35
+ "eval_loss": NaN,
36
+ "eval_precisions": [
37
+ 1.0,
38
+ 1.0,
39
+ 1.0,
40
+ 1.0
41
+ ],
42
+ "eval_reference_length": 18771,
43
+ "eval_runtime": 122.6086,
44
+ "eval_samples_per_second": 8.384,
45
+ "eval_steps_per_second": 1.052,
46
+ "eval_translation_length": 18771,
47
+ "step": 289
48
+ },
49
+ {
50
+ "epoch": 2.99,
51
+ "eval_bleu": 1.0,
52
+ "eval_brevity_penalty": 1.0,
53
+ "eval_length_ratio": 1.0,
54
+ "eval_loss": NaN,
55
+ "eval_precisions": [
56
+ 1.0,
57
+ 1.0,
58
+ 1.0,
59
+ 1.0
60
+ ],
61
+ "eval_reference_length": 18771,
62
+ "eval_runtime": 122.4683,
63
+ "eval_samples_per_second": 8.394,
64
+ "eval_steps_per_second": 1.053,
65
+ "eval_translation_length": 18771,
66
+ "step": 433
67
+ },
68
+ {
69
+ "epoch": 3.46,
70
+ "learning_rate": 1e-05,
71
+ "loss": 0.0,
72
+ "step": 500
73
+ },
74
+ {
75
+ "epoch": 4.0,
76
+ "eval_bleu": 1.0,
77
+ "eval_brevity_penalty": 1.0,
78
+ "eval_length_ratio": 1.0,
79
+ "eval_loss": NaN,
80
+ "eval_precisions": [
81
+ 1.0,
82
+ 1.0,
83
+ 1.0,
84
+ 1.0
85
+ ],
86
+ "eval_reference_length": 18771,
87
+ "eval_runtime": 122.621,
88
+ "eval_samples_per_second": 8.384,
89
+ "eval_steps_per_second": 1.052,
90
+ "eval_translation_length": 18771,
91
+ "step": 578
92
+ },
93
+ {
94
+ "epoch": 5.0,
95
+ "eval_bleu": 1.0,
96
+ "eval_brevity_penalty": 1.0,
97
+ "eval_length_ratio": 1.0,
98
+ "eval_loss": NaN,
99
+ "eval_precisions": [
100
+ 1.0,
101
+ 1.0,
102
+ 1.0,
103
+ 1.0
104
+ ],
105
+ "eval_reference_length": 18771,
106
+ "eval_runtime": 122.3833,
107
+ "eval_samples_per_second": 8.4,
108
+ "eval_steps_per_second": 1.054,
109
+ "eval_translation_length": 18771,
110
+ "step": 723
111
+ },
112
+ {
113
+ "epoch": 5.99,
114
+ "eval_bleu": 1.0,
115
+ "eval_brevity_penalty": 1.0,
116
+ "eval_length_ratio": 1.0,
117
+ "eval_loss": NaN,
118
+ "eval_precisions": [
119
+ 1.0,
120
+ 1.0,
121
+ 1.0,
122
+ 1.0
123
+ ],
124
+ "eval_reference_length": 18771,
125
+ "eval_runtime": 122.7364,
126
+ "eval_samples_per_second": 8.376,
127
+ "eval_steps_per_second": 1.051,
128
+ "eval_translation_length": 18771,
129
+ "step": 867
130
+ },
131
+ {
132
+ "epoch": 6.91,
133
+ "learning_rate": 1e-05,
134
+ "loss": 0.0,
135
+ "step": 1000
136
+ },
137
+ {
138
+ "epoch": 7.0,
139
+ "eval_bleu": 1.0,
140
+ "eval_brevity_penalty": 1.0,
141
+ "eval_length_ratio": 1.0,
142
+ "eval_loss": NaN,
143
+ "eval_precisions": [
144
+ 1.0,
145
+ 1.0,
146
+ 1.0,
147
+ 1.0
148
+ ],
149
+ "eval_reference_length": 18771,
150
+ "eval_runtime": 122.9033,
151
+ "eval_samples_per_second": 8.364,
152
+ "eval_steps_per_second": 1.05,
153
+ "eval_translation_length": 18771,
154
+ "step": 1012
155
+ },
156
+ {
157
+ "epoch": 8.0,
158
+ "eval_bleu": 1.0,
159
+ "eval_brevity_penalty": 1.0,
160
+ "eval_length_ratio": 1.0,
161
+ "eval_loss": NaN,
162
+ "eval_precisions": [
163
+ 1.0,
164
+ 1.0,
165
+ 1.0,
166
+ 1.0
167
+ ],
168
+ "eval_reference_length": 18771,
169
+ "eval_runtime": 123.0241,
170
+ "eval_samples_per_second": 8.356,
171
+ "eval_steps_per_second": 1.049,
172
+ "eval_translation_length": 18771,
173
+ "step": 1157
174
+ },
175
+ {
176
+ "epoch": 9.0,
177
+ "eval_bleu": 1.0,
178
+ "eval_brevity_penalty": 1.0,
179
+ "eval_length_ratio": 1.0,
180
+ "eval_loss": NaN,
181
+ "eval_precisions": [
182
+ 1.0,
183
+ 1.0,
184
+ 1.0,
185
+ 1.0
186
+ ],
187
+ "eval_reference_length": 18771,
188
+ "eval_runtime": 122.4135,
189
+ "eval_samples_per_second": 8.398,
190
+ "eval_steps_per_second": 1.054,
191
+ "eval_translation_length": 18771,
192
+ "step": 1301
193
+ },
194
+ {
195
+ "epoch": 10.0,
196
+ "eval_bleu": 1.0,
197
+ "eval_brevity_penalty": 1.0,
198
+ "eval_length_ratio": 1.0,
199
+ "eval_loss": NaN,
200
+ "eval_precisions": [
201
+ 1.0,
202
+ 1.0,
203
+ 1.0,
204
+ 1.0
205
+ ],
206
+ "eval_reference_length": 18771,
207
+ "eval_runtime": 122.6454,
208
+ "eval_samples_per_second": 8.382,
209
+ "eval_steps_per_second": 1.052,
210
+ "eval_translation_length": 18771,
211
+ "step": 1446
212
+ },
213
+ {
214
+ "epoch": 10.37,
215
+ "learning_rate": 1e-05,
216
+ "loss": 0.0,
217
+ "step": 1500
218
+ },
219
+ {
220
+ "epoch": 10.99,
221
+ "eval_bleu": 1.0,
222
+ "eval_brevity_penalty": 1.0,
223
+ "eval_length_ratio": 1.0,
224
+ "eval_loss": NaN,
225
+ "eval_precisions": [
226
+ 1.0,
227
+ 1.0,
228
+ 1.0,
229
+ 1.0
230
+ ],
231
+ "eval_reference_length": 18771,
232
+ "eval_runtime": 122.2623,
233
+ "eval_samples_per_second": 8.408,
234
+ "eval_steps_per_second": 1.055,
235
+ "eval_translation_length": 18771,
236
+ "step": 1590
237
+ },
238
+ {
239
+ "epoch": 12.0,
240
+ "eval_bleu": 1.0,
241
+ "eval_brevity_penalty": 1.0,
242
+ "eval_length_ratio": 1.0,
243
+ "eval_loss": NaN,
244
+ "eval_precisions": [
245
+ 1.0,
246
+ 1.0,
247
+ 1.0,
248
+ 1.0
249
+ ],
250
+ "eval_reference_length": 18771,
251
+ "eval_runtime": 122.4484,
252
+ "eval_samples_per_second": 8.395,
253
+ "eval_steps_per_second": 1.054,
254
+ "eval_translation_length": 18771,
255
+ "step": 1735
256
+ },
257
+ {
258
+ "epoch": 13.0,
259
+ "eval_bleu": 1.0,
260
+ "eval_brevity_penalty": 1.0,
261
+ "eval_length_ratio": 1.0,
262
+ "eval_loss": NaN,
263
+ "eval_precisions": [
264
+ 1.0,
265
+ 1.0,
266
+ 1.0,
267
+ 1.0
268
+ ],
269
+ "eval_reference_length": 18771,
270
+ "eval_runtime": 122.9159,
271
+ "eval_samples_per_second": 8.363,
272
+ "eval_steps_per_second": 1.049,
273
+ "eval_translation_length": 18771,
274
+ "step": 1880
275
+ },
276
+ {
277
+ "epoch": 13.83,
278
+ "learning_rate": 1e-05,
279
+ "loss": 0.0,
280
+ "step": 2000
281
+ },
282
+ {
283
+ "epoch": 13.99,
284
+ "eval_bleu": 1.0,
285
+ "eval_brevity_penalty": 1.0,
286
+ "eval_length_ratio": 1.0,
287
+ "eval_loss": NaN,
288
+ "eval_precisions": [
289
+ 1.0,
290
+ 1.0,
291
+ 1.0,
292
+ 1.0
293
+ ],
294
+ "eval_reference_length": 18771,
295
+ "eval_runtime": 122.5545,
296
+ "eval_samples_per_second": 8.388,
297
+ "eval_steps_per_second": 1.053,
298
+ "eval_translation_length": 18771,
299
+ "step": 2024
300
+ },
301
+ {
302
+ "epoch": 15.0,
303
+ "eval_bleu": 1.0,
304
+ "eval_brevity_penalty": 1.0,
305
+ "eval_length_ratio": 1.0,
306
+ "eval_loss": NaN,
307
+ "eval_precisions": [
308
+ 1.0,
309
+ 1.0,
310
+ 1.0,
311
+ 1.0
312
+ ],
313
+ "eval_reference_length": 18771,
314
+ "eval_runtime": 122.6122,
315
+ "eval_samples_per_second": 8.384,
316
+ "eval_steps_per_second": 1.052,
317
+ "eval_translation_length": 18771,
318
+ "step": 2169
319
+ },
320
+ {
321
+ "epoch": 16.0,
322
+ "eval_bleu": 1.0,
323
+ "eval_brevity_penalty": 1.0,
324
+ "eval_length_ratio": 1.0,
325
+ "eval_loss": NaN,
326
+ "eval_precisions": [
327
+ 1.0,
328
+ 1.0,
329
+ 1.0,
330
+ 1.0
331
+ ],
332
+ "eval_reference_length": 18771,
333
+ "eval_runtime": 122.6643,
334
+ "eval_samples_per_second": 8.381,
335
+ "eval_steps_per_second": 1.052,
336
+ "eval_translation_length": 18771,
337
+ "step": 2314
338
+ },
339
+ {
340
+ "epoch": 17.0,
341
+ "eval_bleu": 1.0,
342
+ "eval_brevity_penalty": 1.0,
343
+ "eval_length_ratio": 1.0,
344
+ "eval_loss": NaN,
345
+ "eval_precisions": [
346
+ 1.0,
347
+ 1.0,
348
+ 1.0,
349
+ 1.0
350
+ ],
351
+ "eval_reference_length": 18771,
352
+ "eval_runtime": 122.6275,
353
+ "eval_samples_per_second": 8.383,
354
+ "eval_steps_per_second": 1.052,
355
+ "eval_translation_length": 18771,
356
+ "step": 2458
357
+ },
358
+ {
359
+ "epoch": 17.29,
360
+ "learning_rate": 1e-05,
361
+ "loss": 0.0,
362
+ "step": 2500
363
+ },
364
+ {
365
+ "epoch": 18.0,
366
+ "eval_bleu": 1.0,
367
+ "eval_brevity_penalty": 1.0,
368
+ "eval_length_ratio": 1.0,
369
+ "eval_loss": NaN,
370
+ "eval_precisions": [
371
+ 1.0,
372
+ 1.0,
373
+ 1.0,
374
+ 1.0
375
+ ],
376
+ "eval_reference_length": 18771,
377
+ "eval_runtime": 122.8755,
378
+ "eval_samples_per_second": 8.366,
379
+ "eval_steps_per_second": 1.05,
380
+ "eval_translation_length": 18771,
381
+ "step": 2603
382
+ },
383
+ {
384
+ "epoch": 18.99,
385
+ "eval_bleu": 1.0,
386
+ "eval_brevity_penalty": 1.0,
387
+ "eval_length_ratio": 1.0,
388
+ "eval_loss": NaN,
389
+ "eval_precisions": [
390
+ 1.0,
391
+ 1.0,
392
+ 1.0,
393
+ 1.0
394
+ ],
395
+ "eval_reference_length": 18771,
396
+ "eval_runtime": 122.518,
397
+ "eval_samples_per_second": 8.391,
398
+ "eval_steps_per_second": 1.053,
399
+ "eval_translation_length": 18771,
400
+ "step": 2747
401
+ },
402
+ {
403
+ "epoch": 19.91,
404
+ "eval_bleu": 1.0,
405
+ "eval_brevity_penalty": 1.0,
406
+ "eval_length_ratio": 1.0,
407
+ "eval_loss": NaN,
408
+ "eval_precisions": [
409
+ 1.0,
410
+ 1.0,
411
+ 1.0,
412
+ 1.0
413
+ ],
414
+ "eval_reference_length": 18771,
415
+ "eval_runtime": 122.5437,
416
+ "eval_samples_per_second": 8.389,
417
+ "eval_steps_per_second": 1.053,
418
+ "eval_translation_length": 18771,
419
+ "step": 2880
420
+ }
421
+ ],
422
+ "logging_steps": 500,
423
+ "max_steps": 2880,
424
+ "num_train_epochs": 20,
425
+ "save_steps": 500,
426
+ "total_flos": 1.2616243364442931e+17,
427
+ "trial_name": null,
428
+ "trial_params": null
429
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e101b52461267c553f7820ea490d90f0c52a8eee984bb696ad906e06ac49bd9a
3
+ size 4664