fatihfauzan26 commited on
Commit
f96e89f
·
verified ·
1 Parent(s): 7a71936

Upload 8 files

Browse files
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/pegasus-cnn_dailymail",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "relu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "PegasusForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "d_model": 1024,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 4096,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 16,
18
+ "decoder_start_token_id": 0,
19
+ "dropout": 0.1,
20
+ "encoder_attention_heads": 16,
21
+ "encoder_ffn_dim": 4096,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 16,
24
+ "eos_token_id": 1,
25
+ "extra_pos_embeddings": 1,
26
+ "forced_eos_token_id": 1,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1",
30
+ "2": "LABEL_2"
31
+ },
32
+ "init_std": 0.02,
33
+ "is_encoder_decoder": true,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1,
37
+ "LABEL_2": 2
38
+ },
39
+ "length_penalty": null,
40
+ "max_length": null,
41
+ "max_position_embeddings": 1024,
42
+ "min_length": null,
43
+ "model_type": "pegasus",
44
+ "normalize_before": true,
45
+ "normalize_embedding": false,
46
+ "num_beams": null,
47
+ "num_hidden_layers": 16,
48
+ "pad_token_id": 0,
49
+ "scale_embedding": true,
50
+ "static_position_embeddings": true,
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.47.1",
53
+ "use_cache": true,
54
+ "vocab_size": 96103
55
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 1,
6
+ "forced_eos_token_id": 1,
7
+ "length_penalty": 0.8,
8
+ "max_length": 128,
9
+ "min_length": 32,
10
+ "num_beams": 8,
11
+ "pad_token_id": 0,
12
+ "transformers_version": "4.47.1"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a362f96e83ee63d413250e7fe697805f4b14bb2fa08e3d6801a19dda0adbfdbb
3
+ size 2283652852
optimizer (1).pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3496ff804704c71d2876bd82e25be034c105e0de9b9d5fcb2da3bab9dd6b3333
3
+ size 4550170737
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d42c643adee7fa7ed111aa44d4a23c4a2434d54cb4045c4c3b359b52ecafecf
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a03b68a83d84fa7f810e8fa677858728ac567e9540b106c0871081a534f5f0
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,467 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6250,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "grad_norm": 24.225746154785156,
14
+ "learning_rate": 1e-05,
15
+ "loss": 10.557,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.16,
20
+ "grad_norm": 24.75214385986328,
21
+ "learning_rate": 2e-05,
22
+ "loss": 9.3749,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.24,
27
+ "grad_norm": 21.598390579223633,
28
+ "learning_rate": 3e-05,
29
+ "loss": 8.3939,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.32,
34
+ "grad_norm": 12.049657821655273,
35
+ "learning_rate": 4e-05,
36
+ "loss": 4.1354,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.4,
41
+ "grad_norm": 5.240299224853516,
42
+ "learning_rate": 5e-05,
43
+ "loss": 0.9051,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.48,
48
+ "grad_norm": 6.658221244812012,
49
+ "learning_rate": 4.91304347826087e-05,
50
+ "loss": 0.737,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.56,
55
+ "grad_norm": 2.5896286964416504,
56
+ "learning_rate": 4.8260869565217394e-05,
57
+ "loss": 0.6799,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.64,
62
+ "grad_norm": 6.020174026489258,
63
+ "learning_rate": 4.739130434782609e-05,
64
+ "loss": 0.6532,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.72,
69
+ "grad_norm": 3.4233405590057373,
70
+ "learning_rate": 4.6521739130434785e-05,
71
+ "loss": 0.6223,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.8,
76
+ "grad_norm": 3.2131102085113525,
77
+ "learning_rate": 4.565217391304348e-05,
78
+ "loss": 0.5963,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.88,
83
+ "grad_norm": 2.3392815589904785,
84
+ "learning_rate": 4.478260869565218e-05,
85
+ "loss": 0.6014,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.96,
90
+ "grad_norm": 1.9733258485794067,
91
+ "learning_rate": 4.391304347826087e-05,
92
+ "loss": 0.5765,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 1.04,
97
+ "grad_norm": 2.700756788253784,
98
+ "learning_rate": 4.304347826086957e-05,
99
+ "loss": 0.554,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 1.12,
104
+ "grad_norm": 5.853904724121094,
105
+ "learning_rate": 4.2173913043478264e-05,
106
+ "loss": 0.5718,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 1.2,
111
+ "grad_norm": 4.578104496002197,
112
+ "learning_rate": 4.130434782608696e-05,
113
+ "loss": 0.5471,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 1.28,
118
+ "grad_norm": 1.733497977256775,
119
+ "learning_rate": 4.0434782608695655e-05,
120
+ "loss": 0.5577,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 1.3599999999999999,
125
+ "grad_norm": 2.4556689262390137,
126
+ "learning_rate": 3.956521739130435e-05,
127
+ "loss": 0.5367,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 1.44,
132
+ "grad_norm": 1.4540470838546753,
133
+ "learning_rate": 3.869565217391305e-05,
134
+ "loss": 0.5277,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 1.52,
139
+ "grad_norm": 2.833214521408081,
140
+ "learning_rate": 3.7826086956521736e-05,
141
+ "loss": 0.5237,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 1.6,
146
+ "grad_norm": 1.5153348445892334,
147
+ "learning_rate": 3.695652173913043e-05,
148
+ "loss": 0.5183,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 1.6800000000000002,
153
+ "grad_norm": 1.163548231124878,
154
+ "learning_rate": 3.6086956521739134e-05,
155
+ "loss": 0.4998,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 1.76,
160
+ "grad_norm": 0.9056810736656189,
161
+ "learning_rate": 3.521739130434783e-05,
162
+ "loss": 0.5205,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 1.8399999999999999,
167
+ "grad_norm": 2.93011736869812,
168
+ "learning_rate": 3.4347826086956526e-05,
169
+ "loss": 0.5067,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 1.92,
174
+ "grad_norm": 1.668942928314209,
175
+ "learning_rate": 3.347826086956522e-05,
176
+ "loss": 0.5001,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 2.0,
181
+ "grad_norm": 8.79544448852539,
182
+ "learning_rate": 3.260869565217392e-05,
183
+ "loss": 0.4944,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 2.08,
188
+ "grad_norm": 2.793776035308838,
189
+ "learning_rate": 3.173913043478261e-05,
190
+ "loss": 0.462,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 2.16,
195
+ "grad_norm": 1.993105173110962,
196
+ "learning_rate": 3.086956521739131e-05,
197
+ "loss": 0.4893,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 2.24,
202
+ "grad_norm": 1.373683214187622,
203
+ "learning_rate": 3e-05,
204
+ "loss": 0.4884,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 2.32,
209
+ "grad_norm": 2.5384674072265625,
210
+ "learning_rate": 2.9130434782608696e-05,
211
+ "loss": 0.4839,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 2.4,
216
+ "grad_norm": 1.294622778892517,
217
+ "learning_rate": 2.826086956521739e-05,
218
+ "loss": 0.4824,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 2.48,
223
+ "grad_norm": 1.2775664329528809,
224
+ "learning_rate": 2.7391304347826085e-05,
225
+ "loss": 0.4675,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 2.56,
230
+ "grad_norm": 1.2705273628234863,
231
+ "learning_rate": 2.6521739130434787e-05,
232
+ "loss": 0.4785,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 2.64,
237
+ "grad_norm": 3.2393271923065186,
238
+ "learning_rate": 2.5652173913043483e-05,
239
+ "loss": 0.4728,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 2.7199999999999998,
244
+ "grad_norm": 1.82649827003479,
245
+ "learning_rate": 2.4782608695652175e-05,
246
+ "loss": 0.474,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 2.8,
251
+ "grad_norm": 1.2423534393310547,
252
+ "learning_rate": 2.391304347826087e-05,
253
+ "loss": 0.4651,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 2.88,
258
+ "grad_norm": 1.142115831375122,
259
+ "learning_rate": 2.3043478260869567e-05,
260
+ "loss": 0.4687,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 2.96,
265
+ "grad_norm": 2.1958296298980713,
266
+ "learning_rate": 2.2173913043478262e-05,
267
+ "loss": 0.456,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 3.04,
272
+ "grad_norm": 4.805281162261963,
273
+ "learning_rate": 2.1304347826086958e-05,
274
+ "loss": 0.4439,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 3.12,
279
+ "grad_norm": 23.097047805786133,
280
+ "learning_rate": 2.0434782608695654e-05,
281
+ "loss": 0.4393,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 3.2,
286
+ "grad_norm": 3.215237617492676,
287
+ "learning_rate": 1.956521739130435e-05,
288
+ "loss": 0.4443,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 3.2800000000000002,
293
+ "grad_norm": 1.1977019309997559,
294
+ "learning_rate": 1.8695652173913045e-05,
295
+ "loss": 0.4333,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 3.36,
300
+ "grad_norm": 1.6901699304580688,
301
+ "learning_rate": 1.782608695652174e-05,
302
+ "loss": 0.4678,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 3.44,
307
+ "grad_norm": 2.7421112060546875,
308
+ "learning_rate": 1.6956521739130433e-05,
309
+ "loss": 0.4529,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 3.52,
314
+ "grad_norm": 1.5662778615951538,
315
+ "learning_rate": 1.608695652173913e-05,
316
+ "loss": 0.4399,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 3.6,
321
+ "grad_norm": 2.1081831455230713,
322
+ "learning_rate": 1.5217391304347828e-05,
323
+ "loss": 0.4531,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 3.68,
328
+ "grad_norm": 1.103431224822998,
329
+ "learning_rate": 1.4347826086956522e-05,
330
+ "loss": 0.4401,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 3.76,
335
+ "grad_norm": 1.3851810693740845,
336
+ "learning_rate": 1.3478260869565218e-05,
337
+ "loss": 0.4401,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 3.84,
342
+ "grad_norm": 1.0307343006134033,
343
+ "learning_rate": 1.2608695652173914e-05,
344
+ "loss": 0.4424,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 3.92,
349
+ "grad_norm": 1.1726175546646118,
350
+ "learning_rate": 1.173913043478261e-05,
351
+ "loss": 0.4459,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 4.0,
356
+ "grad_norm": 1.542671799659729,
357
+ "learning_rate": 1.0869565217391305e-05,
358
+ "loss": 0.4389,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 4.08,
363
+ "grad_norm": 1.4532389640808105,
364
+ "learning_rate": 1e-05,
365
+ "loss": 0.4361,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 4.16,
370
+ "grad_norm": 3.246967077255249,
371
+ "learning_rate": 9.130434782608697e-06,
372
+ "loss": 0.4452,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 4.24,
377
+ "grad_norm": 0.9646230936050415,
378
+ "learning_rate": 8.26086956521739e-06,
379
+ "loss": 0.4239,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 4.32,
384
+ "grad_norm": 1.250227451324463,
385
+ "learning_rate": 7.391304347826088e-06,
386
+ "loss": 0.4218,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 4.4,
391
+ "grad_norm": 1.2563761472702026,
392
+ "learning_rate": 6.521739130434783e-06,
393
+ "loss": 0.431,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 4.48,
398
+ "grad_norm": 0.9907436370849609,
399
+ "learning_rate": 5.652173913043479e-06,
400
+ "loss": 0.4297,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 4.5600000000000005,
405
+ "grad_norm": 1.0406742095947266,
406
+ "learning_rate": 4.782608695652174e-06,
407
+ "loss": 0.4403,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 4.64,
412
+ "grad_norm": 1.2739229202270508,
413
+ "learning_rate": 3.91304347826087e-06,
414
+ "loss": 0.438,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 4.72,
419
+ "grad_norm": 1.569171667098999,
420
+ "learning_rate": 3.0434782608695654e-06,
421
+ "loss": 0.4199,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 4.8,
426
+ "grad_norm": 1.1578859090805054,
427
+ "learning_rate": 2.173913043478261e-06,
428
+ "loss": 0.4202,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 4.88,
433
+ "grad_norm": 1.2546783685684204,
434
+ "learning_rate": 1.3043478260869564e-06,
435
+ "loss": 0.4451,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 4.96,
440
+ "grad_norm": 0.965720534324646,
441
+ "learning_rate": 4.347826086956522e-07,
442
+ "loss": 0.4295,
443
+ "step": 6200
444
+ }
445
+ ],
446
+ "logging_steps": 100,
447
+ "max_steps": 6250,
448
+ "num_input_tokens_seen": 0,
449
+ "num_train_epochs": 5,
450
+ "save_steps": 1250,
451
+ "stateful_callbacks": {
452
+ "TrainerControl": {
453
+ "args": {
454
+ "should_epoch_stop": false,
455
+ "should_evaluate": false,
456
+ "should_log": false,
457
+ "should_save": true,
458
+ "should_training_stop": true
459
+ },
460
+ "attributes": {}
461
+ }
462
+ },
463
+ "total_flos": 1.80591525888e+16,
464
+ "train_batch_size": 4,
465
+ "trial_name": null,
466
+ "trial_params": null
467
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ed61ebd1d77a551f336c1df166fbeb455da699cf69a6a154ba17645a2db084
3
+ size 5304