Hugging Face's logo

devrunner09
/
llama2-law-qa-v1

PEFT
Model card Files Community
devrunner09 commited on
Commit
3146bcf
·
1 Parent(s): 94d2846

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. README.md +32 -1
  2. adapter_model.bin +1 -1
  3. rng_state.pth +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +34 -0
  7. trainer_state.json +499 -0
  8. training_args.bin +3 -0
README.md CHANGED
@@ -1,3 +1,34 @@
1
  ---
2
- license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ library_name: peft
3
  ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.6.0.dev0
33
+
34
+ - PEFT 0.6.0.dev0
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68d38262bb084e6d2d19f104054c2e604d01e799a1fe5c0556d07cb435aaa127
3
  size 134263757
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:725f0ee2e4867c5a7affe87ea07cd402bdfa10d77f35296c876bf9941d325754
3
  size 134263757
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a03171526cf65548de1c4a878ff0008fdec7ff52d17a9e0c182dccf6bd86ba9
3
+ size 14575
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<PAD>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "use_default_system_prompt": true,
33
+ "use_fast": true
34
+ }
trainer_state.json ADDED
@@ -0,0 +1,499 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.07732755954222084,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 0.0002,
14
+ "loss": 2.1645,
15
+ "step": 25
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 0.0002,
20
+ "loss": 1.9507,
21
+ "step": 50
22
+ },
23
+ {
24
+ "epoch": 0.0,
25
+ "learning_rate": 0.0002,
26
+ "loss": 1.502,
27
+ "step": 75
28
+ },
29
+ {
30
+ "epoch": 0.0,
31
+ "learning_rate": 0.0002,
32
+ "loss": 1.7333,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 0.0,
37
+ "learning_rate": 0.0002,
38
+ "loss": 1.2266,
39
+ "step": 125
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 0.0002,
44
+ "loss": 1.604,
45
+ "step": 150
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.2927,
51
+ "step": 175
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "learning_rate": 0.0002,
56
+ "loss": 1.4849,
57
+ "step": 200
58
+ },
59
+ {
60
+ "epoch": 0.01,
61
+ "learning_rate": 0.0002,
62
+ "loss": 1.2372,
63
+ "step": 225
64
+ },
65
+ {
66
+ "epoch": 0.01,
67
+ "learning_rate": 0.0002,
68
+ "loss": 1.4155,
69
+ "step": 250
70
+ },
71
+ {
72
+ "epoch": 0.01,
73
+ "learning_rate": 0.0002,
74
+ "loss": 1.1745,
75
+ "step": 275
76
+ },
77
+ {
78
+ "epoch": 0.01,
79
+ "learning_rate": 0.0002,
80
+ "loss": 1.3327,
81
+ "step": 300
82
+ },
83
+ {
84
+ "epoch": 0.01,
85
+ "learning_rate": 0.0002,
86
+ "loss": 1.1347,
87
+ "step": 325
88
+ },
89
+ {
90
+ "epoch": 0.01,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.2828,
93
+ "step": 350
94
+ },
95
+ {
96
+ "epoch": 0.01,
97
+ "learning_rate": 0.0002,
98
+ "loss": 1.3051,
99
+ "step": 375
100
+ },
101
+ {
102
+ "epoch": 0.02,
103
+ "learning_rate": 0.0002,
104
+ "loss": 1.4646,
105
+ "step": 400
106
+ },
107
+ {
108
+ "epoch": 0.02,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.2109,
111
+ "step": 425
112
+ },
113
+ {
114
+ "epoch": 0.02,
115
+ "learning_rate": 0.0002,
116
+ "loss": 1.3195,
117
+ "step": 450
118
+ },
119
+ {
120
+ "epoch": 0.02,
121
+ "learning_rate": 0.0002,
122
+ "loss": 1.3475,
123
+ "step": 475
124
+ },
125
+ {
126
+ "epoch": 0.02,
127
+ "learning_rate": 0.0002,
128
+ "loss": 1.4109,
129
+ "step": 500
130
+ },
131
+ {
132
+ "epoch": 0.02,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.0661,
135
+ "step": 525
136
+ },
137
+ {
138
+ "epoch": 0.02,
139
+ "learning_rate": 0.0002,
140
+ "loss": 1.2554,
141
+ "step": 550
142
+ },
143
+ {
144
+ "epoch": 0.02,
145
+ "learning_rate": 0.0002,
146
+ "loss": 1.1572,
147
+ "step": 575
148
+ },
149
+ {
150
+ "epoch": 0.02,
151
+ "learning_rate": 0.0002,
152
+ "loss": 1.3693,
153
+ "step": 600
154
+ },
155
+ {
156
+ "epoch": 0.02,
157
+ "learning_rate": 0.0002,
158
+ "loss": 0.9443,
159
+ "step": 625
160
+ },
161
+ {
162
+ "epoch": 0.03,
163
+ "learning_rate": 0.0002,
164
+ "loss": 1.3281,
165
+ "step": 650
166
+ },
167
+ {
168
+ "epoch": 0.03,
169
+ "learning_rate": 0.0002,
170
+ "loss": 1.189,
171
+ "step": 675
172
+ },
173
+ {
174
+ "epoch": 0.03,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.3747,
177
+ "step": 700
178
+ },
179
+ {
180
+ "epoch": 0.03,
181
+ "learning_rate": 0.0002,
182
+ "loss": 1.0517,
183
+ "step": 725
184
+ },
185
+ {
186
+ "epoch": 0.03,
187
+ "learning_rate": 0.0002,
188
+ "loss": 1.3771,
189
+ "step": 750
190
+ },
191
+ {
192
+ "epoch": 0.03,
193
+ "learning_rate": 0.0002,
194
+ "loss": 0.9529,
195
+ "step": 775
196
+ },
197
+ {
198
+ "epoch": 0.03,
199
+ "learning_rate": 0.0002,
200
+ "loss": 1.3633,
201
+ "step": 800
202
+ },
203
+ {
204
+ "epoch": 0.03,
205
+ "learning_rate": 0.0002,
206
+ "loss": 1.1759,
207
+ "step": 825
208
+ },
209
+ {
210
+ "epoch": 0.03,
211
+ "learning_rate": 0.0002,
212
+ "loss": 1.2803,
213
+ "step": 850
214
+ },
215
+ {
216
+ "epoch": 0.03,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.1455,
219
+ "step": 875
220
+ },
221
+ {
222
+ "epoch": 0.03,
223
+ "learning_rate": 0.0002,
224
+ "loss": 1.2917,
225
+ "step": 900
226
+ },
227
+ {
228
+ "epoch": 0.04,
229
+ "learning_rate": 0.0002,
230
+ "loss": 0.9807,
231
+ "step": 925
232
+ },
233
+ {
234
+ "epoch": 0.04,
235
+ "learning_rate": 0.0002,
236
+ "loss": 1.2193,
237
+ "step": 950
238
+ },
239
+ {
240
+ "epoch": 0.04,
241
+ "learning_rate": 0.0002,
242
+ "loss": 1.0852,
243
+ "step": 975
244
+ },
245
+ {
246
+ "epoch": 0.04,
247
+ "learning_rate": 0.0002,
248
+ "loss": 1.2919,
249
+ "step": 1000
250
+ },
251
+ {
252
+ "epoch": 0.04,
253
+ "learning_rate": 0.0002,
254
+ "loss": 1.1368,
255
+ "step": 1025
256
+ },
257
+ {
258
+ "epoch": 0.04,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.2861,
261
+ "step": 1050
262
+ },
263
+ {
264
+ "epoch": 0.04,
265
+ "learning_rate": 0.0002,
266
+ "loss": 1.162,
267
+ "step": 1075
268
+ },
269
+ {
270
+ "epoch": 0.04,
271
+ "learning_rate": 0.0002,
272
+ "loss": 1.3554,
273
+ "step": 1100
274
+ },
275
+ {
276
+ "epoch": 0.04,
277
+ "learning_rate": 0.0002,
278
+ "loss": 1.0723,
279
+ "step": 1125
280
+ },
281
+ {
282
+ "epoch": 0.04,
283
+ "learning_rate": 0.0002,
284
+ "loss": 1.1713,
285
+ "step": 1150
286
+ },
287
+ {
288
+ "epoch": 0.05,
289
+ "learning_rate": 0.0002,
290
+ "loss": 1.258,
291
+ "step": 1175
292
+ },
293
+ {
294
+ "epoch": 0.05,
295
+ "learning_rate": 0.0002,
296
+ "loss": 1.3437,
297
+ "step": 1200
298
+ },
299
+ {
300
+ "epoch": 0.05,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.1127,
303
+ "step": 1225
304
+ },
305
+ {
306
+ "epoch": 0.05,
307
+ "learning_rate": 0.0002,
308
+ "loss": 1.295,
309
+ "step": 1250
310
+ },
311
+ {
312
+ "epoch": 0.05,
313
+ "learning_rate": 0.0002,
314
+ "loss": 1.0447,
315
+ "step": 1275
316
+ },
317
+ {
318
+ "epoch": 0.05,
319
+ "learning_rate": 0.0002,
320
+ "loss": 1.1771,
321
+ "step": 1300
322
+ },
323
+ {
324
+ "epoch": 0.05,
325
+ "learning_rate": 0.0002,
326
+ "loss": 1.1057,
327
+ "step": 1325
328
+ },
329
+ {
330
+ "epoch": 0.05,
331
+ "learning_rate": 0.0002,
332
+ "loss": 1.2026,
333
+ "step": 1350
334
+ },
335
+ {
336
+ "epoch": 0.05,
337
+ "learning_rate": 0.0002,
338
+ "loss": 1.1061,
339
+ "step": 1375
340
+ },
341
+ {
342
+ "epoch": 0.05,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.3012,
345
+ "step": 1400
346
+ },
347
+ {
348
+ "epoch": 0.06,
349
+ "learning_rate": 0.0002,
350
+ "loss": 1.1393,
351
+ "step": 1425
352
+ },
353
+ {
354
+ "epoch": 0.06,
355
+ "learning_rate": 0.0002,
356
+ "loss": 1.3238,
357
+ "step": 1450
358
+ },
359
+ {
360
+ "epoch": 0.06,
361
+ "learning_rate": 0.0002,
362
+ "loss": 1.1414,
363
+ "step": 1475
364
+ },
365
+ {
366
+ "epoch": 0.06,
367
+ "learning_rate": 0.0002,
368
+ "loss": 1.3037,
369
+ "step": 1500
370
+ },
371
+ {
372
+ "epoch": 0.06,
373
+ "learning_rate": 0.0002,
374
+ "loss": 1.1731,
375
+ "step": 1525
376
+ },
377
+ {
378
+ "epoch": 0.06,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.1238,
381
+ "step": 1550
382
+ },
383
+ {
384
+ "epoch": 0.06,
385
+ "learning_rate": 0.0002,
386
+ "loss": 0.9542,
387
+ "step": 1575
388
+ },
389
+ {
390
+ "epoch": 0.06,
391
+ "learning_rate": 0.0002,
392
+ "loss": 1.1471,
393
+ "step": 1600
394
+ },
395
+ {
396
+ "epoch": 0.06,
397
+ "learning_rate": 0.0002,
398
+ "loss": 0.9938,
399
+ "step": 1625
400
+ },
401
+ {
402
+ "epoch": 0.06,
403
+ "learning_rate": 0.0002,
404
+ "loss": 1.2156,
405
+ "step": 1650
406
+ },
407
+ {
408
+ "epoch": 0.06,
409
+ "learning_rate": 0.0002,
410
+ "loss": 1.03,
411
+ "step": 1675
412
+ },
413
+ {
414
+ "epoch": 0.07,
415
+ "learning_rate": 0.0002,
416
+ "loss": 1.2215,
417
+ "step": 1700
418
+ },
419
+ {
420
+ "epoch": 0.07,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.0335,
423
+ "step": 1725
424
+ },
425
+ {
426
+ "epoch": 0.07,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.3059,
429
+ "step": 1750
430
+ },
431
+ {
432
+ "epoch": 0.07,
433
+ "learning_rate": 0.0002,
434
+ "loss": 0.9583,
435
+ "step": 1775
436
+ },
437
+ {
438
+ "epoch": 0.07,
439
+ "learning_rate": 0.0002,
440
+ "loss": 1.1925,
441
+ "step": 1800
442
+ },
443
+ {
444
+ "epoch": 0.07,
445
+ "learning_rate": 0.0002,
446
+ "loss": 1.0331,
447
+ "step": 1825
448
+ },
449
+ {
450
+ "epoch": 0.07,
451
+ "learning_rate": 0.0002,
452
+ "loss": 1.2639,
453
+ "step": 1850
454
+ },
455
+ {
456
+ "epoch": 0.07,
457
+ "learning_rate": 0.0002,
458
+ "loss": 0.9898,
459
+ "step": 1875
460
+ },
461
+ {
462
+ "epoch": 0.07,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.2714,
465
+ "step": 1900
466
+ },
467
+ {
468
+ "epoch": 0.07,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.049,
471
+ "step": 1925
472
+ },
473
+ {
474
+ "epoch": 0.08,
475
+ "learning_rate": 0.0002,
476
+ "loss": 1.2586,
477
+ "step": 1950
478
+ },
479
+ {
480
+ "epoch": 0.08,
481
+ "learning_rate": 0.0002,
482
+ "loss": 1.0331,
483
+ "step": 1975
484
+ },
485
+ {
486
+ "epoch": 0.08,
487
+ "learning_rate": 0.0002,
488
+ "loss": 1.2745,
489
+ "step": 2000
490
+ }
491
+ ],
492
+ "logging_steps": 25,
493
+ "max_steps": 25864,
494
+ "num_train_epochs": 1,
495
+ "save_steps": 2000,
496
+ "total_flos": 1.6927075537256448e+16,
497
+ "trial_name": null,
498
+ "trial_params": null
499
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:673f4ce5e1fea1564a5b5c36bce4eaf7cbfa6c2129073227154255ba5cedfe7c
3
+ size 4027