mgoin commited on
Commit
879bd2e
1 Parent(s): 1ece7f1

Upload folder using huggingface_hub

Browse files
arc_challenge.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "arc_challenge": {
4
+ "acc": 0.48378839590443684,
5
+ "acc_stderr": 0.014603708567414945,
6
+ "acc_norm": 0.507679180887372,
7
+ "acc_norm_stderr": 0.014609667440892574
8
+ }
9
+ },
10
+ "versions": {
11
+ "arc_challenge": 0
12
+ },
13
+ "config": {
14
+ "model": "sparseml",
15
+ "model_args": "pretrained=/nm/drive1/shubhra/cerebras/experiments/spft-retrained_sparse50_llama2_DATAUpdated_KDFalse_GCTrue_LR1e-4_E2-/combined/,trust_remote_code=True",
16
+ "num_fewshot": 25,
17
+ "batch_size": "16",
18
+ "batch_sizes": [],
19
+ "device": "cuda:0",
20
+ "no_cache": true,
21
+ "limit": null,
22
+ "bootstrap_iters": 100000,
23
+ "description_dict": {}
24
+ }
25
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 32,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "tokenizer_class": "LlamaTokenizerFast",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.36.2",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.36.2"
6
+ }
gsm8k.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "gsm8k": {
4
+ "acc": 0.16376042456406367,
5
+ "acc_stderr": 0.010193237214420945
6
+ }
7
+ },
8
+ "versions": {
9
+ "gsm8k": 0
10
+ },
11
+ "config": {
12
+ "model": "sparseml",
13
+ "model_args": "pretrained=/nm/drive1/shubhra/cerebras/experiments/spft-retrained_sparse50_llama2_DATAUpdated_KDFalse_GCTrue_LR1e-4_E2-/combined/,trust_remote_code=True",
14
+ "num_fewshot": 5,
15
+ "batch_size": "8",
16
+ "batch_sizes": [],
17
+ "device": "cuda:0",
18
+ "no_cache": true,
19
+ "limit": null,
20
+ "bootstrap_iters": 100000,
21
+ "description_dict": {}
22
+ }
23
+ }
hellaswag.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "hellaswag": {
4
+ "acc": 0.5931089424417447,
5
+ "acc_stderr": 0.0049025025147385985,
6
+ "acc_norm": 0.7885879306910973,
7
+ "acc_norm_stderr": 0.004074754687134514
8
+ }
9
+ },
10
+ "versions": {
11
+ "hellaswag": 0
12
+ },
13
+ "config": {
14
+ "model": "sparseml",
15
+ "model_args": "pretrained=/nm/drive1/shubhra/cerebras/experiments/spft-retrained_sparse50_llama2_DATAUpdated_KDFalse_GCTrue_LR1e-4_E2-/combined/,trust_remote_code=True",
16
+ "num_fewshot": 10,
17
+ "batch_size": "16",
18
+ "batch_sizes": [],
19
+ "device": "cuda:0",
20
+ "no_cache": true,
21
+ "limit": null,
22
+ "bootstrap_iters": 100000,
23
+ "description_dict": {}
24
+ }
25
+ }
mmlu.json ADDED
@@ -0,0 +1,417 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "hendrycksTest-abstract_algebra": {
4
+ "acc": 0.27,
5
+ "acc_stderr": 0.0446196043338474,
6
+ "acc_norm": 0.27,
7
+ "acc_norm_stderr": 0.0446196043338474
8
+ },
9
+ "hendrycksTest-anatomy": {
10
+ "acc": 0.4444444444444444,
11
+ "acc_stderr": 0.04292596718256981,
12
+ "acc_norm": 0.4444444444444444,
13
+ "acc_norm_stderr": 0.04292596718256981
14
+ },
15
+ "hendrycksTest-astronomy": {
16
+ "acc": 0.4473684210526316,
17
+ "acc_stderr": 0.04046336883978251,
18
+ "acc_norm": 0.4473684210526316,
19
+ "acc_norm_stderr": 0.04046336883978251
20
+ },
21
+ "hendrycksTest-business_ethics": {
22
+ "acc": 0.43,
23
+ "acc_stderr": 0.04975698519562428,
24
+ "acc_norm": 0.43,
25
+ "acc_norm_stderr": 0.04975698519562428
26
+ },
27
+ "hendrycksTest-clinical_knowledge": {
28
+ "acc": 0.4528301886792453,
29
+ "acc_stderr": 0.030635627957961823,
30
+ "acc_norm": 0.4528301886792453,
31
+ "acc_norm_stderr": 0.030635627957961823
32
+ },
33
+ "hendrycksTest-college_biology": {
34
+ "acc": 0.4513888888888889,
35
+ "acc_stderr": 0.04161402398403279,
36
+ "acc_norm": 0.4513888888888889,
37
+ "acc_norm_stderr": 0.04161402398403279
38
+ },
39
+ "hendrycksTest-college_chemistry": {
40
+ "acc": 0.37,
41
+ "acc_stderr": 0.04852365870939099,
42
+ "acc_norm": 0.37,
43
+ "acc_norm_stderr": 0.04852365870939099
44
+ },
45
+ "hendrycksTest-college_computer_science": {
46
+ "acc": 0.35,
47
+ "acc_stderr": 0.0479372485441102,
48
+ "acc_norm": 0.35,
49
+ "acc_norm_stderr": 0.0479372485441102
50
+ },
51
+ "hendrycksTest-college_mathematics": {
52
+ "acc": 0.23,
53
+ "acc_stderr": 0.04229525846816508,
54
+ "acc_norm": 0.23,
55
+ "acc_norm_stderr": 0.04229525846816508
56
+ },
57
+ "hendrycksTest-college_medicine": {
58
+ "acc": 0.3699421965317919,
59
+ "acc_stderr": 0.036812296333943194,
60
+ "acc_norm": 0.3699421965317919,
61
+ "acc_norm_stderr": 0.036812296333943194
62
+ },
63
+ "hendrycksTest-college_physics": {
64
+ "acc": 0.20588235294117646,
65
+ "acc_stderr": 0.04023382273617746,
66
+ "acc_norm": 0.20588235294117646,
67
+ "acc_norm_stderr": 0.04023382273617746
68
+ },
69
+ "hendrycksTest-computer_security": {
70
+ "acc": 0.59,
71
+ "acc_stderr": 0.049431107042371025,
72
+ "acc_norm": 0.59,
73
+ "acc_norm_stderr": 0.049431107042371025
74
+ },
75
+ "hendrycksTest-conceptual_physics": {
76
+ "acc": 0.39148936170212767,
77
+ "acc_stderr": 0.03190701242326812,
78
+ "acc_norm": 0.39148936170212767,
79
+ "acc_norm_stderr": 0.03190701242326812
80
+ },
81
+ "hendrycksTest-econometrics": {
82
+ "acc": 0.2719298245614035,
83
+ "acc_stderr": 0.04185774424022056,
84
+ "acc_norm": 0.2719298245614035,
85
+ "acc_norm_stderr": 0.04185774424022056
86
+ },
87
+ "hendrycksTest-electrical_engineering": {
88
+ "acc": 0.42758620689655175,
89
+ "acc_stderr": 0.04122737111370333,
90
+ "acc_norm": 0.42758620689655175,
91
+ "acc_norm_stderr": 0.04122737111370333
92
+ },
93
+ "hendrycksTest-elementary_mathematics": {
94
+ "acc": 0.3148148148148148,
95
+ "acc_stderr": 0.02391998416404773,
96
+ "acc_norm": 0.3148148148148148,
97
+ "acc_norm_stderr": 0.02391998416404773
98
+ },
99
+ "hendrycksTest-formal_logic": {
100
+ "acc": 0.2777777777777778,
101
+ "acc_stderr": 0.04006168083848878,
102
+ "acc_norm": 0.2777777777777778,
103
+ "acc_norm_stderr": 0.04006168083848878
104
+ },
105
+ "hendrycksTest-global_facts": {
106
+ "acc": 0.29,
107
+ "acc_stderr": 0.045604802157206845,
108
+ "acc_norm": 0.29,
109
+ "acc_norm_stderr": 0.045604802157206845
110
+ },
111
+ "hendrycksTest-high_school_biology": {
112
+ "acc": 0.5,
113
+ "acc_stderr": 0.028444006199428714,
114
+ "acc_norm": 0.5,
115
+ "acc_norm_stderr": 0.028444006199428714
116
+ },
117
+ "hendrycksTest-high_school_chemistry": {
118
+ "acc": 0.31527093596059114,
119
+ "acc_stderr": 0.03269080871970186,
120
+ "acc_norm": 0.31527093596059114,
121
+ "acc_norm_stderr": 0.03269080871970186
122
+ },
123
+ "hendrycksTest-high_school_computer_science": {
124
+ "acc": 0.44,
125
+ "acc_stderr": 0.04988876515698589,
126
+ "acc_norm": 0.44,
127
+ "acc_norm_stderr": 0.04988876515698589
128
+ },
129
+ "hendrycksTest-high_school_european_history": {
130
+ "acc": 0.593939393939394,
131
+ "acc_stderr": 0.03834816355401181,
132
+ "acc_norm": 0.593939393939394,
133
+ "acc_norm_stderr": 0.03834816355401181
134
+ },
135
+ "hendrycksTest-high_school_geography": {
136
+ "acc": 0.48484848484848486,
137
+ "acc_stderr": 0.03560716516531061,
138
+ "acc_norm": 0.48484848484848486,
139
+ "acc_norm_stderr": 0.03560716516531061
140
+ },
141
+ "hendrycksTest-high_school_government_and_politics": {
142
+ "acc": 0.6269430051813472,
143
+ "acc_stderr": 0.03490205592048573,
144
+ "acc_norm": 0.6269430051813472,
145
+ "acc_norm_stderr": 0.03490205592048573
146
+ },
147
+ "hendrycksTest-high_school_macroeconomics": {
148
+ "acc": 0.3871794871794872,
149
+ "acc_stderr": 0.02469721693087894,
150
+ "acc_norm": 0.3871794871794872,
151
+ "acc_norm_stderr": 0.02469721693087894
152
+ },
153
+ "hendrycksTest-high_school_mathematics": {
154
+ "acc": 0.2851851851851852,
155
+ "acc_stderr": 0.027528599210340496,
156
+ "acc_norm": 0.2851851851851852,
157
+ "acc_norm_stderr": 0.027528599210340496
158
+ },
159
+ "hendrycksTest-high_school_microeconomics": {
160
+ "acc": 0.42436974789915966,
161
+ "acc_stderr": 0.032104790510157764,
162
+ "acc_norm": 0.42436974789915966,
163
+ "acc_norm_stderr": 0.032104790510157764
164
+ },
165
+ "hendrycksTest-high_school_physics": {
166
+ "acc": 0.31788079470198677,
167
+ "acc_stderr": 0.03802039760107903,
168
+ "acc_norm": 0.31788079470198677,
169
+ "acc_norm_stderr": 0.03802039760107903
170
+ },
171
+ "hendrycksTest-high_school_psychology": {
172
+ "acc": 0.5743119266055046,
173
+ "acc_stderr": 0.0211992359724708,
174
+ "acc_norm": 0.5743119266055046,
175
+ "acc_norm_stderr": 0.0211992359724708
176
+ },
177
+ "hendrycksTest-high_school_statistics": {
178
+ "acc": 0.35648148148148145,
179
+ "acc_stderr": 0.03266478331527272,
180
+ "acc_norm": 0.35648148148148145,
181
+ "acc_norm_stderr": 0.03266478331527272
182
+ },
183
+ "hendrycksTest-high_school_us_history": {
184
+ "acc": 0.6029411764705882,
185
+ "acc_stderr": 0.0343413116471913,
186
+ "acc_norm": 0.6029411764705882,
187
+ "acc_norm_stderr": 0.0343413116471913
188
+ },
189
+ "hendrycksTest-high_school_world_history": {
190
+ "acc": 0.6666666666666666,
191
+ "acc_stderr": 0.0306858205966108,
192
+ "acc_norm": 0.6666666666666666,
193
+ "acc_norm_stderr": 0.0306858205966108
194
+ },
195
+ "hendrycksTest-human_aging": {
196
+ "acc": 0.5426008968609866,
197
+ "acc_stderr": 0.033435777055830646,
198
+ "acc_norm": 0.5426008968609866,
199
+ "acc_norm_stderr": 0.033435777055830646
200
+ },
201
+ "hendrycksTest-human_sexuality": {
202
+ "acc": 0.4732824427480916,
203
+ "acc_stderr": 0.04379024936553894,
204
+ "acc_norm": 0.4732824427480916,
205
+ "acc_norm_stderr": 0.04379024936553894
206
+ },
207
+ "hendrycksTest-international_law": {
208
+ "acc": 0.6776859504132231,
209
+ "acc_stderr": 0.04266416363352167,
210
+ "acc_norm": 0.6776859504132231,
211
+ "acc_norm_stderr": 0.04266416363352167
212
+ },
213
+ "hendrycksTest-jurisprudence": {
214
+ "acc": 0.5370370370370371,
215
+ "acc_stderr": 0.04820403072760627,
216
+ "acc_norm": 0.5370370370370371,
217
+ "acc_norm_stderr": 0.04820403072760627
218
+ },
219
+ "hendrycksTest-logical_fallacies": {
220
+ "acc": 0.4601226993865031,
221
+ "acc_stderr": 0.03915857291436971,
222
+ "acc_norm": 0.4601226993865031,
223
+ "acc_norm_stderr": 0.03915857291436971
224
+ },
225
+ "hendrycksTest-machine_learning": {
226
+ "acc": 0.35714285714285715,
227
+ "acc_stderr": 0.04547960999764376,
228
+ "acc_norm": 0.35714285714285715,
229
+ "acc_norm_stderr": 0.04547960999764376
230
+ },
231
+ "hendrycksTest-management": {
232
+ "acc": 0.5825242718446602,
233
+ "acc_stderr": 0.048828405482122375,
234
+ "acc_norm": 0.5825242718446602,
235
+ "acc_norm_stderr": 0.048828405482122375
236
+ },
237
+ "hendrycksTest-marketing": {
238
+ "acc": 0.6367521367521367,
239
+ "acc_stderr": 0.03150712523091264,
240
+ "acc_norm": 0.6367521367521367,
241
+ "acc_norm_stderr": 0.03150712523091264
242
+ },
243
+ "hendrycksTest-medical_genetics": {
244
+ "acc": 0.43,
245
+ "acc_stderr": 0.04975698519562428,
246
+ "acc_norm": 0.43,
247
+ "acc_norm_stderr": 0.04975698519562428
248
+ },
249
+ "hendrycksTest-miscellaneous": {
250
+ "acc": 0.6245210727969349,
251
+ "acc_stderr": 0.017316613197182786,
252
+ "acc_norm": 0.6245210727969349,
253
+ "acc_norm_stderr": 0.017316613197182786
254
+ },
255
+ "hendrycksTest-moral_disputes": {
256
+ "acc": 0.5086705202312138,
257
+ "acc_stderr": 0.026915047355369818,
258
+ "acc_norm": 0.5086705202312138,
259
+ "acc_norm_stderr": 0.026915047355369818
260
+ },
261
+ "hendrycksTest-moral_scenarios": {
262
+ "acc": 0.24134078212290502,
263
+ "acc_stderr": 0.014310999547961447,
264
+ "acc_norm": 0.24134078212290502,
265
+ "acc_norm_stderr": 0.014310999547961447
266
+ },
267
+ "hendrycksTest-nutrition": {
268
+ "acc": 0.4869281045751634,
269
+ "acc_stderr": 0.028620130800700246,
270
+ "acc_norm": 0.4869281045751634,
271
+ "acc_norm_stderr": 0.028620130800700246
272
+ },
273
+ "hendrycksTest-philosophy": {
274
+ "acc": 0.5466237942122186,
275
+ "acc_stderr": 0.028274359854894238,
276
+ "acc_norm": 0.5466237942122186,
277
+ "acc_norm_stderr": 0.028274359854894238
278
+ },
279
+ "hendrycksTest-prehistory": {
280
+ "acc": 0.5061728395061729,
281
+ "acc_stderr": 0.027818623962583295,
282
+ "acc_norm": 0.5061728395061729,
283
+ "acc_norm_stderr": 0.027818623962583295
284
+ },
285
+ "hendrycksTest-professional_accounting": {
286
+ "acc": 0.3617021276595745,
287
+ "acc_stderr": 0.0286638201471995,
288
+ "acc_norm": 0.3617021276595745,
289
+ "acc_norm_stderr": 0.0286638201471995
290
+ },
291
+ "hendrycksTest-professional_law": {
292
+ "acc": 0.3741851368970013,
293
+ "acc_stderr": 0.012359335618172061,
294
+ "acc_norm": 0.3741851368970013,
295
+ "acc_norm_stderr": 0.012359335618172061
296
+ },
297
+ "hendrycksTest-professional_medicine": {
298
+ "acc": 0.45588235294117646,
299
+ "acc_stderr": 0.030254372573976687,
300
+ "acc_norm": 0.45588235294117646,
301
+ "acc_norm_stderr": 0.030254372573976687
302
+ },
303
+ "hendrycksTest-professional_psychology": {
304
+ "acc": 0.43300653594771243,
305
+ "acc_stderr": 0.020045442473324227,
306
+ "acc_norm": 0.43300653594771243,
307
+ "acc_norm_stderr": 0.020045442473324227
308
+ },
309
+ "hendrycksTest-public_relations": {
310
+ "acc": 0.4818181818181818,
311
+ "acc_stderr": 0.04785964010794916,
312
+ "acc_norm": 0.4818181818181818,
313
+ "acc_norm_stderr": 0.04785964010794916
314
+ },
315
+ "hendrycksTest-security_studies": {
316
+ "acc": 0.5020408163265306,
317
+ "acc_stderr": 0.0320089533497105,
318
+ "acc_norm": 0.5020408163265306,
319
+ "acc_norm_stderr": 0.0320089533497105
320
+ },
321
+ "hendrycksTest-sociology": {
322
+ "acc": 0.5671641791044776,
323
+ "acc_stderr": 0.03503490923673281,
324
+ "acc_norm": 0.5671641791044776,
325
+ "acc_norm_stderr": 0.03503490923673281
326
+ },
327
+ "hendrycksTest-us_foreign_policy": {
328
+ "acc": 0.7,
329
+ "acc_stderr": 0.046056618647183814,
330
+ "acc_norm": 0.7,
331
+ "acc_norm_stderr": 0.046056618647183814
332
+ },
333
+ "hendrycksTest-virology": {
334
+ "acc": 0.3795180722891566,
335
+ "acc_stderr": 0.03777798822748018,
336
+ "acc_norm": 0.3795180722891566,
337
+ "acc_norm_stderr": 0.03777798822748018
338
+ },
339
+ "hendrycksTest-world_religions": {
340
+ "acc": 0.6783625730994152,
341
+ "acc_stderr": 0.03582529442573122,
342
+ "acc_norm": 0.6783625730994152,
343
+ "acc_norm_stderr": 0.03582529442573122
344
+ }
345
+ },
346
+ "versions": {
347
+ "hendrycksTest-abstract_algebra": 1,
348
+ "hendrycksTest-anatomy": 1,
349
+ "hendrycksTest-astronomy": 1,
350
+ "hendrycksTest-business_ethics": 1,
351
+ "hendrycksTest-clinical_knowledge": 1,
352
+ "hendrycksTest-college_biology": 1,
353
+ "hendrycksTest-college_chemistry": 1,
354
+ "hendrycksTest-college_computer_science": 1,
355
+ "hendrycksTest-college_mathematics": 1,
356
+ "hendrycksTest-college_medicine": 1,
357
+ "hendrycksTest-college_physics": 1,
358
+ "hendrycksTest-computer_security": 1,
359
+ "hendrycksTest-conceptual_physics": 1,
360
+ "hendrycksTest-econometrics": 1,
361
+ "hendrycksTest-electrical_engineering": 1,
362
+ "hendrycksTest-elementary_mathematics": 1,
363
+ "hendrycksTest-formal_logic": 1,
364
+ "hendrycksTest-global_facts": 1,
365
+ "hendrycksTest-high_school_biology": 1,
366
+ "hendrycksTest-high_school_chemistry": 1,
367
+ "hendrycksTest-high_school_computer_science": 1,
368
+ "hendrycksTest-high_school_european_history": 1,
369
+ "hendrycksTest-high_school_geography": 1,
370
+ "hendrycksTest-high_school_government_and_politics": 1,
371
+ "hendrycksTest-high_school_macroeconomics": 1,
372
+ "hendrycksTest-high_school_mathematics": 1,
373
+ "hendrycksTest-high_school_microeconomics": 1,
374
+ "hendrycksTest-high_school_physics": 1,
375
+ "hendrycksTest-high_school_psychology": 1,
376
+ "hendrycksTest-high_school_statistics": 1,
377
+ "hendrycksTest-high_school_us_history": 1,
378
+ "hendrycksTest-high_school_world_history": 1,
379
+ "hendrycksTest-human_aging": 1,
380
+ "hendrycksTest-human_sexuality": 1,
381
+ "hendrycksTest-international_law": 1,
382
+ "hendrycksTest-jurisprudence": 1,
383
+ "hendrycksTest-logical_fallacies": 1,
384
+ "hendrycksTest-machine_learning": 1,
385
+ "hendrycksTest-management": 1,
386
+ "hendrycksTest-marketing": 1,
387
+ "hendrycksTest-medical_genetics": 1,
388
+ "hendrycksTest-miscellaneous": 1,
389
+ "hendrycksTest-moral_disputes": 1,
390
+ "hendrycksTest-moral_scenarios": 1,
391
+ "hendrycksTest-nutrition": 1,
392
+ "hendrycksTest-philosophy": 1,
393
+ "hendrycksTest-prehistory": 1,
394
+ "hendrycksTest-professional_accounting": 1,
395
+ "hendrycksTest-professional_law": 1,
396
+ "hendrycksTest-professional_medicine": 1,
397
+ "hendrycksTest-professional_psychology": 1,
398
+ "hendrycksTest-public_relations": 1,
399
+ "hendrycksTest-security_studies": 1,
400
+ "hendrycksTest-sociology": 1,
401
+ "hendrycksTest-us_foreign_policy": 1,
402
+ "hendrycksTest-virology": 1,
403
+ "hendrycksTest-world_religions": 1
404
+ },
405
+ "config": {
406
+ "model": "sparseml",
407
+ "model_args": "pretrained=/nm/drive1/shubhra/cerebras/experiments/spft-retrained_sparse50_llama2_DATAUpdated_KDFalse_GCTrue_LR1e-4_E2-/combined/,trust_remote_code=True",
408
+ "num_fewshot": 5,
409
+ "batch_size": "6",
410
+ "batch_sizes": [],
411
+ "device": "cuda:0",
412
+ "no_cache": true,
413
+ "limit": null,
414
+ "bootstrap_iters": 100000,
415
+ "description_dict": {}
416
+ }
417
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e47fe9fd318069e7ee2a472dbe4ad080b4c3127b04875ccd6cf625cd1859cec8
3
+ size 4840396416
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:815a4aab0adef8956a90ee4711a9ba04746dff1ede33e0e6cd6d7283af4d99c9
3
+ size 4857206856
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:407c17215840ddff080cec2a971d22b91585b2a6ad6061a5662fe58bc93ab290
3
+ size 4857206904
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3caecadccd0780842dc4466784476142ecc702299bd78e2004e21584436e90
3
+ size 4857206904
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c45d761b7fb02c0b37f9759ff2fe21d63385d636287967161859d05133e3752e
3
+ size 4857206904
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba538e1dcc19d3549862c58a6a070c9b709a52ead548370270adcd18d6fec88
3
+ size 2684472112
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26953662464
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
296
+ "model.norm.weight": "model-00006-of-00006.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": null,
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }
truthfulqa_mc.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "truthfulqa_mc": {
4
+ "mc1": 0.29008567931456547,
5
+ "mc1_stderr": 0.01588623687420952,
6
+ "mc2": 0.44404926558063107,
7
+ "mc2_stderr": 0.015030682044375404
8
+ }
9
+ },
10
+ "versions": {
11
+ "truthfulqa_mc": 1
12
+ },
13
+ "config": {
14
+ "model": "sparseml",
15
+ "model_args": "pretrained=/nm/drive1/shubhra/cerebras/experiments/spft-retrained_sparse50_llama2_DATAUpdated_KDFalse_GCTrue_LR1e-4_E2-/combined/,trust_remote_code=True",
16
+ "num_fewshot": 0,
17
+ "batch_size": "64",
18
+ "batch_sizes": [],
19
+ "device": "cuda:0",
20
+ "no_cache": true,
21
+ "limit": null,
22
+ "bootstrap_iters": 100000,
23
+ "description_dict": {}
24
+ }
25
+ }
winogrande.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "winogrande": {
4
+ "acc": 0.7261247040252565,
5
+ "acc_stderr": 0.012533292732620292
6
+ }
7
+ },
8
+ "versions": {
9
+ "winogrande": 0
10
+ },
11
+ "config": {
12
+ "model": "sparseml",
13
+ "model_args": "pretrained=/nm/drive1/shubhra/cerebras/experiments/spft-retrained_sparse50_llama2_DATAUpdated_KDFalse_GCTrue_LR1e-4_E2-/combined/,trust_remote_code=True",
14
+ "num_fewshot": 5,
15
+ "batch_size": "64",
16
+ "batch_sizes": [],
17
+ "device": null,
18
+ "no_cache": true,
19
+ "limit": null,
20
+ "bootstrap_iters": 100000,
21
+ "description_dict": {}
22
+ }
23
+ }