kmfoda commited on
Commit
3faa21a
·
verified ·
1 Parent(s): 64b4df2

Run 8. Outer Step 0. Inner Step 0. Peers 0.

Browse files
config.json ADDED
@@ -0,0 +1,289 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PrimeIntellect/llama-1b-fresh",
3
+ "all_reduce_scores": {
4
+ "0": "SUCCESS",
5
+ "1": "SUCCESS",
6
+ "2": "SUCCESS",
7
+ "3": "SUCCESS",
8
+ "4": "SUCCESS",
9
+ "5": "SUCCESS",
10
+ "6": "SUCCESS",
11
+ "7": "SUCCESS",
12
+ "8": "SUCCESS",
13
+ "9": "SUCCESS",
14
+ "10": "SUCCESS",
15
+ "11": "SUCCESS",
16
+ "12": "SUCCESS",
17
+ "13": "SUCCESS",
18
+ "14": "SUCCESS",
19
+ "15": "SUCCESS",
20
+ "16": "SUCCESS",
21
+ "17": "SUCCESS",
22
+ "18": "SUCCESS",
23
+ "19": "SUCCESS",
24
+ "20": "SUCCESS",
25
+ "21": "SUCCESS",
26
+ "22": "SUCCESS",
27
+ "23": "SUCCESS",
28
+ "24": "SUCCESS",
29
+ "25": "SUCCESS",
30
+ "26": "SUCCESS",
31
+ "27": "SUCCESS",
32
+ "28": "SUCCESS",
33
+ "29": "SUCCESS",
34
+ "30": "SUCCESS",
35
+ "31": "SUCCESS",
36
+ "32": "SUCCESS",
37
+ "33": "SUCCESS",
38
+ "34": "SUCCESS",
39
+ "35": "SUCCESS",
40
+ "36": "SUCCESS",
41
+ "37": "SUCCESS",
42
+ "38": "SUCCESS",
43
+ "39": "SUCCESS",
44
+ "40": "SUCCESS",
45
+ "41": "SUCCESS",
46
+ "42": "SUCCESS",
47
+ "43": "SUCCESS",
48
+ "44": "SUCCESS",
49
+ "45": "SUCCESS",
50
+ "46": "SUCCESS",
51
+ "47": "SUCCESS",
52
+ "48": "SUCCESS",
53
+ "49": "SUCCESS",
54
+ "50": "SUCCESS",
55
+ "51": "SUCCESS",
56
+ "52": "SUCCESS",
57
+ "53": "SUCCESS",
58
+ "54": "SUCCESS",
59
+ "55": "SUCCESS",
60
+ "56": "SUCCESS",
61
+ "57": "SUCCESS",
62
+ "58": "SUCCESS",
63
+ "59": "SUCCESS",
64
+ "60": "SUCCESS",
65
+ "61": "SUCCESS",
66
+ "62": "SUCCESS",
67
+ "63": "SUCCESS",
68
+ "64": "SUCCESS",
69
+ "65": "SUCCESS",
70
+ "66": "SUCCESS",
71
+ "67": "SUCCESS",
72
+ "68": "SUCCESS",
73
+ "69": "SUCCESS",
74
+ "70": "SUCCESS",
75
+ "71": "SUCCESS",
76
+ "72": "SUCCESS",
77
+ "73": "SUCCESS",
78
+ "74": "SUCCESS",
79
+ "75": "SUCCESS",
80
+ "76": "SUCCESS",
81
+ "77": "SUCCESS",
82
+ "78": "SUCCESS",
83
+ "79": "SUCCESS",
84
+ "80": "SUCCESS",
85
+ "81": "SUCCESS",
86
+ "82": "SUCCESS",
87
+ "83": "SUCCESS",
88
+ "84": "SUCCESS",
89
+ "85": "SUCCESS",
90
+ "86": "SUCCESS",
91
+ "87": "SUCCESS",
92
+ "88": "SUCCESS",
93
+ "89": "SUCCESS",
94
+ "90": "SUCCESS",
95
+ "91": "SUCCESS",
96
+ "92": "SUCCESS",
97
+ "93": "SUCCESS",
98
+ "94": "SUCCESS",
99
+ "95": "SUCCESS",
100
+ "96": "SUCCESS",
101
+ "97": "SUCCESS",
102
+ "98": "SUCCESS",
103
+ "99": "SUCCESS",
104
+ "100": "SUCCESS",
105
+ "101": "SUCCESS",
106
+ "102": "SUCCESS",
107
+ "103": "SUCCESS",
108
+ "104": "SUCCESS",
109
+ "105": "SUCCESS",
110
+ "106": "SUCCESS",
111
+ "107": "SUCCESS",
112
+ "108": "SUCCESS",
113
+ "109": "SUCCESS",
114
+ "110": "SUCCESS",
115
+ "111": "SUCCESS",
116
+ "112": "SUCCESS",
117
+ "113": "SUCCESS",
118
+ "114": "SUCCESS",
119
+ "115": "SUCCESS",
120
+ "116": "SUCCESS",
121
+ "117": "SUCCESS",
122
+ "118": "SUCCESS",
123
+ "119": "SUCCESS",
124
+ "120": "SUCCESS",
125
+ "121": "SUCCESS",
126
+ "122": "SUCCESS",
127
+ "123": "SUCCESS",
128
+ "124": "SUCCESS",
129
+ "125": "SUCCESS",
130
+ "126": "SUCCESS",
131
+ "127": "SUCCESS",
132
+ "128": "SUCCESS",
133
+ "129": "SUCCESS",
134
+ "130": "SUCCESS",
135
+ "131": "SUCCESS",
136
+ "132": "SUCCESS",
137
+ "133": "SUCCESS",
138
+ "134": "SUCCESS",
139
+ "135": "SUCCESS",
140
+ "136": "SUCCESS",
141
+ "137": "SUCCESS",
142
+ "138": "SUCCESS",
143
+ "139": "SUCCESS",
144
+ "140": "SUCCESS",
145
+ "141": "SUCCESS",
146
+ "142": "SUCCESS",
147
+ "143": "SUCCESS",
148
+ "144": "SUCCESS",
149
+ "145": "SUCCESS",
150
+ "146": "SUCCESS",
151
+ "147": "SUCCESS",
152
+ "148": "SUCCESS",
153
+ "149": "SUCCESS",
154
+ "150": "SUCCESS",
155
+ "151": "SUCCESS",
156
+ "152": "SUCCESS",
157
+ "153": "SUCCESS",
158
+ "154": "SUCCESS",
159
+ "155": "SUCCESS",
160
+ "156": "SUCCESS",
161
+ "157": "SUCCESS",
162
+ "158": "SUCCESS",
163
+ "159": "SUCCESS",
164
+ "160": "SUCCESS",
165
+ "161": "SUCCESS",
166
+ "162": "SUCCESS",
167
+ "163": "SUCCESS",
168
+ "164": "SUCCESS",
169
+ "165": "SUCCESS",
170
+ "166": "SUCCESS",
171
+ "167": "SUCCESS",
172
+ "168": "SUCCESS",
173
+ "169": "SUCCESS",
174
+ "170": "SUCCESS",
175
+ "171": "SUCCESS",
176
+ "172": "SUCCESS",
177
+ "173": "SUCCESS",
178
+ "174": "SUCCESS",
179
+ "175": "SUCCESS",
180
+ "176": "SUCCESS",
181
+ "177": "SUCCESS",
182
+ "178": "SUCCESS",
183
+ "179": "SUCCESS",
184
+ "180": "SUCCESS",
185
+ "181": "SUCCESS",
186
+ "182": "SUCCESS",
187
+ "183": "SUCCESS",
188
+ "184": "SUCCESS",
189
+ "185": "SUCCESS",
190
+ "186": "SUCCESS",
191
+ "187": "SUCCESS",
192
+ "188": "SUCCESS",
193
+ "189": "SUCCESS",
194
+ "190": "SUCCESS",
195
+ "191": "SUCCESS",
196
+ "192": "SUCCESS",
197
+ "193": "SUCCESS",
198
+ "194": "SUCCESS",
199
+ "195": "SUCCESS",
200
+ "196": "SUCCESS",
201
+ "197": "SUCCESS",
202
+ "198": "SUCCESS",
203
+ "199": "SUCCESS",
204
+ "200": "SUCCESS",
205
+ "201": "SUCCESS",
206
+ "202": "SUCCESS",
207
+ "203": "SUCCESS",
208
+ "204": "SUCCESS",
209
+ "205": "SUCCESS",
210
+ "206": "SUCCESS",
211
+ "207": "SUCCESS",
212
+ "208": "SUCCESS",
213
+ "209": "SUCCESS",
214
+ "210": "SUCCESS",
215
+ "211": "SUCCESS",
216
+ "212": "SUCCESS",
217
+ "213": "SUCCESS",
218
+ "214": "SUCCESS",
219
+ "215": "SUCCESS",
220
+ "216": "SUCCESS",
221
+ "217": "SUCCESS",
222
+ "218": "SUCCESS",
223
+ "219": "SUCCESS",
224
+ "220": "SUCCESS",
225
+ "221": "SUCCESS",
226
+ "222": "SUCCESS",
227
+ "223": "SUCCESS",
228
+ "224": "SUCCESS",
229
+ "225": "SUCCESS",
230
+ "226": "SUCCESS",
231
+ "227": "SUCCESS",
232
+ "228": "SUCCESS",
233
+ "229": "SUCCESS",
234
+ "230": "SUCCESS",
235
+ "231": "SUCCESS",
236
+ "232": "SUCCESS",
237
+ "233": "SUCCESS",
238
+ "234": "SUCCESS",
239
+ "235": "SUCCESS",
240
+ "236": "SUCCESS",
241
+ "237": "SUCCESS",
242
+ "238": "SUCCESS",
243
+ "239": "SUCCESS",
244
+ "240": "SUCCESS",
245
+ "241": "SUCCESS",
246
+ "242": "SUCCESS",
247
+ "243": "SUCCESS",
248
+ "244": "SUCCESS",
249
+ "245": "SUCCESS",
250
+ "246": "SUCCESS",
251
+ "247": "SUCCESS",
252
+ "248": "SUCCESS",
253
+ "249": "SUCCESS",
254
+ "250": "SUCCESS",
255
+ "251": "SUCCESS",
256
+ "252": "SUCCESS",
257
+ "253": "SUCCESS",
258
+ "254": "SUCCESS",
259
+ "255": "SUCCESS"
260
+ },
261
+ "architectures": [
262
+ "LlamaForCausalLM"
263
+ ],
264
+ "attention_bias": false,
265
+ "attention_dropout": 0.0,
266
+ "bos_token_id": 1,
267
+ "eos_token_id": 2,
268
+ "hidden_act": "silu",
269
+ "hidden_size": 2048,
270
+ "initializer_range": 0.02,
271
+ "inner_step": 0,
272
+ "intermediate_size": 5632,
273
+ "last_allreduce_block": 6317911,
274
+ "max_position_embeddings": 2048,
275
+ "mlp_bias": false,
276
+ "model_type": "llama",
277
+ "num_attention_heads": 32,
278
+ "num_hidden_layers": 22,
279
+ "num_key_value_heads": 4,
280
+ "pretraining_tp": 1,
281
+ "rms_norm_eps": 1e-05,
282
+ "rope_scaling": null,
283
+ "rope_theta": 10000.0,
284
+ "tie_word_embeddings": false,
285
+ "torch_dtype": "float32",
286
+ "transformers_version": "4.39.3",
287
+ "use_cache": false,
288
+ "vocab_size": 32000
289
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.39.3",
6
+ "use_cache": false
7
+ }
inner_optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f03b4538aadd6f3edee22d997775232187ff14eb4f4eb85dbd4b83aa13f2e68
3
+ size 1856
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0303ea636d75eed0f7e908165b39fa6ccbcb262952c865db83ff8fa6feabd55e
3
+ size 4400216536
outer_optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8373116af142de765e312ec14dbea5e263cb207b15ffdf646956df0cfd16d879
3
+ size 4400252568
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "extra_special_tokens": {},
36
+ "legacy": false,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": null,
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }