tensor-tech commited on
Commit
ad13e69
·
verified ·
1 Parent(s): 16b5b1c

Run 5. Outer Step 33. Inner Step 2.

Browse files
Files changed (4) hide show
  1. config.json +293 -0
  2. generation_config.json +7 -0
  3. inner_optimizer.pt +3 -0
  4. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,293 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "all_reduce_scores": {
3
+ "0": "NON_PARTICIPATING",
4
+ "1": "SUCCESS",
5
+ "10": "SUCCESS",
6
+ "100": "NON_PARTICIPATING",
7
+ "101": "NON_PARTICIPATING",
8
+ "102": "NON_PARTICIPATING",
9
+ "103": "NON_PARTICIPATING",
10
+ "104": "NON_PARTICIPATING",
11
+ "105": "NON_PARTICIPATING",
12
+ "106": "NON_PARTICIPATING",
13
+ "107": "NON_PARTICIPATING",
14
+ "108": "NON_PARTICIPATING",
15
+ "109": "NON_PARTICIPATING",
16
+ "11": "SUCCESS",
17
+ "110": "NON_PARTICIPATING",
18
+ "111": "NON_PARTICIPATING",
19
+ "112": "NON_PARTICIPATING",
20
+ "113": "NON_PARTICIPATING",
21
+ "114": "NON_PARTICIPATING",
22
+ "115": "NON_PARTICIPATING",
23
+ "116": "NON_PARTICIPATING",
24
+ "117": "NON_PARTICIPATING",
25
+ "118": "NON_PARTICIPATING",
26
+ "119": "NON_PARTICIPATING",
27
+ "12": "SUCCESS",
28
+ "120": "NON_PARTICIPATING",
29
+ "121": "NON_PARTICIPATING",
30
+ "122": "NON_PARTICIPATING",
31
+ "123": "NON_PARTICIPATING",
32
+ "124": "NON_PARTICIPATING",
33
+ "125": "NON_PARTICIPATING",
34
+ "126": "NON_PARTICIPATING",
35
+ "127": "NON_PARTICIPATING",
36
+ "128": "NON_PARTICIPATING",
37
+ "129": "NON_PARTICIPATING",
38
+ "13": "SUCCESS",
39
+ "130": "NON_PARTICIPATING",
40
+ "131": "NON_PARTICIPATING",
41
+ "132": "NON_PARTICIPATING",
42
+ "133": "NON_PARTICIPATING",
43
+ "134": "NON_PARTICIPATING",
44
+ "135": "NON_PARTICIPATING",
45
+ "136": "NON_PARTICIPATING",
46
+ "137": "SUCCESS",
47
+ "138": "NON_PARTICIPATING",
48
+ "139": "NON_PARTICIPATING",
49
+ "14": "SUCCESS",
50
+ "140": "NON_PARTICIPATING",
51
+ "141": "NON_PARTICIPATING",
52
+ "142": "NON_PARTICIPATING",
53
+ "143": "NON_PARTICIPATING",
54
+ "144": "NON_PARTICIPATING",
55
+ "145": "NON_PARTICIPATING",
56
+ "146": "NON_PARTICIPATING",
57
+ "147": "NON_PARTICIPATING",
58
+ "148": "NON_PARTICIPATING",
59
+ "149": "NON_PARTICIPATING",
60
+ "15": "SUCCESS",
61
+ "150": "NON_PARTICIPATING",
62
+ "151": "NON_PARTICIPATING",
63
+ "152": "NON_PARTICIPATING",
64
+ "153": "NON_PARTICIPATING",
65
+ "154": "NON_PARTICIPATING",
66
+ "155": "NON_PARTICIPATING",
67
+ "156": "NON_PARTICIPATING",
68
+ "157": "NON_PARTICIPATING",
69
+ "158": "NON_PARTICIPATING",
70
+ "159": "NON_PARTICIPATING",
71
+ "16": "SUCCESS",
72
+ "160": "NON_PARTICIPATING",
73
+ "161": "NON_PARTICIPATING",
74
+ "162": "NON_PARTICIPATING",
75
+ "163": "NON_PARTICIPATING",
76
+ "164": "NON_PARTICIPATING",
77
+ "165": "NON_PARTICIPATING",
78
+ "166": "NON_PARTICIPATING",
79
+ "167": "NON_PARTICIPATING",
80
+ "168": "NON_PARTICIPATING",
81
+ "169": "NON_PARTICIPATING",
82
+ "17": "SUCCESS",
83
+ "170": "NON_PARTICIPATING",
84
+ "171": "NON_PARTICIPATING",
85
+ "172": "NON_PARTICIPATING",
86
+ "173": "NON_PARTICIPATING",
87
+ "174": "NON_PARTICIPATING",
88
+ "175": "NON_PARTICIPATING",
89
+ "176": "NON_PARTICIPATING",
90
+ "177": "NON_PARTICIPATING",
91
+ "178": "NON_PARTICIPATING",
92
+ "179": "NON_PARTICIPATING",
93
+ "18": "SUCCESS",
94
+ "180": "NON_PARTICIPATING",
95
+ "181": "SUCCESS",
96
+ "182": "NON_PARTICIPATING",
97
+ "183": "NON_PARTICIPATING",
98
+ "184": "NON_PARTICIPATING",
99
+ "185": "NON_PARTICIPATING",
100
+ "186": "NON_PARTICIPATING",
101
+ "187": "NON_PARTICIPATING",
102
+ "188": "NON_PARTICIPATING",
103
+ "189": "NON_PARTICIPATING",
104
+ "19": "SUCCESS",
105
+ "190": "NON_PARTICIPATING",
106
+ "191": "NON_PARTICIPATING",
107
+ "192": "NON_PARTICIPATING",
108
+ "193": "NON_PARTICIPATING",
109
+ "194": "NON_PARTICIPATING",
110
+ "195": "NON_PARTICIPATING",
111
+ "196": "NON_PARTICIPATING",
112
+ "197": "NON_PARTICIPATING",
113
+ "198": "NON_PARTICIPATING",
114
+ "199": "NON_PARTICIPATING",
115
+ "2": "SUCCESS",
116
+ "20": "SUCCESS",
117
+ "200": "NON_PARTICIPATING",
118
+ "201": "NON_PARTICIPATING",
119
+ "202": "NON_PARTICIPATING",
120
+ "203": "NON_PARTICIPATING",
121
+ "204": "NON_PARTICIPATING",
122
+ "205": "NON_PARTICIPATING",
123
+ "206": "NON_PARTICIPATING",
124
+ "207": "NON_PARTICIPATING",
125
+ "208": "NON_PARTICIPATING",
126
+ "209": "NON_PARTICIPATING",
127
+ "21": "SUCCESS",
128
+ "210": "NON_PARTICIPATING",
129
+ "211": "NON_PARTICIPATING",
130
+ "212": "NON_PARTICIPATING",
131
+ "213": "NON_PARTICIPATING",
132
+ "214": "NON_PARTICIPATING",
133
+ "215": "NON_PARTICIPATING",
134
+ "216": "NON_PARTICIPATING",
135
+ "217": "NON_PARTICIPATING",
136
+ "218": "NON_PARTICIPATING",
137
+ "219": "NON_PARTICIPATING",
138
+ "22": "SUCCESS",
139
+ "220": "NON_PARTICIPATING",
140
+ "221": "NON_PARTICIPATING",
141
+ "222": "NON_PARTICIPATING",
142
+ "223": "SUCCESS",
143
+ "224": "NON_PARTICIPATING",
144
+ "225": "NON_PARTICIPATING",
145
+ "226": "NON_PARTICIPATING",
146
+ "227": "NON_PARTICIPATING",
147
+ "228": "NON_PARTICIPATING",
148
+ "229": "NON_PARTICIPATING",
149
+ "23": "SUCCESS",
150
+ "230": "SUCCESS",
151
+ "231": "NON_PARTICIPATING",
152
+ "232": "NON_PARTICIPATING",
153
+ "233": "NON_PARTICIPATING",
154
+ "234": "NON_PARTICIPATING",
155
+ "235": "NON_PARTICIPATING",
156
+ "236": "NON_PARTICIPATING",
157
+ "237": "NON_PARTICIPATING",
158
+ "238": "NON_PARTICIPATING",
159
+ "239": "NON_PARTICIPATING",
160
+ "24": "SUCCESS",
161
+ "240": "NON_PARTICIPATING",
162
+ "241": "NON_PARTICIPATING",
163
+ "242": "SUCCESS",
164
+ "243": "NON_PARTICIPATING",
165
+ "244": "NON_PARTICIPATING",
166
+ "245": "NON_PARTICIPATING",
167
+ "246": "NON_PARTICIPATING",
168
+ "247": "NON_PARTICIPATING",
169
+ "248": "NON_PARTICIPATING",
170
+ "249": "NON_PARTICIPATING",
171
+ "25": "SUCCESS",
172
+ "250": "NON_PARTICIPATING",
173
+ "251": "NON_PARTICIPATING",
174
+ "252": "NON_PARTICIPATING",
175
+ "253": "NON_PARTICIPATING",
176
+ "254": "NON_PARTICIPATING",
177
+ "255": "SUCCESS",
178
+ "26": "NON_PARTICIPATING",
179
+ "27": "SUCCESS",
180
+ "28": "SUCCESS",
181
+ "29": "SUCCESS",
182
+ "3": "SUCCESS",
183
+ "30": "SUCCESS",
184
+ "31": "SUCCESS",
185
+ "32": "SUCCESS",
186
+ "33": "NON_PARTICIPATING",
187
+ "34": "NON_PARTICIPATING",
188
+ "35": "SUCCESS",
189
+ "36": "SUCCESS",
190
+ "37": "SUCCESS",
191
+ "38": "SUCCESS",
192
+ "39": "SUCCESS",
193
+ "4": "SUCCESS",
194
+ "40": "SUCCESS",
195
+ "41": "SUCCESS",
196
+ "42": "SUCCESS",
197
+ "43": "SUCCESS",
198
+ "44": "SUCCESS",
199
+ "45": "SUCCESS",
200
+ "46": "SUCCESS",
201
+ "47": "SUCCESS",
202
+ "48": "SUCCESS",
203
+ "49": "SUCCESS",
204
+ "5": "SUCCESS",
205
+ "50": "SUCCESS",
206
+ "51": "SUCCESS",
207
+ "52": "SUCCESS",
208
+ "53": "SUCCESS",
209
+ "54": "SUCCESS",
210
+ "55": "SUCCESS",
211
+ "56": "SUCCESS",
212
+ "57": "SUCCESS",
213
+ "58": "SUCCESS",
214
+ "59": "SUCCESS",
215
+ "6": "SUCCESS",
216
+ "60": "SUCCESS",
217
+ "61": "SUCCESS",
218
+ "62": "SUCCESS",
219
+ "63": "SUCCESS",
220
+ "64": "SUCCESS",
221
+ "65": "SUCCESS",
222
+ "66": "SUCCESS",
223
+ "67": "SUCCESS",
224
+ "68": "SUCCESS",
225
+ "69": "SUCCESS",
226
+ "7": "SUCCESS",
227
+ "70": "SUCCESS",
228
+ "71": "SUCCESS",
229
+ "72": "SUCCESS",
230
+ "73": "SUCCESS",
231
+ "74": "SUCCESS",
232
+ "75": "SUCCESS",
233
+ "76": "SUCCESS",
234
+ "77": "SUCCESS",
235
+ "78": "SUCCESS",
236
+ "79": "SUCCESS",
237
+ "8": "SUCCESS",
238
+ "80": "SUCCESS",
239
+ "81": "SUCCESS",
240
+ "82": "SUCCESS",
241
+ "83": "SUCCESS",
242
+ "84": "SUCCESS",
243
+ "85": "SUCCESS",
244
+ "86": "SUCCESS",
245
+ "87": "SUCCESS",
246
+ "88": "SUCCESS",
247
+ "89": "SUCCESS",
248
+ "9": "SUCCESS",
249
+ "90": "SUCCESS",
250
+ "91": "SUCCESS",
251
+ "92": "SUCCESS",
252
+ "93": "SUCCESS",
253
+ "94": "SUCCESS",
254
+ "95": "SUCCESS",
255
+ "96": "NON_PARTICIPATING",
256
+ "97": "SUCCESS",
257
+ "98": "SUCCESS",
258
+ "99": "SUCCESS"
259
+ },
260
+ "architectures": [
261
+ "LlamaForCausalLM"
262
+ ],
263
+ "attention_bias": false,
264
+ "attention_dropout": 0.0,
265
+ "block_list": [
266
+ 5744367,
267
+ 5744387
268
+ ],
269
+ "bos_token_id": 1,
270
+ "eos_token_id": 2,
271
+ "head_dim": 64,
272
+ "hidden_act": "silu",
273
+ "hidden_size": 2048,
274
+ "initializer_range": 0.02,
275
+ "inner_step": 2,
276
+ "intermediate_size": 5632,
277
+ "last_allreduce_block": 5741992,
278
+ "max_position_embeddings": 2048,
279
+ "mlp_bias": false,
280
+ "model_type": "llama",
281
+ "num_attention_heads": 32,
282
+ "num_hidden_layers": 22,
283
+ "num_key_value_heads": 4,
284
+ "pretraining_tp": 1,
285
+ "rms_norm_eps": 1e-05,
286
+ "rope_scaling": null,
287
+ "rope_theta": 10000.0,
288
+ "tie_word_embeddings": false,
289
+ "torch_dtype": "float32",
290
+ "transformers_version": "4.52.4",
291
+ "use_cache": false,
292
+ "vocab_size": 32000
293
+ }
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": "4.52.4",
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:c6e81ab8e00fb0b0812d7421ef84e8736660724ac7e33e0093c1e4033d241bf6
3
+ size 8800564561
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752c25b95c93fc63311663da47b374864504b1f97e70a820fe97af40d88dc653
3
+ size 4400216536