kmfoda commited on
Commit
1e903d9
·
verified ·
1 Parent(s): 811a719

Run 10. Outer Step 102. Inner Step 0. Peers 64.

Browse files
Files changed (4) hide show
  1. config.json +43 -43
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "aalv2/c67-h25",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NON_PARTICIPATING",
@@ -13,28 +13,28 @@
13
  "106": "SUCCESS",
14
  "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
- "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
- "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
- "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "SUCCESS",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
- "123": "NOT_ALIVE",
33
  "124": "SUCCESS",
34
  "125": "NON_PARTICIPATING",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
@@ -42,13 +42,13 @@
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
- "135": "NOT_ALIVE",
46
- "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
@@ -66,9 +66,9 @@
66
  "154": "NON_PARTICIPATING",
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
- "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
- "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
  "161": "NON_PARTICIPATING",
@@ -76,17 +76,17 @@
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
- "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
- "170": "SUCCESS",
85
- "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
- "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
@@ -97,13 +97,13 @@
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
- "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
- "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
@@ -121,11 +121,11 @@
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
- "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
- "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
@@ -137,14 +137,14 @@
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
- "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "NON_PARTICIPATING",
147
- "227": "NOT_ALIVE",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
@@ -170,7 +170,7 @@
170
  "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
@@ -180,15 +180,15 @@
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "NON_PARTICIPATING",
183
- "3": "SUCCESS",
184
- "30": "NOT_ALIVE",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
- "36": "NON_PARTICIPATING",
191
- "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
@@ -196,10 +196,10 @@
196
  "41": "NOT_ALIVE",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
- "44": "NOT_ALIVE",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
- "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
@@ -210,32 +210,32 @@
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
- "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
- "59": "SUCCESS",
216
  "6": "NON_PARTICIPATING",
217
  "60": "SUCCESS",
218
  "61": "SUCCESS",
219
- "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
- "7": "NON_PARTICIPATING",
228
- "70": "SUCCESS",
229
  "71": "SUCCESS",
230
  "72": "SUCCESS",
231
  "73": "NOT_ALIVE",
232
- "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
- "79": "SUCCESS",
238
- "8": "NOT_ALIVE",
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
@@ -243,12 +243,12 @@
243
  "84": "SUCCESS",
244
  "85": "NOT_ALIVE",
245
  "86": "SUCCESS",
246
- "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
- "91": "NON_PARTICIPATING",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6521671,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "aalv2/c71-h22",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NON_PARTICIPATING",
 
13
  "106": "SUCCESS",
14
  "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
+ "109": "SUCCESS",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
+ "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "NON_PARTICIPATING",
26
  "118": "SUCCESS",
27
  "119": "SUCCESS",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "SUCCESS",
33
  "124": "SUCCESS",
34
  "125": "NON_PARTICIPATING",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
 
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
+ "135": "NON_PARTICIPATING",
46
+ "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
 
66
  "154": "NON_PARTICIPATING",
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
+ "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
  "161": "NON_PARTICIPATING",
 
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
+ "170": "NOT_ALIVE",
85
+ "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
+ "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
 
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
+ "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
 
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
+ "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
 
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
+ "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
+ "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "SUCCESS",
147
+ "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
 
170
  "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
 
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "NON_PARTICIPATING",
183
+ "3": "NOT_ALIVE",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
+ "36": "SUCCESS",
191
+ "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
 
196
  "41": "NOT_ALIVE",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
+ "44": "SUCCESS",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
+ "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
 
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
+ "59": "NOT_ALIVE",
216
  "6": "NON_PARTICIPATING",
217
  "60": "SUCCESS",
218
  "61": "SUCCESS",
219
+ "62": "NON_PARTICIPATING",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
+ "7": "NOT_ALIVE",
228
+ "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
  "72": "SUCCESS",
231
  "73": "NOT_ALIVE",
232
+ "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
+ "79": "NON_PARTICIPATING",
238
+ "8": "SUCCESS",
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
 
243
  "84": "SUCCESS",
244
  "85": "NOT_ALIVE",
245
  "86": "SUCCESS",
246
+ "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
+ "91": "SUCCESS",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6522031,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73e0ba708c5d1964b9f55c7f1aa386df383fb761b1b8317fc3c4bbc065127e42
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9716e3ed7598658c8d78d03ef9c3c268a02441b3a2585f60467bbc1c52c3db48
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9651166d2b9971fe6d2fa6c339a4e9dada0ed35c35b88a7ace81e0a2dcdd4fce
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8596b37adb515a96a413cb056d167fb48f9aadfcc86e31e32fcdaf4f0f75f34e
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b84ed879a5c1014801d78764dafa2235156ecfd1f566af527341bb789f2bd548
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:728a3847fdcd32f86c441672a3976633f453f416d277faaccad043a0532c080a
3
  size 4400252568