kmfoda commited on
Commit
7c60c6b
·
verified ·
1 Parent(s): 693eb93

Run 10. Outer Step 111. Inner Step 0. Peers 60.

Browse files
Files changed (4) hide show
  1. config.json +66 -66
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -2,10 +2,10 @@
2
  "_name_or_path": "aalv2/c67-h25",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "FAIL",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
- "101": "NON_PARTICIPATING",
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
@@ -13,29 +13,29 @@
13
  "106": "SUCCESS",
14
  "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
- "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
- "111": "FAIL",
20
  "112": "SUCCESS",
21
- "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
- "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
- "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
- "123": "SUCCESS",
33
- "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
- "126": "NON_PARTICIPATING",
36
  "127": "SUCCESS",
37
- "128": "NON_PARTICIPATING",
38
- "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
@@ -43,7 +43,7 @@
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",
@@ -65,28 +65,28 @@
65
  "153": "SUCCESS",
66
  "154": "NON_PARTICIPATING",
67
  "155": "NOT_ALIVE",
68
- "156": "NON_PARTICIPATING",
69
  "157": "SUCCESS",
70
- "158": "NOT_ALIVE",
71
- "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
- "161": "SUCCESS",
75
  "162": "NOT_ALIVE",
76
- "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
- "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
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": "FAIL",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
@@ -94,22 +94,22 @@
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
- "182": "NOT_ALIVE",
98
  "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
- "187": "NOT_ALIVE",
103
- "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
- "192": "NOT_ALIVE",
109
- "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
- "196": "NON_PARTICIPATING",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
@@ -121,12 +121,12 @@
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": "NOT_ALIVE",
130
  "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
@@ -140,23 +140,23 @@
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
- "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
- "225": "NON_PARTICIPATING",
146
- "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
- "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
- "231": "NON_PARTICIPATING",
153
- "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
- "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
- "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
@@ -164,8 +164,8 @@
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "NOT_ALIVE",
168
- "246": "SUCCESS",
169
  "247": "NOT_ALIVE",
170
  "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
@@ -177,35 +177,35 @@
177
  "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
  "26": "SUCCESS",
180
- "27": "NOT_ALIVE",
181
- "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
185
- "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "SUCCESS",
190
- "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
- "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
- "44": "SUCCESS",
200
- "45": "NOT_ALIVE",
201
- "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NOT_ALIVE",
208
- "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
@@ -213,49 +213,49 @@
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
- "6": "NON_PARTICIPATING",
217
- "60": "SUCCESS",
218
  "61": "SUCCESS",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
- "64": "FAIL",
222
- "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
- "70": "NON_PARTICIPATING",
229
  "71": "SUCCESS",
230
- "72": "NON_PARTICIPATING",
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": "SUCCESS",
238
- "8": "SUCCESS",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
- "85": "NOT_ALIVE",
245
- "86": "FAIL",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
- "91": "NON_PARTICIPATING",
252
- "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
- "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
- "96": "NOT_ALIVE",
257
- "97": "NOT_ALIVE",
258
- "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6525594,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
2
  "_name_or_path": "aalv2/c67-h25",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "NON_PARTICIPATING",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
+ "101": "SUCCESS",
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
 
13
  "106": "SUCCESS",
14
  "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
+ "109": "SUCCESS",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
+ "111": "NOT_ALIVE",
20
  "112": "SUCCESS",
21
+ "113": "FAIL",
22
  "114": "NON_PARTICIPATING",
23
+ "115": "SUCCESS",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
+ "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "NOT_ALIVE",
33
+ "124": "NOT_ALIVE",
34
  "125": "NON_PARTICIPATING",
35
+ "126": "SUCCESS",
36
  "127": "SUCCESS",
37
+ "128": "NOT_ALIVE",
38
+ "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
 
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
+ "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
 
65
  "153": "SUCCESS",
66
  "154": "NON_PARTICIPATING",
67
  "155": "NOT_ALIVE",
68
+ "156": "NOT_ALIVE",
69
  "157": "SUCCESS",
70
+ "158": "NON_PARTICIPATING",
71
+ "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
+ "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
+ "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
+ "168": "NOT_ALIVE",
82
  "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
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",
 
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
+ "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
+ "187": "NON_PARTICIPATING",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
+ "192": "NON_PARTICIPATING",
109
+ "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
+ "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
 
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": "SUCCESS",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
 
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
+ "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
+ "225": "NOT_ALIVE",
146
+ "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
+ "23": "SUCCESS",
151
  "230": "NON_PARTICIPATING",
152
+ "231": "SUCCESS",
153
+ "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
+ "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
 
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NON_PARTICIPATING",
168
+ "246": "NOT_ALIVE",
169
  "247": "NOT_ALIVE",
170
  "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
 
177
  "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
  "26": "SUCCESS",
180
+ "27": "NON_PARTICIPATING",
181
+ "28": "SUCCESS",
182
  "29": "NON_PARTICIPATING",
183
  "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
185
+ "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "SUCCESS",
190
+ "36": "SUCCESS",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
+ "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
+ "44": "NOT_ALIVE",
200
+ "45": "NON_PARTICIPATING",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NOT_ALIVE",
208
+ "52": "NON_PARTICIPATING",
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
 
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
+ "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
+ "64": "SUCCESS",
222
+ "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
+ "70": "SUCCESS",
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": "NOT_ALIVE",
238
+ "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
+ "85": "NON_PARTICIPATING",
245
+ "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
+ "91": "SUCCESS",
252
+ "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
+ "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
+ "96": "NON_PARTICIPATING",
257
+ "97": "NON_PARTICIPATING",
258
+ "98": "NON_PARTICIPATING",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6526028,
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:e1913b4d306deab98cbe226df925d76e4ca9c3e3ddb23de5633f6801288c3548
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f4c25ffb6a26c00929517b741bde2bc80e5ca38a880bdcd5081daa2eac16b2c
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88aec7b07bd9422f5bc281e206ef7a4e488890c76c065505aaac99bb2eb7c934
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1689507688424a258a1837215973e90057add479da5140c79b51883d3b5e5dc1
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c056031d66fc45078bf5379f422e37ce49e22cf8f2ae646a30cd7e0f240d794
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c4dcf70d3a2892687dd152a27b4c1fc768fc83ba31419fa2e1bafdc5fd1445
3
  size 4400252568