kmfoda commited on
Commit
39a65b5
·
verified ·
1 Parent(s): 72f2d41

Run 10. Outer Step 53. Inner Step 0. Peers 9.

Browse files
Files changed (4) hide show
  1. config.json +86 -86
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -2,41 +2,41 @@
2
  "_name_or_path": "aalv2/c71-h22",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NON_PARTICIPATING",
6
- "10": "FAIL",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
- "102": "FAIL",
10
- "103": "FAIL",
11
  "104": "NOT_ALIVE",
12
  "105": "FAIL",
13
- "106": "FAIL",
14
- "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "FAIL",
17
  "11": "FAIL",
18
- "110": "NON_PARTICIPATING",
19
- "111": "FAIL",
20
  "112": "NON_PARTICIPATING",
21
- "113": "FAIL",
22
  "114": "FAIL",
23
  "115": "NON_PARTICIPATING",
24
  "116": "FAIL",
25
- "117": "NON_PARTICIPATING",
26
  "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "NON_PARTICIPATING",
31
- "122": "NON_PARTICIPATING",
32
  "123": "FAIL",
33
  "124": "NON_PARTICIPATING",
34
- "125": "NON_PARTICIPATING",
35
  "126": "FAIL",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NON_PARTICIPATING",
38
- "129": "NON_PARTICIPATING",
39
- "13": "FAIL",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
@@ -45,71 +45,71 @@
45
  "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
- "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
- "142": "FAIL",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "FAIL",
58
- "147": "FAIL",
59
- "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
- "15": "NON_PARTICIPATING",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "FAIL",
66
  "154": "FAIL",
67
- "155": "FAIL",
68
- "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
- "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "FAIL",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
- "169": "NON_PARTICIPATING",
83
- "17": "NON_PARTICIPATING",
84
  "170": "NOT_ALIVE",
85
  "171": "FAIL",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
- "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
- "182": "NON_PARTICIPATING",
98
- "183": "FAIL",
99
  "184": "FAIL",
100
- "185": "FAIL",
101
  "186": "FAIL",
102
  "187": "NON_PARTICIPATING",
103
- "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
- "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
- "196": "FAIL",
113
  "197": "NON_PARTICIPATING",
114
  "198": "FAIL",
115
  "199": "NON_PARTICIPATING",
@@ -118,44 +118,44 @@
118
  "200": "FAIL",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "FAIL",
124
  "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
- "21": "NON_PARTICIPATING",
129
- "210": "NON_PARTICIPATING",
130
  "211": "FAIL",
131
- "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
- "214": "NOT_ALIVE",
134
- "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
  "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
- "221": "FAIL",
142
- "222": "FAIL",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
- "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
- "23": "NOT_ALIVE",
151
- "230": "FAIL",
152
  "231": "NON_PARTICIPATING",
153
  "232": "FAIL",
154
  "233": "NON_PARTICIPATING",
155
- "234": "FAIL",
156
- "235": "FAIL",
157
  "236": "NON_PARTICIPATING",
158
- "237": "FAIL",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
@@ -164,96 +164,96 @@
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": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
- "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
- "254": "NOT_ALIVE",
178
- "255": "FAIL",
179
- "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
- "28": "NOT_ALIVE",
182
- "29": "FAIL",
183
  "3": "FAIL",
184
  "30": "NON_PARTICIPATING",
185
  "31": "FAIL",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
- "35": "FAIL",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
193
- "39": "NOT_ALIVE",
194
- "4": "FAIL",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
- "44": "FAIL",
200
  "45": "NON_PARTICIPATING",
201
- "46": "FAIL",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
- "49": "NON_PARTICIPATING",
205
  "5": "NON_PARTICIPATING",
206
- "50": "NOT_ALIVE",
207
- "51": "FAIL",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
- "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
- "61": "NON_PARTICIPATING",
219
- "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
  "64": "FAIL",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
- "69": "NON_PARTICIPATING",
227
- "7": "FAIL",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "FAIL",
233
- "75": "NOT_ALIVE",
234
- "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "FAIL",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
- "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
- "89": "FAIL",
249
  "9": "NON_PARTICIPATING",
250
- "90": "FAIL",
251
  "91": "NON_PARTICIPATING",
252
- "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
- "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
- "96": "FAIL",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6495996,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
2
  "_name_or_path": "aalv2/c71-h22",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "FAIL",
6
+ "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
+ "102": "SUCCESS",
10
+ "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "FAIL",
13
+ "106": "NOT_ALIVE",
14
+ "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
  "109": "FAIL",
17
  "11": "FAIL",
18
+ "110": "FAIL",
19
+ "111": "NOT_ALIVE",
20
  "112": "NON_PARTICIPATING",
21
+ "113": "NON_PARTICIPATING",
22
  "114": "FAIL",
23
  "115": "NON_PARTICIPATING",
24
  "116": "FAIL",
25
+ "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "FAIL",
31
+ "122": "FAIL",
32
  "123": "FAIL",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "FAIL",
35
  "126": "FAIL",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "FAIL",
38
+ "129": "FAIL",
39
+ "13": "NON_PARTICIPATING",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
 
45
  "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
+ "138": "FAIL",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
+ "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "FAIL",
58
+ "147": "NON_PARTICIPATING",
59
+ "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "FAIL",
66
  "154": "FAIL",
67
+ "155": "NON_PARTICIPATING",
68
+ "156": "FAIL",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "FAIL",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
+ "161": "FAIL",
75
  "162": "NOT_ALIVE",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "FAIL",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "FAIL",
83
+ "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "FAIL",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
+ "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
+ "182": "FAIL",
98
+ "183": "NOT_ALIVE",
99
  "184": "FAIL",
100
+ "185": "NOT_ALIVE",
101
  "186": "FAIL",
102
  "187": "NON_PARTICIPATING",
103
+ "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "FAIL",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
+ "196": "NON_PARTICIPATING",
113
  "197": "NON_PARTICIPATING",
114
  "198": "FAIL",
115
  "199": "NON_PARTICIPATING",
 
118
  "200": "FAIL",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
+ "205": "NOT_ALIVE",
124
  "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
+ "21": "FAIL",
129
+ "210": "FAIL",
130
  "211": "FAIL",
131
+ "212": "FAIL",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "FAIL",
134
+ "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
  "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "NON_PARTICIPATING",
142
+ "222": "NON_PARTICIPATING",
143
+ "223": "FAIL",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
+ "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
+ "23": "NON_PARTICIPATING",
151
+ "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "FAIL",
154
  "233": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
 
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "SUCCESS",
168
+ "246": "FAIL",
169
  "247": "NOT_ALIVE",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
+ "252": "FAIL",
176
  "253": "NOT_ALIVE",
177
+ "254": "NON_PARTICIPATING",
178
+ "255": "NON_PARTICIPATING",
179
+ "26": "NOT_ALIVE",
180
  "27": "NOT_ALIVE",
181
+ "28": "NON_PARTICIPATING",
182
+ "29": "NON_PARTICIPATING",
183
  "3": "FAIL",
184
  "30": "NON_PARTICIPATING",
185
  "31": "FAIL",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "FAIL",
189
+ "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
193
+ "39": "NON_PARTICIPATING",
194
+ "4": "NON_PARTICIPATING",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
+ "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
+ "49": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
+ "50": "NON_PARTICIPATING",
207
+ "51": "NOT_ALIVE",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "FAIL",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "NOT_ALIVE",
218
+ "61": "FAIL",
219
+ "62": "SUCCESS",
220
  "63": "NON_PARTICIPATING",
221
  "64": "FAIL",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
+ "69": "FAIL",
227
+ "7": "NON_PARTICIPATING",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "FAIL",
233
+ "75": "NON_PARTICIPATING",
234
+ "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
+ "82": "FAIL",
242
  "83": "NOT_ALIVE",
243
  "84": "FAIL",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
+ "87": "FAIL",
247
  "88": "NOT_ALIVE",
248
+ "89": "NOT_ALIVE",
249
  "9": "NON_PARTICIPATING",
250
+ "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
+ "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
+ "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
+ "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6496409,
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 sha256:59b96c9fdcd0321bdd46fc45a930a629df746ee918412f5193df73b7593fb75c
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bedcf8033ea712b58d943ff533deb523e440d09954379c700c45aceb83ee329
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f75fba273d49f3d8ae9a0a03f43f782e9715afeb4c8246715286bd77cefbd57c
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dacfaa7ad99404a1f0c92693c7b7cd71fa807775ada403a503b4010e100bbe6b
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24b5d2203a8add33de44b93aa5bdb544ccee08bd6c87f9945259997d15441373
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43d859880732cf14a8435121f1603f29a53eaa222194a0570af9eff38644dd0
3
  size 4400252568