kmfoda commited on
Commit
2b393d1
·
verified ·
1 Parent(s): 1b82d47

Run 10. Outer Step 96. Inner Step 0. Peers 5.

Browse files
Files changed (4) hide show
  1. config.json +105 -105
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -2,48 +2,48 @@
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": "NON_PARTICIPATING",
9
- "102": "SUCCESS",
10
- "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
- "105": "SUCCESS",
13
- "106": "SUCCESS",
14
- "107": "SUCCESS",
15
- "108": "NOT_ALIVE",
16
- "109": "SUCCESS",
17
- "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
- "111": "SUCCESS",
20
- "112": "NOT_ALIVE",
21
- "113": "SUCCESS",
22
- "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
- "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
- "119": "SUCCESS",
28
- "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
- "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
- "123": "SUCCESS",
33
- "124": "SUCCESS",
34
- "125": "SUCCESS",
35
- "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
- "128": "SUCCESS",
38
- "129": "FAIL",
39
- "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "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": "NOT_ALIVE",
@@ -52,7 +52,7 @@
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
- "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
@@ -62,31 +62,31 @@
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NOT_ALIVE",
71
- "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
- "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
- "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
- "166": "NOT_ALIVE",
80
- "167": "NON_PARTICIPATING",
81
- "168": "SUCCESS",
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": "NOT_ALIVE",
@@ -96,11 +96,11 @@
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
- "184": "SUCCESS",
100
- "185": "SUCCESS",
101
- "186": "SUCCESS",
102
- "187": "SUCCESS",
103
- "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
@@ -109,26 +109,26 @@
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
- "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
- "198": "SUCCESS",
115
- "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "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": "NON_PARTICIPATING",
128
- "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
- "211": "SUCCESS",
131
- "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
@@ -138,25 +138,25 @@
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
- "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
- "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
- "225": "NOT_ALIVE",
146
  "226": "NON_PARTICIPATING",
147
- "227": "SUCCESS",
148
- "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
- "231": "SUCCESS",
153
- "232": "SUCCESS",
154
  "233": "NON_PARTICIPATING",
155
- "234": "NOT_ALIVE",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
- "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
@@ -165,95 +165,95 @@
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",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
- "255": "SUCCESS",
179
- "26": "SUCCESS",
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": "SUCCESS",
190
- "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
- "4": "NOT_ALIVE",
195
- "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
- "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
- "44": "NOT_ALIVE",
200
- "45": "NON_PARTICIPATING",
201
- "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
- "51": "NON_PARTICIPATING",
208
- "52": "SUCCESS",
209
- "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
- "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
- "61": "NON_PARTICIPATING",
219
- "62": "SUCCESS",
220
- "63": "NOT_ALIVE",
221
- "64": "NON_PARTICIPATING",
222
- "65": "SUCCESS",
223
  "66": "SUCCESS",
224
- "67": "NOT_ALIVE",
225
- "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
- "7": "SUCCESS",
228
- "70": "NON_PARTICIPATING",
229
- "71": "NOT_ALIVE",
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": "SUCCESS",
238
- "8": "SUCCESS",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
- "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
- "86": "SUCCESS",
246
- "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
- "9": "NON_PARTICIPATING",
250
  "90": "NON_PARTICIPATING",
251
- "91": "NON_PARTICIPATING",
252
- "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
- "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
  "99": "NOT_ALIVE"
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6519016,
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": "NOT_ALIVE",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
+ "101": "NOT_ALIVE",
9
+ "102": "NOT_ALIVE",
10
+ "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "FAIL",
13
+ "106": "FAIL",
14
+ "107": "FAIL",
15
+ "108": "NON_PARTICIPATING",
16
+ "109": "NON_PARTICIPATING",
17
+ "11": "FAIL",
18
  "110": "NOT_ALIVE",
19
+ "111": "FAIL",
20
+ "112": "NON_PARTICIPATING",
21
+ "113": "FAIL",
22
+ "114": "FAIL",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "FAIL",
26
  "118": "NOT_ALIVE",
27
+ "119": "FAIL",
28
+ "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "FAIL",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "FAIL",
33
+ "124": "FAIL",
34
+ "125": "FAIL",
35
+ "126": "FAIL",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "FAIL",
38
+ "129": "NON_PARTICIPATING",
39
+ "13": "FAIL",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
+ "135": "NOT_ALIVE",
46
+ "136": "FAIL",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NOT_ALIVE",
 
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
+ "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
 
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
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": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "NON_PARTICIPATING",
80
+ "167": "NOT_ALIVE",
81
+ "168": "FAIL",
82
+ "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
+ "170": "FAIL",
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": "NOT_ALIVE",
 
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
+ "184": "FAIL",
100
+ "185": "FAIL",
101
+ "186": "FAIL",
102
+ "187": "FAIL",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
 
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
+ "196": "NON_PARTICIPATING",
113
  "197": "NOT_ALIVE",
114
+ "198": "FAIL",
115
+ "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "FAIL",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
+ "205": "FAIL",
124
+ "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
+ "21": "FAIL",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "NOT_ALIVE",
131
+ "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
 
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
+ "221": "FAIL",
142
  "222": "NOT_ALIVE",
143
+ "223": "FAIL",
144
  "224": "NOT_ALIVE",
145
+ "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
+ "227": "FAIL",
148
+ "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
+ "231": "FAIL",
153
+ "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
 
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
+ "246": "FAIL",
169
  "247": "NOT_ALIVE",
170
+ "248": "FAIL",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "FAIL",
179
+ "26": "FAIL",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "NON_PARTICIPATING",
183
+ "3": "FAIL",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "FAIL",
190
+ "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
+ "4": "NON_PARTICIPATING",
195
+ "40": "NOT_ALIVE",
196
  "41": "NOT_ALIVE",
197
+ "42": "FAIL",
198
  "43": "NOT_ALIVE",
199
+ "44": "FAIL",
200
+ "45": "SUCCESS",
201
+ "46": "FAIL",
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": "FAIL",
209
+ "53": "NOT_ALIVE",
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": "NON_PARTICIPATING",
218
+ "61": "FAIL",
219
+ "62": "NOT_ALIVE",
220
+ "63": "FAIL",
221
+ "64": "FAIL",
222
+ "65": "NOT_ALIVE",
223
  "66": "SUCCESS",
224
+ "67": "NON_PARTICIPATING",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
+ "7": "FAIL",
228
+ "70": "FAIL",
229
+ "71": "NON_PARTICIPATING",
230
+ "72": "FAIL",
231
  "73": "NOT_ALIVE",
232
+ "74": "FAIL",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
+ "79": "FAIL",
238
+ "8": "FAIL",
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": "FAIL",
246
+ "87": "FAIL",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
+ "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
+ "91": "FAIL",
252
+ "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
+ "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
+ "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
  "99": "NOT_ALIVE"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6519379,
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:df926e7fff6c7e24301cc2a9a6f76aebd8c37ea90d085042da15269809a6ddab
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:603387a78268f595c49aab80ecab21e5cda9524b6f35cf5a0b7b95ab43f3870d
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2b66b89f86f3d9d72a97febea0de608edfbd83bd79159e3af43942272126639
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ed315265754ba4c8e04d4aacfaf9a0432a2e71684b924f17f5110d2eb7ea7b
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:531e88e3ad83be2f49620982d9ab03f8ab3e0c304af97058749a2b5577e9b325
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a985876094fbf8e721d53f73ef51148455b2240843d4d2a1f67e1afcb0b7c77
3
  size 4400252568