kmfoda commited on
Commit
0d36869
·
verified ·
1 Parent(s): 0cc3afd

Run 10. Outer Step 82. Inner Step 0. Peers 63.

Browse files
Files changed (4) hide show
  1. config.json +63 -63
  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/c71-h21",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NON_PARTICIPATING",
@@ -11,18 +11,18 @@
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
  "106": "NON_PARTICIPATING",
14
- "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
- "11": "SUCCESS",
18
- "110": "NON_PARTICIPATING",
19
  "111": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "SUCCESS",
25
- "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
@@ -30,61 +30,61 @@
30
  "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
- "124": "SUCCESS",
34
  "125": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NON_PARTICIPATING",
38
- "129": "SUCCESS",
39
- "13": "NOT_ALIVE",
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": "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": "NOT_ALIVE",
54
  "143": "NOT_ALIVE",
55
- "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
- "146": "NOT_ALIVE",
58
- "147": "NON_PARTICIPATING",
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": "SUCCESS",
66
- "154": "NOT_ALIVE",
67
- "155": "NON_PARTICIPATING",
68
  "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
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": "SUCCESS",
81
  "168": "SUCCESS",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
- "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
@@ -96,41 +96,41 @@
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
- "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
- "19": "NON_PARTICIPATING",
106
- "190": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
114
  "198": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
- "20": "SUCCESS",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
- "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
- "209": "NON_PARTICIPATING",
128
  "21": "NON_PARTICIPATING",
129
- "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
- "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
@@ -138,29 +138,29 @@
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
- "221": "SUCCESS",
142
- "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "NON_PARTICIPATING",
147
  "227": "SUCCESS",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
- "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
- "231": "NOT_ALIVE",
153
  "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "NOT_ALIVE",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
@@ -176,30 +176,30 @@
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
- "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
- "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
- "35": "NOT_ALIVE",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
193
- "39": "NOT_ALIVE",
194
  "4": "NON_PARTICIPATING",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
- "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
- "45": "FAIL",
201
  "46": "NON_PARTICIPATING",
202
- "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
@@ -212,25 +212,25 @@
212
  "56": "NON_PARTICIPATING",
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NON_PARTICIPATING",
217
- "60": "FAIL",
218
  "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
- "63": "NOT_ALIVE",
221
- "64": "NOT_ALIVE",
222
- "65": "NOT_ALIVE",
223
  "66": "SUCCESS",
224
- "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
- "69": "NON_PARTICIPATING",
227
- "7": "NOT_ALIVE",
228
- "70": "NON_PARTICIPATING",
229
  "71": "SUCCESS",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
233
- "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
@@ -242,7 +242,7 @@
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
- "86": "NOT_ALIVE",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
@@ -253,9 +253,9 @@
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
- "98": "NOT_ALIVE",
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": 6512341,
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",
 
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
  "106": "NON_PARTICIPATING",
14
+ "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
+ "11": "NON_PARTICIPATING",
18
+ "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "SUCCESS",
25
+ "117": "NOT_ALIVE",
26
  "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
 
30
  "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
+ "124": "NON_PARTICIPATING",
34
  "125": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "NOT_ALIVE",
38
+ "129": "NOT_ALIVE",
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": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "FAIL",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NOT_ALIVE",
54
  "143": "NOT_ALIVE",
55
+ "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
+ "146": "SUCCESS",
58
+ "147": "SUCCESS",
59
  "148": "NOT_ALIVE",
60
+ "149": "NOT_ALIVE",
61
+ "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
+ "154": "NON_PARTICIPATING",
67
+ "155": "NOT_ALIVE",
68
  "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
+ "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "NON_PARTICIPATING",
80
  "167": "SUCCESS",
81
  "168": "SUCCESS",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
+ "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
+ "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
 
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
+ "184": "NOT_ALIVE",
100
  "185": "SUCCESS",
101
  "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
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": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
+ "20": "NON_PARTICIPATING",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
+ "202": "NOT_ALIVE",
121
+ "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "NOT_ALIVE",
128
  "21": "NON_PARTICIPATING",
129
+ "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
+ "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
 
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "NOT_ALIVE",
142
+ "222": "NOT_ALIVE",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "NOT_ALIVE",
147
  "227": "SUCCESS",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
+ "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
+ "231": "SUCCESS",
153
  "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
 
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
+ "26": "NOT_ALIVE",
180
  "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
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": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NON_PARTICIPATING",
195
+ "40": "NOT_ALIVE",
196
  "41": "NOT_ALIVE",
197
+ "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
+ "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
+ "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "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": "NON_PARTICIPATING",
220
+ "63": "SUCCESS",
221
+ "64": "SUCCESS",
222
+ "65": "NON_PARTICIPATING",
223
  "66": "SUCCESS",
224
+ "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
+ "69": "SUCCESS",
227
+ "7": "NON_PARTICIPATING",
228
+ "70": "SUCCESS",
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",
 
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "SUCCESS",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
 
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
+ "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
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": 6513165,
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 sha256:3674d2b60db97d769bcb73c1759b66b7c1434a9f2c463addcfd11ec4aa157ec9
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2679cbfa7985b26a7a064d03360c1feb8eb623fb159205b198937c883171ffdf
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:604ef503a5efd2a908aacc0236a6114c7761e320b4b3e838631df1905305f2ca
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7be96aaf7ab9fa7b0ad0a3ae9743a846f6a322240da31ef6c57ad37e4b03302b
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a270f43916db3d562134b5942e392633df644cfeb64e272fe6db33a55e8df763
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d86b8144df884eeec132f9d2aff2c8299317dc69b3121ef342ae503de4d2fc02
3
  size 4400252568