kmfoda commited on
Commit
dec30da
·
verified ·
1 Parent(s): 2254e6c

Run 8. Outer Step 94. Inner Step 0. Peers 62.

Browse files
Files changed (4) hide show
  1. config.json +93 -93
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,80 +1,80 @@
1
  {
2
- "_name_or_path": "aalv2/c70-h12",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
- "102": "NOT_ALIVE",
10
- "103": "SUCCESS",
11
  "104": "NOT_ALIVE",
12
  "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
- "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
- "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
- "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
- "118": "NON_PARTICIPATING",
27
- "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
- "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
- "122": "SUCCESS",
32
- "123": "SUCCESS",
33
  "124": "SUCCESS",
34
  "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
- "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
- "130": "NOT_ALIVE",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
- "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
- "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
- "138": "SUCCESS",
49
- "139": "NOT_ALIVE",
50
- "14": "SUCCESS",
51
  "140": "SUCCESS",
52
- "141": "NOT_ALIVE",
53
  "142": "NOT_ALIVE",
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
- "145": "NOT_ALIVE",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
- "148": "NON_PARTICIPATING",
60
  "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
- "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
- "154": "NOT_ALIVE",
67
  "155": "SUCCESS",
68
  "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
- "16": "SUCCESS",
73
  "160": "SUCCESS",
74
  "161": "SUCCESS",
75
- "162": "NOT_ALIVE",
76
- "163": "NON_PARTICIPATING",
77
- "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
@@ -86,26 +86,26 @@
86
  "172": "NOT_ALIVE",
87
  "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
- "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
- "178": "NOT_ALIVE",
93
- "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NOT_ALIVE",
98
  "183": "SUCCESS",
99
- "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
- "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
- "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "SUCCESS",
108
- "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
@@ -119,82 +119,82 @@
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NOT_ALIVE",
122
- "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
- "208": "SUCCESS",
127
- "209": "NON_PARTICIPATING",
128
- "21": "SUCCESS",
129
- "210": "SUCCESS",
130
  "211": "SUCCESS",
131
  "212": "NOT_ALIVE",
132
- "213": "NON_PARTICIPATING",
133
- "214": "NON_PARTICIPATING",
134
- "215": "NOT_ALIVE",
135
  "216": "SUCCESS",
136
- "217": "NOT_ALIVE",
137
- "218": "FAIL",
138
- "219": "SUCCESS",
139
  "22": "SUCCESS",
140
- "220": "SUCCESS",
141
  "221": "NOT_ALIVE",
142
- "222": "SUCCESS",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
- "227": "NOT_ALIVE",
148
- "228": "SUCCESS",
149
- "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
- "236": "SUCCESS",
158
- "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
- "242": "NOT_ALIVE",
165
  "243": "NON_PARTICIPATING",
166
- "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "NOT_ALIVE",
169
  "247": "SUCCESS",
170
  "248": "SUCCESS",
171
- "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
  "251": "SUCCESS",
175
- "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
- "254": "NOT_ALIVE",
178
  "255": "SUCCESS",
179
  "26": "NOT_ALIVE",
180
  "27": "SUCCESS",
181
- "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
- "32": "SUCCESS",
187
- "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
- "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
- "40": "NOT_ALIVE",
196
- "41": "SUCCESS",
197
- "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
  "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
@@ -204,56 +204,56 @@
204
  "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
- "51": "NOT_ALIVE",
208
- "52": "SUCCESS",
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "SUCCESS",
213
- "57": "NON_PARTICIPATING",
214
- "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
- "61": "NOT_ALIVE",
219
- "62": "NOT_ALIVE",
220
- "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
- "65": "SUCCESS",
223
- "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
- "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
- "71": "SUCCESS",
230
  "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
- "74": "FAIL",
233
  "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
- "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
237
- "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
- "83": "NON_PARTICIPATING",
243
- "84": "SUCCESS",
244
- "85": "NOT_ALIVE",
245
- "86": "NOT_ALIVE",
246
- "87": "SUCCESS",
247
- "88": "SUCCESS",
248
  "89": "NOT_ALIVE",
249
- "9": "SUCCESS",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
- "93": "SUCCESS",
254
  "94": "NON_PARTICIPATING",
255
- "95": "NOT_ALIVE",
256
- "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
  "98": "NOT_ALIVE",
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": 6411158,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "aalv2/c71-h7",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
+ "102": "NON_PARTICIPATING",
10
+ "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
+ "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
+ "110": "SUCCESS",
19
  "111": "NOT_ALIVE",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
+ "118": "NOT_ALIVE",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
+ "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
+ "122": "NON_PARTICIPATING",
32
+ "123": "NOT_ALIVE",
33
  "124": "SUCCESS",
34
  "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
+ "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
+ "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
+ "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
+ "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
+ "138": "NOT_ALIVE",
49
+ "139": "SUCCESS",
50
+ "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
+ "141": "NON_PARTICIPATING",
53
  "142": "NOT_ALIVE",
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
+ "145": "SUCCESS",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "NOT_ALIVE",
60
  "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
+ "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
+ "154": "SUCCESS",
67
  "155": "SUCCESS",
68
  "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
+ "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
  "161": "SUCCESS",
75
+ "162": "NON_PARTICIPATING",
76
+ "163": "NOT_ALIVE",
77
+ "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
 
86
  "172": "NOT_ALIVE",
87
  "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
+ "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
+ "178": "NON_PARTICIPATING",
93
+ "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NOT_ALIVE",
98
  "183": "SUCCESS",
99
+ "184": "NON_PARTICIPATING",
100
+ "185": "SUCCESS",
101
  "186": "NON_PARTICIPATING",
102
+ "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
+ "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "SUCCESS",
108
+ "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
 
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NOT_ALIVE",
122
+ "204": "SUCCESS",
123
  "205": "NOT_ALIVE",
124
+ "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
+ "208": "NON_PARTICIPATING",
127
+ "209": "NOT_ALIVE",
128
+ "21": "NOT_ALIVE",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
  "212": "NOT_ALIVE",
132
+ "213": "SUCCESS",
133
+ "214": "NOT_ALIVE",
134
+ "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
+ "217": "SUCCESS",
137
+ "218": "SUCCESS",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
+ "220": "FAIL",
141
  "221": "NOT_ALIVE",
142
+ "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
+ "227": "SUCCESS",
148
+ "228": "NOT_ALIVE",
149
+ "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
+ "236": "NON_PARTICIPATING",
158
+ "237": "NOT_ALIVE",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
+ "244": "NOT_ALIVE",
167
  "245": "SUCCESS",
168
  "246": "NOT_ALIVE",
169
  "247": "SUCCESS",
170
  "248": "SUCCESS",
171
+ "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
  "251": "SUCCESS",
175
+ "252": "NON_PARTICIPATING",
176
  "253": "SUCCESS",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
  "26": "NOT_ALIVE",
180
  "27": "SUCCESS",
181
+ "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
+ "32": "NOT_ALIVE",
187
+ "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
+ "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "NON_PARTICIPATING",
196
+ "41": "NOT_ALIVE",
197
+ "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
 
204
  "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
+ "51": "FAIL",
208
+ "52": "NON_PARTICIPATING",
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "SUCCESS",
213
+ "57": "NOT_ALIVE",
214
+ "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
+ "61": "SUCCESS",
219
+ "62": "SUCCESS",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
+ "65": "NOT_ALIVE",
223
+ "66": "NOT_ALIVE",
224
+ "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
+ "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
+ "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "NON_PARTICIPATING",
233
  "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
+ "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
+ "79": "NON_PARTICIPATING",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
+ "83": "NOT_ALIVE",
243
+ "84": "NOT_ALIVE",
244
+ "85": "NON_PARTICIPATING",
245
+ "86": "NON_PARTICIPATING",
246
+ "87": "NON_PARTICIPATING",
247
+ "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
+ "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
+ "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "SUCCESS",
256
+ "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6412880,
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:fc1d23d65f3e5f1731a27211815d3e1def9b2136e849194f0af950e2a083f03b
3
  size 4924928111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c400132d31a5364a1bdf59db20d6c1f92a80a894fa0f917184c9af7b6c1b75bd
3
  size 4924928111
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a98902c4af6aa5930050e6cf6df01edb00e12bbc00f0e832420b6b8c7ad7b67
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a536652f6184b3c85c3ba1c6ff546bf49606ec82b4e1d17b86434297d0aa253
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43d4777f4dc3d7e7224076ac65cd322af6a32d2ace2ab5d03b412f8ced6138af
3
  size 4400252933
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03957ea6e3d437b486a0cb4fc6bd14f50756e3064c192a560e191ad112a66283
3
  size 4400252933