kmfoda commited on
Commit
30d7242
·
verified ·
1 Parent(s): 2325a3a

Run 10. Outer Step 63. Inner Step 0. Peers 27.

Browse files
Files changed (4) hide show
  1. config.json +89 -89
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -2,51 +2,51 @@
2
  "_name_or_path": "aalv2/c70-h5",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NOT_ALIVE",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
- "101": "SUCCESS",
9
- "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "SUCCESS",
13
- "106": "SUCCESS",
14
  "107": "NON_PARTICIPATING",
15
- "108": "NON_PARTICIPATING",
16
- "109": "SUCCESS",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
- "111": "SUCCESS",
20
- "112": "SUCCESS",
21
- "113": "SUCCESS",
22
- "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
- "116": "SUCCESS",
25
  "117": "NON_PARTICIPATING",
26
- "118": "NOT_ALIVE",
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": "SUCCESS",
34
- "125": "SUCCESS",
35
- "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NON_PARTICIPATING",
38
- "129": "NON_PARTICIPATING",
39
  "13": "NON_PARTICIPATING",
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",
@@ -62,18 +62,18 @@
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "SUCCESS",
66
  "154": "SUCCESS",
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
- "161": "SUCCESS",
75
  "162": "NOT_ALIVE",
76
- "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
@@ -82,13 +82,13 @@
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
- "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NOT_ALIVE",
94
  "18": "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": "NON_PARTICIPATING",
102
  "187": "NON_PARTICIPATING",
103
- "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
@@ -109,53 +109,53 @@
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
- "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
- "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
- "20": "NON_PARTICIPATING",
118
- "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
- "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
- "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
- "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
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": "NON_PARTICIPATING",
147
- "227": "NON_PARTICIPATING",
148
- "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
- "23": "NON_PARTICIPATING",
151
- "230": "SUCCESS",
152
- "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
- "235": "SUCCESS",
157
- "236": "NON_PARTICIPATING",
158
- "237": "NOT_ALIVE",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
@@ -164,10 +164,10 @@
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "NOT_ALIVE",
168
- "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
- "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "NOT_ALIVE",
173
  "250": "NOT_ALIVE",
@@ -179,57 +179,57 @@
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
- "29": "SUCCESS",
183
- "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
- "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
- "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "SUCCESS",
207
- "51": "SUCCESS",
208
  "52": "SUCCESS",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
- "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
- "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
- "60": "SUCCESS",
218
- "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
221
- "64": "SUCCESS",
222
  "65": "NON_PARTICIPATING",
223
- "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
- "69": "SUCCESS",
227
- "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
- "71": "NON_PARTICIPATING",
230
- "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
- "74": "NON_PARTICIPATING",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
@@ -238,24 +238,24 @@
238
  "8": "NON_PARTICIPATING",
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
- "82": "SUCCESS",
242
  "83": "NOT_ALIVE",
243
- "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
- "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
- "89": "SUCCESS",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NOT_ALIVE",
251
- "91": "NOT_ALIVE",
252
- "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
- "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
- "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6500409,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
2
  "_name_or_path": "aalv2/c70-h5",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "NON_PARTICIPATING",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
+ "101": "FAIL",
9
+ "102": "FAIL",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
+ "106": "FAIL",
14
  "107": "NON_PARTICIPATING",
15
+ "108": "NOT_ALIVE",
16
+ "109": "FAIL",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
+ "111": "FAIL",
20
+ "112": "NOT_ALIVE",
21
+ "113": "NOT_ALIVE",
22
+ "114": "FAIL",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "FAIL",
27
  "119": "NON_PARTICIPATING",
28
+ "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "NON_PARTICIPATING",
31
+ "122": "SUCCESS",
32
+ "123": "FAIL",
33
+ "124": "NON_PARTICIPATING",
34
+ "125": "FAIL",
35
+ "126": "FAIL",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "SUCCESS",
38
+ "129": "SUCCESS",
39
  "13": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
 
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
  "154": "SUCCESS",
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "FAIL",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
+ "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
+ "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
 
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
+ "171": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
 
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
+ "184": "FAIL",
100
  "185": "SUCCESS",
101
  "186": "NON_PARTICIPATING",
102
  "187": "NON_PARTICIPATING",
103
+ "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
 
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
+ "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
+ "198": "FAIL",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
+ "20": "SUCCESS",
118
+ "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
+ "202": "NOT_ALIVE",
121
+ "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
+ "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
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": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
+ "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "FAIL",
142
+ "222": "NON_PARTICIPATING",
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": "NOT_ALIVE",
151
+ "230": "FAIL",
152
+ "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "FAIL",
157
+ "236": "NOT_ALIVE",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
 
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NON_PARTICIPATING",
168
+ "246": "FAIL",
169
  "247": "NOT_ALIVE",
170
+ "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "NOT_ALIVE",
173
  "250": "NOT_ALIVE",
 
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
+ "29": "FAIL",
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": "SUCCESS",
190
+ "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
+ "4": "SUCCESS",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "NON_PARTICIPATING",
197
+ "42": "FAIL",
198
  "43": "NOT_ALIVE",
199
+ "44": "FAIL",
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": "SUCCESS",
207
+ "51": "FAIL",
208
  "52": "SUCCESS",
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": "FAIL",
216
  "6": "NOT_ALIVE",
217
+ "60": "FAIL",
218
+ "61": "FAIL",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
221
+ "64": "NOT_ALIVE",
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": "NOT_ALIVE",
230
+ "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
+ "74": "FAIL",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
 
238
  "8": "NON_PARTICIPATING",
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
+ "82": "FAIL",
242
  "83": "NOT_ALIVE",
243
+ "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
+ "87": "FAIL",
247
  "88": "NOT_ALIVE",
248
+ "89": "FAIL",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NOT_ALIVE",
251
+ "91": "NON_PARTICIPATING",
252
+ "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
+ "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
+ "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6500846,
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 sha256:0dc2e9485ad6421cb66ac6c2f72c1233d3b6df0cba6ae7ca7a1578f626a9a083
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:431d356501c3c9d86fcbe4eea5a0711ec221de0632726c6a5e2459b16d5225a5
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cb84fb654e6149be1304a6a01b7215df11235f8b826c3d4a8eee0a30bc570e3
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c592f314872be5ab1070bb63ac9bc63367e48041483f460d9a317fc3473062
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fccf40439a6bac40872094ca804a65c0982b62a89bb5b020fe87e8ae54a5a619
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d575e2dcd2e2bba56a10a804916dee0376591e84b0cf0a40eaa3d05e49751739
3
  size 4400252568