kmfoda commited on
Commit
c62646e
·
verified ·
1 Parent(s): 5eafd17

Run 10. Outer Step 105. Inner Step 0. Peers 55.

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
@@ -2,38 +2,38 @@
2
  "_name_or_path": "aalv2/c67-h25",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "SUCCESS",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
- "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "SUCCESS",
13
- "106": "NON_PARTICIPATING",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
  "109": "NON_PARTICIPATING",
17
- "11": "FAIL",
18
  "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
- "112": "NON_PARTICIPATING",
21
- "113": "NON_PARTICIPATING",
22
- "114": "NOT_ALIVE",
23
- "115": "NOT_ALIVE",
24
  "116": "SUCCESS",
25
- "117": "FAIL",
26
  "118": "NON_PARTICIPATING",
27
- "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
- "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
- "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
- "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "FAIL",
@@ -46,43 +46,43 @@
46
  "136": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
- "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
- "142": "FAIL",
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
- "146": "SUCCESS",
58
- "147": "SUCCESS",
59
- "148": "NON_PARTICIPATING",
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": "FAIL",
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
- "157": "SUCCESS",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
- "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
- "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
- "168": "NON_PARTICIPATING",
82
- "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
- "170": "SUCCESS",
85
- "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
@@ -97,66 +97,66 @@
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
- "186": "FAIL",
102
- "187": "FAIL",
103
- "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
- "190": "FAIL",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
- "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NON_PARTICIPATING",
118
- "200": "FAIL",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
- "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
- "21": "FAIL",
129
- "210": "NOT_ALIVE",
130
- "211": "SUCCESS",
131
- "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
- "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
- "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "NON_PARTICIPATING",
147
- "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
- "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
- "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
- "234": "SUCCESS",
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",
@@ -165,48 +165,48 @@
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
- "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
- "248": "NON_PARTICIPATING",
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": "SUCCESS",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
- "3": "NON_PARTICIPATING",
184
- "30": "NOT_ALIVE",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "NON_PARTICIPATING",
190
- "36": "NON_PARTICIPATING",
191
- "37": "SUCCESS",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
- "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
- "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
  "44": "FAIL",
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": "NOT_ALIVE",
208
  "52": "SUCCESS",
209
- "53": "FAIL",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
@@ -214,38 +214,38 @@
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
- "60": "NOT_ALIVE",
218
- "61": "NON_PARTICIPATING",
219
- "62": "NON_PARTICIPATING",
220
  "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
- "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
- "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
- "7": "SUCCESS",
228
- "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
- "72": "NOT_ALIVE",
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": "NON_PARTICIPATING",
238
- "8": "NOT_ALIVE",
239
- "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
- "84": "NON_PARTICIPATING",
244
- "85": "SUCCESS",
245
- "86": "SUCCESS",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
- "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
@@ -253,8 +253,8 @@
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "NOT_ALIVE",
257
- "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6523298,
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": "NON_PARTICIPATING",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
+ "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
+ "106": "SUCCESS",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
  "109": "NON_PARTICIPATING",
17
+ "11": "NOT_ALIVE",
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": "SUCCESS",
26
  "118": "NON_PARTICIPATING",
27
+ "119": "SUCCESS",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "SUCCESS",
35
  "126": "NON_PARTICIPATING",
36
+ "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "FAIL",
 
46
  "136": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
53
+ "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "NOT_ALIVE",
58
+ "147": "NON_PARTICIPATING",
59
+ "148": "NOT_ALIVE",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
+ "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "FAIL",
66
+ "154": "NON_PARTICIPATING",
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
+ "157": "NOT_ALIVE",
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": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
+ "168": "SUCCESS",
82
+ "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
+ "170": "NOT_ALIVE",
85
+ "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
 
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
+ "185": "SUCCESS",
101
+ "186": "NOT_ALIVE",
102
+ "187": "NON_PARTICIPATING",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
+ "196": "NON_PARTICIPATING",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
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": "NON_PARTICIPATING",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
+ "21": "SUCCESS",
129
+ "210": "NON_PARTICIPATING",
130
+ "211": "NON_PARTICIPATING",
131
+ "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
+ "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
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": "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": "SUCCESS",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
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": "SUCCESS",
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": "NOT_ALIVE",
178
+ "255": "FAIL",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
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": "SUCCESS",
190
+ "36": "SUCCESS",
191
+ "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
+ "40": "NOT_ALIVE",
196
  "41": "NOT_ALIVE",
197
+ "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "FAIL",
200
+ "45": "SUCCESS",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
+ "50": "SUCCESS",
207
  "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
209
+ "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
 
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
+ "60": "SUCCESS",
218
+ "61": "SUCCESS",
219
+ "62": "SUCCESS",
220
  "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
+ "66": "SUCCESS",
224
+ "67": "NON_PARTICIPATING",
225
+ "68": "FAIL",
226
  "69": "NON_PARTICIPATING",
227
+ "7": "NON_PARTICIPATING",
228
+ "70": "NON_PARTICIPATING",
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",
237
+ "79": "SUCCESS",
238
+ "8": "SUCCESS",
239
+ "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
+ "84": "SUCCESS",
244
+ "85": "NOT_ALIVE",
245
+ "86": "NOT_ALIVE",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
+ "89": "SUCCESS",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
 
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
+ "96": "SUCCESS",
257
+ "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6523662,
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:e1300e30db23a06d82cf2be1191d42dfc0ec15e30c88493e866bee83578b128f
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:689555cb3e1d04f7b5096b7cf4202ab079cb26f4e2de5d1818233bf5c12b9371
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ada6576cbd31e41f76e39f02193aa66822e679a10eaaffaac4d6d9f75da32352
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c628e046920629bcc0212822e153be34ba2aabf6e1e935cc9a17a6e6bc7100
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac253d78e715f783fa7d54fa8bad23ed2f95b8779874d1d1bbda92ef1caf645e
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd6218b16ec10f7db5409e33b612b92ef0c10c69973635964754ebf0c66057de
3
  size 4400252568