kmfoda commited on
Commit
ff744dc
·
verified ·
1 Parent(s): c481687

Run 10. Outer Step 65. Inner Step 0. Peers 28.

Browse files
Files changed (4) hide show
  1. config.json +100 -100
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,42 +1,42 @@
1
  {
2
- "_name_or_path": "aalv2/c71-h21",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NON_PARTICIPATING",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
- "101": "SUCCESS",
9
- "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
20
- "112": "NON_PARTICIPATING",
21
- "113": "NON_PARTICIPATING",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "SUCCESS",
25
- "117": "SUCCESS",
26
- "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
- "122": "SUCCESS",
32
  "123": "SUCCESS",
33
  "124": "SUCCESS",
34
- "125": "SUCCESS",
35
- "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NOT_ALIVE",
38
- "129": "SUCCESS",
39
- "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
@@ -45,48 +45,48 @@
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": "NOT_ALIVE",
53
- "142": "SUCCESS",
54
  "143": "NOT_ALIVE",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
- "146": "SUCCESS",
58
- "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
- "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
  "154": "SUCCESS",
67
- "155": "NON_PARTICIPATING",
68
- "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
- "169": "NOT_ALIVE",
83
- "17": "SUCCESS",
84
- "170": "SUCCESS",
85
- "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
@@ -96,39 +96,39 @@
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
- "184": "SUCCESS",
100
- "185": "NOT_ALIVE",
101
- "186": "SUCCESS",
102
- "187": "NOT_ALIVE",
103
- "188": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
- "198": "SUCCESS",
115
- "199": "SUCCESS",
116
- "2": "NON_PARTICIPATING",
117
- "20": "SUCCESS",
118
- "200": "SUCCESS",
119
- "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
- "205": "NOT_ALIVE",
124
- "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
- "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
- "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
@@ -137,115 +137,115 @@
137
  "218": "NOT_ALIVE",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
- "220": "NOT_ALIVE",
141
- "221": "SUCCESS",
142
- "222": "SUCCESS",
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": "NON_PARTICIPATING",
150
- "23": "NON_PARTICIPATING",
151
- "230": "NON_PARTICIPATING",
152
- "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
  "233": "NON_PARTICIPATING",
155
- "234": "NOT_ALIVE",
156
- "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NON_PARTICIPATING",
163
- "241": "SUCCESS",
164
  "242": "NON_PARTICIPATING",
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": "NOT_ALIVE",
173
- "250": "SUCCESS",
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": "NOT_ALIVE",
182
- "29": "SUCCESS",
183
- "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
185
  "31": "SUCCESS",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
- "35": "NOT_ALIVE",
190
  "36": "NON_PARTICIPATING",
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": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
- "44": "NOT_ALIVE",
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": "NON_PARTICIPATING",
208
- "52": "SUCCESS",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
  "57": "SUCCESS",
214
  "58": "NON_PARTICIPATING",
215
- "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
- "61": "SUCCESS",
219
- "62": "NON_PARTICIPATING",
220
- "63": "NOT_ALIVE",
221
- "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
- "66": "SUCCESS",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
- "7": "NON_PARTICIPATING",
228
- "70": "NOT_ALIVE",
229
- "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
- "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
- "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
- "79": "NOT_ALIVE",
238
  "8": "NON_PARTICIPATING",
239
- "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
- "82": "SUCCESS",
242
- "83": "NOT_ALIVE",
243
- "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
- "89": "SUCCESS",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NON_PARTICIPATING",
@@ -255,7 +255,7 @@
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
258
- "98": "NOT_ALIVE",
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": 6501715,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
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": "NON_PARTICIPATING",
14
+ "107": "NON_PARTICIPATING",
15
+ "108": "NOT_ALIVE",
16
+ "109": "FAIL",
17
+ "11": "NON_PARTICIPATING",
18
+ "110": "NOT_ALIVE",
19
+ "111": "FAIL",
20
+ "112": "FAIL",
21
+ "113": "FAIL",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "SUCCESS",
25
+ "117": "NON_PARTICIPATING",
26
+ "118": "FAIL",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
+ "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "SUCCESS",
34
+ "125": "FAIL",
35
+ "126": "NOT_ALIVE",
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",
 
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
+ "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
+ "141": "NON_PARTICIPATING",
53
+ "142": "FAIL",
54
  "143": "NOT_ALIVE",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
+ "146": "FAIL",
58
+ "147": "FAIL",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
  "154": "SUCCESS",
67
+ "155": "SUCCESS",
68
+ "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "SUCCESS",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "NON_PARTICIPATING",
83
+ "17": "NON_PARTICIPATING",
84
+ "170": "FAIL",
85
+ "171": "NON_PARTICIPATING",
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",
 
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
+ "184": "NOT_ALIVE",
100
+ "185": "FAIL",
101
+ "186": "NON_PARTICIPATING",
102
+ "187": "NON_PARTICIPATING",
103
+ "188": "FAIL",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
+ "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
+ "198": "FAIL",
115
+ "199": "FAIL",
116
+ "2": "FAIL",
117
+ "20": "FAIL",
118
+ "200": "FAIL",
119
+ "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
+ "205": "FAIL",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
+ "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
+ "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
 
137
  "218": "NOT_ALIVE",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
+ "220": "NON_PARTICIPATING",
141
+ "221": "NOT_ALIVE",
142
+ "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
+ "225": "NOT_ALIVE",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
+ "228": "NON_PARTICIPATING",
149
+ "229": "SUCCESS",
150
+ "23": "NOT_ALIVE",
151
+ "230": "FAIL",
152
+ "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
+ "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "NOT_ALIVE",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NON_PARTICIPATING",
163
+ "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
+ "246": "SUCCESS",
169
  "247": "NOT_ALIVE",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "NOT_ALIVE",
173
+ "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "FAIL",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
+ "28": "NON_PARTICIPATING",
182
+ "29": "NOT_ALIVE",
183
+ "3": "FAIL",
184
  "30": "NON_PARTICIPATING",
185
  "31": "SUCCESS",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
+ "34": "SUCCESS",
189
+ "35": "FAIL",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
+ "4": "FAIL",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
+ "42": "FAIL",
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",
206
+ "50": "NON_PARTICIPATING",
207
+ "51": "FAIL",
208
+ "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
  "57": "SUCCESS",
214
  "58": "NON_PARTICIPATING",
215
+ "59": "FAIL",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
+ "61": "FAIL",
219
+ "62": "NOT_ALIVE",
220
+ "63": "NON_PARTICIPATING",
221
+ "64": "SUCCESS",
222
  "65": "NON_PARTICIPATING",
223
+ "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
+ "7": "FAIL",
228
+ "70": "NON_PARTICIPATING",
229
+ "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "FAIL",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
+ "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
+ "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
+ "80": "FAIL",
240
  "81": "NOT_ALIVE",
241
+ "82": "NOT_ALIVE",
242
+ "83": "NON_PARTICIPATING",
243
+ "84": "FAIL",
244
  "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
+ "89": "FAIL",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NON_PARTICIPATING",
 
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
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": 6502101,
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 sha256:41058fc9f29e88b9dfcfbab86b6449d6c5115e95acfa2e32ec0ce5c9bf2db5c1
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e8f4240a40abca6e6b89d9bfc4b4478f86f602c57cc16bb19241641ecafb90b
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffe8b3707f517b8ae87fe38774d8d7ea288c35df36f3d262e4e0ea11a667803e
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ef0e64379ed237274d685d3357c3256b11eb24083ac55e3c52803935ef0f95
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:195141002518506ec08bca371ac98f00acd981cca2a41dd044e2678ae67d27ed
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b340a2a81d387c9d3f53fdaa971ae593cd0950c43addbd369e8a79a440df89
3
  size 4400252568