kmfoda commited on
Commit
944cda3
·
verified ·
1 Parent(s): 4970735

Run 10. Outer Step 50. Inner Step 0. Peers 64.

Browse files
Files changed (4) hide show
  1. config.json +46 -46
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -2,11 +2,11 @@
2
  "_name_or_path": "aalv2/c71-h22",
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": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
@@ -21,21 +21,21 @@
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
- "116": "SUCCESS",
25
  "117": "NON_PARTICIPATING",
26
- "118": "NOT_ALIVE",
27
- "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
- "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "SUCCESS",
38
- "129": "NON_PARTICIPATING",
39
  "13": "NON_PARTICIPATING",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
@@ -46,7 +46,7 @@
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",
@@ -54,7 +54,7 @@
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
- "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
@@ -71,13 +71,13 @@
71
  "159": "SUCCESS",
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": "SUCCESS",
80
- "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
@@ -88,19 +88,19 @@
88
  "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
- "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
- "182": "SUCCESS",
98
- "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
- "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
- "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
@@ -115,19 +115,19 @@
115
  "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
- "200": "NON_PARTICIPATING",
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": "NOT_ALIVE",
129
- "210": "NON_PARTICIPATING",
130
- "211": "NOT_ALIVE",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
@@ -135,27 +135,27 @@
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
- "219": "SUCCESS",
139
- "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
- "222": "NOT_ALIVE",
143
- "223": "NOT_ALIVE",
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": "NON_PARTICIPATING",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
- "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
  "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
@@ -175,22 +175,22 @@
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "SUCCESS",
178
- "255": "SUCCESS",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "NON_PARTICIPATING",
183
  "3": "SUCCESS",
184
- "30": "NOT_ALIVE",
185
- "31": "NOT_ALIVE",
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": "NOT_ALIVE",
193
- "39": "SUCCESS",
194
  "4": "SUCCESS",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
@@ -198,7 +198,7 @@
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
- "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
@@ -210,7 +210,7 @@
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
- "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
@@ -224,8 +224,8 @@
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
- "7": "SUCCESS",
228
- "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
@@ -238,11 +238,11 @@
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
- "82": "SUCCESS",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
- "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6494836,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
2
  "_name_or_path": "aalv2/c71-h22",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "SUCCESS",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
+ "101": "SUCCESS",
9
+ "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
 
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "SUCCESS",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "SUCCESS",
38
+ "129": "NOT_ALIVE",
39
  "13": "NON_PARTICIPATING",
40
  "130": "NOT_ALIVE",
41
  "131": "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": "NOT_ALIVE",
 
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
 
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
+ "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
80
+ "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
 
88
  "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
+ "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
+ "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
+ "182": "NON_PARTICIPATING",
98
+ "183": "SUCCESS",
99
  "184": "SUCCESS",
100
+ "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
+ "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
 
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": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
+ "21": "NON_PARTICIPATING",
129
+ "210": "SUCCESS",
130
+ "211": "SUCCESS",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
 
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "NOT_ALIVE",
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": "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": "SUCCESS",
156
  "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "SUCCESS",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
 
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "SUCCESS",
178
+ "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "NON_PARTICIPATING",
183
  "3": "SUCCESS",
184
+ "30": "NON_PARTICIPATING",
185
+ "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "NOT_ALIVE",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
+ "38": "NON_PARTICIPATING",
193
+ "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
 
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
 
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
+ "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
 
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
+ "7": "NOT_ALIVE",
228
+ "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
 
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
+ "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "SUCCESS",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6495220,
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:c83cb6055644d4ec7e8891bc19d52fc776f7d09fc06c5e1ed7102f40729c06b3
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e4c46e0d9ed04b5f8221b8efa0e7b6c2361f1bd316f2dd8642136704cd552f
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e520c8b6d8dd64fb0d5b622b3343ef4d65521f14bb0acf299a92c6b506e08d59
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b8157bf094ffc72b198c9c99d6c3852384ef05455e18cf4e51d6aa7e13d06c4
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b683bc04c32cfa896a5aaffc1e7a7df89c07b89699d3a52394c9b2f634e604f
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bd707cd96bf3d7a0c1a0f886e9533e6482f686631c6f3a06f045897f0e5031a
3
  size 4400252568