kmfoda commited on
Commit
4334f64
·
verified ·
1 Parent(s): 9250215

Run 10. Outer Step 23. Inner Step 0. Peers 61.

Browse files
Files changed (4) hide show
  1. config.json +64 -64
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,38 +1,38 @@
1
  {
2
- "_name_or_path": "aalv2/c71-h21",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
- "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
- "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
  "106": "NON_PARTICIPATING",
14
- "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
  "109": "SUCCESS",
17
- "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
- "111": "NOT_ALIVE",
20
  "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
- "118": "NOT_ALIVE",
27
- "119": "FAIL",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
- "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
- "125": "NOT_ALIVE",
35
- "126": "NON_PARTICIPATING",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
@@ -41,8 +41,8 @@
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
- "134": "NOT_ALIVE",
45
- "135": "NOT_ALIVE",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
@@ -55,7 +55,7 @@
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
- "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
@@ -64,31 +64,31 @@
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
  "154": "SUCCESS",
67
- "155": "NOT_ALIVE",
68
- "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
- "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
- "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
- "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
- "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
- "173": "FAIL",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NON_PARTICIPATING",
@@ -102,50 +102,50 @@
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
- "19": "NON_PARTICIPATING",
106
- "190": "SUCCESS",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
- "195": "NOT_ALIVE",
112
  "196": "SUCCESS",
113
- "197": "NON_PARTICIPATING",
114
  "198": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
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": "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": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
- "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
- "219": "SUCCESS",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
  "222": "SUCCESS",
143
- "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
- "227": "SUCCESS",
148
- "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
@@ -156,15 +156,15 @@
156
  "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
159
- "238": "SUCCESS",
160
- "239": "NON_PARTICIPATING",
161
- "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
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",
@@ -174,25 +174,25 @@
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
- "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
- "29": "SUCCESS",
183
  "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
- "31": "NOT_ALIVE",
186
- "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
- "35": "NON_PARTICIPATING",
190
- "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
  "39": "SUCCESS",
194
  "4": "SUCCESS",
195
- "40": "SUCCESS",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
@@ -207,32 +207,32 @@
207
  "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
- "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
  "57": "NOT_ALIVE",
214
- "58": "NON_PARTICIPATING",
215
- "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NOT_ALIVE",
219
  "62": "NON_PARTICIPATING",
220
- "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
  "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
- "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
- "74": "FAIL",
233
- "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
- "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
  "8": "SUCCESS",
@@ -240,21 +240,21 @@
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
- "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
- "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "SUCCESS",
250
- "90": "SUCCESS",
251
- "91": "NON_PARTICIPATING",
252
- "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
- "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
- "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6479528,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "strnan01/llama-1b-hot-6",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
+ "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
+ "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
  "106": "NON_PARTICIPATING",
14
+ "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "SUCCESS",
17
+ "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "NON_PARTICIPATING",
27
+ "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
+ "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
+ "125": "SUCCESS",
35
+ "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
 
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
+ "134": "NON_PARTICIPATING",
45
+ "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
 
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
+ "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
 
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
  "154": "SUCCESS",
67
+ "155": "NON_PARTICIPATING",
68
+ "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
+ "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
+ "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
+ "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
+ "170": "SUCCESS",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
+ "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
+ "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NON_PARTICIPATING",
 
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
+ "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
+ "195": "SUCCESS",
112
  "196": "SUCCESS",
113
+ "197": "NOT_ALIVE",
114
  "198": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
116
+ "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
+ "200": "FAIL",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
+ "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
+ "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
+ "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "NOT_ALIVE",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
  "222": "SUCCESS",
143
+ "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
+ "227": "NON_PARTICIPATING",
148
+ "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
 
156
  "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
159
+ "238": "NON_PARTICIPATING",
160
+ "239": "NOT_ALIVE",
161
+ "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "SUCCESS",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
  "248": "NON_PARTICIPATING",
 
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
+ "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
+ "29": "NOT_ALIVE",
183
  "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
+ "31": "NON_PARTICIPATING",
186
+ "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "SUCCESS",
190
+ "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
  "39": "SUCCESS",
194
  "4": "SUCCESS",
195
+ "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
 
207
  "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
+ "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
  "57": "NOT_ALIVE",
214
+ "58": "NOT_ALIVE",
215
+ "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NOT_ALIVE",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
  "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
+ "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "SUCCESS",
233
+ "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
+ "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
  "8": "SUCCESS",
 
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
+ "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "NOT_ALIVE",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "SUCCESS",
250
+ "90": "NOT_ALIVE",
251
+ "91": "NOT_ALIVE",
252
+ "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
+ "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6479877,
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:b5034a62d0038faa913fdba84eea53b4a7b8764b35e15500eb6aabffb4f4ee95
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b248da48de6c6019608a50d95007cd6a463454b9596525fce99972f67d8ceb
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6dbaa2aa32b89d3aee77fec3be1f206dfe287f302cfcc494b8026f26d14d4c3
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3be436df37e40daad54edd4a85925350b2a92e72d4dd5aab61da44639e7d90da
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a4fcec7ad4b735c3f3705831d3d378e1ee7d080c04c04264ebbb3335b1229a3
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3005dc3c2fdb88a6c4a741af6c79690e1b05ac7feb4850c5b91231b095f29758
3
  size 4400252568