kmfoda commited on
Commit
9e95995
·
verified ·
1 Parent(s): beb53e9

Run 10. Outer Step 32. Inner Step 0. Peers 63.

Browse files
Files changed (4) hide show
  1. config.json +80 -80
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,40 +1,40 @@
1
  {
2
- "_name_or_path": "aalv2/c68-h7",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "FAIL",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
- "106": "NON_PARTICIPATING",
14
  "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
- "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
- "114": "FAIL",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
- "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "NON_PARTICIPATING",
31
- "122": "FAIL",
32
- "123": "FAIL",
33
  "124": "NOT_ALIVE",
34
- "125": "FAIL",
35
  "126": "NON_PARTICIPATING",
36
- "127": "NON_PARTICIPATING",
37
- "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
@@ -45,27 +45,27 @@
45
  "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
- "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
- "142": "FAIL",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
- "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
- "15": "FAIL",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
- "154": "NON_PARTICIPATING",
67
- "155": "FAIL",
68
- "156": "FAIL",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
@@ -77,135 +77,135 @@
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
- "167": "SUCCESS",
81
  "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
- "170": "FAIL",
85
  "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "FAIL",
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": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
  "184": "SUCCESS",
100
- "185": "FAIL",
101
- "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
- "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
- "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
- "198": "FAIL",
115
- "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
127
- "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
- "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
- "214": "FAIL",
134
  "215": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
142
  "222": "SUCCESS",
143
- "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
- "225": "NOT_ALIVE",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
- "228": "NON_PARTICIPATING",
149
- "229": "FAIL",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "NOT_ALIVE",
155
- "234": "SUCCESS",
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": "NOT_ALIVE",
163
- "241": "FAIL",
164
  "242": "NOT_ALIVE",
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": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
- "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
  "254": "SUCCESS",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
- "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
- "35": "FAIL",
190
  "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
- "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
- "4": "NOT_ALIVE",
195
- "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
- "45": "FAIL",
201
- "46": "FAIL",
202
- "47": "FAIL",
203
- "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
- "5": "NON_PARTICIPATING",
206
- "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
- "52": "NOT_ALIVE",
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
@@ -214,19 +214,19 @@
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
- "60": "FAIL",
218
  "61": "NOT_ALIVE",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NOT_ALIVE",
221
- "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
- "7": "NON_PARTICIPATING",
228
  "70": "SUCCESS",
229
- "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
@@ -235,27 +235,27 @@
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
- "8": "FAIL",
239
  "80": "NOT_ALIVE",
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": "SUCCESS",
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
  },
261
  "architectures": [
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6484784,
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": "NOT_ALIVE",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "SUCCESS",
13
+ "106": "SUCCESS",
14
  "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
+ "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "NOT_ALIVE",
31
+ "122": "NON_PARTICIPATING",
32
+ "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
+ "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
+ "127": "NOT_ALIVE",
37
+ "128": "SUCCESS",
38
  "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
 
45
  "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
+ "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
+ "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "SUCCESS",
66
+ "154": "SUCCESS",
67
+ "155": "NON_PARTICIPATING",
68
+ "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
 
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
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",
89
+ "175": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
101
+ "186": "NOT_ALIVE",
102
  "187": "NOT_ALIVE",
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": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
+ "198": "NOT_ALIVE",
115
+ "199": "NOT_ALIVE",
116
  "2": "NON_PARTICIPATING",
117
+ "20": "SUCCESS",
118
+ "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
+ "202": "NOT_ALIVE",
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": "NOT_ALIVE",
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
+ "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
+ "214": "NOT_ALIVE",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
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": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
+ "233": "NON_PARTICIPATING",
155
+ "234": "NOT_ALIVE",
156
+ "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
  "246": "SUCCESS",
169
  "247": "NOT_ALIVE",
170
+ "248": "NOT_ALIVE",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
+ "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "SUCCESS",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
+ "29": "SUCCESS",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "NON_PARTICIPATING",
190
  "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
+ "4": "SUCCESS",
195
+ "40": "SUCCESS",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
+ "45": "SUCCESS",
201
+ "46": "SUCCESS",
202
+ "47": "NON_PARTICIPATING",
203
+ "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "SUCCESS",
206
+ "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "NON_PARTICIPATING",
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
 
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NOT_ALIVE",
221
+ "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
+ "7": "SUCCESS",
228
  "70": "SUCCESS",
229
+ "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
 
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
+ "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "NON_PARTICIPATING",
246
+ "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
+ "89": "NOT_ALIVE",
249
  "9": "SUCCESS",
250
+ "90": "SUCCESS",
251
+ "91": "SUCCESS",
252
+ "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
+ "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6485218,
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 sha256:4ed859c06a79a4e228f9b0243324b834fac90cd4bfc02d9f9f4f991165ec950b
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a91be06073004ca25b0e5fcddd6d9655d40f1e32c1e86615dee29e150918c7de
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37757a643c6abcdc776d351e76de281cfa90b189a741fa2d1420838e4f858ee5
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a21d1078ec15fd04ca22cc3463f392aec48f3b78f6ec17706b513d80f077de5
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:292867f42185b2a37589972870fb638dc5cac42e92739d987997797235d00531
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2bbc96faf6a7241b8e40308bfcec495aa9e72dbf05e0f378917ff1e39f6e229
3
  size 4400252568