kmfoda commited on
Commit
42435d2
·
verified ·
1 Parent(s): 17372cf

Run 10. Outer Step 34. Inner Step 0. Peers 63.

Browse files
Files changed (4) hide show
  1. config.json +58 -58
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "_name_or_path": "strnan01/llama-1b-hot-6",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
- "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
@@ -12,14 +12,14 @@
12
  "105": "SUCCESS",
13
  "106": "NON_PARTICIPATING",
14
  "107": "SUCCESS",
15
- "108": "NON_PARTICIPATING",
16
- "109": "NOT_ALIVE",
17
  "11": "SUCCESS",
18
- "110": "NON_PARTICIPATING",
19
- "111": "NOT_ALIVE",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
- "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
@@ -27,14 +27,14 @@
27
  "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "NOT_ALIVE",
31
- "122": "NOT_ALIVE",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NON_PARTICIPATING",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
@@ -42,10 +42,10 @@
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
- "135": "NOT_ALIVE",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
- "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
@@ -57,14 +57,14 @@
57
  "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
- "149": "NOT_ALIVE",
61
- "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
  "154": "SUCCESS",
67
- "155": "SUCCESS",
68
  "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
@@ -76,19 +76,19 @@
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
- "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
- "168": "NON_PARTICIPATING",
82
- "169": "SUCCESS",
83
- "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
- "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
@@ -96,7 +96,7 @@
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
- "184": "NON_PARTICIPATING",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
@@ -105,23 +105,23 @@
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
- "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
- "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NON_PARTICIPATING",
117
  "20": "SUCCESS",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
- "202": "NOT_ALIVE",
121
- "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "SUCCESS",
124
- "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
@@ -130,15 +130,15 @@
130
  "211": "SUCCESS",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
- "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
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": "NON_PARTICIPATING",
142
  "222": "SUCCESS",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
@@ -146,14 +146,14 @@
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
- "229": "SUCCESS",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
- "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
- "234": "SUCCESS",
156
- "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
@@ -165,9 +165,9 @@
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
- "246": "NOT_ALIVE",
169
  "247": "NOT_ALIVE",
170
- "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
@@ -180,12 +180,12 @@
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
- "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
  "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
@@ -198,10 +198,10 @@
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
  "45": "SUCCESS",
201
- "46": "NOT_ALIVE",
202
- "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
- "49": "NON_PARTICIPATING",
205
  "5": "SUCCESS",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
@@ -209,23 +209,23 @@
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
- "56": "NON_PARTICIPATING",
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "NOT_ALIVE",
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": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
- "69": "FAIL",
227
  "7": "SUCCESS",
228
- "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
@@ -236,22 +236,22 @@
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "SUCCESS",
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": "SUCCESS",
249
  "9": "SUCCESS",
250
- "90": "SUCCESS",
251
  "91": "SUCCESS",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
- "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6485652,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "aalv2/c68-h7",
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": "SUCCESS",
 
12
  "105": "SUCCESS",
13
  "106": "NON_PARTICIPATING",
14
  "107": "SUCCESS",
15
+ "108": "NOT_ALIVE",
16
+ "109": "SUCCESS",
17
  "11": "SUCCESS",
18
+ "110": "NOT_ALIVE",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
+ "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
 
27
  "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "NON_PARTICIPATING",
31
+ "122": "SUCCESS",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NON_PARTICIPATING",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "SUCCESS",
38
  "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
 
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "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",
 
57
  "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "NON_PARTICIPATING",
61
+ "15": "SUCCESS",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
  "154": "SUCCESS",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
 
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "NOT_ALIVE",
82
+ "169": "NOT_ALIVE",
83
+ "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
+ "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
+ "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
+ "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
+ "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
 
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
+ "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "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": "SUCCESS",
115
  "199": "NOT_ALIVE",
116
  "2": "NON_PARTICIPATING",
117
  "20": "SUCCESS",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
+ "202": "NON_PARTICIPATING",
121
+ "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
+ "205": "NON_PARTICIPATING",
124
+ "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
 
130
  "211": "SUCCESS",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
+ "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
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": "SUCCESS",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
 
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
+ "232": "SUCCESS",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "NOT_ALIVE",
156
+ "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
 
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",
 
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
+ "3": "SUCCESS",
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": "SUCCESS",
191
  "37": "NOT_ALIVE",
 
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
  "45": "SUCCESS",
201
+ "46": "SUCCESS",
202
+ "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
+ "49": "NOT_ALIVE",
205
  "5": "SUCCESS",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
 
209
  "53": "SUCCESS",
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",
217
+ "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
+ "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
+ "65": "NON_PARTICIPATING",
223
+ "66": "NOT_ALIVE",
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": "NOT_ALIVE",
 
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "SUCCESS",
239
+ "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
+ "85": "NOT_ALIVE",
245
+ "86": "SUCCESS",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
  "9": "SUCCESS",
250
+ "90": "NON_PARTICIPATING",
251
  "91": "SUCCESS",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6486040,
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 sha256:746cc48f230ecaafb13b14961a7fac36fbc343fba4e036d06ed7e2f2c7feca68
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ae5171afcd95b4bd87a38681f947e37e672fce6e40d06831c4a87c5b659fd8
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d217185dd2d04f932cb3a562089923fcf85ff83ed129124f19213d4bc7738e49
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae13b9ded3cede4a3c729dc4c258bb78cd84f13f18ee079a84f16d87add7aa76
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c902660ca81da1bb8031e461a93afed2cb9f0c2ce9e1cbbd7a2fbfbd294fc21
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6aae017dda82ea552a95e86bb81b29c12e37f9348d7cdfca1de247f9cd48ec4
3
  size 4400252568