kmfoda commited on
Commit
82a6094
·
verified ·
1 Parent(s): 5a9ff2e

Run 10. Outer Step 11. Inner Step 0. Peers 39.

Browse files
Files changed (4) hide show
  1. config.json +104 -104
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,43 +1,43 @@
1
  {
2
- "_name_or_path": "aalv2/c71-h22",
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": "NOT_ALIVE",
10
- "103": "FAIL",
11
  "104": "NOT_ALIVE",
12
- "105": "FAIL",
13
  "106": "NON_PARTICIPATING",
14
- "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
- "109": "FAIL",
17
  "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
- "111": "FAIL",
20
- "112": "FAIL",
21
- "113": "FAIL",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
- "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
- "123": "FAIL",
33
  "124": "NON_PARTICIPATING",
34
- "125": "FAIL",
35
- "126": "FAIL",
36
- "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
- "13": "FAIL",
40
- "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
@@ -47,118 +47,118 @@
47
  "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NOT_ALIVE",
50
- "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
- "142": "FAIL",
54
  "143": "NON_PARTICIPATING",
55
- "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
- "146": "FAIL",
58
- "147": "FAIL",
59
  "148": "NON_PARTICIPATING",
60
  "149": "FAIL",
61
  "15": "FAIL",
62
  "150": "FAIL",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "FAIL",
66
- "154": "NOT_ALIVE",
67
- "155": "NON_PARTICIPATING",
68
- "156": "FAIL",
69
- "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
- "16": "NON_PARTICIPATING",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
- "162": "NOT_ALIVE",
76
- "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
- "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
- "167": "NOT_ALIVE",
81
- "168": "NOT_ALIVE",
82
  "169": "NON_PARTICIPATING",
83
- "17": "NON_PARTICIPATING",
84
- "170": "FAIL",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
- "173": "FAIL",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
- "179": "NON_PARTICIPATING",
94
- "18": "NOT_ALIVE",
95
- "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
- "184": "FAIL",
100
- "185": "FAIL",
101
- "186": "FAIL",
102
  "187": "NOT_ALIVE",
103
- "188": "FAIL",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
  "190": "FAIL",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
- "193": "NON_PARTICIPATING",
110
- "194": "NON_PARTICIPATING",
111
- "195": "NON_PARTICIPATING",
112
- "196": "FAIL",
113
- "197": "NOT_ALIVE",
114
  "198": "FAIL",
115
- "199": "FAIL",
116
  "2": "NON_PARTICIPATING",
117
- "20": "NON_PARTICIPATING",
118
  "200": "FAIL",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "NOT_ALIVE",
124
- "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
- "209": "FAIL",
128
- "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
- "212": "FAIL",
132
- "213": "NOT_ALIVE",
133
  "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
- "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
- "221": "FAIL",
142
  "222": "FAIL",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
- "225": "NON_PARTICIPATING",
146
- "226": "NOT_ALIVE",
147
- "227": "NOT_ALIVE",
148
  "228": "NOT_ALIVE",
149
- "229": "NON_PARTICIPATING",
150
  "23": "FAIL",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
- "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
- "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
- "237": "FAIL",
159
- "238": "FAIL",
160
  "239": "NON_PARTICIPATING",
161
- "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
@@ -167,70 +167,70 @@
167
  "245": "FAIL",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
- "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
- "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "FAIL",
180
  "27": "NOT_ALIVE",
181
- "28": "FAIL",
182
  "29": "NON_PARTICIPATING",
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": "FAIL",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
- "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
- "4": "FAIL",
195
- "40": "FAIL",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
- "44": "FAIL",
200
  "45": "NON_PARTICIPATING",
201
- "46": "FAIL",
202
- "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
- "5": "NON_PARTICIPATING",
206
  "50": "NON_PARTICIPATING",
207
- "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "FAIL",
213
- "57": "NOT_ALIVE",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
- "60": "FAIL",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
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": "NON_PARTICIPATING",
228
- "70": "NON_PARTICIPATING",
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "FAIL",
233
- "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
@@ -239,23 +239,23 @@
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
- "83": "NON_PARTICIPATING",
243
- "84": "FAIL",
244
- "85": "FAIL",
245
- "86": "FAIL",
246
  "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
- "89": "NON_PARTICIPATING",
249
- "9": "FAIL",
250
- "90": "FAIL",
251
- "91": "FAIL",
252
- "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
  "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
- "97": "NON_PARTICIPATING",
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": 6472423,
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": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
+ "102": "FAIL",
10
+ "103": "SUCCESS",
11
  "104": "NOT_ALIVE",
12
+ "105": "SUCCESS",
13
  "106": "NON_PARTICIPATING",
14
+ "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
+ "109": "NON_PARTICIPATING",
17
  "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
+ "112": "NON_PARTICIPATING",
21
+ "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
+ "119": "FAIL",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "NON_PARTICIPATING",
35
+ "126": "NON_PARTICIPATING",
36
+ "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
+ "13": "NON_PARTICIPATING",
40
+ "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
 
47
  "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NOT_ALIVE",
50
+ "14": "SUCCESS",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
+ "142": "NON_PARTICIPATING",
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": "FAIL",
61
  "15": "FAIL",
62
  "150": "FAIL",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "SUCCESS",
66
+ "154": "NON_PARTICIPATING",
67
+ "155": "FAIL",
68
+ "156": "SUCCESS",
69
+ "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
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": "FAIL",
82
  "169": "NON_PARTICIPATING",
83
+ "17": "NOT_ALIVE",
84
+ "170": "SUCCESS",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
+ "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
+ "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
+ "179": "NOT_ALIVE",
94
+ "18": "NON_PARTICIPATING",
95
+ "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
+ "184": "SUCCESS",
100
+ "185": "NON_PARTICIPATING",
101
+ "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
+ "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
  "190": "FAIL",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NOT_ALIVE",
110
+ "194": "NOT_ALIVE",
111
+ "195": "FAIL",
112
+ "196": "SUCCESS",
113
+ "197": "NON_PARTICIPATING",
114
  "198": "FAIL",
115
+ "199": "SUCCESS",
116
  "2": "NON_PARTICIPATING",
117
+ "20": "FAIL",
118
  "200": "FAIL",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
+ "205": "SUCCESS",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "SUCCESS",
128
+ "21": "FAIL",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
+ "212": "SUCCESS",
132
+ "213": "NON_PARTICIPATING",
133
  "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
+ "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "FAIL",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
+ "225": "NOT_ALIVE",
146
+ "226": "NON_PARTICIPATING",
147
+ "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
+ "229": "NOT_ALIVE",
150
  "23": "FAIL",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
+ "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "SUCCESS",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
+ "24": "FAIL",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
 
167
  "245": "FAIL",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
+ "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
+ "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
+ "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
186
+ "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "SUCCESS",
189
+ "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
+ "4": "SUCCESS",
195
+ "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
+ "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NON_PARTICIPATING",
202
+ "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
+ "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
+ "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "FAIL",
213
+ "57": "SUCCESS",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "SUCCESS",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
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": "FAIL",
227
+ "7": "FAIL",
228
+ "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "FAIL",
233
+ "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
 
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
+ "83": "NOT_ALIVE",
243
+ "84": "SUCCESS",
244
+ "85": "NOT_ALIVE",
245
+ "86": "NON_PARTICIPATING",
246
  "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
+ "89": "SUCCESS",
249
+ "9": "SUCCESS",
250
+ "90": "SUCCESS",
251
+ "91": "NON_PARTICIPATING",
252
+ "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
  "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
+ "97": "FAIL",
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": 6472789,
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 sha256:1202055f796a6be0e58ed52589455162f2757f35547a2c0050aebaf9b427f801
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fb49205fa1340fd009dd8ded62db86eae5611e4aa036cac2de42587d248e7ee
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eed6c31340bd0d09ed8ae43c7979094a4e713fdbbac6a5f62cdd47ffb54339fd
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:186d14d497e54a83ee125e1e5a4df64e9448c520c5b8cb5998a2caff3bbdc704
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:902fd9008c1a2f3067f97b89f37468745ceac20fb062a0954d8a6abc2ba008e5
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7aa46d782e8defed92f65a1a68e10d51f3280a50c8dfb51b14e4b58e63e1e89
3
  size 4400252568