kmfoda commited on
Commit
b074063
·
verified ·
1 Parent(s): 05263db

Run 10. Outer Step 14. Inner Step 0. Peers 1.

Browse files
Files changed (4) hide show
  1. config.json +107 -107
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,47 +1,47 @@
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": "SUCCESS",
10
- "103": "SUCCESS",
11
  "104": "NOT_ALIVE",
12
- "105": "SUCCESS",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
- "109": "SUCCESS",
17
  "11": "NON_PARTICIPATING",
18
  "110": "NOT_ALIVE",
19
- "111": "SUCCESS",
20
- "112": "SUCCESS",
21
- "113": "SUCCESS",
22
- "114": "SUCCESS",
23
- "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
- "117": "NOT_ALIVE",
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": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
- "125": "SUCCESS",
35
- "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
- "13": "SUCCESS",
40
- "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
- "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
@@ -50,121 +50,121 @@
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
- "142": "NOT_ALIVE",
54
- "143": "NON_PARTICIPATING",
55
- "144": "SUCCESS",
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": "FAIL",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
- "154": "SUCCESS",
67
  "155": "NOT_ALIVE",
68
- "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
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": "SUCCESS",
82
- "169": "SUCCESS",
83
- "17": "NOT_ALIVE",
84
- "170": "SUCCESS",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
- "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
- "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
- "18": "NON_PARTICIPATING",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
- "184": "NOT_ALIVE",
100
- "185": "NON_PARTICIPATING",
101
- "186": "SUCCESS",
102
- "187": "NOT_ALIVE",
103
- "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
- "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
- "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
- "195": "SUCCESS",
112
- "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
- "198": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
116
- "2": "SUCCESS",
117
- "20": "SUCCESS",
118
- "200": "SUCCESS",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "NON_PARTICIPATING",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
- "209": "NOT_ALIVE",
128
- "21": "SUCCESS",
129
- "210": "NOT_ALIVE",
130
- "211": "SUCCESS",
131
  "212": "FAIL",
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": "NOT_ALIVE",
142
- "222": "SUCCESS",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "NOT_ALIVE",
147
- "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
- "229": "FAIL",
150
- "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
- "232": "SUCCESS",
154
- "233": "SUCCESS",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
- "237": "SUCCESS",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
@@ -174,58 +174,58 @@
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
- "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NOT_ALIVE",
180
  "27": "NOT_ALIVE",
181
- "28": "NON_PARTICIPATING",
182
- "29": "SUCCESS",
183
- "3": "NOT_ALIVE",
184
- "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "FAIL",
190
- "36": "FAIL",
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": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
- "46": "SUCCESS",
202
- "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
- "5": "NON_PARTICIPATING",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
- "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
- "56": "SUCCESS",
213
  "57": "FAIL",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
  "62": "NON_PARTICIPATING",
220
- "63": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
@@ -235,25 +235,25 @@
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
- "8": "SUCCESS",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NON_PARTICIPATING",
243
- "84": "SUCCESS",
244
- "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
  "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
- "89": "SUCCESS",
249
- "9": "SUCCESS",
250
- "90": "FAIL",
251
  "91": "FAIL",
252
- "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
- "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "NOT_ALIVE",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6474408,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "3jun1/M7",
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": "NOT_ALIVE",
10
+ "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
+ "105": "FAIL",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
+ "109": "FAIL",
17
  "11": "NON_PARTICIPATING",
18
  "110": "NOT_ALIVE",
19
+ "111": "FAIL",
20
+ "112": "NOT_ALIVE",
21
+ "113": "FAIL",
22
+ "114": "FAIL",
23
+ "115": "NOT_ALIVE",
24
+ "116": "FAIL",
25
+ "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
+ "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
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": "NOT_ALIVE",
39
+ "13": "FAIL",
40
+ "130": "NOT_ALIVE",
41
  "131": "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",
 
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
+ "142": "FAIL",
54
+ "143": "NOT_ALIVE",
55
+ "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
+ "146": "FAIL",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "FAIL",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
+ "154": "FAIL",
67
  "155": "NOT_ALIVE",
68
+ "156": "FAIL",
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": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
+ "167": "NOT_ALIVE",
81
+ "168": "FAIL",
82
+ "169": "FAIL",
83
+ "17": "NON_PARTICIPATING",
84
+ "170": "FAIL",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
+ "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
+ "177": "FAIL",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
+ "18": "FAIL",
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": "NON_PARTICIPATING",
103
+ "188": "FAIL",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
+ "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "FAIL",
110
  "194": "NOT_ALIVE",
111
+ "195": "NON_PARTICIPATING",
112
+ "196": "FAIL",
113
  "197": "NON_PARTICIPATING",
114
+ "198": "FAIL",
115
  "199": "NON_PARTICIPATING",
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": "FAIL",
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": "NON_PARTICIPATING",
133
+ "214": "FAIL",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
+ "219": "NOT_ALIVE",
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": "NON_PARTICIPATING",
147
+ "227": "FAIL",
148
  "228": "NOT_ALIVE",
149
+ "229": "NOT_ALIVE",
150
+ "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
+ "232": "FAIL",
154
+ "233": "FAIL",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "FAIL",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
+ "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
 
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
+ "254": "FAIL",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
+ "28": "NOT_ALIVE",
182
+ "29": "FAIL",
183
+ "3": "NON_PARTICIPATING",
184
+ "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "FAIL",
190
+ "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
+ "39": "FAIL",
194
+ "4": "FAIL",
195
+ "40": "FAIL",
196
+ "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
+ "44": "FAIL",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NOT_ALIVE",
202
+ "47": "FAIL",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
+ "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
+ "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
+ "56": "FAIL",
213
  "57": "FAIL",
214
  "58": "NON_PARTICIPATING",
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": "FAIL",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
+ "69": "NOT_ALIVE",
227
+ "7": "NOT_ALIVE",
228
+ "70": "FAIL",
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
 
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
+ "8": "FAIL",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NON_PARTICIPATING",
243
+ "84": "FAIL",
244
+ "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
  "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
+ "89": "NOT_ALIVE",
249
+ "9": "NOT_ALIVE",
250
+ "90": "NON_PARTICIPATING",
251
  "91": "FAIL",
252
+ "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
+ "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
+ "96": "FAIL",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6475232,
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:ace48c88283d9405698ea10590953fc4836814c63f54ae26b0430b5d8607f2c0
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3665f1e843c4a079c476bf98c05f0b55bccfea40c385c10876199b76ff7fc000
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76cacab577027b0ec57088e13b9ec7a58203065d97d1750416bff2acaf09d3af
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7d86c066e69cbb8f7d2bd8cd960af0bf2af40715f93c6a3b93e794e2500d032
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dd488646ac575217cc0f08a9d9e2f5019770b97f353819a325bebceef13960b
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74760f8bbdd38f013e130f62cf441cdf2da100d253cdd67a1067809a5b7be3e0
3
  size 4400252568