kmfoda commited on
Commit
bf27534
·
verified ·
1 Parent(s): 638d20b

Run 10. Outer Step 5. Inner Step 0. Peers 13.

Browse files
Files changed (4) hide show
  1. config.json +108 -108
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -2,41 +2,41 @@
2
  "_name_or_path": "asim22/sub38-42",
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": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
- "105": "NOT_ALIVE",
13
- "106": "NOT_ALIVE",
14
- "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
- "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
- "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
- "113": "SUCCESS",
22
- "114": "SUCCESS",
23
- "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
- "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
- "120": "SUCCESS",
30
  "121": "NOT_ALIVE",
31
  "122": "FAIL",
32
- "123": "NON_PARTICIPATING",
33
- "124": "NOT_ALIVE",
34
  "125": "NON_PARTICIPATING",
35
- "126": "NON_PARTICIPATING",
36
- "127": "NOT_ALIVE",
37
- "128": "NOT_ALIVE",
38
- "129": "NON_PARTICIPATING",
39
- "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
@@ -55,25 +55,25 @@
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
- "147": "SUCCESS",
59
  "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
  "15": "FAIL",
62
- "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
- "154": "SUCCESS",
67
- "155": "NON_PARTICIPATING",
68
- "156": "NON_PARTICIPATING",
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": "SUCCESS",
76
- "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
@@ -81,161 +81,161 @@
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
- "170": "SUCCESS",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
- "174": "SUCCESS",
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": "SUCCESS",
96
- "181": "NON_PARTICIPATING",
97
- "182": "SUCCESS",
98
- "183": "SUCCESS",
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": "NON_PARTICIPATING",
108
- "192": "NON_PARTICIPATING",
109
  "193": "SUCCESS",
110
  "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
  "196": "NON_PARTICIPATING",
113
- "197": "NON_PARTICIPATING",
114
- "198": "SUCCESS",
115
- "199": "NOT_ALIVE",
116
- "2": "FAIL",
117
- "20": "NON_PARTICIPATING",
118
- "200": "SUCCESS",
119
- "201": "NOT_ALIVE",
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": "NON_PARTICIPATING",
128
- "21": "NON_PARTICIPATING",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
- "212": "SUCCESS",
132
- "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
- "221": "SUCCESS",
142
- "222": "NON_PARTICIPATING",
143
- "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
- "225": "SUCCESS",
146
- "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
- "228": "SUCCESS",
149
- "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
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": "SUCCESS",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
- "24": "FAIL",
162
  "240": "NOT_ALIVE",
163
  "241": "NOT_ALIVE",
164
- "242": "SUCCESS",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "NON_PARTICIPATING",
168
- "246": "NON_PARTICIPATING",
169
- "247": "NON_PARTICIPATING",
170
- "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
- "252": "NON_PARTICIPATING",
176
- "253": "SUCCESS",
177
  "254": "NON_PARTICIPATING",
178
- "255": "NOT_ALIVE",
179
- "26": "SUCCESS",
180
- "27": "NON_PARTICIPATING",
181
- "28": "NOT_ALIVE",
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": "SUCCESS",
189
  "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
- "4": "SUCCESS",
195
  "40": "NON_PARTICIPATING",
196
- "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
- "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
- "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
- "5": "NOT_ALIVE",
206
- "50": "SUCCESS",
207
- "51": "NOT_ALIVE",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
- "55": "SUCCESS",
212
- "56": "NON_PARTICIPATING",
213
- "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "FAIL",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
- "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
  "63": "FAIL",
221
  "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
- "66": "SUCCESS",
224
- "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
- "69": "SUCCESS",
227
  "7": "NON_PARTICIPATING",
228
- "70": "NON_PARTICIPATING",
229
  "71": "NOT_ALIVE",
230
- "72": "NON_PARTICIPATING",
231
- "73": "SUCCESS",
232
- "74": "SUCCESS",
233
- "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
- "79": "SUCCESS",
238
- "8": "NON_PARTICIPATING",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
@@ -243,15 +243,15 @@
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
- "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
  "89": "SUCCESS",
249
  "9": "NON_PARTICIPATING",
250
- "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
  "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
- "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6465631,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
2
  "_name_or_path": "asim22/sub38-42",
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": "FAIL",
10
+ "103": "FAIL",
11
  "104": "NOT_ALIVE",
12
+ "105": "NON_PARTICIPATING",
13
+ "106": "NON_PARTICIPATING",
14
+ "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
+ "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
+ "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
+ "113": "FAIL",
22
+ "114": "NOT_ALIVE",
23
+ "115": "FAIL",
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": "FAIL",
32
+ "123": "FAIL",
33
+ "124": "SUCCESS",
34
  "125": "NON_PARTICIPATING",
35
+ "126": "NOT_ALIVE",
36
+ "127": "FAIL",
37
+ "128": "NON_PARTICIPATING",
38
+ "129": "NOT_ALIVE",
39
+ "13": "FAIL",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
 
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
+ "147": "NON_PARTICIPATING",
59
  "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
  "15": "FAIL",
62
+ "150": "FAIL",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "FAIL",
66
+ "154": "FAIL",
67
+ "155": "SUCCESS",
68
+ "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
+ "162": "NON_PARTICIPATING",
76
+ "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
 
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
+ "170": "FAIL",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
+ "174": "NON_PARTICIPATING",
89
+ "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
+ "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
  "179": "NON_PARTICIPATING",
94
+ "18": "NON_PARTICIPATING",
95
+ "180": "FAIL",
96
+ "181": "NOT_ALIVE",
97
+ "182": "FAIL",
98
+ "183": "NON_PARTICIPATING",
99
+ "184": "FAIL",
100
+ "185": "NOT_ALIVE",
101
+ "186": "FAIL",
102
  "187": "NOT_ALIVE",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
+ "19": "NOT_ALIVE",
106
  "190": "FAIL",
107
  "191": "NON_PARTICIPATING",
108
+ "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
110
  "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
  "196": "NON_PARTICIPATING",
113
+ "197": "NOT_ALIVE",
114
+ "198": "NON_PARTICIPATING",
115
+ "199": "FAIL",
116
+ "2": "NOT_ALIVE",
117
+ "20": "SUCCESS",
118
+ "200": "NON_PARTICIPATING",
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": "FAIL",
129
+ "210": "FAIL",
130
  "211": "NON_PARTICIPATING",
131
+ "212": "NOT_ALIVE",
132
+ "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
+ "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "NON_PARTICIPATING",
142
+ "222": "FAIL",
143
+ "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
+ "225": "FAIL",
146
+ "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
+ "228": "NON_PARTICIPATING",
149
+ "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "NOT_ALIVE",
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": "NOT_ALIVE",
164
+ "242": "FAIL",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NOT_ALIVE",
168
+ "246": "FAIL",
169
+ "247": "NOT_ALIVE",
170
+ "248": "FAIL",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
+ "252": "FAIL",
176
+ "253": "FAIL",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "NON_PARTICIPATING",
179
+ "26": "FAIL",
180
+ "27": "NOT_ALIVE",
181
+ "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
+ "3": "FAIL",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
186
+ "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
+ "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
+ "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "SUCCESS",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
+ "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
+ "46": "SUCCESS",
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": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
+ "55": "NON_PARTICIPATING",
212
+ "56": "NOT_ALIVE",
213
+ "57": "FAIL",
214
  "58": "NOT_ALIVE",
215
  "59": "FAIL",
216
  "6": "NOT_ALIVE",
217
+ "60": "NOT_ALIVE",
218
+ "61": "FAIL",
219
  "62": "NON_PARTICIPATING",
220
  "63": "FAIL",
221
  "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
+ "66": "NOT_ALIVE",
224
+ "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
+ "69": "FAIL",
227
  "7": "NON_PARTICIPATING",
228
+ "70": "FAIL",
229
  "71": "NOT_ALIVE",
230
+ "72": "FAIL",
231
+ "73": "NON_PARTICIPATING",
232
+ "74": "FAIL",
233
+ "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
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",
 
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
+ "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
  "89": "SUCCESS",
249
  "9": "NON_PARTICIPATING",
250
+ "90": "FAIL",
251
  "91": "NON_PARTICIPATING",
252
  "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6466263,
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:d78283d760932631c24d8aad6bd7cc97fb57c6ba84ecd3e86a2c4e3b488fdc71
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24806632550ad6cbceca3315820cf8528dc8be9c18bce9cd768d4d62d8af9fb
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8206101405c080aaa289892cdbeaeb6bce52874f350208cc329b8ef8cc22a54b
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700514102a2315f92541f4e8d3708646bfd751e1dbaa5e48f0435b52a35b1ff0
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3970fe873a8fa52be69a96dbe85e7d0879528af17ace7d9d3d967c1d3c1e91bb
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd72e711ed48c1298416718fb944fae21441e9eaf7694e3782437dcec9a4625
3
  size 4400252568