kmfoda commited on
Commit
03700e9
·
verified ·
1 Parent(s): bb6d936

Run 10. Outer Step 18. Inner Step 0. Peers 55.

Browse files
Files changed (4) hide show
  1. config.json +76 -76
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -3,40 +3,40 @@
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": "FAIL",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
- "109": "NOT_ALIVE",
17
- "11": "FAIL",
18
  "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
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": "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": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
- "13": "NON_PARTICIPATING",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
@@ -50,20 +50,20 @@
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
- "142": "NOT_ALIVE",
54
  "143": "NOT_ALIVE",
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": "NOT_ALIVE",
62
- "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
- "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
@@ -72,7 +72,7 @@
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",
@@ -81,146 +81,146 @@
81
  "168": "SUCCESS",
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
- "170": "FAIL",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
- "18": "SUCCESS",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
- "183": "NON_PARTICIPATING",
99
- "184": "NOT_ALIVE",
100
- "185": "NON_PARTICIPATING",
101
- "186": "FAIL",
102
  "187": "NOT_ALIVE",
103
- "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
- "19": "NON_PARTICIPATING",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
- "193": "NON_PARTICIPATING",
110
- "194": "NOT_ALIVE",
111
- "195": "NON_PARTICIPATING",
112
  "196": "SUCCESS",
113
- "197": "NOT_ALIVE",
114
  "198": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
116
- "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
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": "FAIL",
128
- "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
- "211": "FAIL",
131
- "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
- "214": "SUCCESS",
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": "FAIL",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "NON_PARTICIPATING",
147
  "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
- "229": "SUCCESS",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
- "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
- "236": "SUCCESS",
158
- "237": "SUCCESS",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "NOT_ALIVE",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
- "3": "FAIL",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "SUCCESS",
190
- "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
- "39": "NON_PARTICIPATING",
194
- "4": "NON_PARTICIPATING",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
- "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
- "44": "NON_PARTICIPATING",
200
- "45": "FAIL",
201
  "46": "SUCCESS",
202
- "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
  "50": "NON_PARTICIPATING",
207
- "51": "NOT_ALIVE",
208
  "52": "NON_PARTICIPATING",
209
- "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
- "56": "SUCCESS",
213
  "57": "SUCCESS",
214
  "58": "NON_PARTICIPATING",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NOT_ALIVE",
219
- "62": "SUCCESS",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
- "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
@@ -229,11 +229,11 @@
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
- "74": "NON_PARTICIPATING",
233
  "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
- "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
  "8": "SUCCESS",
239
  "80": "NOT_ALIVE",
@@ -241,9 +241,9 @@
241
  "82": "NOT_ALIVE",
242
  "83": "NON_PARTICIPATING",
243
  "84": "SUCCESS",
244
- "85": "NOT_ALIVE",
245
- "86": "NON_PARTICIPATING",
246
- "87": "NOT_ALIVE",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "SUCCESS",
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6476411,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
+ "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
10
  "103": "SUCCESS",
11
  "104": "NOT_ALIVE",
12
+ "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
+ "109": "SUCCESS",
17
+ "11": "NOT_ALIVE",
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": "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": "SUCCESS",
36
+ "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
+ "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "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": "NOT_ALIVE",
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": "SUCCESS",
66
+ "154": "SUCCESS",
67
  "155": "NOT_ALIVE",
68
  "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
 
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
+ "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
 
81
  "168": "SUCCESS",
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
+ "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
+ "177": "FAIL",
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": "SUCCESS",
99
+ "184": "SUCCESS",
100
+ "185": "NOT_ALIVE",
101
+ "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
+ "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
+ "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "SUCCESS",
110
+ "194": "NON_PARTICIPATING",
111
+ "195": "NOT_ALIVE",
112
  "196": "SUCCESS",
113
+ "197": "NON_PARTICIPATING",
114
  "198": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
116
+ "2": "NON_PARTICIPATING",
117
  "20": "SUCCESS",
118
  "200": "SUCCESS",
119
+ "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
+ "205": "NOT_ALIVE",
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": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "FAIL",
139
+ "22": "NON_PARTICIPATING",
140
+ "220": "NOT_ALIVE",
141
+ "221": "SUCCESS",
142
  "222": "FAIL",
143
+ "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "NOT_ALIVE",
147
  "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
+ "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
+ "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
+ "236": "FAIL",
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": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
+ "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
+ "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
+ "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "SUCCESS",
190
+ "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
+ "39": "SUCCESS",
194
+ "4": "SUCCESS",
195
+ "40": "NOT_ALIVE",
196
  "41": "NOT_ALIVE",
197
+ "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
+ "44": "SUCCESS",
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": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
+ "56": "NON_PARTICIPATING",
213
  "57": "SUCCESS",
214
  "58": "NON_PARTICIPATING",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NOT_ALIVE",
219
+ "62": "NON_PARTICIPATING",
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": "SUCCESS",
 
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
+ "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
+ "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
  "8": "SUCCESS",
239
  "80": "NOT_ALIVE",
 
241
  "82": "NOT_ALIVE",
242
  "83": "NON_PARTICIPATING",
243
  "84": "SUCCESS",
244
+ "85": "NON_PARTICIPATING",
245
+ "86": "NOT_ALIVE",
246
+ "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "SUCCESS",
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6477264,
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 sha256:21602a540471a0981049a493d5825d18515f6c446a4b2fc2e772ae9867a089c9
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36f17a1639c53a3fe29355f35a5549c7bbea4f11aca6bfa59a1b8fbe865b71b
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66f63dc9f08928221605a8045389a40551d768888d37f5f45859ba3868668748
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0777c8d539760c3de6e16ce21100483d3ea6f2f2fb734b1c2d98ed423e579ffa
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3de006bc3a12079e6048ad0fe6817e5347b6be1c45b1ad45f9ddb8c83040485d
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b85fea8508809ce401821fd4c84fe28ce5b4795e2d7edffe84bf95c5fd510afe
3
  size 4400252568