kmfoda commited on
Commit
f2a5435
·
verified ·
1 Parent(s): 944cda3

Run 10. Outer Step 51. Inner Step 0. Peers 62.

Browse files
Files changed (4) hide show
  1. config.json +56 -56
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -5,25 +5,25 @@
5
  "1": "SUCCESS",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
- "101": "SUCCESS",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "SUCCESS",
13
  "106": "SUCCESS",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
- "11": "NOT_ALIVE",
18
- "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
- "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
- "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
@@ -31,12 +31,12 @@
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
- "125": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
- "128": "SUCCESS",
38
  "129": "NOT_ALIVE",
39
- "13": "NON_PARTICIPATING",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
@@ -45,44 +45,44 @@
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
- "138": "NOT_ALIVE",
49
- "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
- "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
- "146": "NOT_ALIVE",
58
- "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
- "149": "NOT_ALIVE",
61
- "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "SUCCESS",
66
- "154": "NOT_ALIVE",
67
- "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
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",
79
- "166": "SUCCESS",
80
- "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
- "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
- "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
@@ -92,28 +92,28 @@
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
- "180": "NOT_ALIVE",
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": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
- "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
- "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
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",
@@ -124,9 +124,9 @@
124
  "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
- "209": "NON_PARTICIPATING",
128
- "21": "NON_PARTICIPATING",
129
- "210": "SUCCESS",
130
  "211": "SUCCESS",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
@@ -139,15 +139,15 @@
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
- "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
- "227": "NON_PARTICIPATING",
148
- "228": "NOT_ALIVE",
149
- "229": "NOT_ALIVE",
150
- "23": "NON_PARTICIPATING",
151
  "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
@@ -175,7 +175,7 @@
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "SUCCESS",
178
- "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
@@ -185,8 +185,8 @@
185
  "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "NOT_ALIVE",
189
- "35": "NOT_ALIVE",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
@@ -203,18 +203,18 @@
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
  "5": "NON_PARTICIPATING",
206
- "50": "SUCCESS",
207
- "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
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": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
  "62": "SUCCESS",
220
  "63": "NOT_ALIVE",
@@ -223,19 +223,19 @@
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
- "69": "SUCCESS",
227
- "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
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": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
- "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
@@ -247,13 +247,13 @@
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
  "9": "NON_PARTICIPATING",
250
- "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
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": 6495220,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
5
  "1": "SUCCESS",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
+ "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
+ "11": "SUCCESS",
18
+ "110": "NON_PARTICIPATING",
19
  "111": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
+ "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "SUCCESS",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
 
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "FAIL",
38
  "129": "NOT_ALIVE",
39
+ "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
 
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
+ "138": "NON_PARTICIPATING",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
+ "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
+ "146": "SUCCESS",
58
+ "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "NON_PARTICIPATING",
61
+ "15": "NON_PARTICIPATING",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
+ "154": "SUCCESS",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
+ "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "NOT_ALIVE",
80
+ "167": "SUCCESS",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
+ "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
 
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
+ "182": "NOT_ALIVE",
98
  "183": "SUCCESS",
99
  "184": "SUCCESS",
100
+ "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
+ "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
+ "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
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",
 
124
  "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "NOT_ALIVE",
128
+ "21": "FAIL",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
 
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
+ "222": "SUCCESS",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
+ "227": "NOT_ALIVE",
148
+ "228": "NON_PARTICIPATING",
149
+ "229": "NON_PARTICIPATING",
150
+ "23": "NOT_ALIVE",
151
  "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
 
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "SUCCESS",
178
+ "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
 
185
  "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "NON_PARTICIPATING",
189
+ "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
 
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
  "5": "NON_PARTICIPATING",
206
+ "50": "NON_PARTICIPATING",
207
+ "51": "SUCCESS",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
+ "56": "NON_PARTICIPATING",
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "SUCCESS",
220
  "63": "NOT_ALIVE",
 
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
+ "69": "NOT_ALIVE",
227
+ "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
+ "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
233
+ "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
+ "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
 
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
  "9": "NON_PARTICIPATING",
250
+ "90": "SUCCESS",
251
  "91": "NON_PARTICIPATING",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
+ "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
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": 6495620,
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 sha256:83e4c46e0d9ed04b5f8221b8efa0e7b6c2361f1bd316f2dd8642136704cd552f
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c635860d43b6dd02f6aeddf6b0df033399ef333b2f16fbe8193c2d5b247992c
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b8157bf094ffc72b198c9c99d6c3852384ef05455e18cf4e51d6aa7e13d06c4
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f843823479ea19dc46bab3ee0dd3a45dba177ddf92ba876b66370f5a262bb56e
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bd707cd96bf3d7a0c1a0f886e9533e6482f686631c6f3a06f045897f0e5031a
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec89156b9335a97bb801dfe261d8a639538a06a23976e2b94d4314a3b62b9488
3
  size 4400252568