kmfoda commited on
Commit
b0bcf3d
·
verified ·
1 Parent(s): 20bdb7a

Run 10. Outer Step 45. Inner Step 0. Peers 62.

Browse files
Files changed (4) hide show
  1. config.json +45 -45
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -5,12 +5,12 @@
5
  "1": "SUCCESS",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
- "101": "NON_PARTICIPATING",
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
- "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
@@ -20,30 +20,30 @@
20
  "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
  "114": "SUCCESS",
23
- "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
- "118": "NON_PARTICIPATING",
27
- "119": "SUCCESS",
28
- "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
- "124": "NOT_ALIVE",
34
- "125": "NON_PARTICIPATING",
35
- "126": "NON_PARTICIPATING",
36
- "127": "NON_PARTICIPATING",
37
  "128": "SUCCESS",
38
  "129": "NON_PARTICIPATING",
39
- "13": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
@@ -51,7 +51,7 @@
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",
@@ -66,23 +66,23 @@
66
  "154": "SUCCESS",
67
  "155": "NOT_ALIVE",
68
  "156": "SUCCESS",
69
- "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
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": "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",
@@ -92,12 +92,12 @@
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": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
@@ -120,17 +120,17 @@
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
- "205": "SUCCESS",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "NOT_ALIVE",
130
  "211": "SUCCESS",
131
- "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
- "214": "NOT_ALIVE",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
@@ -139,7 +139,7 @@
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
- "222": "NOT_ALIVE",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
@@ -147,16 +147,16 @@
147
  "227": "SUCCESS",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
- "23": "SUCCESS",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
  "233": "NON_PARTICIPATING",
155
- "234": "NOT_ALIVE",
156
  "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
@@ -165,9 +165,9 @@
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
- "246": "NOT_ALIVE",
169
  "247": "NOT_ALIVE",
170
- "248": "NOT_ALIVE",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
@@ -181,7 +181,7 @@
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
- "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
@@ -190,7 +190,7 @@
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
- "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
  "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
@@ -198,7 +198,7 @@
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
- "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
@@ -216,16 +216,16 @@
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
- "62": "NON_PARTICIPATING",
220
  "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
- "69": "NOT_ALIVE",
227
  "7": "SUCCESS",
228
- "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
@@ -236,7 +236,7 @@
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
- "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
@@ -245,18 +245,18 @@
245
  "86": "SUCCESS",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
- "89": "SUCCESS",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
- "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
  "98": "NOT_ALIVE",
259
- "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6492438,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
5
  "1": "SUCCESS",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
+ "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
+ "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
 
20
  "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
  "114": "SUCCESS",
23
+ "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
+ "118": "NOT_ALIVE",
27
+ "119": "NON_PARTICIPATING",
28
+ "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
+ "124": "NON_PARTICIPATING",
34
+ "125": "SUCCESS",
35
+ "126": "SUCCESS",
36
+ "127": "NOT_ALIVE",
37
  "128": "SUCCESS",
38
  "129": "NON_PARTICIPATING",
39
+ "13": "SUCCESS",
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",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
 
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
+ "143": "NOT_ALIVE",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
 
66
  "154": "SUCCESS",
67
  "155": "NOT_ALIVE",
68
  "156": "SUCCESS",
69
+ "157": "NOT_ALIVE",
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": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
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": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
+ "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
 
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
+ "205": "NOT_ALIVE",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "NOT_ALIVE",
130
  "211": "SUCCESS",
131
+ "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "SUCCESS",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
 
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
+ "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
 
147
  "227": "SUCCESS",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
+ "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "SUCCESS",
156
  "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
 
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": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
 
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
 
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "SUCCESS",
195
  "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
 
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
 
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
+ "62": "SUCCESS",
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": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
+ "70": "NON_PARTICIPATING",
229
  "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
 
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
+ "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
 
245
  "86": "SUCCESS",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
+ "89": "NOT_ALIVE",
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": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "NOT_ALIVE",
259
+ "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6492801,
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:ddc3479cbbf682b87e7593a9c4d56fac5c1f22123874823584940698827de1c9
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02489749c6a43cbec270702a6b18c9ec6902838c4ef594e4978011dd2619a31b
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2f63af5c3a712df368ac17d10552eb79f23900da0d579fcbe8453c59fa6d2b1
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0897712db429c95b8c3bd505d60978bb5b97cb3c8dbf2d6ef5450a30d6ebbb8c
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1290a2db0963bcb502d44766dd78b3fdd3ab910e9191970de4d49b2c1847ba68
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2deb0151956045578a748542be3f35a83377b221be4c7c1aebc5c9432813d75c
3
  size 4400252568