kmfoda commited on
Commit
a337a4b
·
verified ·
1 Parent(s): 1b5e2e3

Run 10. Outer Step 41. Inner Step 0. Peers 60.

Browse files
Files changed (4) hide show
  1. config.json +51 -51
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -3,25 +3,25 @@
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
- "10": "NOT_ALIVE",
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": "NOT_ALIVE",
17
- "11": "FAIL",
18
  "110": "NOT_ALIVE",
19
- "111": "NOT_ALIVE",
20
  "112": "NON_PARTICIPATING",
21
- "113": "NOT_ALIVE",
22
  "114": "SUCCESS",
23
- "115": "NON_PARTICIPATING",
24
- "116": "SUCCESS",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
@@ -31,7 +31,7 @@
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
- "125": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
@@ -54,7 +54,7 @@
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
- "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
@@ -66,7 +66,7 @@
66
  "154": "SUCCESS",
67
  "155": "NOT_ALIVE",
68
  "156": "SUCCESS",
69
- "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
@@ -76,28 +76,28 @@
76
  "163": "NON_PARTICIPATING",
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": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
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",
@@ -105,8 +105,8 @@
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",
@@ -118,15 +118,15 @@
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
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": "SUCCESS",
129
- "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
@@ -139,24 +139,24 @@
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",
146
  "226": "NON_PARTICIPATING",
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": "SUCCESS",
156
- "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
@@ -170,33 +170,33 @@
170
  "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
- "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
- "255": "SUCCESS",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
- "28": "NOT_ALIVE",
182
- "29": "NOT_ALIVE",
183
- "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
  "31": "SUCCESS",
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": "SUCCESS",
195
  "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
- "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
@@ -209,13 +209,13 @@
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": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
- "61": "NON_PARTICIPATING",
219
  "62": "SUCCESS",
220
  "63": "NOT_ALIVE",
221
  "64": "SUCCESS",
@@ -225,7 +225,7 @@
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
  "7": "SUCCESS",
228
- "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
@@ -236,22 +236,22 @@
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",
243
- "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
- "86": "SUCCESS",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
- "89": "SUCCESS",
249
  "9": "SUCCESS",
250
  "90": "NOT_ALIVE",
251
  "91": "SUCCESS",
252
- "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
- "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6491025,
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": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "SUCCESS",
10
+ "103": "SUCCESS",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
+ "108": "NOT_ALIVE",
16
+ "109": "SUCCESS",
17
+ "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
+ "111": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
+ "113": "NON_PARTICIPATING",
22
  "114": "SUCCESS",
23
+ "115": "NOT_ALIVE",
24
+ "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
 
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
 
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
+ "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
 
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",
 
76
  "163": "NON_PARTICIPATING",
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": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
+ "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
+ "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
+ "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
+ "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
 
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
+ "192": "SUCCESS",
109
+ "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
  "196": "SUCCESS",
 
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
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": "SUCCESS",
130
  "211": "SUCCESS",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
 
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
+ "222": "NOT_ALIVE",
143
+ "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
+ "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
+ "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
+ "231": "NOT_ALIVE",
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",
 
170
  "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
+ "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
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",
188
  "34": "NOT_ALIVE",
189
+ "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
+ "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
193
+ "39": "FAIL",
194
  "4": "SUCCESS",
195
  "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
+ "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
 
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": "NON_PARTICIPATING",
218
+ "61": "NOT_ALIVE",
219
  "62": "SUCCESS",
220
  "63": "NOT_ALIVE",
221
  "64": "SUCCESS",
 
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
  "7": "SUCCESS",
228
+ "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
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",
243
+ "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
+ "89": "NOT_ALIVE",
249
  "9": "SUCCESS",
250
  "90": "NOT_ALIVE",
251
  "91": "SUCCESS",
252
+ "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
+ "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6491384,
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 sha256:2c7d2cea1909222a68d5feb7db47c6ce202d2b4cddf1369cc5e71f3b49ab2095
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a61ff623657ec436bc9376f7a3437d3beaccc2eb42544ec5bc58f20299f85289
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7e59a2310dc7216977fa1cf11c14826f987133139490954da5ba13b9618e7cb
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8341bd05d022a07063d06504c2578d244f3c9b556ecbd691af891f068e465500
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27955901b88fb6bf09ad57716fce80728ba3f35cb5d2f00ca477a6ade6c0f7ee
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd71ff2be96e03858dcd03cf70402b1a999f7313bd4e2b7895002c677b68394
3
  size 4400252568