kmfoda commited on
Commit
37f9819
·
verified ·
1 Parent(s): 5a08b3f

Run 10. Outer Step 107. Inner Step 0. Peers 60.

Browse files
Files changed (4) hide show
  1. config.json +49 -49
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -6,44 +6,44 @@
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
- "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
- "106": "NON_PARTICIPATING",
14
- "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
- "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
- "115": "SUCCESS",
24
  "116": "SUCCESS",
25
- "117": "NOT_ALIVE",
26
  "118": "SUCCESS",
27
  "119": "SUCCESS",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
- "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
- "123": "FAIL",
33
  "124": "NON_PARTICIPATING",
34
  "125": "SUCCESS",
35
  "126": "NON_PARTICIPATING",
36
- "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
- "13": "FAIL",
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": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
@@ -62,23 +62,23 @@
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "SUCCESS",
66
  "154": "FAIL",
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": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
- "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
- "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
@@ -86,7 +86,7 @@
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
- "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
@@ -99,11 +99,11 @@
99
  "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
- "187": "SUCCESS",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
- "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
@@ -121,42 +121,42 @@
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
- "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
- "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
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": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
- "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
- "227": "NON_PARTICIPATING",
148
- "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
- "231": "SUCCESS",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
- "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
@@ -164,10 +164,10 @@
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "NOT_ALIVE",
168
- "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
- "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
@@ -177,27 +177,27 @@
177
  "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
  "26": "SUCCESS",
180
- "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
- "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "SUCCESS",
190
  "36": "SUCCESS",
191
- "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
- "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
- "45": "SUCCESS",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
@@ -212,20 +212,20 @@
212
  "56": "NON_PARTICIPATING",
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
- "59": "SUCCESS",
216
- "6": "NOT_ALIVE",
217
- "60": "FAIL",
218
  "61": "SUCCESS",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
- "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
- "70": "NON_PARTICIPATING",
229
  "71": "SUCCESS",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
@@ -234,18 +234,18 @@
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
- "79": "FAIL",
238
  "8": "SUCCESS",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NOT_ALIVE",
245
- "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
- "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
@@ -253,7 +253,7 @@
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "FAIL",
257
  "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
  "99": "NOT_ALIVE"
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6524019,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
+ "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
+ "106": "SUCCESS",
14
+ "107": "FAIL",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
+ "111": "NOT_ALIVE",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
+ "115": "NOT_ALIVE",
24
  "116": "SUCCESS",
25
+ "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "SUCCESS",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
+ "121": "FAIL",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
  "125": "SUCCESS",
35
  "126": "NON_PARTICIPATING",
36
+ "127": "SUCCESS",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
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",
 
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
  "154": "FAIL",
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
+ "157": "SUCCESS",
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": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
+ "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
 
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
+ "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
 
99
  "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
+ "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
 
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
+ "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
+ "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
+ "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
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": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
+ "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
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": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
 
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NON_PARTICIPATING",
168
+ "246": "SUCCESS",
169
  "247": "NOT_ALIVE",
170
+ "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
 
177
  "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
  "26": "SUCCESS",
180
+ "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
+ "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "NOT_ALIVE",
190
  "36": "SUCCESS",
191
+ "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
+ "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
+ "45": "NON_PARTICIPATING",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
 
212
  "56": "NON_PARTICIPATING",
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
+ "59": "NON_PARTICIPATING",
216
+ "6": "SUCCESS",
217
+ "60": "SUCCESS",
218
  "61": "SUCCESS",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
+ "66": "SUCCESS",
224
  "67": "NOT_ALIVE",
225
  "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
+ "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
 
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
+ "79": "NON_PARTICIPATING",
238
  "8": "SUCCESS",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
+ "82": "SUCCESS",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NOT_ALIVE",
245
+ "86": "SUCCESS",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
+ "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
 
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
+ "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
  "99": "NOT_ALIVE"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6524389,
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:bd9ea608c2ec7b90c59b909f3b3af0595803c8cd24bb965877aa829fb61252c1
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7997d1a2686474b31f7c834e26206bad592011c0aa7a782c8d704e669a29f63c
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce82c11c4b1bb8498d27cd14f368047e1ab622601cbc9b455e524dc71c21ec08
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60830c9a77ecab0aa5873178996b8bc2da3b82b2138833bbb925a954c9c9d12
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c715de87dc49b44a4ba5c42944361c236cc0a30136c84a547d74e9fbf4e96768
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc8683e674b56c7ea77faf695ae26c6f0fb588c54b4a22e44feffa30c10b670
3
  size 4400252568