kmfoda commited on
Commit
59ee47d
·
verified ·
1 Parent(s): 7e2f78f

Run 7. Outer Step 135. Inner Step 0. Peers 33.

Browse files
Files changed (4) hide show
  1. config.json +43 -43
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "AussieAck/D9_model",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
@@ -28,9 +28,9 @@
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
- "122": "NOT_ALIVE",
32
  "123": "NOT_ALIVE",
33
- "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
@@ -38,24 +38,24 @@
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
- "131": "NOT_ALIVE",
42
  "132": "SUCCESS",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
  "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "NOT_ALIVE",
49
- "139": "NON_PARTICIPATING",
50
  "14": "SUCCESS",
51
- "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
- "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
@@ -64,27 +64,27 @@
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
  "154": "NON_PARTICIPATING",
67
- "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "SUCCESS",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
- "163": "NON_PARTICIPATING",
77
- "164": "NOT_ALIVE",
78
- "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
- "167": "NOT_ALIVE",
81
- "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
- "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
- "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
@@ -100,12 +100,12 @@
100
  "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
  "187": "SUCCESS",
103
- "188": "NOT_ALIVE",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
- "191": "SUCCESS",
108
- "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "SUCCESS",
111
  "195": "NOT_ALIVE",
@@ -118,7 +118,7 @@
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
@@ -126,8 +126,8 @@
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
- "210": "NOT_ALIVE",
130
- "211": "SUCCESS",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
  "214": "SUCCESS",
@@ -135,7 +135,7 @@
135
  "216": "SUCCESS",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
- "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
@@ -144,7 +144,7 @@
144
  "224": "NON_PARTICIPATING",
145
  "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
- "227": "NOT_ALIVE",
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
@@ -153,8 +153,8 @@
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
- "235": "NOT_ALIVE",
157
- "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
@@ -162,23 +162,23 @@
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
- "243": "NOT_ALIVE",
166
- "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
  "246": "SUCCESS",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
- "27": "NON_PARTICIPATING",
181
- "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
@@ -189,7 +189,7 @@
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
- "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
@@ -206,7 +206,7 @@
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "NON_PARTICIPATING",
209
- "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
@@ -218,17 +218,17 @@
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
- "64": "NON_PARTICIPATING",
222
- "65": "NOT_ALIVE",
223
- "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
- "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
@@ -245,17 +245,17 @@
245
  "86": "NON_PARTICIPATING",
246
  "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
- "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
- "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
- "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6318148,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "fjtusu/distrisudo",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
 
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
+ "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
33
+ "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
 
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
+ "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
  "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "NON_PARTICIPATING",
49
+ "139": "SUCCESS",
50
  "14": "SUCCESS",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
+ "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
 
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
  "154": "NON_PARTICIPATING",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
+ "163": "SUCCESS",
77
+ "164": "NON_PARTICIPATING",
78
+ "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
+ "167": "NON_PARTICIPATING",
81
+ "168": "NOT_ALIVE",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
+ "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
 
100
  "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
  "187": "SUCCESS",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
+ "191": "NON_PARTICIPATING",
108
+ "192": "NON_PARTICIPATING",
109
  "193": "NOT_ALIVE",
110
  "194": "SUCCESS",
111
  "195": "NOT_ALIVE",
 
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
 
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
+ "210": "NON_PARTICIPATING",
130
+ "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
  "214": "SUCCESS",
 
135
  "216": "SUCCESS",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
 
144
  "224": "NON_PARTICIPATING",
145
  "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
+ "227": "NON_PARTICIPATING",
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
 
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "NON_PARTICIPATING",
157
+ "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
 
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
+ "243": "NON_PARTICIPATING",
166
+ "244": "NOT_ALIVE",
167
  "245": "NOT_ALIVE",
168
  "246": "SUCCESS",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
  "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
+ "27": "SUCCESS",
181
+ "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
 
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
 
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "NON_PARTICIPATING",
209
+ "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
 
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
+ "64": "SUCCESS",
222
+ "65": "NON_PARTICIPATING",
223
+ "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
+ "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
+ "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
 
245
  "86": "NON_PARTICIPATING",
246
  "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
+ "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
+ "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
+ "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6318940,
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 sha256:5088094604e87f36f2d41b5b4ffb645c11fe7042b94c2cc72cfeb8b3ee172861
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700292059a945777924ff51744d61f5905a82d13d18842d6052a9a1aa6fb368f
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a817ae5c4105e4bae29901580f6f5ccb4fc124fe22303c2ff0328c5cbcb5cbb6
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00bbe21b42ff149abe7cd7084ab677cfa4af65090f9ab9149b51fd3fd638ccf
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1edb17525c9749f55c604d654c30af68d4c50a4952e279146418213eabef96a
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcdc14d104dc301c183d65ad47b81e74a1559c069ece18f2133b3bbfc2daa458
3
  size 4400252568