kmfoda commited on
Commit
7e2f78f
·
verified ·
1 Parent(s): b03292e

Run 7. Outer Step 134. Inner Step 0. Peers 33.

Browse files
Files changed (4) hide show
  1. config.json +32 -32
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "_name_or_path": "fjtusu/distrisudo",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
- "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
@@ -17,19 +17,19 @@
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
- "112": "NON_PARTICIPATING",
21
- "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
- "117": "NON_PARTICIPATING",
26
  "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "NOT_ALIVE",
32
- "123": "NON_PARTICIPATING",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
@@ -37,23 +37,23 @@
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
- "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
- "132": "NOT_ALIVE",
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": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
@@ -64,17 +64,17 @@
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": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
@@ -90,7 +90,7 @@
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
- "179": "NOT_ALIVE",
94
  "18": "SUCCESS",
95
  "180": "NOT_ALIVE",
96
  "181": "SUCCESS",
@@ -100,7 +100,7 @@
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",
@@ -125,11 +125,11 @@
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
- "21": "SUCCESS",
129
- "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
  "212": "NON_PARTICIPATING",
132
- "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
  "216": "SUCCESS",
@@ -148,7 +148,7 @@
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
@@ -171,13 +171,13 @@
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
- "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
- "26": "NOT_ALIVE",
180
- "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
@@ -198,7 +198,7 @@
198
  "43": "NON_PARTICIPATING",
199
  "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
- "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
@@ -206,7 +206,7 @@
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",
@@ -215,11 +215,11 @@
215
  "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
- "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
- "64": "NOT_ALIVE",
222
- "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
@@ -249,7 +249,7 @@
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",
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6317391,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "AussieAck/D9_model",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
+ "100": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
 
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
+ "112": "SUCCESS",
21
+ "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
+ "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
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",
 
37
  "128": "NOT_ALIVE",
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",
 
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",
 
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
+ "179": "NON_PARTICIPATING",
94
  "18": "SUCCESS",
95
  "180": "NOT_ALIVE",
96
  "181": "SUCCESS",
 
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",
 
125
  "207": "NOT_ALIVE",
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",
134
  "215": "NOT_ALIVE",
135
  "216": "SUCCESS",
 
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
+ "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "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",
 
198
  "43": "NON_PARTICIPATING",
199
  "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
+ "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
 
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",
 
215
  "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
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",
 
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",
 
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",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21880feada2ddfc9c41ddc1a25a3cc608ad25642ee3ae0b9587b6e97e83588a6
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5088094604e87f36f2d41b5b4ffb645c11fe7042b94c2cc72cfeb8b3ee172861
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:910e7c869b285bbc508e2935c57b7b9903642c015d24cafd5d976094ecea39ec
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a817ae5c4105e4bae29901580f6f5ccb4fc124fe22303c2ff0328c5cbcb5cbb6
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7777fcad31e32edd413c6e43be6a32bc8b7a3fd8ca1f25f59c801fd09467e49d
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1edb17525c9749f55c604d654c30af68d4c50a4952e279146418213eabef96a
3
  size 4400252568