kmfoda commited on
Commit
74f7789
·
verified ·
1 Parent(s): 50d5570

Run 7. Outer Step 80. Inner Step 0. Peers 33.

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
@@ -1,11 +1,11 @@
1
  {
2
- "_name_or_path": "asim22/sub38-241",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
- "100": "NOT_ALIVE",
8
- "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
@@ -17,20 +17,20 @@
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
- "112": "NOT_ALIVE",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
- "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
- "117": "NON_PARTICIPATING",
26
- "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
- "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
@@ -40,12 +40,12 @@
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "SUCCESS",
43
- "133": "NOT_ALIVE",
44
  "134": "SUCCESS",
45
- "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
- "137": "NOT_ALIVE",
48
- "138": "NON_PARTICIPATING",
49
  "139": "SUCCESS",
50
  "14": "SUCCESS",
51
  "140": "SUCCESS",
@@ -54,9 +54,9 @@
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "SUCCESS",
57
- "146": "SUCCESS",
58
  "147": "NOT_ALIVE",
59
- "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "SUCCESS",
62
  "150": "NOT_ALIVE",
@@ -64,7 +64,7 @@
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",
@@ -85,17 +85,17 @@
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
- "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "FAIL",
92
  "178": "SUCCESS",
93
  "179": "NON_PARTICIPATING",
94
- "18": "SUCCESS",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "NOT_ALIVE",
99
  "184": "NOT_ALIVE",
100
  "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
@@ -112,7 +112,7 @@
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
- "199": "FAIL",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
@@ -128,7 +128,7 @@
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
- "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
@@ -145,25 +145,25 @@
145
  "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
- "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
- "234": "NOT_ALIVE",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
- "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "SUCCESS",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
- "244": "NON_PARTICIPATING",
167
  "245": "NON_PARTICIPATING",
168
  "246": "SUCCESS",
169
  "247": "NON_PARTICIPATING",
@@ -171,23 +171,23 @@
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",
185
- "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "SUCCESS",
190
- "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
@@ -197,7 +197,7 @@
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
- "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "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",
@@ -214,8 +214,8 @@
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
- "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
@@ -223,14 +223,14 @@
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
- "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
- "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
@@ -239,11 +239,11 @@
239
  "80": "SUCCESS",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NON_PARTICIPATING",
243
- "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
- "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
@@ -256,7 +256,7 @@
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
- "99": "SUCCESS"
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": 6276151,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "AussieAck/D24_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",
11
  "104": "NON_PARTICIPATING",
 
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
+ "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
+ "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
+ "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
+ "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
 
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "SUCCESS",
43
+ "133": "SUCCESS",
44
  "134": "SUCCESS",
45
+ "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
+ "137": "NON_PARTICIPATING",
48
+ "138": "SUCCESS",
49
  "139": "SUCCESS",
50
  "14": "SUCCESS",
51
  "140": "SUCCESS",
 
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "SUCCESS",
57
+ "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
+ "148": "SUCCESS",
60
  "149": "NON_PARTICIPATING",
61
  "15": "SUCCESS",
62
  "150": "NOT_ALIVE",
 
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": "NON_PARTICIPATING",
 
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
+ "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
+ "177": "NOT_ALIVE",
92
  "178": "SUCCESS",
93
  "179": "NON_PARTICIPATING",
94
+ "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
+ "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
 
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
 
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
+ "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
 
145
  "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
+ "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
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": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
+ "241": "NOT_ALIVE",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
+ "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
  "246": "SUCCESS",
169
  "247": "NON_PARTICIPATING",
 
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": "NON_PARTICIPATING",
181
+ "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
+ "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "NON_PARTICIPATING",
190
+ "36": "SUCCESS",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
 
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
+ "45": "NOT_ALIVE",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
 
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "NON_PARTICIPATING",
209
+ "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
 
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
+ "60": "NOT_ALIVE",
218
+ "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
 
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
+ "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
+ "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
+ "75": "SUCCESS",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
 
239
  "80": "SUCCESS",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
+ "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
+ "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
 
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
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": 6276862,
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:ef4498cb7c7e536f6a6c8b24d905c345528e628772d1f09ca4c0bb32161d08ba
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56c12319913741a9350c564e5ec0b1966e3cc78b22d036d26b11d65a26afdf3
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1278bb64708b04e49970e5ce87844b62876fca83c5a82c4e65d62ff4331956b
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7f59d553d1a3a4cc66ea822fd922efb81afbb33486377056e467b8598aae154
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00003c7583c2d5459497add20e2554668bb2373f2a953029cf7f072da7d8b006
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:063edf984f60dcb3461032597c3fd25d7688f2971608be45b27c9cf5b1ee54bb
3
  size 4400252568