kmfoda commited on
Commit
4cc91f9
·
verified ·
1 Parent(s): 97fa26f

Run 10. Outer Step 58. Inner Step 0. Peers 63.

Browse files
Files changed (4) hide show
  1. config.json +64 -64
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -2,12 +2,12 @@
2
  "_name_or_path": "aalv2/c71-h21",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NOT_ALIVE",
6
- "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
- "101": "SUCCESS",
9
  "102": "SUCCESS",
10
- "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
  "106": "SUCCESS",
@@ -17,23 +17,23 @@
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NOT_ALIVE",
20
- "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
- "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "SUCCESS",
25
  "117": "NOT_ALIVE",
26
- "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
- "122": "NOT_ALIVE",
32
  "123": "SUCCESS",
33
- "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
  "126": "SUCCESS",
36
- "127": "NOT_ALIVE",
37
  "128": "SUCCESS",
38
  "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
@@ -51,14 +51,14 @@
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
- "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
  "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
- "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
@@ -66,27 +66,27 @@
66
  "154": "SUCCESS",
67
  "155": "SUCCESS",
68
  "156": "NON_PARTICIPATING",
69
- "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
- "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
- "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
- "166": "NON_PARTICIPATING",
80
- "167": "NOT_ALIVE",
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": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
@@ -95,12 +95,12 @@
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
- "183": "SUCCESS",
99
  "184": "SUCCESS",
100
- "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
- "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
  "190": "NON_PARTICIPATING",
@@ -115,23 +115,23 @@
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
  "20": "SUCCESS",
118
- "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
- "202": "NOT_ALIVE",
121
- "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
- "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
- "209": "NOT_ALIVE",
128
  "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
- "211": "NON_PARTICIPATING",
131
- "212": "SUCCESS",
132
- "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
- "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
@@ -142,66 +142,66 @@
142
  "222": "SUCCESS",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
- "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "SUCCESS",
150
- "23": "NOT_ALIVE",
151
  "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
- "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
- "235": "NON_PARTICIPATING",
157
- "236": "NOT_ALIVE",
158
- "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
- "239": "NOT_ALIVE",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
  "241": "SUCCESS",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "NOT_ALIVE",
168
  "246": "SUCCESS",
169
  "247": "NOT_ALIVE",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "NOT_ALIVE",
173
- "250": "NON_PARTICIPATING",
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": "SUCCESS",
182
- "29": "NON_PARTICIPATING",
183
  "3": "SUCCESS",
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": "NON_PARTICIPATING",
192
- "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
- "4": "SUCCESS",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
- "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
- "44": "NOT_ALIVE",
200
- "45": "NOT_ALIVE",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
- "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "SUCCESS",
207
  "51": "NON_PARTICIPATING",
@@ -216,47 +216,47 @@
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "SUCCESS",
219
- "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
  "64": "SUCCESS",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
- "69": "NOT_ALIVE",
227
  "7": "SUCCESS",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
233
- "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NON_PARTICIPATING",
239
- "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
- "82": "NOT_ALIVE",
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": "SUCCESS",
249
  "9": "NON_PARTICIPATING",
250
  "90": "SUCCESS",
251
  "91": "NON_PARTICIPATING",
252
- "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
- "99": "NON_PARTICIPATING"
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": 6498111,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
2
  "_name_or_path": "aalv2/c71-h21",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "NON_PARTICIPATING",
6
+ "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
+ "101": "NON_PARTICIPATING",
9
  "102": "SUCCESS",
10
+ "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
  "106": "SUCCESS",
 
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NOT_ALIVE",
20
+ "112": "NOT_ALIVE",
21
  "113": "SUCCESS",
22
+ "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "SUCCESS",
25
  "117": "NOT_ALIVE",
26
+ "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
+ "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
+ "124": "NOT_ALIVE",
34
  "125": "NON_PARTICIPATING",
35
  "126": "SUCCESS",
36
+ "127": "NON_PARTICIPATING",
37
  "128": "SUCCESS",
38
  "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
 
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
+ "143": "NOT_ALIVE",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
  "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "NON_PARTICIPATING",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
 
66
  "154": "SUCCESS",
67
  "155": "SUCCESS",
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": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "NOT_ALIVE",
80
+ "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "NON_PARTICIPATING",
83
+ "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
  "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
+ "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
 
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
+ "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
+ "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
+ "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
  "190": "NON_PARTICIPATING",
 
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
  "20": "SUCCESS",
118
+ "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
+ "202": "NON_PARTICIPATING",
121
+ "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "SUCCESS",
131
+ "212": "NON_PARTICIPATING",
132
+ "213": "NOT_ALIVE",
133
  "214": "SUCCESS",
134
+ "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
 
142
  "222": "SUCCESS",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
+ "225": "NOT_ALIVE",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "SUCCESS",
150
+ "23": "NON_PARTICIPATING",
151
  "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
+ "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
+ "235": "SUCCESS",
157
+ "236": "NON_PARTICIPATING",
158
+ "237": "SUCCESS",
159
  "238": "NON_PARTICIPATING",
160
+ "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
  "241": "SUCCESS",
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": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "NOT_ALIVE",
173
+ "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
+ "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
+ "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
+ "28": "NON_PARTICIPATING",
182
+ "29": "SUCCESS",
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": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
+ "38": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
200
+ "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
+ "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "SUCCESS",
207
  "51": "NON_PARTICIPATING",
 
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "SUCCESS",
219
+ "62": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
221
  "64": "SUCCESS",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
+ "69": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
233
+ "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NON_PARTICIPATING",
239
+ "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
+ "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "SUCCESS",
246
+ "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
+ "89": "NOT_ALIVE",
249
  "9": "NON_PARTICIPATING",
250
  "90": "SUCCESS",
251
  "91": "NON_PARTICIPATING",
252
+ "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
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": 6498484,
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 sha256:96cf26eed0c93da4abd3ac84013cfe2220b3cf12edd85ddd32601fc280d040c0
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5f73143fc17995c7fc50d550c2dc0db27b32e3888fa7b4180ad53154234661
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bce493d10bbc521d55c1b4425c81ba990b1688e1ea3dc6ac10f840b6cfeee50
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:657e9bf577135cc2a9f833497fa6984e2c20ef8a7ebd749548c0f63e7768a317
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a5f400497020913406e532290000868fe95cdb74d3c163bbc75e39dc5b0519d
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b92ce72702d1981441d34b848321532461f7efa71853cabe4dcb2e7ff5ccaba6
3
  size 4400252568