kmfoda commited on
Commit
c13cc8c
·
verified ·
1 Parent(s): 15eb384

Run 10. Outer Step 8. Inner Step 0. Peers 1.

Browse files
Files changed (4) hide show
  1. config.json +115 -115
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,13 +1,13 @@
1
  {
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": "NOT_ALIVE",
9
- "102": "FAIL",
10
- "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "FAIL",
13
  "106": "FAIL",
@@ -15,56 +15,56 @@
15
  "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
  "11": "NON_PARTICIPATING",
18
- "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
- "112": "NON_PARTICIPATING",
21
  "113": "FAIL",
22
- "114": "NOT_ALIVE",
23
- "115": "FAIL",
24
- "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
- "118": "NON_PARTICIPATING",
27
- "119": "FAIL",
28
  "12": "NOT_ALIVE",
29
- "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
- "123": "FAIL",
33
- "124": "FAIL",
34
  "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
- "127": "FAIL",
37
  "128": "NON_PARTICIPATING",
38
- "129": "NOT_ALIVE",
39
- "13": "FAIL",
40
- "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
- "133": "SUCCESS",
44
- "134": "NON_PARTICIPATING",
45
- "135": "FAIL",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
- "138": "NON_PARTICIPATING",
49
  "139": "NOT_ALIVE",
50
- "14": "FAIL",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
- "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "FAIL",
59
- "148": "FAIL",
60
- "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
- "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
- "154": "NOT_ALIVE",
67
- "155": "NON_PARTICIPATING",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
@@ -73,84 +73,84 @@
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "FAIL",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
- "173": "NOT_ALIVE",
88
- "174": "NON_PARTICIPATING",
89
- "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "FAIL",
92
  "178": "NOT_ALIVE",
93
- "179": "NOT_ALIVE",
94
  "18": "NON_PARTICIPATING",
95
- "180": "FAIL",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
- "184": "FAIL",
100
  "185": "FAIL",
101
- "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "FAIL",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
  "190": "FAIL",
107
- "191": "NON_PARTICIPATING",
108
- "192": "NON_PARTICIPATING",
109
- "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
- "195": "NON_PARTICIPATING",
112
  "196": "FAIL",
113
  "197": "NON_PARTICIPATING",
114
- "198": "NON_PARTICIPATING",
115
  "199": "FAIL",
116
- "2": "FAIL",
117
- "20": "NON_PARTICIPATING",
118
- "200": "FAIL",
119
- "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "NOT_ALIVE",
124
  "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "FAIL",
128
- "21": "FAIL",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
- "212": "FAIL",
132
- "213": "NON_PARTICIPATING",
133
- "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
- "218": "NOT_ALIVE",
138
- "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
- "221": "NON_PARTICIPATING",
142
- "222": "NOT_ALIVE",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
- "225": "NON_PARTICIPATING",
146
  "226": "FAIL",
147
  "227": "FAIL",
148
- "228": "NOT_ALIVE",
149
- "229": "NON_PARTICIPATING",
150
- "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
- "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
@@ -158,105 +158,105 @@
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
- "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
- "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "FAIL",
168
- "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
- "248": "FAIL",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
  "252": "FAIL",
176
- "253": "FAIL",
177
- "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "FAIL",
180
  "27": "NOT_ALIVE",
181
- "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
- "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
- "35": "FAIL",
190
- "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
- "38": "NOT_ALIVE",
193
- "39": "NON_PARTICIPATING",
194
- "4": "SUCCESS",
195
- "40": "NON_PARTICIPATING",
196
- "41": "FAIL",
197
- "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
  "44": "FAIL",
200
- "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
- "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
- "50": "NOT_ALIVE",
207
- "51": "FAIL",
208
- "52": "NOT_ALIVE",
209
- "53": "FAIL",
210
  "54": "NOT_ALIVE",
211
- "55": "NOT_ALIVE",
212
- "56": "NOT_ALIVE",
213
- "57": "FAIL",
214
- "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
221
- "64": "FAIL",
222
  "65": "NOT_ALIVE",
223
- "66": "SUCCESS",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "FAIL",
227
- "7": "NOT_ALIVE",
228
- "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
- "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
- "74": "FAIL",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
- "8": "NOT_ALIVE",
239
- "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
- "83": "NON_PARTICIPATING",
243
  "84": "FAIL",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
- "87": "NON_PARTICIPATING",
247
- "88": "NON_PARTICIPATING",
248
- "89": "FAIL",
249
- "9": "SUCCESS",
250
- "90": "NON_PARTICIPATING",
251
  "91": "NON_PARTICIPATING",
252
- "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
- "96": "NON_PARTICIPATING",
257
- "97": "NON_PARTICIPATING",
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": 6468297,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "aalv2/c71-h23",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "FAIL",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
+ "102": "NON_PARTICIPATING",
10
+ "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "FAIL",
13
  "106": "FAIL",
 
15
  "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
  "11": "NON_PARTICIPATING",
18
+ "110": "FAIL",
19
  "111": "NON_PARTICIPATING",
20
+ "112": "FAIL",
21
  "113": "FAIL",
22
+ "114": "FAIL",
23
+ "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "NOT_ALIVE",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
+ "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "NON_PARTICIPATING",
33
+ "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
+ "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
+ "129": "NON_PARTICIPATING",
39
+ "13": "NOT_ALIVE",
40
+ "130": "FAIL",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "NON_PARTICIPATING",
44
+ "134": "NOT_ALIVE",
45
+ "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
+ "138": "NOT_ALIVE",
49
  "139": "NOT_ALIVE",
50
+ "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
+ "144": "FAIL",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "FAIL",
59
+ "148": "NON_PARTICIPATING",
60
+ "149": "FAIL",
61
  "15": "NOT_ALIVE",
62
+ "150": "FAIL",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "FAIL",
66
+ "154": "FAIL",
67
+ "155": "FAIL",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
 
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "FAIL",
83
  "17": "NON_PARTICIPATING",
84
  "170": "FAIL",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
+ "173": "NON_PARTICIPATING",
88
+ "174": "NOT_ALIVE",
89
+ "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
+ "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
+ "179": "FAIL",
94
  "18": "NON_PARTICIPATING",
95
+ "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
+ "184": "NON_PARTICIPATING",
100
  "185": "FAIL",
101
+ "186": "FAIL",
102
  "187": "NOT_ALIVE",
103
  "188": "FAIL",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
  "190": "FAIL",
107
+ "191": "NOT_ALIVE",
108
+ "192": "NOT_ALIVE",
109
+ "193": "FAIL",
110
  "194": "NOT_ALIVE",
111
+ "195": "FAIL",
112
  "196": "FAIL",
113
  "197": "NON_PARTICIPATING",
114
+ "198": "FAIL",
115
  "199": "FAIL",
116
+ "2": "NON_PARTICIPATING",
117
+ "20": "NOT_ALIVE",
118
+ "200": "NON_PARTICIPATING",
119
+ "201": "FAIL",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
+ "205": "FAIL",
124
  "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "FAIL",
128
+ "21": "NON_PARTICIPATING",
129
+ "210": "FAIL",
130
  "211": "NON_PARTICIPATING",
131
+ "212": "NOT_ALIVE",
132
+ "213": "NOT_ALIVE",
133
+ "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
+ "218": "NON_PARTICIPATING",
138
+ "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
+ "221": "NOT_ALIVE",
142
+ "222": "FAIL",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
+ "225": "NOT_ALIVE",
146
  "226": "FAIL",
147
  "227": "FAIL",
148
+ "228": "NON_PARTICIPATING",
149
+ "229": "FAIL",
150
+ "23": "NON_PARTICIPATING",
151
+ "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
+ "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
 
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
+ "24": "FAIL",
162
  "240": "NOT_ALIVE",
163
+ "241": "FAIL",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NOT_ALIVE",
168
+ "246": "NOT_ALIVE",
169
  "247": "NON_PARTICIPATING",
170
+ "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "FAIL",
176
+ "253": "NOT_ALIVE",
177
+ "254": "FAIL",
178
  "255": "NON_PARTICIPATING",
179
  "26": "FAIL",
180
  "27": "NOT_ALIVE",
181
+ "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
+ "3": "FAIL",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
+ "34": "NOT_ALIVE",
189
+ "35": "NON_PARTICIPATING",
190
+ "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
+ "39": "FAIL",
194
+ "4": "NOT_ALIVE",
195
+ "40": "FAIL",
196
+ "41": "NON_PARTICIPATING",
197
+ "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "FAIL",
200
+ "45": "NON_PARTICIPATING",
201
  "46": "NOT_ALIVE",
202
+ "47": "FAIL",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
+ "50": "NON_PARTICIPATING",
207
+ "51": "NON_PARTICIPATING",
208
+ "52": "NON_PARTICIPATING",
209
+ "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
+ "55": "NON_PARTICIPATING",
212
+ "56": "FAIL",
213
+ "57": "NON_PARTICIPATING",
214
+ "58": "NON_PARTICIPATING",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "FAIL",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
221
+ "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
+ "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "FAIL",
227
+ "7": "FAIL",
228
+ "70": "NON_PARTICIPATING",
229
  "71": "NOT_ALIVE",
230
+ "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
+ "8": "NON_PARTICIPATING",
239
+ "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
+ "83": "NOT_ALIVE",
243
  "84": "FAIL",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
+ "87": "FAIL",
247
+ "88": "FAIL",
248
+ "89": "NOT_ALIVE",
249
+ "9": "NOT_ALIVE",
250
+ "90": "FAIL",
251
  "91": "NON_PARTICIPATING",
252
+ "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
  "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
+ "96": "FAIL",
257
+ "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
+ "99": "FAIL"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6470715,
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 sha256:66ac2e1d6831b30f089c3a732c3c7cbc5444fe9291c32a4b79ce7a71133115bc
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6a67265c6f0dd05a68825e4bed2ce0e9bde50347da903e0525a641f47120056
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b47a91c9cd640580694ed28910eb18916dd9859aef59c10d495fc0b470aa9fe
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e19afc241f7b074dc5aef54aecd47dea029007ae92dd8ae92d04bf60a3c332c6
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ae888fd5d0bff61caa6252afc38a1a32305188b911fd1b288b71fbcf8109af3
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01db4282e85c8b757f2987ef44e109a5df0873d90a4087d390deaf914fbdc361
3
  size 4400252568