kmfoda commited on
Commit
c90f1e3
·
verified ·
1 Parent(s): 12e9a7b

Run 10. Outer Step 48. Inner Step 0. Peers 59.

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
@@ -1,166 +1,166 @@
1
  {
2
- "_name_or_path": "aalv2/c70-h11",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "FAIL",
6
- "10": "FAIL",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
- "102": "FAIL",
10
- "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "FAIL",
13
- "106": "NON_PARTICIPATING",
14
- "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
- "109": "FAIL",
17
- "11": "FAIL",
18
  "110": "NOT_ALIVE",
19
- "111": "FAIL",
20
  "112": "NON_PARTICIPATING",
21
- "113": "FAIL",
22
- "114": "FAIL",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
- "117": "NOT_ALIVE",
26
- "118": "FAIL",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "NON_PARTICIPATING",
31
- "122": "NOT_ALIVE",
32
- "123": "FAIL",
33
  "124": "NON_PARTICIPATING",
34
- "125": "FAIL",
35
- "126": "FAIL",
36
  "127": "NON_PARTICIPATING",
37
- "128": "FAIL",
38
  "129": "NON_PARTICIPATING",
39
- "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
- "135": "NOT_ALIVE",
46
- "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
- "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
- "142": "FAIL",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
- "146": "NON_PARTICIPATING",
58
- "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "FAIL",
66
- "154": "FAIL",
67
  "155": "NOT_ALIVE",
68
- "156": "FAIL",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
- "159": "FAIL",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
- "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
- "166": "FAIL",
80
- "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
- "169": "FAIL",
83
- "17": "NOT_ALIVE",
84
- "170": "FAIL",
85
- "171": "FAIL",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
- "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
- "182": "NOT_ALIVE",
98
- "183": "FAIL",
99
  "184": "FAIL",
100
- "185": "FAIL",
101
- "186": "FAIL",
102
  "187": "NOT_ALIVE",
103
- "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
- "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
- "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
- "198": "FAIL",
115
- "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "FAIL",
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": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
- "21": "FAIL",
129
- "210": "FAIL",
130
- "211": "NOT_ALIVE",
131
- "212": "FAIL",
132
- "213": "NON_PARTICIPATING",
133
- "214": "FAIL",
134
- "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
- "218": "NON_PARTICIPATING",
138
- "219": "FAIL",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
- "221": "FAIL",
142
- "222": "NON_PARTICIPATING",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "NON_PARTICIPATING",
147
- "227": "FAIL",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
- "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
- "232": "FAIL",
154
  "233": "NON_PARTICIPATING",
155
- "234": "FAIL",
156
- "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
- "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "FAIL",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
@@ -170,66 +170,66 @@
170
  "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
- "252": "FAIL",
176
  "253": "NOT_ALIVE",
177
- "254": "FAIL",
178
- "255": "FAIL",
179
- "26": "FAIL",
180
  "27": "NOT_ALIVE",
181
- "28": "NON_PARTICIPATING",
182
- "29": "FAIL",
183
- "3": "FAIL",
184
  "30": "NON_PARTICIPATING",
185
- "31": "FAIL",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
- "39": "NON_PARTICIPATING",
194
- "4": "FAIL",
195
- "40": "FAIL",
196
  "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
- "44": "FAIL",
200
- "45": "NON_PARTICIPATING",
201
- "46": "FAIL",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
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": "NOT_ALIVE",
212
- "56": "NOT_ALIVE",
213
- "57": "FAIL",
214
  "58": "NOT_ALIVE",
215
- "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
- "60": "FAIL",
218
- "61": "NON_PARTICIPATING",
219
- "62": "FAIL",
220
  "63": "NOT_ALIVE",
221
- "64": "FAIL",
222
- "65": "NON_PARTICIPATING",
223
- "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
- "71": "NON_PARTICIPATING",
230
- "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
- "74": "FAIL",
233
  "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
@@ -238,25 +238,25 @@
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
- "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
  "86": "FAIL",
246
- "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
- "89": "NOT_ALIVE",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
- "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
- "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NOT_ALIVE",
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": 6493593,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "aalv2/c71-h22",
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": "SUCCESS",
10
+ "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
+ "105": "SUCCESS",
13
+ "106": "SUCCESS",
14
+ "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
+ "109": "SUCCESS",
17
+ "11": "NON_PARTICIPATING",
18
  "110": "NOT_ALIVE",
19
+ "111": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
+ "113": "SUCCESS",
22
+ "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "SUCCESS",
25
+ "117": "NON_PARTICIPATING",
26
+ "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "SUCCESS",
31
+ "122": "NON_PARTICIPATING",
32
+ "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "NOT_ALIVE",
35
+ "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
+ "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
+ "135": "NON_PARTICIPATING",
46
+ "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
+ "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "SUCCESS",
58
+ "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NON_PARTICIPATING",
66
+ "154": "SUCCESS",
67
  "155": "NOT_ALIVE",
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": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "SUCCESS",
80
+ "167": "SUCCESS",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "NOT_ALIVE",
83
+ "17": "NON_PARTICIPATING",
84
+ "170": "SUCCESS",
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": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
+ "182": "NON_PARTICIPATING",
98
+ "183": "SUCCESS",
99
  "184": "FAIL",
100
+ "185": "SUCCESS",
101
+ "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
+ "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
+ "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
+ "196": "NON_PARTICIPATING",
113
  "197": "NOT_ALIVE",
114
+ "198": "SUCCESS",
115
+ "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
  "20": "FAIL",
118
+ "200": "FAIL",
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": "NOT_ALIVE",
130
+ "211": "SUCCESS",
131
+ "212": "SUCCESS",
132
+ "213": "NOT_ALIVE",
133
+ "214": "SUCCESS",
134
+ "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
+ "218": "NOT_ALIVE",
138
+ "219": "SUCCESS",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "SUCCESS",
142
+ "222": "NOT_ALIVE",
143
+ "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "SUCCESS",
147
+ "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
+ "23": "NON_PARTICIPATING",
151
+ "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
+ "232": "SUCCESS",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
+ "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "NOT_ALIVE",
159
  "238": "NON_PARTICIPATING",
160
+ "239": "SUCCESS",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
+ "241": "SUCCESS",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
 
170
  "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
+ "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
+ "254": "NON_PARTICIPATING",
178
+ "255": "NON_PARTICIPATING",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
+ "28": "SUCCESS",
182
+ "29": "NOT_ALIVE",
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": "SUCCESS",
194
+ "4": "NON_PARTICIPATING",
195
+ "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
+ "44": "NON_PARTICIPATING",
200
+ "45": "SUCCESS",
201
+ "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
  "5": "NON_PARTICIPATING",
206
+ "50": "SUCCESS",
207
+ "51": "SUCCESS",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
+ "56": "NON_PARTICIPATING",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
+ "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
+ "60": "SUCCESS",
218
+ "61": "NOT_ALIVE",
219
+ "62": "NON_PARTICIPATING",
220
  "63": "NOT_ALIVE",
221
+ "64": "SUCCESS",
222
+ "65": "NOT_ALIVE",
223
+ "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
+ "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
+ "71": "NOT_ALIVE",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
+ "74": "NON_PARTICIPATING",
233
  "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
 
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
+ "82": "SUCCESS",
242
  "83": "NOT_ALIVE",
243
+ "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
  "86": "FAIL",
246
+ "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
+ "89": "SUCCESS",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NOT_ALIVE",
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": "NOT_ALIVE",
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": 6494453,
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:ff7b4d0ed84ce439a78d4ef7983f6213049bdc3aafed0e24b6b927b3e7ffdd1b
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eabc439bd393e4054b1e0e426c8c6c9a79fc343275bd200ff0090836548c96b4
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4eb3bfb7b3e19127afbcf704d7774ef59f774b019bb77e4993541809da1a331
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:543576c44fd56892d443682eb010cb8a1324ab32046a29b16f744b793f3195f0
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a57889e5583d873a6e3fd7c19597d5232161c94388cdf9f8bc94f6429f80f62
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30d831fb75902a7dfd8b7542c6c8303322032044254f59a409f8cf7f582439f5
3
  size 4400252568