kmfoda commited on
Commit
9250215
·
verified ·
1 Parent(s): 1509147

Run 10. Outer Step 22. Inner Step 0. Peers 60.

Browse files
Files changed (4) hide show
  1. config.json +79 -79
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,48 +1,48 @@
1
  {
2
- "_name_or_path": "strnan01/llama-1b-hot-6",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "FAIL",
6
- "10": "FAIL",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
- "102": "SUCCESS",
10
- "103": "FAIL",
11
  "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
- "109": "NOT_ALIVE",
17
- "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
- "111": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
- "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
- "118": "NON_PARTICIPATING",
27
- "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
- "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
- "123": "NOT_ALIVE",
33
  "124": "NOT_ALIVE",
34
- "125": "NON_PARTICIPATING",
35
- "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
- "129": "NOT_ALIVE",
39
- "13": "FAIL",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
- "134": "NON_PARTICIPATING",
45
- "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
@@ -50,86 +50,86 @@
50
  "14": "NON_PARTICIPATING",
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": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
- "149": "NON_PARTICIPATING",
61
- "15": "NON_PARTICIPATING",
62
  "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
- "153": "NOT_ALIVE",
66
  "154": "SUCCESS",
67
- "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
- "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
- "168": "NOT_ALIVE",
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
- "170": "FAIL",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
- "173": "NOT_ALIVE",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
  "179": "NON_PARTICIPATING",
94
- "18": "SUCCESS",
95
- "180": "SUCCESS",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
- "184": "NOT_ALIVE",
100
  "185": "NOT_ALIVE",
101
- "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
- "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
- "195": "SUCCESS",
112
  "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
- "20": "NOT_ALIVE",
118
- "200": "FAIL",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
- "205": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
- "213": "SUCCESS",
133
  "214": "SUCCESS",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
@@ -139,78 +139,78 @@
139
  "22": "NON_PARTICIPATING",
140
  "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
- "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
- "225": "SUCCESS",
146
  "226": "NON_PARTICIPATING",
147
  "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
- "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NON_PARTICIPATING",
154
- "233": "NOT_ALIVE",
155
- "234": "SUCCESS",
156
- "235": "NON_PARTICIPATING",
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": "FAIL",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
- "248": "FAIL",
171
- "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
- "252": "FAIL",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
- "255": "SUCCESS",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
- "3": "FAIL",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
- "35": "NOT_ALIVE",
190
- "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
- "38": "FAIL",
193
- "39": "NOT_ALIVE",
194
- "4": "FAIL",
195
- "40": "NON_PARTICIPATING",
196
- "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
- "44": "FAIL",
200
- "45": "NON_PARTICIPATING",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
  "5": "NON_PARTICIPATING",
206
  "50": "NON_PARTICIPATING",
207
- "51": "NOT_ALIVE",
208
- "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
- "57": "FAIL",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
@@ -224,14 +224,14 @@
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
- "7": "FAIL",
228
  "70": "NOT_ALIVE",
229
- "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
- "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
- "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
@@ -239,16 +239,16 @@
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NON_PARTICIPATING",
243
- "84": "FAIL",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
- "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "SUCCESS",
250
- "90": "NON_PARTICIPATING",
251
- "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6479163,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "aalv2/c71-h21",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "SUCCESS",
6
+ "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
+ "102": "NOT_ALIVE",
10
+ "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "SUCCESS",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
+ "109": "SUCCESS",
17
+ "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "NOT_ALIVE",
20
  "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
+ "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "NOT_ALIVE",
27
+ "119": "FAIL",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
+ "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
+ "125": "NOT_ALIVE",
35
+ "126": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
44
+ "134": "NOT_ALIVE",
45
+ "135": "NOT_ALIVE",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
 
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
+ "142": "SUCCESS",
54
+ "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
+ "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "NOT_ALIVE",
61
+ "15": "SUCCESS",
62
  "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
+ "153": "SUCCESS",
66
  "154": "SUCCESS",
67
+ "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
+ "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
  "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
+ "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
+ "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
+ "173": "FAIL",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
  "179": "NON_PARTICIPATING",
94
+ "18": "NON_PARTICIPATING",
95
+ "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
+ "184": "SUCCESS",
100
  "185": "NOT_ALIVE",
101
+ "186": "NOT_ALIVE",
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
+ "190": "SUCCESS",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
+ "195": "NOT_ALIVE",
112
  "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
+ "20": "SUCCESS",
118
+ "200": "SUCCESS",
119
  "201": "NON_PARTICIPATING",
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": "NOT_ALIVE",
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",
 
139
  "22": "NON_PARTICIPATING",
140
  "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
+ "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
+ "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
+ "229": "NON_PARTICIPATING",
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": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
159
+ "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
+ "241": "SUCCESS",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "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": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
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": "NON_PARTICIPATING",
190
+ "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
+ "38": "SUCCESS",
193
+ "39": "SUCCESS",
194
+ "4": "SUCCESS",
195
+ "40": "SUCCESS",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
+ "44": "SUCCESS",
200
+ "45": "SUCCESS",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
  "5": "NON_PARTICIPATING",
206
  "50": "NON_PARTICIPATING",
207
+ "51": "NON_PARTICIPATING",
208
+ "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "NOT_ALIVE",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
 
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
+ "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
+ "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "FAIL",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
 
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
+ "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
+ "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "SUCCESS",
250
+ "90": "SUCCESS",
251
+ "91": "NON_PARTICIPATING",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6479528,
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:fcacbcef04b30fc012762dbe977f938ada428fca859245f75fb6155ede72d732
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5034a62d0038faa913fdba84eea53b4a7b8764b35e15500eb6aabffb4f4ee95
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a020999a113a2c326ae2ca2de7a6b6d8f08fd21bbe6b719e45096f916bd95353
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6dbaa2aa32b89d3aee77fec3be1f206dfe287f302cfcc494b8026f26d14d4c3
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1c213ea1c297a38755e92b65f108932087198b4cc879f5750fefa2bb8a87756
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a4fcec7ad4b735c3f3705831d3d378e1ee7d080c04c04264ebbb3335b1229a3
3
  size 4400252568