kmfoda commited on
Commit
0025b21
·
verified ·
1 Parent(s): b7c0fa1

Run 10. Outer Step 100. Inner Step 0. Peers 62.

Browse files
Files changed (4) hide show
  1. config.json +49 -49
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "strn4n/llama-1b-hot-12",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NON_PARTICIPATING",
@@ -9,32 +9,32 @@
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
- "107": "SUCCESS",
15
- "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
  "112": "SUCCESS",
21
- "113": "SUCCESS",
22
- "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
- "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
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": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
@@ -42,11 +42,11 @@
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": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
@@ -56,7 +56,7 @@
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",
@@ -67,13 +67,13 @@
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NON_PARTICIPATING",
71
- "159": "NOT_ALIVE",
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": "SUCCESS",
@@ -82,11 +82,11 @@
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
- "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
- "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
@@ -94,12 +94,12 @@
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
- "182": "NOT_ALIVE",
98
  "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
- "186": "NOT_ALIVE",
102
- "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
@@ -121,11 +121,11 @@
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
- "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
- "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
@@ -143,7 +143,7 @@
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "SUCCESS",
147
  "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
@@ -155,7 +155,7 @@
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NOT_ALIVE",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
@@ -167,37 +167,37 @@
167
  "245": "NON_PARTICIPATING",
168
  "246": "SUCCESS",
169
  "247": "NOT_ALIVE",
170
- "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
- "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
- "254": "NOT_ALIVE",
178
  "255": "SUCCESS",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
- "29": "NOT_ALIVE",
183
- "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
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",
194
  "4": "NOT_ALIVE",
195
- "40": "NOT_ALIVE",
196
  "41": "NOT_ALIVE",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
- "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
@@ -209,20 +209,20 @@
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
- "56": "NON_PARTICIPATING",
213
- "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
- "6": "NON_PARTICIPATING",
217
  "60": "SUCCESS",
218
- "61": "NON_PARTICIPATING",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "SUCCESS",
@@ -236,27 +236,27 @@
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
  "8": "SUCCESS",
239
- "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NOT_ALIVE",
245
- "86": "NOT_ALIVE",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
  "9": "NOT_ALIVE",
250
- "90": "NON_PARTICIPATING",
251
- "91": "SUCCESS",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
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": 6520929,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "aalv2/c67-h25",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NON_PARTICIPATING",
 
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "SUCCESS",
13
  "106": "SUCCESS",
14
+ "107": "NOT_ALIVE",
15
+ "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
  "112": "SUCCESS",
21
+ "113": "NOT_ALIVE",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
+ "119": "SUCCESS",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
+ "124": "NON_PARTICIPATING",
34
+ "125": "SUCCESS",
35
  "126": "SUCCESS",
36
+ "127": "NOT_ALIVE",
37
+ "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
 
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
+ "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
 
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "NOT_ALIVE",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
 
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NOT_ALIVE",
71
+ "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
+ "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
 
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
+ "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
+ "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
 
94
  "18": "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": "NON_PARTICIPATING",
102
+ "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
 
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
+ "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
 
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "NON_PARTICIPATING",
147
  "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
 
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
 
167
  "245": "NON_PARTICIPATING",
168
  "246": "SUCCESS",
169
  "247": "NOT_ALIVE",
170
+ "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
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": "SUCCESS",
182
+ "29": "NON_PARTICIPATING",
183
+ "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
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": "NOT_ALIVE",
195
+ "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
+ "45": "NON_PARTICIPATING",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
 
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
+ "56": "NOT_ALIVE",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
+ "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
+ "61": "SUCCESS",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "SUCCESS",
 
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
  "8": "SUCCESS",
239
+ "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NOT_ALIVE",
245
+ "86": "SUCCESS",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
  "9": "NOT_ALIVE",
250
+ "90": "NOT_ALIVE",
251
+ "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
+ "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6521322,
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:edd0512f815bf65f7d22f15c45f6d8047b57c52edd6b0b0ca052342333665ad0
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414094cef435f08fb8b111ee7da6bfa276dbaa8a32cd860ecef830a1d4e746a9
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e07089a9f3c7c715950b218c84b044ae9df6688008244d1641f91b90deea82d6
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df001b15449f636749b3902d0b1679f059aace4883929654079fecea1a51551
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1296ada37cc6649722107187e474bf3b4bfdbb951465902d1a97743525f68d19
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:964118bac9204fac11cf571ab184d9e9345c124aa6742c7ed08ab5c973c5e4df
3
  size 4400252568