kmfoda commited on
Commit
66835f5
·
verified ·
1 Parent(s): 437fc15

Run 7. Outer Step 82. Inner Step 0. Peers 33.

Browse files
Files changed (4) hide show
  1. config.json +39 -39
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
- "_name_or_path": "strnan01/llama-1b-hot-6",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
- "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
- "105": "NOT_ALIVE",
13
  "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
@@ -20,16 +20,16 @@
20
  "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
- "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
- "118": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
@@ -41,16 +41,16 @@
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
- "134": "SUCCESS",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
- "137": "NON_PARTICIPATING",
48
- "138": "NON_PARTICIPATING",
49
  "139": "SUCCESS",
50
- "14": "SUCCESS",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
- "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
@@ -58,7 +58,7 @@
58
  "147": "NOT_ALIVE",
59
  "148": "SUCCESS",
60
  "149": "NON_PARTICIPATING",
61
- "15": "FAIL",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
@@ -66,7 +66,7 @@
66
  "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
- "157": "NOT_ALIVE",
70
  "158": "SUCCESS",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
@@ -81,15 +81,15 @@
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
- "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
- "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
- "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
@@ -97,14 +97,14 @@
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
- "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
- "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
- "191": "FAIL",
108
  "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
@@ -118,7 +118,7 @@
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
@@ -130,16 +130,16 @@
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
- "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
- "216": "SUCCESS",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
142
- "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
@@ -152,7 +152,7 @@
152
  "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
- "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
@@ -164,8 +164,8 @@
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
- "245": "NOT_ALIVE",
168
- "246": "SUCCESS",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
@@ -176,8 +176,8 @@
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
- "26": "NOT_ALIVE",
180
- "27": "NON_PARTICIPATING",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
@@ -192,7 +192,7 @@
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
@@ -205,7 +205,7 @@
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
- "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
@@ -213,7 +213,7 @@
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
- "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
@@ -233,13 +233,13 @@
233
  "75": "SUCCESS",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
- "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
- "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
@@ -251,12 +251,12 @@
251
  "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
- "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
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": 6277584,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "STR-NaN/llama-1b-hot-10",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
+ "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
+ "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
 
20
  "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
+ "115": "SUCCESS",
24
  "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "SUCCESS",
27
+ "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
+ "122": "NOT_ALIVE",
32
+ "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
 
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
+ "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
+ "137": "NOT_ALIVE",
48
+ "138": "SUCCESS",
49
  "139": "SUCCESS",
50
+ "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
+ "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
 
58
  "147": "NOT_ALIVE",
59
  "148": "SUCCESS",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
 
66
  "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
+ "157": "NON_PARTICIPATING",
70
  "158": "SUCCESS",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
 
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
+ "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
+ "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
+ "178": "SUCCESS",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
 
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
+ "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
+ "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "SUCCESS",
108
  "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
 
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": "NON_PARTICIPATING",
 
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
+ "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
+ "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
142
+ "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
 
152
  "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
+ "234": "NOT_ALIVE",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
 
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
+ "245": "NON_PARTICIPATING",
168
+ "246": "NOT_ALIVE",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
 
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
+ "26": "NON_PARTICIPATING",
180
+ "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
 
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
+ "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
 
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
+ "52": "SUCCESS",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
 
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
+ "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
 
233
  "75": "SUCCESS",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
+ "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
+ "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
 
251
  "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
+ "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6278293,
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 sha256:0f218c136921c127ce3278e971e5a55af1aaeab2711be21655322c145bd06016
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33ca9169ee68eed1c217f836ccd44f49aba6aaf7cb7fda33aa7333ca85ab52a
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b552c9748e57a10c4351a0b88042f979b098dc8ce0640f9734d9ae520999d676
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e819ce45cf3e0383a49235344e07fe05f156c3b8f77582d8797645a8101eab0c
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:711ec04a43ef8bd0cc97d9dbbd4865bdff481fece27333332d37d10399d8df88
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c975ae75dcb5f92d7cf5644a3ac99bd9309480b12a4cff5cc64649b14d71587
3
  size 4400252568