kmfoda commited on
Commit
1321e40
·
verified ·
1 Parent(s): ebd9e16

Run 10. Outer Step 29. Inner Step 0. Peers 1.

Browse files
Files changed (4) hide show
  1. config.json +99 -99
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,42 +1,42 @@
1
  {
2
- "_name_or_path": "strnan01/llama-1b-hot-6",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "FAIL",
6
- "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
- "102": "SUCCESS",
10
- "103": "SUCCESS",
11
  "104": "NOT_ALIVE",
12
  "105": "NOT_ALIVE",
13
- "106": "NOT_ALIVE",
14
- "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
- "109": "NOT_ALIVE",
17
- "11": "SUCCESS",
18
- "110": "NOT_ALIVE",
19
- "111": "SUCCESS",
20
- "112": "NON_PARTICIPATING",
21
- "113": "SUCCESS",
22
- "114": "SUCCESS",
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": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
- "122": "NOT_ALIVE",
32
- "123": "NOT_ALIVE",
33
  "124": "NOT_ALIVE",
34
- "125": "NOT_ALIVE",
35
- "126": "NON_PARTICIPATING",
36
- "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
- "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
@@ -45,7 +45,7 @@
45
  "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
- "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
@@ -54,17 +54,17 @@
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": "NOT_ALIVE",
62
- "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "SUCCESS",
66
- "154": "SUCCESS",
67
- "155": "NOT_ALIVE",
68
  "156": "FAIL",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
@@ -73,159 +73,159 @@
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
- "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
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": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
- "182": "NOT_ALIVE",
98
- "183": "NON_PARTICIPATING",
99
- "184": "SUCCESS",
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": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
112
  "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
- "198": "SUCCESS",
115
- "199": "NON_PARTICIPATING",
116
- "2": "NOT_ALIVE",
117
- "20": "SUCCESS",
118
- "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "SUCCESS",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "FAIL",
129
  "210": "NON_PARTICIPATING",
130
- "211": "SUCCESS",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
- "214": "SUCCESS",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
- "219": "SUCCESS",
139
- "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
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": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
- "229": "FAIL",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
- "231": "NOT_ALIVE",
153
- "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
- "234": "FAIL",
156
  "235": "FAIL",
157
- "236": "NOT_ALIVE",
158
- "237": "FAIL",
159
- "238": "NOT_ALIVE",
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",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
- "248": "NOT_ALIVE",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
- "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
- "254": "SUCCESS",
178
  "255": "NON_PARTICIPATING",
179
- "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
- "28": "NON_PARTICIPATING",
182
- "29": "SUCCESS",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
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": "NOT_ALIVE",
192
- "38": "FAIL",
193
  "39": "FAIL",
194
  "4": "FAIL",
195
- "40": "SUCCESS",
196
- "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
- "44": "SUCCESS",
200
- "45": "NOT_ALIVE",
201
  "46": "FAIL",
202
  "47": "FAIL",
203
  "48": "NON_PARTICIPATING",
204
- "49": "NON_PARTICIPATING",
205
- "5": "SUCCESS",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "FAIL",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
- "56": "NON_PARTICIPATING",
213
- "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
  "61": "NOT_ALIVE",
219
- "62": "NON_PARTICIPATING",
220
  "63": "NOT_ALIVE",
221
- "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
- "69": "SUCCESS",
227
  "7": "FAIL",
228
- "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
@@ -235,28 +235,28 @@
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
- "8": "SUCCESS",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
- "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
- "86": "NOT_ALIVE",
246
- "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
- "89": "NON_PARTICIPATING",
249
- "9": "FAIL",
250
- "90": "NON_PARTICIPATING",
251
  "91": "FAIL",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
- "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "SUCCESS",
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": 6482230,
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": "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": "NOT_ALIVE",
13
+ "106": "NON_PARTICIPATING",
14
+ "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
+ "109": "FAIL",
17
+ "11": "FAIL",
18
+ "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
+ "112": "FAIL",
21
+ "113": "FAIL",
22
+ "114": "FAIL",
23
+ "115": "NOT_ALIVE",
24
+ "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "FAIL",
27
+ "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
+ "122": "NON_PARTICIPATING",
32
+ "123": "FAIL",
33
  "124": "NOT_ALIVE",
34
+ "125": "FAIL",
35
+ "126": "FAIL",
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",
 
45
  "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
+ "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
 
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
+ "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "NON_PARTICIPATING",
61
+ "15": "NON_PARTICIPATING",
62
+ "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
+ "154": "NOT_ALIVE",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "FAIL",
69
  "157": "NON_PARTICIPATING",
70
  "158": "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": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
+ "170": "FAIL",
85
+ "171": "FAIL",
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": "FAIL",
99
+ "184": "FAIL",
100
  "185": "FAIL",
101
+ "186": "NOT_ALIVE",
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": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
112
  "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
+ "198": "NON_PARTICIPATING",
115
+ "199": "NOT_ALIVE",
116
+ "2": "NON_PARTICIPATING",
117
+ "20": "FAIL",
118
+ "200": "FAIL",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
+ "205": "FAIL",
124
+ "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "FAIL",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "FAIL",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "FAIL",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "FAIL",
139
+ "22": "NON_PARTICIPATING",
140
  "220": "NOT_ALIVE",
141
+ "221": "NON_PARTICIPATING",
142
+ "222": "FAIL",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
+ "231": "NON_PARTICIPATING",
153
+ "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "NOT_ALIVE",
156
  "235": "FAIL",
157
+ "236": "NON_PARTICIPATING",
158
+ "237": "NON_PARTICIPATING",
159
+ "238": "FAIL",
160
  "239": "NON_PARTICIPATING",
161
+ "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
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": "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": "FAIL",
182
+ "29": "FAIL",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
+ "31": "FAIL",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "FAIL",
189
+ "35": "FAIL",
190
+ "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
  "39": "FAIL",
194
  "4": "FAIL",
195
+ "40": "FAIL",
196
+ "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
+ "44": "FAIL",
200
+ "45": "FAIL",
201
  "46": "FAIL",
202
  "47": "FAIL",
203
  "48": "NON_PARTICIPATING",
204
+ "49": "NOT_ALIVE",
205
+ "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "FAIL",
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": "NOT_ALIVE",
218
  "61": "NOT_ALIVE",
219
+ "62": "FAIL",
220
  "63": "NOT_ALIVE",
221
+ "64": "FAIL",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
+ "69": "FAIL",
227
  "7": "FAIL",
228
+ "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
 
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
+ "8": "FAIL",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
+ "84": "FAIL",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "NON_PARTICIPATING",
246
+ "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
+ "89": "NOT_ALIVE",
249
+ "9": "NON_PARTICIPATING",
250
+ "90": "FAIL",
251
  "91": "FAIL",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
+ "96": "FAIL",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
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": 6482613,
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:b84458a817f8a97587d0ce1121c8a602faed9aa1b6d0a77c781d1acedeb47252
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e4f3363e37e97f4cefb5ea8e6e334c7fb045cef4f3df39d6f9aff2a3aaeae7
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cc5e6ebfa3765109127e5ef6e29ff7bebb1c6cbc1fa4a4993392f5f923ef700
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6529c0683531c46da25b9c2d3952f26906738ac64eec66de405d6117b7329ecf
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05f93b18456639d1c16208f1af4dcb063c34294be5ea99e369391f3adc5abd2e
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640c575d8b960fdb0ea60799a62f07a0627efac56e6254edb6a4ae2caae77dcf
3
  size 4400252568