kmfoda commited on
Commit
693eb93
·
verified ·
1 Parent(s): d8075e9

Run 10. Outer Step 110. Inner Step 0. Peers 56.

Browse files
Files changed (4) hide show
  1. config.json +56 -56
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -2,55 +2,55 @@
2
  "_name_or_path": "aalv2/c67-h25",
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": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
- "106": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
- "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
- "117": "NOT_ALIVE",
26
- "118": "NOT_ALIVE",
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": "NON_PARTICIPATING",
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": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
- "136": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
53
- "142": "NOT_ALIVE",
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
@@ -63,11 +63,11 @@
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
- "154": "FAIL",
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "SUCCESS",
70
- "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
@@ -78,11 +78,11 @@
78
  "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
- "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
- "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
@@ -94,16 +94,16 @@
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": "NOT_ALIVE",
102
  "187": "NOT_ALIVE",
103
- "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
- "190": "SUCCESS",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
@@ -126,9 +126,9 @@
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "SUCCESS",
129
- "210": "NON_PARTICIPATING",
130
- "211": "SUCCESS",
131
- "212": "FAIL",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
@@ -147,25 +147,25 @@
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
- "23": "SUCCESS",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
- "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
- "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
- "240": "NON_PARTICIPATING",
163
  "241": "NOT_ALIVE",
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": "SUCCESS",
171
  "249": "NOT_ALIVE",
@@ -175,58 +175,58 @@
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
- "255": "NOT_ALIVE",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
185
- "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "SUCCESS",
190
- "36": "NOT_ALIVE",
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": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
- "45": "NON_PARTICIPATING",
201
- "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
- "50": "SUCCESS",
207
  "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
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": "NON_PARTICIPATING",
217
  "60": "SUCCESS",
218
- "61": "NOT_ALIVE",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
- "64": "SUCCESS",
222
  "65": "NON_PARTICIPATING",
223
- "66": "SUCCESS",
224
  "67": "NON_PARTICIPATING",
225
- "68": "FAIL",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NON_PARTICIPATING",
229
- "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
@@ -236,27 +236,27 @@
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
238
  "8": "SUCCESS",
239
- "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
- "84": "NOT_ALIVE",
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": "NON_PARTICIPATING",
252
- "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
- "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
- "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
- "99": "NOT_ALIVE"
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": 6525186,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
2
  "_name_or_path": "aalv2/c67-h25",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "FAIL",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
+ "101": "NON_PARTICIPATING",
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
+ "106": "SUCCESS",
14
  "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
+ "111": "FAIL",
20
  "112": "SUCCESS",
21
+ "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
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": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
+ "127": "SUCCESS",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
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": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
53
+ "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
 
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
+ "154": "NON_PARTICIPATING",
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "SUCCESS",
70
+ "158": "NOT_ALIVE",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
 
78
  "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
+ "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
+ "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
 
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": "SUCCESS",
101
+ "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
+ "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
 
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "SUCCESS",
129
+ "210": "NOT_ALIVE",
130
+ "211": "NOT_ALIVE",
131
+ "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
 
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
+ "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
+ "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
+ "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
+ "240": "NOT_ALIVE",
163
  "241": "NOT_ALIVE",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NOT_ALIVE",
168
+ "246": "SUCCESS",
169
  "247": "NOT_ALIVE",
170
  "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
 
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "SUCCESS",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
185
+ "31": "NOT_ALIVE",
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": "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": "NOT_ALIVE",
201
+ "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
+ "50": "NON_PARTICIPATING",
207
  "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
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": "NON_PARTICIPATING",
217
  "60": "SUCCESS",
218
+ "61": "SUCCESS",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
+ "64": "FAIL",
222
  "65": "NON_PARTICIPATING",
223
+ "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NON_PARTICIPATING",
229
+ "71": "SUCCESS",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
 
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
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": "FAIL",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
+ "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
+ "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
+ "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
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": 6525594,
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 sha256:28ae1d8f938f9377ed1a703dd2b6ceb523dc945268e29ba362252dbc9e589f1f
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1913b4d306deab98cbe226df925d76e4ca9c3e3ddb23de5633f6801288c3548
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec90759810accce80b6ec508debd15c5eaeba99fd3e8b8c51ede0109c20d7aa4
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88aec7b07bd9422f5bc281e206ef7a4e488890c76c065505aaac99bb2eb7c934
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:583f41b2b6512082b357ca37d96204a58fb8108338c36a4141273bfa229a5af8
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c056031d66fc45078bf5379f422e37ce49e22cf8f2ae646a30cd7e0f240d794
3
  size 4400252568