kmfoda commited on
Commit
46e378d
·
verified ·
1 Parent(s): e5695a1

Run 10. Outer Step 72. Inner Step 0. Peers 60.

Browse files
Files changed (4) hide show
  1. config.json +61 -61
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,23 +1,23 @@
1
  {
2
- "_name_or_path": "aalv2/c71-h21",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
  "10": "SUCCESS",
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": "NOT_ALIVE",
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",
@@ -25,18 +25,18 @@
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
- "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
- "123": "SUCCESS",
33
  "124": "SUCCESS",
34
- "125": "SUCCESS",
35
- "126": "NON_PARTICIPATING",
36
- "127": "NON_PARTICIPATING",
37
- "128": "SUCCESS",
38
- "129": "NOT_ALIVE",
39
- "13": "NON_PARTICIPATING",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
@@ -45,25 +45,25 @@
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
- "138": "NON_PARTICIPATING",
49
- "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
- "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
  "143": "NOT_ALIVE",
55
- "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
- "147": "NOT_ALIVE",
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": "FAIL",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
@@ -96,23 +96,23 @@
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
- "184": "SUCCESS",
100
  "185": "SUCCESS",
101
- "186": "SUCCESS",
102
- "187": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
  "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "SUCCESS",
115
- "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
  "200": "SUCCESS",
@@ -120,22 +120,22 @@
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
- "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
  "21": "NON_PARTICIPATING",
129
  "210": "SUCCESS",
130
- "211": "NOT_ALIVE",
131
- "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
- "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
@@ -150,14 +150,14 @@
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
- "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
- "237": "SUCCESS",
159
  "238": "NON_PARTICIPATING",
160
- "239": "NOT_ALIVE",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
@@ -165,7 +165,7 @@
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",
@@ -174,9 +174,9 @@
174
  "251": "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": "SUCCESS",
182
  "29": "NON_PARTICIPATING",
@@ -192,41 +192,41 @@
192
  "38": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
  "4": "SUCCESS",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
- "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
- "50": "NON_PARTICIPATING",
207
- "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
- "56": "NOT_ALIVE",
213
- "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
- "59": "SUCCESS",
216
  "6": "NON_PARTICIPATING",
217
- "60": "FAIL",
218
- "61": "NOT_ALIVE",
219
- "62": "NON_PARTICIPATING",
220
- "63": "NON_PARTICIPATING",
221
  "64": "SUCCESS",
222
  "65": "NON_PARTICIPATING",
223
  "66": "SUCCESS",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
- "7": "SUCCESS",
228
- "70": "NON_PARTICIPATING",
229
- "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
@@ -235,7 +235,7 @@
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
- "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "SUCCESS",
@@ -246,7 +246,7 @@
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",
@@ -255,8 +255,8 @@
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": 6507647,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "strnan01/llama-1b-hot-6",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
+ "101": "SUCCESS",
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
+ "106": "NOT_ALIVE",
14
+ "107": "NON_PARTICIPATING",
15
+ "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
+ "11": "NON_PARTICIPATING",
18
+ "110": "SUCCESS",
19
+ "111": "SUCCESS",
20
+ "112": "NOT_ALIVE",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "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": "NOT_ALIVE",
33
  "124": "SUCCESS",
34
+ "125": "NOT_ALIVE",
35
+ "126": "SUCCESS",
36
+ "127": "NOT_ALIVE",
37
+ "128": "NOT_ALIVE",
38
+ "129": "NON_PARTICIPATING",
39
+ "13": "FAIL",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "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",
53
  "142": "SUCCESS",
54
  "143": "NOT_ALIVE",
55
+ "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
+ "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "NON_PARTICIPATING",
61
+ "15": "NON_PARTICIPATING",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
+ "154": "SUCCESS",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
 
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
+ "184": "NON_PARTICIPATING",
100
  "185": "SUCCESS",
101
+ "186": "NOT_ALIVE",
102
+ "187": "SUCCESS",
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": "NOT_ALIVE",
112
  "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "SUCCESS",
115
+ "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
  "200": "SUCCESS",
 
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
+ "205": "SUCCESS",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
  "21": "NON_PARTICIPATING",
129
  "210": "SUCCESS",
130
+ "211": "NON_PARTICIPATING",
131
+ "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
+ "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
 
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
+ "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
+ "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
 
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
+ "246": "NOT_ALIVE",
169
  "247": "NOT_ALIVE",
170
  "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
 
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
+ "254": "NOT_ALIVE",
178
  "255": "SUCCESS",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "NON_PARTICIPATING",
 
192
  "38": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
  "4": "SUCCESS",
195
+ "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
+ "50": "SUCCESS",
207
+ "51": "SUCCESS",
208
  "52": "SUCCESS",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
+ "56": "NON_PARTICIPATING",
213
+ "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
+ "59": "NOT_ALIVE",
216
  "6": "NON_PARTICIPATING",
217
+ "60": "NOT_ALIVE",
218
+ "61": "NON_PARTICIPATING",
219
+ "62": "NOT_ALIVE",
220
+ "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "NON_PARTICIPATING",
223
  "66": "SUCCESS",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
+ "7": "NON_PARTICIPATING",
228
+ "70": "NOT_ALIVE",
229
+ "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
 
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
+ "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "SUCCESS",
 
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
+ "9": "NON_PARTICIPATING",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
  "92": "SUCCESS",
 
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
+ "98": "SUCCESS",
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": 6508025,
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:bd79a3243f8c5007407d4af91a288fcd84692275fad778b01b4294385b7b78cf
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a73d6ab97a7dabb2f48d6820146417b405f9a4b7ac99748c4970bec24f6a84
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbf18405ac15a16947244555d9bcc49ce96e029348ff974cf9c95e49fce0a4b2
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5320e518612643fbbe0401d18c206e1761e806e7f035830ff1e108a0e103cd21
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51a05756b46310af02a3c1019f07677edeebc31ea13493ad8e1ed52f1882be9f
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4cca55bbf779688d410791c1fe5f3565b304b9c4f874ca9cb0559a8f5366f35
3
  size 4400252568