kmfoda commited on
Commit
3eb7a54
·
verified ·
1 Parent(s): 2523527

Run 10. Outer Step 80. Inner Step 0. Peers 61.

Browse files
Files changed (4) hide show
  1. config.json +66 -66
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,60 +1,60 @@
1
  {
2
- "_name_or_path": "strnan01/llama-1b-hot-6",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
14
  "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
- "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
- "111": "NOT_ALIVE",
20
- "112": "NOT_ALIVE",
21
- "113": "NOT_ALIVE",
22
  "114": "SUCCESS",
23
- "115": "NON_PARTICIPATING",
24
  "116": "SUCCESS",
25
- "117": "NOT_ALIVE",
26
- "118": "NON_PARTICIPATING",
27
- "119": "NOT_ALIVE",
28
- "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "SUCCESS",
34
  "125": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NON_PARTICIPATING",
38
  "129": "SUCCESS",
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": "NOT_ALIVE",
46
- "136": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
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": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
- "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
@@ -67,17 +67,17 @@
67
  "155": "NON_PARTICIPATING",
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": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
- "166": "NON_PARTICIPATING",
80
- "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
@@ -86,9 +86,9 @@
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": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
@@ -100,7 +100,7 @@
100
  "185": "SUCCESS",
101
  "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
- "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
  "190": "NON_PARTICIPATING",
@@ -112,10 +112,10 @@
112
  "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
@@ -127,15 +127,15 @@
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": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
- "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
@@ -143,23 +143,23 @@
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "NOT_ALIVE",
147
  "227": "SUCCESS",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
- "23": "NOT_ALIVE",
151
- "230": "NOT_ALIVE",
152
  "231": "SUCCESS",
153
- "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
- "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
  "238": "SUCCESS",
160
- "239": "NOT_ALIVE",
161
  "24": "NON_PARTICIPATING",
162
- "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
@@ -170,28 +170,28 @@
170
  "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "NOT_ALIVE",
173
- "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
- "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
- "254": "NOT_ALIVE",
178
- "255": "SUCCESS",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
- "28": "NOT_ALIVE",
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": "NON_PARTICIPATING",
191
- "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
- "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
196
  "41": "NOT_ALIVE",
197
  "42": "SUCCESS",
@@ -203,27 +203,27 @@
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
- "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
- "56": "NON_PARTICIPATING",
213
- "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
- "59": "SUCCESS",
216
- "6": "NON_PARTICIPATING",
217
  "60": "SUCCESS",
218
- "61": "SUCCESS",
219
- "62": "SUCCESS",
220
  "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
- "65": "NOT_ALIVE",
223
  "66": "SUCCESS",
224
- "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
- "69": "SUCCESS",
227
  "7": "SUCCESS",
228
  "70": "NON_PARTICIPATING",
229
  "71": "SUCCESS",
@@ -242,7 +242,7 @@
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
- "86": "NOT_ALIVE",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
@@ -251,12 +251,12 @@
251
  "91": "SUCCESS",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
- "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
- "98": "NON_PARTICIPATING",
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": 6511585,
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": "NON_PARTICIPATING",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
+ "101": "SUCCESS",
9
+ "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "FAIL",
13
  "106": "NON_PARTICIPATING",
14
  "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
+ "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "SUCCESS",
20
+ "112": "NON_PARTICIPATING",
21
+ "113": "SUCCESS",
22
  "114": "SUCCESS",
23
+ "115": "NOT_ALIVE",
24
  "116": "SUCCESS",
25
+ "117": "NON_PARTICIPATING",
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": "SUCCESS",
34
  "125": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "NOT_ALIVE",
38
  "129": "SUCCESS",
39
+ "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
  "135": "NOT_ALIVE",
46
+ "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "NOT_ALIVE",
52
+ "141": "NON_PARTICIPATING",
53
  "142": "SUCCESS",
54
  "143": "NOT_ALIVE",
55
+ "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
 
67
  "155": "NON_PARTICIPATING",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NOT_ALIVE",
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",
80
+ "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
 
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
+ "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
+ "177": "NON_PARTICIPATING",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
 
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",
 
112
  "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "SUCCESS",
115
+ "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
+ "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
 
127
  "209": "NON_PARTICIPATING",
128
  "21": "NON_PARTICIPATING",
129
  "210": "SUCCESS",
130
+ "211": "NON_PARTICIPATING",
131
+ "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
+ "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
 
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "NON_PARTICIPATING",
147
  "227": "SUCCESS",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
+ "23": "NON_PARTICIPATING",
151
+ "230": "NON_PARTICIPATING",
152
  "231": "SUCCESS",
153
+ "232": "SUCCESS",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
  "238": "SUCCESS",
160
+ "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
+ "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
 
170
  "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "NOT_ALIVE",
173
+ "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
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": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "NON_PARTICIPATING",
189
+ "35": "NOT_ALIVE",
190
  "36": "NON_PARTICIPATING",
191
+ "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
+ "4": "NON_PARTICIPATING",
195
  "40": "NOT_ALIVE",
196
  "41": "NOT_ALIVE",
197
  "42": "SUCCESS",
 
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": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
+ "56": "NOT_ALIVE",
213
+ "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
+ "59": "NOT_ALIVE",
216
+ "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
+ "61": "NOT_ALIVE",
219
+ "62": "NON_PARTICIPATING",
220
  "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
+ "65": "NON_PARTICIPATING",
223
  "66": "SUCCESS",
224
+ "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
+ "69": "FAIL",
227
  "7": "SUCCESS",
228
  "70": "NON_PARTICIPATING",
229
  "71": "SUCCESS",
 
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "SUCCESS",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
 
251
  "91": "SUCCESS",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
+ "98": "NOT_ALIVE",
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": 6511953,
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 sha256:673a58746ac6c9a98faa74727af6c245c30b4b38a14b922ea268720e521936a6
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d93867b150c2fd4b2e31a22d99bd154e9b59d6c1ab66f3ca3ce1e62253e3cb7
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2239efdcae55bff895f4be859de9fad6febebaa20f29a57c6fb882d07040a376
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7675ecef3dca44bc542dc7232abf5281404ad92ffaa76334529647cab6c98d19
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fd6aa48a1f8b3c6cfa34dea91a280bb45315d4d5b82a94041008bdbc58f82f2
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052aa4f8e75bb7624537e43915b95dc35c0760a60d452fb53dd78f5fb196cb80
3
  size 4400252568