kmfoda commited on
Commit
6fc6630
·
verified ·
1 Parent(s): 7830bc7

Run 7. Outer Step 51. Inner Step 0. Peers 32.

Browse files
Files changed (4) hide show
  1. config.json +31 -31
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "asim22/sub38-178",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
@@ -17,7 +17,7 @@
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
@@ -35,7 +35,7 @@
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
- "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
  "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
@@ -45,7 +45,7 @@
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "NON_PARTICIPATING",
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
@@ -54,7 +54,7 @@
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
- "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
@@ -73,10 +73,10 @@
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
- "163": "FAIL",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
- "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
@@ -84,12 +84,12 @@
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
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": "FAIL",
93
  "179": "SUCCESS",
94
  "18": "SUCCESS",
95
  "180": "NOT_ALIVE",
@@ -98,7 +98,7 @@
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
- "186": "NOT_ALIVE",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
@@ -106,29 +106,29 @@
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NOT_ALIVE",
109
- "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
- "198": "NOT_ALIVE",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
- "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
- "211": "SUCCESS",
131
- "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
@@ -137,9 +137,9 @@
137
  "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
- "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
- "222": "SUCCESS",
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
@@ -148,16 +148,16 @@
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
- "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
- "234": "NOT_ALIVE",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
- "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "SUCCESS",
@@ -165,15 +165,15 @@
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
- "246": "NON_PARTICIPATING",
169
- "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
- "253": "FAIL",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NOT_ALIVE",
@@ -187,7 +187,7 @@
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
  "35": "SUCCESS",
190
- "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
@@ -208,12 +208,12 @@
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
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": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
@@ -223,7 +223,7 @@
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
@@ -256,7 +256,7 @@
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
- "99": "FAIL"
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": 6253513,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "aalv2/c71-h7",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
 
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
+ "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
 
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
+ "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
 
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "SUCCESS",
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
 
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
+ "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
 
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
+ "166": "FAIL",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
 
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
+ "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
+ "178": "NOT_ALIVE",
93
  "179": "SUCCESS",
94
  "18": "SUCCESS",
95
  "180": "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",
 
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NOT_ALIVE",
109
+ "193": "SUCCESS",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
+ "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "NOT_ALIVE",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
+ "211": "NON_PARTICIPATING",
131
+ "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
 
137
  "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
+ "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
+ "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
 
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
+ "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
+ "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "NOT_ALIVE",
159
  "238": "NOT_ALIVE",
160
+ "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "SUCCESS",
 
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
+ "246": "SUCCESS",
169
+ "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
+ "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NOT_ALIVE",
 
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
  "35": "SUCCESS",
190
+ "36": "SUCCESS",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
 
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
+ "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
+ "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
 
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
+ "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
 
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6254239,
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 sha256:5a773f953d09cc84783c283903729728de49521bb1de3593ed450b036ad0299c
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d583dc061971bebaf52010d5c25d7d3cb9c7055eacb3f7123af1e86d507f9e08
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e91cfca6bc0f24a8f738a56cf89a20bdaeaef65fc418e58a3b2fdf5e71ca0ce4
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fc1e7af7dfa33166fbf2fc725e0ae1403f175e33fc88e85691a41e43021678f
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca786ec1f30ba5883f1a74f6ac39a26ebf079d9135085dbad1ab95dc0eb27dc2
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647a24a6f68882b485c0fd472bd94c3f4186c07517106233b3fa29bfc814dda8
3
  size 4400252568