kmfoda commited on
Commit
fa9ea9e
·
verified ·
1 Parent(s): 0d64e4f

Run 4. Outer Step 16. Inner Step 0. Peers 79.

Browse files
Files changed (4) hide show
  1. config.json +41 -41
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "_name_or_path": "anthum/AR9",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
6
- "1": "SUCCESS",
7
  "10": "SUCCESS",
8
  "100": "NON_PARTICIPATING",
9
  "101": "SUCCESS",
@@ -12,38 +12,38 @@
12
  "104": "NON_PARTICIPATING",
13
  "105": "NON_PARTICIPATING",
14
  "106": "NON_PARTICIPATING",
15
- "107": "NON_PARTICIPATING",
16
  "108": "NON_PARTICIPATING",
17
  "109": "SUCCESS",
18
  "11": "NON_PARTICIPATING",
19
  "110": "SUCCESS",
20
- "111": "NON_PARTICIPATING",
21
  "112": "NON_PARTICIPATING",
22
  "113": "NON_PARTICIPATING",
23
- "114": "SUCCESS",
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
26
  "117": "NON_PARTICIPATING",
27
  "118": "NON_PARTICIPATING",
28
  "119": "NON_PARTICIPATING",
29
  "12": "SUCCESS",
30
- "120": "FAIL",
31
  "121": "NON_PARTICIPATING",
32
  "122": "NON_PARTICIPATING",
33
- "123": "FAIL",
34
  "124": "NON_PARTICIPATING",
35
  "125": "NON_PARTICIPATING",
36
  "126": "NON_PARTICIPATING",
37
  "127": "SUCCESS",
38
  "128": "NON_PARTICIPATING",
39
- "129": "SUCCESS",
40
  "13": "NON_PARTICIPATING",
41
  "130": "NON_PARTICIPATING",
42
  "131": "NON_PARTICIPATING",
43
  "132": "SUCCESS",
44
  "133": "NON_PARTICIPATING",
45
  "134": "NON_PARTICIPATING",
46
- "135": "SUCCESS",
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
  "138": "NON_PARTICIPATING",
@@ -55,21 +55,21 @@
55
  "143": "NON_PARTICIPATING",
56
  "144": "NON_PARTICIPATING",
57
  "145": "NON_PARTICIPATING",
58
- "146": "SUCCESS",
59
- "147": "SUCCESS",
60
  "148": "SUCCESS",
61
  "149": "SUCCESS",
62
  "15": "SUCCESS",
63
- "150": "SUCCESS",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
  "153": "NON_PARTICIPATING",
67
  "154": "SUCCESS",
68
- "155": "SUCCESS",
69
- "156": "SUCCESS",
70
  "157": "NON_PARTICIPATING",
71
  "158": "NON_PARTICIPATING",
72
- "159": "FAIL",
73
  "16": "SUCCESS",
74
  "160": "NON_PARTICIPATING",
75
  "161": "NON_PARTICIPATING",
@@ -78,21 +78,21 @@
78
  "164": "NON_PARTICIPATING",
79
  "165": "NON_PARTICIPATING",
80
  "166": "NON_PARTICIPATING",
81
- "167": "FAIL",
82
  "168": "NON_PARTICIPATING",
83
  "169": "NON_PARTICIPATING",
84
  "17": "SUCCESS",
85
  "170": "SUCCESS",
86
  "171": "NON_PARTICIPATING",
87
- "172": "SUCCESS",
88
- "173": "SUCCESS",
89
  "174": "NON_PARTICIPATING",
90
  "175": "NON_PARTICIPATING",
91
  "176": "NON_PARTICIPATING",
92
  "177": "NON_PARTICIPATING",
93
  "178": "NON_PARTICIPATING",
94
  "179": "NON_PARTICIPATING",
95
- "18": "NON_PARTICIPATING",
96
  "180": "NON_PARTICIPATING",
97
  "181": "NON_PARTICIPATING",
98
  "182": "NON_PARTICIPATING",
@@ -100,16 +100,16 @@
100
  "184": "NON_PARTICIPATING",
101
  "185": "NON_PARTICIPATING",
102
  "186": "SUCCESS",
103
- "187": "SUCCESS",
104
  "188": "NON_PARTICIPATING",
105
  "189": "NON_PARTICIPATING",
106
  "19": "NON_PARTICIPATING",
107
  "190": "NON_PARTICIPATING",
108
- "191": "NON_PARTICIPATING",
109
  "192": "SUCCESS",
110
  "193": "NON_PARTICIPATING",
111
- "194": "NON_PARTICIPATING",
112
- "195": "NON_PARTICIPATING",
113
  "196": "NON_PARTICIPATING",
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
@@ -119,14 +119,14 @@
119
  "200": "SUCCESS",
120
  "201": "SUCCESS",
121
  "202": "NON_PARTICIPATING",
122
- "203": "NON_PARTICIPATING",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
125
  "206": "NON_PARTICIPATING",
126
  "207": "NON_PARTICIPATING",
127
  "208": "NON_PARTICIPATING",
128
  "209": "NON_PARTICIPATING",
129
- "21": "NON_PARTICIPATING",
130
  "210": "NON_PARTICIPATING",
131
  "211": "NON_PARTICIPATING",
132
  "212": "NON_PARTICIPATING",
@@ -144,27 +144,27 @@
144
  "223": "SUCCESS",
145
  "224": "NON_PARTICIPATING",
146
  "225": "SUCCESS",
147
- "226": "SUCCESS",
148
  "227": "NON_PARTICIPATING",
149
  "228": "NON_PARTICIPATING",
150
  "229": "NON_PARTICIPATING",
151
  "23": "SUCCESS",
152
  "230": "NON_PARTICIPATING",
153
- "231": "SUCCESS",
154
  "232": "NON_PARTICIPATING",
155
- "233": "SUCCESS",
156
  "234": "NON_PARTICIPATING",
157
  "235": "NON_PARTICIPATING",
158
  "236": "NON_PARTICIPATING",
159
  "237": "NON_PARTICIPATING",
160
  "238": "NON_PARTICIPATING",
161
  "239": "NON_PARTICIPATING",
162
- "24": "NON_PARTICIPATING",
163
  "240": "NON_PARTICIPATING",
164
- "241": "SUCCESS",
165
  "242": "NON_PARTICIPATING",
166
  "243": "NON_PARTICIPATING",
167
- "244": "NON_PARTICIPATING",
168
  "245": "NON_PARTICIPATING",
169
  "246": "NON_PARTICIPATING",
170
  "247": "SUCCESS",
@@ -180,13 +180,13 @@
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
  "28": "NON_PARTICIPATING",
183
- "29": "NON_PARTICIPATING",
184
  "3": "NON_PARTICIPATING",
185
  "30": "NON_PARTICIPATING",
186
  "31": "NON_PARTICIPATING",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
189
- "34": "NON_PARTICIPATING",
190
  "35": "NON_PARTICIPATING",
191
  "36": "NON_PARTICIPATING",
192
  "37": "SUCCESS",
@@ -212,20 +212,20 @@
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
214
  "57": "NON_PARTICIPATING",
215
- "58": "SUCCESS",
216
  "59": "NON_PARTICIPATING",
217
- "6": "SUCCESS",
218
  "60": "NON_PARTICIPATING",
219
  "61": "SUCCESS",
220
  "62": "SUCCESS",
221
- "63": "FAIL",
222
- "64": "FAIL",
223
  "65": "NON_PARTICIPATING",
224
  "66": "NON_PARTICIPATING",
225
  "67": "SUCCESS",
226
  "68": "NON_PARTICIPATING",
227
  "69": "NON_PARTICIPATING",
228
- "7": "NON_PARTICIPATING",
229
  "70": "NON_PARTICIPATING",
230
  "71": "NON_PARTICIPATING",
231
  "72": "NON_PARTICIPATING",
@@ -242,7 +242,7 @@
242
  "82": "SUCCESS",
243
  "83": "NON_PARTICIPATING",
244
  "84": "SUCCESS",
245
- "85": "SUCCESS",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
  "88": "NON_PARTICIPATING",
@@ -257,7 +257,7 @@
257
  "96": "SUCCESS",
258
  "97": "NON_PARTICIPATING",
259
  "98": "SUCCESS",
260
- "99": "SUCCESS"
261
  },
262
  "architectures": [
263
  "GPTOptim"
@@ -275,7 +275,7 @@
275
  "initializer_range": 0.02,
276
  "inner_step": 0,
277
  "inner_steps": 0,
278
- "last_allreduce_block": 5513324,
279
  "layer_norm_epsilon": 1e-05,
280
  "model_type": "gpt_optimized",
281
  "n_embd": 1280,
 
1
  {
2
+ "_name_or_path": "penguin102/c66-h20",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
6
+ "1": "NON_PARTICIPATING",
7
  "10": "SUCCESS",
8
  "100": "NON_PARTICIPATING",
9
  "101": "SUCCESS",
 
12
  "104": "NON_PARTICIPATING",
13
  "105": "NON_PARTICIPATING",
14
  "106": "NON_PARTICIPATING",
15
+ "107": "SUCCESS",
16
  "108": "NON_PARTICIPATING",
17
  "109": "SUCCESS",
18
  "11": "NON_PARTICIPATING",
19
  "110": "SUCCESS",
20
+ "111": "SUCCESS",
21
  "112": "NON_PARTICIPATING",
22
  "113": "NON_PARTICIPATING",
23
+ "114": "NON_PARTICIPATING",
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
26
  "117": "NON_PARTICIPATING",
27
  "118": "NON_PARTICIPATING",
28
  "119": "NON_PARTICIPATING",
29
  "12": "SUCCESS",
30
+ "120": "NON_PARTICIPATING",
31
  "121": "NON_PARTICIPATING",
32
  "122": "NON_PARTICIPATING",
33
+ "123": "SUCCESS",
34
  "124": "NON_PARTICIPATING",
35
  "125": "NON_PARTICIPATING",
36
  "126": "NON_PARTICIPATING",
37
  "127": "SUCCESS",
38
  "128": "NON_PARTICIPATING",
39
+ "129": "FAIL",
40
  "13": "NON_PARTICIPATING",
41
  "130": "NON_PARTICIPATING",
42
  "131": "NON_PARTICIPATING",
43
  "132": "SUCCESS",
44
  "133": "NON_PARTICIPATING",
45
  "134": "NON_PARTICIPATING",
46
+ "135": "NON_PARTICIPATING",
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
  "138": "NON_PARTICIPATING",
 
55
  "143": "NON_PARTICIPATING",
56
  "144": "NON_PARTICIPATING",
57
  "145": "NON_PARTICIPATING",
58
+ "146": "NON_PARTICIPATING",
59
+ "147": "NON_PARTICIPATING",
60
  "148": "SUCCESS",
61
  "149": "SUCCESS",
62
  "15": "SUCCESS",
63
+ "150": "NON_PARTICIPATING",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
  "153": "NON_PARTICIPATING",
67
  "154": "SUCCESS",
68
+ "155": "NON_PARTICIPATING",
69
+ "156": "NON_PARTICIPATING",
70
  "157": "NON_PARTICIPATING",
71
  "158": "NON_PARTICIPATING",
72
+ "159": "NON_PARTICIPATING",
73
  "16": "SUCCESS",
74
  "160": "NON_PARTICIPATING",
75
  "161": "NON_PARTICIPATING",
 
78
  "164": "NON_PARTICIPATING",
79
  "165": "NON_PARTICIPATING",
80
  "166": "NON_PARTICIPATING",
81
+ "167": "NON_PARTICIPATING",
82
  "168": "NON_PARTICIPATING",
83
  "169": "NON_PARTICIPATING",
84
  "17": "SUCCESS",
85
  "170": "SUCCESS",
86
  "171": "NON_PARTICIPATING",
87
+ "172": "NON_PARTICIPATING",
88
+ "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
  "175": "NON_PARTICIPATING",
91
  "176": "NON_PARTICIPATING",
92
  "177": "NON_PARTICIPATING",
93
  "178": "NON_PARTICIPATING",
94
  "179": "NON_PARTICIPATING",
95
+ "18": "SUCCESS",
96
  "180": "NON_PARTICIPATING",
97
  "181": "NON_PARTICIPATING",
98
  "182": "NON_PARTICIPATING",
 
100
  "184": "NON_PARTICIPATING",
101
  "185": "NON_PARTICIPATING",
102
  "186": "SUCCESS",
103
+ "187": "NON_PARTICIPATING",
104
  "188": "NON_PARTICIPATING",
105
  "189": "NON_PARTICIPATING",
106
  "19": "NON_PARTICIPATING",
107
  "190": "NON_PARTICIPATING",
108
+ "191": "SUCCESS",
109
  "192": "SUCCESS",
110
  "193": "NON_PARTICIPATING",
111
+ "194": "FAIL",
112
+ "195": "SUCCESS",
113
  "196": "NON_PARTICIPATING",
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
 
119
  "200": "SUCCESS",
120
  "201": "SUCCESS",
121
  "202": "NON_PARTICIPATING",
122
+ "203": "SUCCESS",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
125
  "206": "NON_PARTICIPATING",
126
  "207": "NON_PARTICIPATING",
127
  "208": "NON_PARTICIPATING",
128
  "209": "NON_PARTICIPATING",
129
+ "21": "SUCCESS",
130
  "210": "NON_PARTICIPATING",
131
  "211": "NON_PARTICIPATING",
132
  "212": "NON_PARTICIPATING",
 
144
  "223": "SUCCESS",
145
  "224": "NON_PARTICIPATING",
146
  "225": "SUCCESS",
147
+ "226": "NON_PARTICIPATING",
148
  "227": "NON_PARTICIPATING",
149
  "228": "NON_PARTICIPATING",
150
  "229": "NON_PARTICIPATING",
151
  "23": "SUCCESS",
152
  "230": "NON_PARTICIPATING",
153
+ "231": "NON_PARTICIPATING",
154
  "232": "NON_PARTICIPATING",
155
+ "233": "NON_PARTICIPATING",
156
  "234": "NON_PARTICIPATING",
157
  "235": "NON_PARTICIPATING",
158
  "236": "NON_PARTICIPATING",
159
  "237": "NON_PARTICIPATING",
160
  "238": "NON_PARTICIPATING",
161
  "239": "NON_PARTICIPATING",
162
+ "24": "SUCCESS",
163
  "240": "NON_PARTICIPATING",
164
+ "241": "NON_PARTICIPATING",
165
  "242": "NON_PARTICIPATING",
166
  "243": "NON_PARTICIPATING",
167
+ "244": "SUCCESS",
168
  "245": "NON_PARTICIPATING",
169
  "246": "NON_PARTICIPATING",
170
  "247": "SUCCESS",
 
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
  "28": "NON_PARTICIPATING",
183
+ "29": "SUCCESS",
184
  "3": "NON_PARTICIPATING",
185
  "30": "NON_PARTICIPATING",
186
  "31": "NON_PARTICIPATING",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
189
+ "34": "SUCCESS",
190
  "35": "NON_PARTICIPATING",
191
  "36": "NON_PARTICIPATING",
192
  "37": "SUCCESS",
 
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
214
  "57": "NON_PARTICIPATING",
215
+ "58": "NON_PARTICIPATING",
216
  "59": "NON_PARTICIPATING",
217
+ "6": "NON_PARTICIPATING",
218
  "60": "NON_PARTICIPATING",
219
  "61": "SUCCESS",
220
  "62": "SUCCESS",
221
+ "63": "SUCCESS",
222
+ "64": "NON_PARTICIPATING",
223
  "65": "NON_PARTICIPATING",
224
  "66": "NON_PARTICIPATING",
225
  "67": "SUCCESS",
226
  "68": "NON_PARTICIPATING",
227
  "69": "NON_PARTICIPATING",
228
+ "7": "SUCCESS",
229
  "70": "NON_PARTICIPATING",
230
  "71": "NON_PARTICIPATING",
231
  "72": "NON_PARTICIPATING",
 
242
  "82": "SUCCESS",
243
  "83": "NON_PARTICIPATING",
244
  "84": "SUCCESS",
245
+ "85": "NON_PARTICIPATING",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
  "88": "NON_PARTICIPATING",
 
257
  "96": "SUCCESS",
258
  "97": "NON_PARTICIPATING",
259
  "98": "SUCCESS",
260
+ "99": "NON_PARTICIPATING"
261
  },
262
  "architectures": [
263
  "GPTOptim"
 
275
  "initializer_range": 0.02,
276
  "inner_step": 0,
277
  "inner_steps": 0,
278
+ "last_allreduce_block": 5516605,
279
  "layer_norm_epsilon": 1e-05,
280
  "model_type": "gpt_optimized",
281
  "n_embd": 1280,
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e128aba3bf876efe13aa00d3bddf7485af87503338b6a6bf8b806f40e4524209
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c826ed7af6ad213749328a5bf1a536514310f0c1dcb65213a872b87471f5c24
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f5216e63ea5fe48c8089322986ba91ccc7301143167773cbc707dabdd9f0914
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c5f6369dec8fef6c1414c01a050c8d9c409a918352ff9cd204bf865d1138997
3
  size 4040701744
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba198fe8153a866b8e5c7f32d3bbc2438b1ba09951fe39f0b256568cb7dd9f46
3
  size 4040805354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25b006c0d5b6edc723a75ad3009edc72c9368024930f0bc324097c2dcc05ce59
3
  size 4040805354