kmfoda commited on
Commit
5dd44eb
·
verified ·
1 Parent(s): 0330f11

Run 4. Outer Step 8. Inner Step 0. Peers 81.

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
@@ -4,17 +4,17 @@
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
6
  "1": "SUCCESS",
7
- "10": "SUCCESS",
8
  "100": "NON_PARTICIPATING",
9
  "101": "SUCCESS",
10
  "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
- "104": "SUCCESS",
13
  "105": "NON_PARTICIPATING",
14
  "106": "NON_PARTICIPATING",
15
  "107": "SUCCESS",
16
  "108": "NON_PARTICIPATING",
17
- "109": "SUCCESS",
18
  "11": "SUCCESS",
19
  "110": "SUCCESS",
20
  "111": "NON_PARTICIPATING",
@@ -24,15 +24,15 @@
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
26
  "117": "SUCCESS",
27
- "118": "NON_PARTICIPATING",
28
  "119": "NON_PARTICIPATING",
29
  "12": "SUCCESS",
30
  "120": "NON_PARTICIPATING",
31
  "121": "NON_PARTICIPATING",
32
  "122": "SUCCESS",
33
- "123": "NON_PARTICIPATING",
34
  "124": "NON_PARTICIPATING",
35
- "125": "SUCCESS",
36
  "126": "NON_PARTICIPATING",
37
  "127": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
@@ -43,7 +43,7 @@
43
  "132": "SUCCESS",
44
  "133": "NON_PARTICIPATING",
45
  "134": "SUCCESS",
46
- "135": "SUCCESS",
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
  "138": "NON_PARTICIPATING",
@@ -54,23 +54,23 @@
54
  "142": "SUCCESS",
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": "SUCCESS",
70
  "157": "NON_PARTICIPATING",
71
  "158": "NON_PARTICIPATING",
72
- "159": "NON_PARTICIPATING",
73
- "16": "NON_PARTICIPATING",
74
  "160": "SUCCESS",
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
@@ -78,7 +78,7 @@
78
  "164": "NON_PARTICIPATING",
79
  "165": "NON_PARTICIPATING",
80
  "166": "NON_PARTICIPATING",
81
- "167": "SUCCESS",
82
  "168": "NON_PARTICIPATING",
83
  "169": "NON_PARTICIPATING",
84
  "17": "SUCCESS",
@@ -89,8 +89,8 @@
89
  "174": "NON_PARTICIPATING",
90
  "175": "SUCCESS",
91
  "176": "NON_PARTICIPATING",
92
- "177": "SUCCESS",
93
- "178": "SUCCESS",
94
  "179": "NON_PARTICIPATING",
95
  "18": "NON_PARTICIPATING",
96
  "180": "NON_PARTICIPATING",
@@ -100,13 +100,13 @@
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": "NON_PARTICIPATING",
109
- "192": "SUCCESS",
110
  "193": "NON_PARTICIPATING",
111
  "194": "NON_PARTICIPATING",
112
  "195": "SUCCESS",
@@ -117,12 +117,12 @@
117
  "2": "SUCCESS",
118
  "20": "SUCCESS",
119
  "200": "SUCCESS",
120
- "201": "NON_PARTICIPATING",
121
- "202": "NON_PARTICIPATING",
122
  "203": "SUCCESS",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
125
- "206": "SUCCESS",
126
  "207": "NON_PARTICIPATING",
127
  "208": "NON_PARTICIPATING",
128
  "209": "NON_PARTICIPATING",
@@ -132,23 +132,23 @@
132
  "212": "NON_PARTICIPATING",
133
  "213": "NON_PARTICIPATING",
134
  "214": "NON_PARTICIPATING",
135
- "215": "NON_PARTICIPATING",
136
  "216": "SUCCESS",
137
  "217": "NON_PARTICIPATING",
138
  "218": "SUCCESS",
139
  "219": "NON_PARTICIPATING",
140
  "22": "SUCCESS",
141
- "220": "NON_PARTICIPATING",
142
- "221": "NON_PARTICIPATING",
143
  "222": "SUCCESS",
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",
@@ -177,29 +177,29 @@
177
  "253": "NON_PARTICIPATING",
178
  "254": "NON_PARTICIPATING",
179
  "255": "SUCCESS",
180
- "26": "SUCCESS",
181
  "27": "SUCCESS",
182
  "28": "NON_PARTICIPATING",
183
  "29": "NON_PARTICIPATING",
184
  "3": "NON_PARTICIPATING",
185
  "30": "SUCCESS",
186
  "31": "NON_PARTICIPATING",
187
- "32": "NON_PARTICIPATING",
188
  "33": "NON_PARTICIPATING",
189
  "34": "SUCCESS",
190
- "35": "NON_PARTICIPATING",
191
  "36": "NON_PARTICIPATING",
192
  "37": "SUCCESS",
193
  "38": "NON_PARTICIPATING",
194
- "39": "SUCCESS",
195
- "4": "SUCCESS",
196
- "40": "SUCCESS",
197
  "41": "SUCCESS",
198
  "42": "NON_PARTICIPATING",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
202
- "46": "NON_PARTICIPATING",
203
  "47": "NON_PARTICIPATING",
204
  "48": "NON_PARTICIPATING",
205
  "49": "SUCCESS",
@@ -245,11 +245,11 @@
245
  "85": "SUCCESS",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
- "88": "SUCCESS",
249
- "89": "SUCCESS",
250
  "9": "NON_PARTICIPATING",
251
- "90": "NON_PARTICIPATING",
252
- "91": "NON_PARTICIPATING",
253
  "92": "NON_PARTICIPATING",
254
  "93": "NON_PARTICIPATING",
255
  "94": "NON_PARTICIPATING",
@@ -275,7 +275,7 @@
275
  "initializer_range": 0.02,
276
  "inner_step": 0,
277
  "inner_steps": 0,
278
- "last_allreduce_block": 5492224,
279
  "layer_norm_epsilon": 1e-05,
280
  "model_type": "gpt_optimized",
281
  "n_embd": 1280,
 
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
6
  "1": "SUCCESS",
7
+ "10": "FAIL",
8
  "100": "NON_PARTICIPATING",
9
  "101": "SUCCESS",
10
  "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
+ "104": "NON_PARTICIPATING",
13
  "105": "NON_PARTICIPATING",
14
  "106": "NON_PARTICIPATING",
15
  "107": "SUCCESS",
16
  "108": "NON_PARTICIPATING",
17
+ "109": "NON_PARTICIPATING",
18
  "11": "SUCCESS",
19
  "110": "SUCCESS",
20
  "111": "NON_PARTICIPATING",
 
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
26
  "117": "SUCCESS",
27
+ "118": "SUCCESS",
28
  "119": "NON_PARTICIPATING",
29
  "12": "SUCCESS",
30
  "120": "NON_PARTICIPATING",
31
  "121": "NON_PARTICIPATING",
32
  "122": "SUCCESS",
33
+ "123": "SUCCESS",
34
  "124": "NON_PARTICIPATING",
35
+ "125": "NON_PARTICIPATING",
36
  "126": "NON_PARTICIPATING",
37
  "127": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
 
43
  "132": "SUCCESS",
44
  "133": "NON_PARTICIPATING",
45
  "134": "SUCCESS",
46
+ "135": "NON_PARTICIPATING",
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
  "138": "NON_PARTICIPATING",
 
54
  "142": "SUCCESS",
55
  "143": "NON_PARTICIPATING",
56
  "144": "NON_PARTICIPATING",
57
+ "145": "SUCCESS",
58
  "146": "NON_PARTICIPATING",
59
+ "147": "SUCCESS",
60
  "148": "SUCCESS",
61
  "149": "SUCCESS",
62
+ "15": "FAIL",
63
+ "150": "SUCCESS",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
+ "153": "SUCCESS",
67
  "154": "SUCCESS",
68
  "155": "NON_PARTICIPATING",
69
+ "156": "FAIL",
70
  "157": "NON_PARTICIPATING",
71
  "158": "NON_PARTICIPATING",
72
+ "159": "SUCCESS",
73
+ "16": "SUCCESS",
74
  "160": "SUCCESS",
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
 
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",
 
89
  "174": "NON_PARTICIPATING",
90
  "175": "SUCCESS",
91
  "176": "NON_PARTICIPATING",
92
+ "177": "FAIL",
93
+ "178": "FAIL",
94
  "179": "NON_PARTICIPATING",
95
  "18": "NON_PARTICIPATING",
96
  "180": "NON_PARTICIPATING",
 
100
  "184": "NON_PARTICIPATING",
101
  "185": "NON_PARTICIPATING",
102
  "186": "SUCCESS",
103
+ "187": "FAIL",
104
  "188": "NON_PARTICIPATING",
105
  "189": "NON_PARTICIPATING",
106
  "19": "NON_PARTICIPATING",
107
  "190": "NON_PARTICIPATING",
108
+ "191": "FAIL",
109
+ "192": "NON_PARTICIPATING",
110
  "193": "NON_PARTICIPATING",
111
  "194": "NON_PARTICIPATING",
112
  "195": "SUCCESS",
 
117
  "2": "SUCCESS",
118
  "20": "SUCCESS",
119
  "200": "SUCCESS",
120
+ "201": "SUCCESS",
121
+ "202": "SUCCESS",
122
  "203": "SUCCESS",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
125
+ "206": "FAIL",
126
  "207": "NON_PARTICIPATING",
127
  "208": "NON_PARTICIPATING",
128
  "209": "NON_PARTICIPATING",
 
132
  "212": "NON_PARTICIPATING",
133
  "213": "NON_PARTICIPATING",
134
  "214": "NON_PARTICIPATING",
135
+ "215": "SUCCESS",
136
  "216": "SUCCESS",
137
  "217": "NON_PARTICIPATING",
138
  "218": "SUCCESS",
139
  "219": "NON_PARTICIPATING",
140
  "22": "SUCCESS",
141
+ "220": "FAIL",
142
+ "221": "FAIL",
143
  "222": "SUCCESS",
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": "NON_PARTICIPATING",
152
  "230": "NON_PARTICIPATING",
153
  "231": "NON_PARTICIPATING",
154
  "232": "NON_PARTICIPATING",
 
177
  "253": "NON_PARTICIPATING",
178
  "254": "NON_PARTICIPATING",
179
  "255": "SUCCESS",
180
+ "26": "FAIL",
181
  "27": "SUCCESS",
182
  "28": "NON_PARTICIPATING",
183
  "29": "NON_PARTICIPATING",
184
  "3": "NON_PARTICIPATING",
185
  "30": "SUCCESS",
186
  "31": "NON_PARTICIPATING",
187
+ "32": "FAIL",
188
  "33": "NON_PARTICIPATING",
189
  "34": "SUCCESS",
190
+ "35": "SUCCESS",
191
  "36": "NON_PARTICIPATING",
192
  "37": "SUCCESS",
193
  "38": "NON_PARTICIPATING",
194
+ "39": "FAIL",
195
+ "4": "FAIL",
196
+ "40": "FAIL",
197
  "41": "SUCCESS",
198
  "42": "NON_PARTICIPATING",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
202
+ "46": "SUCCESS",
203
  "47": "NON_PARTICIPATING",
204
  "48": "NON_PARTICIPATING",
205
  "49": "SUCCESS",
 
245
  "85": "SUCCESS",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
+ "88": "NON_PARTICIPATING",
249
+ "89": "FAIL",
250
  "9": "NON_PARTICIPATING",
251
+ "90": "SUCCESS",
252
+ "91": "FAIL",
253
  "92": "NON_PARTICIPATING",
254
  "93": "NON_PARTICIPATING",
255
  "94": "NON_PARTICIPATING",
 
275
  "initializer_range": 0.02,
276
  "inner_step": 0,
277
  "inner_steps": 0,
278
+ "last_allreduce_block": 5499548,
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 sha256:57f17aa75a17b31c8b77d2e1d93d4007c06cb72f61e71a9ae685eb7651287814
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a606695e0adec9477b43c25b1e1268bab930e40a7fa6c5c73bcb3688e34e5e8
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4f8b6dd3d7ad4374d40b109946c60e4f678ceb9b8602f6da5f934ef6f6bd806
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1ad854fc14e509aa4a615119d509af3a3d9894ec41b0d8805f1d7f5c626682
3
  size 4040701744
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48b1a7bd502f9533b0a7936afb0a35aab21d2c85e3a992e2496cb697e166381e
3
  size 4040805354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:207d8838847bb2bb3d0e68733699338cf4c0540a683262b5f75f1bd7077fc90d
3
  size 4040805354