MBA4215 commited on
Commit
80af79c
·
verified ·
1 Parent(s): 428323d

Run 5. Outer Step 49. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +43 -43
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -2,10 +2,10 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
@@ -13,9 +13,9 @@
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
- "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
- "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
@@ -25,14 +25,14 @@
25
  "117": "NOT_ALIVE",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
- "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
- "123": "NON_PARTICIPATING",
33
  "124": "SUCCESS",
34
  "125": "NOT_ALIVE",
35
- "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
38
  "129": "SUCCESS",
@@ -40,14 +40,14 @@
40
  "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
- "133": "NOT_ALIVE",
44
  "134": "SUCCESS",
45
- "135": "NOT_ALIVE",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
- "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "SUCCESS",
53
  "142": "SUCCESS",
@@ -65,18 +65,18 @@
65
  "153": "NOT_ALIVE",
66
  "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
- "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
- "160": "NOT_ALIVE",
74
- "161": "SUCCESS",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "SUCCESS",
78
  "165": "NOT_ALIVE",
79
- "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
@@ -85,13 +85,13 @@
85
  "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
- "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
- "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
@@ -99,13 +99,13 @@
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
- "187": "SUCCESS",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
- "192": "NON_PARTICIPATING",
109
  "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
@@ -118,7 +118,7 @@
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NOT_ALIVE",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
@@ -126,12 +126,12 @@
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "SUCCESS",
129
- "210": "NON_PARTICIPATING",
130
- "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
- "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
@@ -139,8 +139,8 @@
139
  "22": "NOT_ALIVE",
140
  "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
- "222": "NON_PARTICIPATING",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
@@ -152,16 +152,16 @@
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
- "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
- "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
- "240": "NON_PARTICIPATING",
163
  "241": "NOT_ALIVE",
164
- "242": "NOT_ALIVE",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
  "245": "NOT_ALIVE",
@@ -171,14 +171,14 @@
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
- "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "SUCCESS",
180
  "27": "SUCCESS",
181
- "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
@@ -187,13 +187,13 @@
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
  "35": "NOT_ALIVE",
190
- "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
- "38": "SUCCESS",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
- "40": "SUCCESS",
196
- "41": "SUCCESS",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "NOT_ALIVE",
@@ -209,7 +209,7 @@
209
  "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
- "56": "SUCCESS",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
@@ -226,7 +226,7 @@
226
  "69": "SUCCESS",
227
  "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
- "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
@@ -236,14 +236,14 @@
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
- "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
- "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
@@ -254,7 +254,7 @@
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
- "97": "SUCCESS",
258
  "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5885457,
268
- 5885538
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
- "inner_step": 31,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5884190,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
+ "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
 
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
+ "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
+ "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
 
25
  "117": "NOT_ALIVE",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
+ "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "NOT_ALIVE",
33
  "124": "SUCCESS",
34
  "125": "NOT_ALIVE",
35
+ "126": "NON_PARTICIPATING",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
38
  "129": "SUCCESS",
 
40
  "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "SUCCESS",
44
  "134": "SUCCESS",
45
+ "135": "NON_PARTICIPATING",
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": "SUCCESS",
53
  "142": "SUCCESS",
 
65
  "153": "NOT_ALIVE",
66
  "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
+ "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
+ "160": "NON_PARTICIPATING",
74
+ "161": "FAIL",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "SUCCESS",
78
  "165": "NOT_ALIVE",
79
+ "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
 
85
  "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
+ "174": "SUCCESS",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
+ "18": "SUCCESS",
95
  "180": "NOT_ALIVE",
96
  "181": "NON_PARTICIPATING",
97
  "182": "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",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
+ "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
 
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
 
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "SUCCESS",
129
+ "210": "SUCCESS",
130
+ "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
 
139
  "22": "NOT_ALIVE",
140
  "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
+ "222": "NOT_ALIVE",
143
+ "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "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": "NOT_ALIVE",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
+ "240": "NOT_ALIVE",
163
  "241": "NOT_ALIVE",
164
+ "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
  "245": "NOT_ALIVE",
 
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
+ "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "SUCCESS",
180
  "27": "SUCCESS",
181
+ "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
 
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
  "35": "NOT_ALIVE",
190
+ "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
+ "40": "NOT_ALIVE",
196
+ "41": "FAIL",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "NOT_ALIVE",
 
209
  "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
+ "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
 
226
  "69": "SUCCESS",
227
  "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
+ "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
 
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
+ "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
+ "87": "FAIL",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
 
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
+ "97": "FAIL",
258
  "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5885650,
268
+ 5885730
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
+ "inner_step": 2,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5885508,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bc278087212af9fc1919c1df3337abe469dcde9bf7e90dc2bb6fd505bad4806
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2ce1fe162168d3ddf0eec8e12957558b35519d6a8185cca726472a34c51ff12
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34fff943bd6da8a0fde905d449114d5854e3658bf65797cdf0c832447315541a
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b961506c1e596aeed12453af4ecf0b9510ef09e17ee6cbef219d919332e805ad
3
  size 4400216536