mujerry commited on
Commit
06ecfcc
·
verified ·
1 Parent(s): 0ab4cc9

Run 11. Outer Step 239. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +50 -50
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -3,23 +3,23 @@
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
- "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
- "103": "NON_PARTICIPATING",
11
- "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "SUCCESS",
15
- "108": "NOT_ALIVE",
16
  "109": "SUCCESS",
17
- "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
- "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
@@ -27,26 +27,26 @@
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "SUCCESS",
30
- "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
- "127": "SUCCESS",
37
- "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NON_PARTICIPATING",
43
  "133": "NOT_ALIVE",
44
- "134": "NON_PARTICIPATING",
45
- "135": "NOT_ALIVE",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
49
- "139": "NOT_ALIVE",
50
  "14": "NON_PARTICIPATING",
51
  "140": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
@@ -62,17 +62,17 @@
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
- "156": "NON_PARTICIPATING",
69
  "157": "SUCCESS",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
- "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
- "162": "SUCCESS",
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NOT_ALIVE",
@@ -83,38 +83,38 @@
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
- "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "SUCCESS",
93
- "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
- "181": "NON_PARTICIPATING",
97
  "182": "SUCCESS",
98
  "183": "NOT_ALIVE",
99
- "184": "SUCCESS",
100
- "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "SUCCESS",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
- "191": "NON_PARTICIPATING",
108
  "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
- "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
- "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
@@ -127,12 +127,12 @@
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
- "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
- "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
@@ -143,13 +143,13 @@
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
- "226": "SUCCESS",
147
  "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
- "23": "SUCCESS",
151
  "230": "SUCCESS",
152
- "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
@@ -160,13 +160,13 @@
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
- "241": "SUCCESS",
164
- "242": "SUCCESS",
165
- "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
- "245": "SUCCESS",
168
  "246": "NOT_ALIVE",
169
- "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
@@ -185,20 +185,20 @@
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "SUCCESS",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
192
- "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
196
- "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
- "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
@@ -214,7 +214,7 @@
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NOT_ALIVE",
@@ -226,7 +226,7 @@
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
- "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
@@ -234,13 +234,13 @@
234
  "76": "SUCCESS",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
- "79": "NON_PARTICIPATING",
238
- "8": "NON_PARTICIPATING",
239
- "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
- "83": "SUCCESS",
243
- "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
@@ -254,7 +254,7 @@
254
  "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NOT_ALIVE",
257
- "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6674095,
268
- 6674125
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
@@ -274,9 +274,9 @@
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
- "inner_step": 31,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6673846,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
+ "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
+ "103": "NOT_ALIVE",
11
+ "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "SUCCESS",
15
+ "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
+ "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
 
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "SUCCESS",
30
+ "121": "SUCCESS",
31
  "122": "NOT_ALIVE",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
+ "127": "NON_PARTICIPATING",
37
+ "128": "SUCCESS",
38
  "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NON_PARTICIPATING",
43
  "133": "NOT_ALIVE",
44
+ "134": "SUCCESS",
45
+ "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
 
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
+ "156": "NOT_ALIVE",
69
  "157": "SUCCESS",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
+ "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
+ "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NOT_ALIVE",
 
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
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": "SUCCESS",
93
+ "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
+ "181": "NOT_ALIVE",
97
  "182": "SUCCESS",
98
  "183": "NOT_ALIVE",
99
+ "184": "NON_PARTICIPATING",
100
+ "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
  "187": "SUCCESS",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
+ "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
+ "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
+ "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
 
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
+ "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
+ "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
 
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
+ "226": "NOT_ALIVE",
147
  "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
+ "23": "NON_PARTICIPATING",
151
  "230": "SUCCESS",
152
+ "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
 
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
+ "241": "NOT_ALIVE",
164
+ "242": "NON_PARTICIPATING",
165
+ "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NON_PARTICIPATING",
168
  "246": "NOT_ALIVE",
169
+ "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
 
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "NON_PARTICIPATING",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
192
+ "38": "SUCCESS",
193
  "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
196
+ "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
+ "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
 
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
+ "60": "NOT_ALIVE",
218
  "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NOT_ALIVE",
 
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
+ "71": "SUCCESS",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
 
234
  "76": "SUCCESS",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
+ "79": "NOT_ALIVE",
238
+ "8": "NOT_ALIVE",
239
+ "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
+ "83": "NON_PARTICIPATING",
243
+ "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
 
254
  "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NOT_ALIVE",
257
+ "97": "SUCCESS",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6674262,
268
+ 6674291
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
 
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
+ "inner_step": 9,
278
  "intermediate_size": 5632,
279
+ "last_allreduce_block": 6674236,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e51b8bf2281f6e679f5199be42a71cc306e67b67a86c0c7a04c07c79b9c3daa
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26996e889e3d7ea7eaf86c5fe192ddb682bba1a35235ab13d5bd7f6649c5cdb
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f224a71098793c4aec8ead48ceab574363fa005cf733fe843cd6fd75b7fd6e6
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86695890e2feaae9ab5253027381566eeed5396a69e030e6f6ecbbc2183cbb50
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65b326856428cc00457cb7290bbff7ce692e418d3cece2c021170f893a372dd3
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3515e67bcb71b526e5e56afab2e198e7db34bc6167336003a3fd4896cbc57aa1
3
  size 4400216536