jockibaba commited on
Commit
72ee6dd
·
verified ·
1 Parent(s): 2bc978a

Run 5. Outer Step 10. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +27 -27
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -5,7 +5,7 @@
5
  "1": "SUCCESS",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NON_PARTICIPATING",
8
- "101": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
@@ -18,7 +18,7 @@
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
- "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
@@ -32,11 +32,11 @@
32
  "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
- "126": "NON_PARTICIPATING",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
- "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "NON_PARTICIPATING",
@@ -45,7 +45,7 @@
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "SUCCESS",
51
  "140": "NON_PARTICIPATING",
@@ -54,7 +54,7 @@
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
57
- "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
@@ -77,9 +77,9 @@
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
- "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
- "169": "NON_PARTICIPATING",
83
  "17": "SUCCESS",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
@@ -89,11 +89,11 @@
89
  "175": "NON_PARTICIPATING",
90
  "176": "NON_PARTICIPATING",
91
  "177": "NON_PARTICIPATING",
92
- "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "SUCCESS",
95
- "180": "SUCCESS",
96
- "181": "SUCCESS",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
@@ -104,12 +104,12 @@
104
  "189": "NON_PARTICIPATING",
105
  "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
- "191": "SUCCESS",
108
  "192": "NON_PARTICIPATING",
109
- "193": "SUCCESS",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
- "196": "NON_PARTICIPATING",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
@@ -120,13 +120,13 @@
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
- "205": "SUCCESS",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
- "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
@@ -134,13 +134,13 @@
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
- "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
  "220": "NON_PARTICIPATING",
141
- "221": "SUCCESS",
142
  "222": "NON_PARTICIPATING",
143
- "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
@@ -159,7 +159,7 @@
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
- "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
@@ -182,7 +182,7 @@
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
  "30": "SUCCESS",
185
- "31": "NON_PARTICIPATING",
186
  "32": "SUCCESS",
187
  "33": "NON_PARTICIPATING",
188
  "34": "SUCCESS",
@@ -197,7 +197,7 @@
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "SUCCESS",
200
- "45": "SUCCESS",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
@@ -217,7 +217,7 @@
217
  "60": "SUCCESS",
218
  "61": "SUCCESS",
219
  "62": "SUCCESS",
220
- "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "SUCCESS",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5712114,
268
- 5712172
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": 32,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5710071,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
5
  "1": "SUCCESS",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NON_PARTICIPATING",
8
+ "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
 
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
+ "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
 
32
  "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
+ "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
+ "13": "FAIL",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "NON_PARTICIPATING",
 
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "SUCCESS",
51
  "140": "NON_PARTICIPATING",
 
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
57
+ "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
 
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
+ "167": "SUCCESS",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "SUCCESS",
83
  "17": "SUCCESS",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
 
89
  "175": "NON_PARTICIPATING",
90
  "176": "NON_PARTICIPATING",
91
  "177": "NON_PARTICIPATING",
92
+ "178": "SUCCESS",
93
  "179": "NON_PARTICIPATING",
94
  "18": "SUCCESS",
95
+ "180": "NON_PARTICIPATING",
96
+ "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
 
104
  "189": "NON_PARTICIPATING",
105
  "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
+ "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
 
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
+ "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
 
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
+ "218": "SUCCESS",
138
  "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
+ "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
 
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
+ "240": "SUCCESS",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
 
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
  "30": "SUCCESS",
185
+ "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NON_PARTICIPATING",
188
  "34": "SUCCESS",
 
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "SUCCESS",
200
+ "45": "FAIL",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
 
217
  "60": "SUCCESS",
218
  "61": "SUCCESS",
219
  "62": "SUCCESS",
220
+ "63": "FAIL",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "SUCCESS",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5712390,
268
+ 5712417
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": 5712312,
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 sha256:91949b09f37d53928e3d75d208ff52ee8dee406ec83ed4ba931afc3d794c02f4
3
  size 8800564561
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cda49df00142c70a4ebb7b0aa48e11414053ef93a08cf54dae0ed99b0a7ce5f
3
  size 8800564561
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee9962bb54c57f89e17c2338a11f70b2ddca32ca23d212d3d428691e39e836bc
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e9fd746ef42477a4de02e3766a053fc4f855b5912cb8e900c241fdf75db2d75
3
  size 4400216536