MBA4215 commited on
Commit
a27cac7
·
verified ·
1 Parent(s): 6322d27

Run 5. Outer Step 12. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +26 -26
  2. inner_optimizer.pt +2 -2
  3. model.safetensors +1 -1
config.json CHANGED
@@ -16,7 +16,7 @@
16
  "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
- "111": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
@@ -26,7 +26,7 @@
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "SUCCESS",
29
- "120": "SUCCESS",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
@@ -39,8 +39,8 @@
39
  "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
- "132": "NON_PARTICIPATING",
43
- "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
@@ -53,17 +53,17 @@
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
- "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
- "148": "SUCCESS",
60
  "149": "NON_PARTICIPATING",
61
  "15": "SUCCESS",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
- "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
@@ -74,7 +74,7 @@
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
- "164": "SUCCESS",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
@@ -92,9 +92,9 @@
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "SUCCESS",
95
- "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
- "182": "SUCCESS",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
@@ -115,15 +115,15 @@
115
  "199": "NON_PARTICIPATING",
116
  "2": "SUCCESS",
117
  "20": "SUCCESS",
118
- "200": "NON_PARTICIPATING",
119
  "201": "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",
@@ -150,8 +150,8 @@
150
  "23": "SUCCESS",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
- "232": "SUCCESS",
154
- "233": "SUCCESS",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
@@ -159,11 +159,11 @@
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",
166
- "244": "NON_PARTICIPATING",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
@@ -196,14 +196,14 @@
196
  "41": "SUCCESS",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
- "44": "NON_PARTICIPATING",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
204
  "49": "SUCCESS",
205
  "5": "SUCCESS",
206
- "50": "NON_PARTICIPATING",
207
  "51": "SUCCESS",
208
  "52": "NON_PARTICIPATING",
209
  "53": "SUCCESS",
@@ -220,9 +220,9 @@
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
- "66": "NON_PARTICIPATING",
224
  "67": "SUCCESS",
225
- "68": "NON_PARTICIPATING",
226
  "69": "SUCCESS",
227
  "7": "SUCCESS",
228
  "70": "SUCCESS",
@@ -242,7 +242,7 @@
242
  "83": "SUCCESS",
243
  "84": "SUCCESS",
244
  "85": "SUCCESS",
245
- "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "SUCCESS",
248
  "89": "SUCCESS",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5714906,
268
- 5714950
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": 33,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5707679,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
16
  "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
 
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "SUCCESS",
29
+ "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
 
39
  "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "SUCCESS",
43
+ "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
 
53
  "142": "NON_PARTICIPATING",
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",
61
  "15": "SUCCESS",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "SUCCESS",
67
  "155": "SUCCESS",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
 
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
+ "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
 
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "SUCCESS",
95
+ "180": "SUCCESS",
96
  "181": "NON_PARTICIPATING",
97
+ "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
 
115
  "199": "NON_PARTICIPATING",
116
  "2": "SUCCESS",
117
  "20": "SUCCESS",
118
+ "200": "SUCCESS",
119
  "201": "NON_PARTICIPATING",
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": "SUCCESS",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
 
150
  "23": "SUCCESS",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
+ "232": "NON_PARTICIPATING",
154
+ "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
 
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",
166
+ "244": "SUCCESS",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
 
196
  "41": "SUCCESS",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
+ "44": "SUCCESS",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
204
  "49": "SUCCESS",
205
  "5": "SUCCESS",
206
+ "50": "SUCCESS",
207
  "51": "SUCCESS",
208
  "52": "NON_PARTICIPATING",
209
  "53": "SUCCESS",
 
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
+ "66": "SUCCESS",
224
  "67": "SUCCESS",
225
+ "68": "SUCCESS",
226
  "69": "SUCCESS",
227
  "7": "SUCCESS",
228
  "70": "SUCCESS",
 
242
  "83": "SUCCESS",
243
  "84": "SUCCESS",
244
  "85": "SUCCESS",
245
+ "86": "SUCCESS",
246
  "87": "SUCCESS",
247
  "88": "SUCCESS",
248
  "89": "SUCCESS",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5715202,
268
+ 5715232
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": 5715078,
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 sha256:0f6d65d890e01aadf9f1c7c44688d592000180ec4091e1dfd155df66ef442c3b
3
- size 8800564012
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5206671cad631bbb158051f0c49e453486d7cc9ad183b2a7d8f3b55150a7d4f0
3
+ size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd30ed740af026dededbd0df0b04c43faee67a8bd09e1f6c5371a0f64bcf2b3
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad5b8affc32ca3822d3ec2a37e5448503d258a7388437acbe93a4557fa80a14
3
  size 4400216536