jockibaba commited on
Commit
7eccba8
·
verified ·
1 Parent(s): ad66c7d

Run 5. Outer Step 23. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +20 -20
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -11,7 +11,7 @@
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
- "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
@@ -19,15 +19,15 @@
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
- "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "SUCCESS",
29
- "120": "NON_PARTICIPATING",
30
- "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
@@ -35,20 +35,20 @@
35
  "126": "NON_PARTICIPATING",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
- "129": "FAIL",
39
  "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "NON_PARTICIPATING",
43
  "133": "NON_PARTICIPATING",
44
- "134": "SUCCESS",
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",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
@@ -70,14 +70,14 @@
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
- "160": "SUCCESS",
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",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "SUCCESS",
@@ -88,7 +88,7 @@
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NON_PARTICIPATING",
91
- "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "SUCCESS",
@@ -118,12 +118,12 @@
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
- "203": "SUCCESS",
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",
@@ -133,9 +133,9 @@
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
- "219": "SUCCESS",
139
  "22": "SUCCESS",
140
  "220": "NON_PARTICIPATING",
141
  "221": "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",
@@ -230,7 +230,7 @@
230
  "72": "SUCCESS",
231
  "73": "SUCCESS",
232
  "74": "SUCCESS",
233
- "75": "SUCCESS",
234
  "76": "SUCCESS",
235
  "77": "SUCCESS",
236
  "78": "SUCCESS",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5729846,
268
- 5729890
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": 5727698,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
+ "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
 
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
+ "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
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",
33
  "124": "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",
43
  "133": "NON_PARTICIPATING",
44
+ "134": "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": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
 
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
+ "160": "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": "SUCCESS",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "SUCCESS",
 
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NON_PARTICIPATING",
91
+ "177": "NON_PARTICIPATING",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "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": "SUCCESS",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
 
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
+ "217": "SUCCESS",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
  "220": "NON_PARTICIPATING",
141
  "221": "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",
 
230
  "72": "SUCCESS",
231
  "73": "SUCCESS",
232
  "74": "SUCCESS",
233
+ "75": "NON_PARTICIPATING",
234
  "76": "SUCCESS",
235
  "77": "SUCCESS",
236
  "78": "SUCCESS",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5730132,
268
+ 5730160
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": 5730062,
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 sha256:4864fb4e61c4934d66c3b954f54680bfef2d548aff1ae90eed717e86b26745a2
3
  size 8800564561
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0411595e751b2c043adad03a8ed07916c7a4519bf8d7f53ead1966c2f7301a
3
  size 8800564561
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5d1f2ef1001d58cc35cb0b3659eed6548af68f74fb46ad8e5c14aba5a2cbbc1
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010b21d5556433115f56fe440ce75345717a31e0f77eca010c35ef0075b8baa5
3
  size 4400216536