ncaagcc commited on
Commit
d0687eb
·
verified ·
1 Parent(s): e040b12

Run 5. Outer Step 129. Inner Step 1.

Browse files
Files changed (3) hide show
  1. config.json +65 -65
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -5,34 +5,34 @@
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
- "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
- "114": "NOT_ALIVE",
23
- "115": "NOT_ALIVE",
24
- "116": "NOT_ALIVE",
25
- "117": "NON_PARTICIPATING",
26
  "118": "NOT_ALIVE",
27
- "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
- "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
- "123": "NOT_ALIVE",
33
- "124": "SUCCESS",
34
- "125": "NOT_ALIVE",
35
- "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
@@ -40,41 +40,41 @@
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
- "133": "NOT_ALIVE",
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": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
- "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
- "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
- "15": "NOT_ALIVE",
62
- "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
- "154": "SUCCESS",
67
- "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NOT_ALIVE",
74
- "161": "NON_PARTICIPATING",
75
- "162": "NOT_ALIVE",
76
  "163": "NOT_ALIVE",
77
- "164": "NON_PARTICIPATING",
78
  "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
@@ -83,8 +83,8 @@
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
- "172": "NON_PARTICIPATING",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
@@ -95,25 +95,25 @@
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "SUCCESS",
99
- "184": "NOT_ALIVE",
100
  "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
- "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
- "195": "NON_PARTICIPATING",
112
- "196": "NON_PARTICIPATING",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
- "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NON_PARTICIPATING",
@@ -121,7 +121,7 @@
121
  "203": "NOT_ALIVE",
122
  "204": "SUCCESS",
123
  "205": "NON_PARTICIPATING",
124
- "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
@@ -129,11 +129,11 @@
129
  "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
- "213": "NON_PARTICIPATING",
133
  "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
@@ -156,25 +156,25 @@
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
- "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
- "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
- "25": "NON_PARTICIPATING",
173
- "250": "SUCCESS",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
- "254": "SUCCESS",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
@@ -182,17 +182,17 @@
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
  "30": "SUCCESS",
185
- "31": "NOT_ALIVE",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
- "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
- "4": "NON_PARTICIPATING",
195
- "40": "FAIL",
196
  "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
@@ -200,9 +200,9 @@
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "SUCCESS",
203
- "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
- "5": "SUCCESS",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
@@ -211,13 +211,13 @@
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
214
- "58": "NON_PARTICIPATING",
215
- "59": "NOT_ALIVE",
216
  "6": "NON_PARTICIPATING",
217
- "60": "NOT_ALIVE",
218
- "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
- "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
@@ -226,18 +226,18 @@
226
  "69": "NOT_ALIVE",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
- "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
- "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
- "76": "NOT_ALIVE",
235
- "77": "SUCCESS",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
- "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "NOT_ALIVE",
@@ -251,10 +251,10 @@
251
  "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
- "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
- "97": "NOT_ALIVE",
258
  "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
260
  },
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5996032,
268
- 5996063
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": 5994342,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
+ "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
+ "108": "SUCCESS",
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
+ "114": "NON_PARTICIPATING",
23
+ "115": "NON_PARTICIPATING",
24
+ "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
  "118": "NOT_ALIVE",
27
+ "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
+ "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
+ "123": "NON_PARTICIPATING",
33
+ "124": "NON_PARTICIPATING",
34
+ "125": "NON_PARTICIPATING",
35
+ "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
 
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
+ "135": "NOT_ALIVE",
46
+ "136": "SUCCESS",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "SUCCESS",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
+ "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
+ "15": "NON_PARTICIPATING",
62
+ "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "NOT_ALIVE",
67
+ "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NOT_ALIVE",
74
+ "161": "NOT_ALIVE",
75
+ "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
+ "164": "SUCCESS",
78
  "165": "NOT_ALIVE",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
 
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
+ "172": "NOT_ALIVE",
87
+ "173": "NOT_ALIVE",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
 
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
+ "183": "NON_PARTICIPATING",
99
+ "184": "NON_PARTICIPATING",
100
  "185": "NOT_ALIVE",
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": "NON_PARTICIPATING",
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
+ "195": "NOT_ALIVE",
112
+ "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
+ "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NON_PARTICIPATING",
 
121
  "203": "NOT_ALIVE",
122
  "204": "SUCCESS",
123
  "205": "NON_PARTICIPATING",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
 
129
  "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
+ "213": "SUCCESS",
133
  "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
+ "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
 
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
+ "241": "NOT_ALIVE",
164
  "242": "NOT_ALIVE",
165
+ "243": "SUCCESS",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
+ "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
 
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
  "30": "SUCCESS",
185
+ "31": "NON_PARTICIPATING",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
+ "4": "NOT_ALIVE",
195
+ "40": "NOT_ALIVE",
196
  "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
 
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "SUCCESS",
203
+ "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
 
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
214
+ "58": "NOT_ALIVE",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NON_PARTICIPATING",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "NOT_ALIVE",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
 
226
  "69": "NOT_ALIVE",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
+ "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
+ "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "NON_PARTICIPATING",
235
+ "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
+ "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "NOT_ALIVE",
 
251
  "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
+ "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
+ "97": "NON_PARTICIPATING",
258
  "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5996228,
268
+ 5996254
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": 1,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5996103,
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 sha256:2f5cb27df723b8d61c7eeb494df5a27a441cf98f10b58baf1fd32f17105176ee
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f11a926fcf990dc8b5feaa0972e0865824b0670f8df27fcbed6da3142b61531a
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eeeb8524355626478245297f5ed436612b32302b6522317c984fbea10a0c8bb8
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd0c7157803f3242ce73107c1c49bbf926cce666b6e74f7fe81f51dec3322140
3
  size 4400216536