MBA4215 commited on
Commit
70d431f
·
verified ·
1 Parent(s): 149572a

Run 5. Outer Step 87. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +75 -75
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -10,49 +10,49 @@
10
  "103": "SUCCESS",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
- "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
- "108": "NOT_ALIVE",
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": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
- "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
- "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
- "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
- "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
- "129": "NON_PARTICIPATING",
39
- "13": "NON_PARTICIPATING",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
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": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
- "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
- "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
@@ -62,21 +62,21 @@
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
- "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
- "155": "NON_PARTICIPATING",
68
  "156": "SUCCESS",
69
- "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
- "16": "NON_PARTICIPATING",
73
- "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NON_PARTICIPATING",
77
- "164": "SUCCESS",
78
- "165": "SUCCESS",
79
- "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
@@ -84,29 +84,29 @@
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
- "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
- "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NON_PARTICIPATING",
95
  "180": "NOT_ALIVE",
96
- "181": "SUCCESS",
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
- "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
- "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
- "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
@@ -116,22 +116,22 @@
116
  "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
- "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NOT_ALIVE",
122
  "204": "NON_PARTICIPATING",
123
- "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
- "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
- "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
- "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
@@ -142,54 +142,54 @@
142
  "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
- "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
- "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
- "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
- "230": "NOT_ALIVE",
152
- "231": "NOT_ALIVE",
153
  "232": "NON_PARTICIPATING",
154
- "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NON_PARTICIPATING",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NON_PARTICIPATING",
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",
170
- "248": "NOT_ALIVE",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
- "253": "NOT_ALIVE",
177
- "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
- "3": "NOT_ALIVE",
184
- "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
- "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
- "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
- "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
194
  "4": "NON_PARTICIPATING",
195
  "40": "SUCCESS",
@@ -200,15 +200,15 @@
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
- "48": "NON_PARTICIPATING",
204
- "49": "NOT_ALIVE",
205
  "5": "SUCCESS",
206
- "50": "NON_PARTICIPATING",
207
- "51": "NOT_ALIVE",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
- "55": "NOT_ALIVE",
212
  "56": "SUCCESS",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
@@ -216,7 +216,7 @@
216
  "6": "NON_PARTICIPATING",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
- "62": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
@@ -231,31 +231,31 @@
231
  "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
- "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
- "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
- "84": "NON_PARTICIPATING",
244
- "85": "NOT_ALIVE",
245
- "86": "NOT_ALIVE",
246
- "87": "NON_PARTICIPATING",
247
- "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NON_PARTICIPATING",
251
- "91": "NON_PARTICIPATING",
252
  "92": "NON_PARTICIPATING",
253
- "93": "NON_PARTICIPATING",
254
  "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
- "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5934801,
268
- 5934828
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": 35,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5933681,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
10
  "103": "SUCCESS",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
+ "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
+ "11": "NON_PARTICIPATING",
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": "NOT_ALIVE",
25
+ "117": "SUCCESS",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
+ "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
+ "129": "NOT_ALIVE",
39
+ "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
+ "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
+ "137": "SUCCESS",
48
+ "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
+ "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
+ "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
 
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
+ "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
+ "155": "NOT_ALIVE",
68
  "156": "SUCCESS",
69
+ "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "NOT_ALIVE",
72
+ "16": "NOT_ALIVE",
73
+ "160": "NOT_ALIVE",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "NOT_ALIVE",
77
+ "164": "NON_PARTICIPATING",
78
+ "165": "NON_PARTICIPATING",
79
+ "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
 
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
+ "177": "NON_PARTICIPATING",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NON_PARTICIPATING",
95
  "180": "NOT_ALIVE",
96
+ "181": "NON_PARTICIPATING",
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
+ "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
+ "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
 
116
  "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
+ "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
+ "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
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",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
 
142
  "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
+ "225": "NON_PARTICIPATING",
146
  "226": "NOT_ALIVE",
147
+ "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
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",
158
+ "237": "NOT_ALIVE",
159
+ "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NON_PARTICIPATING",
163
+ "241": "NOT_ALIVE",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
+ "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
+ "253": "NON_PARTICIPATING",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "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": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "SUCCESS",
193
  "39": "SUCCESS",
194
  "4": "NON_PARTICIPATING",
195
  "40": "SUCCESS",
 
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
+ "48": "NOT_ALIVE",
204
+ "49": "NON_PARTICIPATING",
205
  "5": "SUCCESS",
206
+ "50": "NOT_ALIVE",
207
+ "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
+ "55": "NON_PARTICIPATING",
212
  "56": "SUCCESS",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
 
216
  "6": "NON_PARTICIPATING",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
+ "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
 
231
  "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
+ "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
+ "84": "NOT_ALIVE",
244
+ "85": "NON_PARTICIPATING",
245
+ "86": "NON_PARTICIPATING",
246
+ "87": "NOT_ALIVE",
247
+ "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NON_PARTICIPATING",
251
+ "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
+ "93": "NOT_ALIVE",
254
  "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
+ "98": "NON_PARTICIPATING",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5934918,
268
+ 5934960
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": 5934830,
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:f468bb5fe134c78b79fe1a95849bd4c80a5a835f9a950787b24d3d61bb6a2484
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac367394c099547822f8eb8304340178b0609f8af685c8af58d4d64bda736e4
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45bf07427afa186571760bf904a3da81a25782bcf27b65a0d30dfdea0b564d54
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dedcd1ed171f133c31acab9a34e5d33dac6c66b2fc8e2cca7551b831b0e00a32
3
  size 4400216536