ncaagcc commited on
Commit
e9eff31
·
verified ·
1 Parent(s): 0e3fe74

Run 5. Outer Step 133. Inner Step 1.

Browse files
Files changed (3) hide show
  1. config.json +66 -66
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -9,32 +9,32 @@
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": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
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": "NOT_ALIVE",
25
- "117": "SUCCESS",
26
- "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
- "123": "NON_PARTICIPATING",
33
- "124": "SUCCESS",
34
- "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
- "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
@@ -43,12 +43,12 @@
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": "NOT_ALIVE",
50
- "14": "SUCCESS",
51
- "140": "NOT_ALIVE",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
@@ -57,31 +57,31 @@
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
- "149": "NOT_ALIVE",
61
- "15": "NOT_ALIVE",
62
- "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "SUCCESS",
66
- "154": "SUCCESS",
67
- "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
- "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
75
- "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
- "164": "SUCCESS",
78
  "165": "SUCCESS",
79
- "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
- "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
- "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
@@ -95,7 +95,7 @@
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",
@@ -104,36 +104,36 @@
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",
113
- "197": "SUCCESS",
114
  "198": "NON_PARTICIPATING",
115
- "199": "NOT_ALIVE",
116
  "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
- "204": "SUCCESS",
123
  "205": "NON_PARTICIPATING",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
- "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
- "212": "NON_PARTICIPATING",
132
  "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
- "215": "SUCCESS",
135
  "216": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
@@ -159,40 +159,40 @@
159
  "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
- "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
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": "NOT_ALIVE",
174
- "251": "NOT_ALIVE",
175
- "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
- "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
- "3": "NOT_ALIVE",
184
- "30": "NON_PARTICIPATING",
185
- "31": "NON_PARTICIPATING",
186
  "32": "SUCCESS",
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": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
@@ -202,10 +202,10 @@
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
- "5": "SUCCESS",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
- "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
@@ -213,7 +213,7 @@
213
  "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
- "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
@@ -227,19 +227,19 @@
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
@@ -251,10 +251,10 @@
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
- "94": "SUCCESS",
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
- 6003212,
268
- 6003241
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": 47,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6000755,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
+ "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
+ "108": "NOT_ALIVE",
16
+ "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
+ "112": "SUCCESS",
21
  "113": "SUCCESS",
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": "NOT_ALIVE",
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": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
+ "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
 
43
  "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
+ "136": "SUCCESS",
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": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
 
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
+ "149": "NON_PARTICIPATING",
61
+ "15": "SUCCESS",
62
+ "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NON_PARTICIPATING",
66
+ "154": "NOT_ALIVE",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
+ "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
75
+ "162": "NOT_ALIVE",
76
  "163": "NOT_ALIVE",
77
+ "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
+ "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
+ "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
 
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
+ "183": "SUCCESS",
99
  "184": "NON_PARTICIPATING",
100
  "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
 
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": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
+ "196": "NOT_ALIVE",
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": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
+ "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
+ "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
+ "212": "NOT_ALIVE",
132
  "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
+ "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
 
159
  "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
+ "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
+ "246": "NOT_ALIVE",
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": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
+ "254": "SUCCESS",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
+ "3": "NON_PARTICIPATING",
184
+ "30": "NOT_ALIVE",
185
+ "31": "NOT_ALIVE",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
  "39": "SUCCESS",
194
  "4": "NON_PARTICIPATING",
195
+ "40": "SUCCESS",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
 
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
+ "52": "FAIL",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
 
213
  "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
+ "6": "NON_PARTICIPATING",
217
  "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
 
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
233
+ "75": "NOT_ALIVE",
234
+ "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
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": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
 
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
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
+ 6003421,
268
+ 6003449
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": 6003212,
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:f646e8e4bcc37dc64fa9243db7efda9a3ebb77cff34127e564e63affd81637d8
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9c795eaf7621dfa2a31bc09fc427b6d2deaa451b95ed624bb35287e6d10579
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb02f2fc19c09170f68b20e18739270352d6f197176ce29772f9240da4a123c5
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:526ae1c996f4d9d6bdef2df20ba16b614711050077a7cc710eb8cabb013c86a2
3
  size 4400216536