ncaagcc commited on
Commit
e2664e5
·
verified ·
1 Parent(s): 2efbf83

Run 5. Outer Step 95. Inner Step 1.

Browse files
Files changed (3) hide show
  1. config.json +74 -74
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -5,24 +5,24 @@
5
  "1": "NON_PARTICIPATING",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
- "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
- "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
- "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
- "111": "NOT_ALIVE",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
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": "NON_PARTICIPATING",
@@ -31,7 +31,7 @@
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
- "125": "NON_PARTICIPATING",
35
  "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
@@ -40,22 +40,22 @@
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": "NOT_ALIVE",
48
- "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
- "14": "SUCCESS",
51
  "140": "NOT_ALIVE",
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": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NON_PARTICIPATING",
@@ -65,54 +65,54 @@
65
  "153": "SUCCESS",
66
  "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
- "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NON_PARTICIPATING",
73
- "160": "NOT_ALIVE",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
- "164": "NON_PARTICIPATING",
78
- "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
- "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
- "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
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": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "SUCCESS",
99
- "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
118
  "200": "NOT_ALIVE",
@@ -131,34 +131,34 @@
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
- "215": "SUCCESS",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
- "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
142
- "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
- "225": "NON_PARTICIPATING",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
- "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
- "233": "NOT_ALIVE",
155
- "234": "NOT_ALIVE",
156
- "235": "NOT_ALIVE",
157
- "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
- "238": "SUCCESS",
160
- "239": "NOT_ALIVE",
161
- "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
@@ -172,59 +172,59 @@
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
- "252": "NOT_ALIVE",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
- "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
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": "SUCCESS",
193
- "39": "SUCCESS",
194
  "4": "NON_PARTICIPATING",
195
  "40": "NON_PARTICIPATING",
196
  "41": "SUCCESS",
197
  "42": "NON_PARTICIPATING",
198
- "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
- "5": "NON_PARTICIPATING",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
- "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
- "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NON_PARTICIPATING",
217
- "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
- "62": "SUCCESS",
220
- "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
- "65": "NON_PARTICIPATING",
223
- "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
- "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
- "7": "NON_PARTICIPATING",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
@@ -232,14 +232,14 @@
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": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
@@ -248,14 +248,14 @@
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
- "91": "NON_PARTICIPATING",
252
- "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
- "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
- "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
- "98": "NON_PARTICIPATING",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5946310,
268
- 5946323
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": 45,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5945066,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
5
  "1": "NON_PARTICIPATING",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
+ "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
+ "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
  "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
+ "111": "NON_PARTICIPATING",
20
+ "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
 
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
 
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NON_PARTICIPATING",
43
+ "133": "SUCCESS",
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": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "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": "NON_PARTICIPATING",
 
65
  "153": "SUCCESS",
66
  "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
+ "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NON_PARTICIPATING",
73
+ "160": "NON_PARTICIPATING",
74
+ "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
+ "164": "SUCCESS",
78
+ "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
+ "172": "SUCCESS",
87
+ "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
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": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
+ "183": "NON_PARTICIPATING",
99
+ "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
+ "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
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": "NON_PARTICIPATING",
118
  "200": "NOT_ALIVE",
 
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",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
142
+ "222": "NOT_ALIVE",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
+ "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
+ "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
+ "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
+ "235": "NON_PARTICIPATING",
157
+ "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
+ "239": "NON_PARTICIPATING",
161
+ "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
 
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
+ "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
+ "28": "NON_PARTICIPATING",
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": "NOT_ALIVE",
190
+ "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NON_PARTICIPATING",
195
  "40": "NON_PARTICIPATING",
196
  "41": "SUCCESS",
197
  "42": "NON_PARTICIPATING",
198
+ "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "SUCCESS",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
+ "53": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
+ "56": "SUCCESS",
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",
220
+ "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
+ "65": "NOT_ALIVE",
223
+ "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
+ "7": "FAIL",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
 
232
  "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
+ "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
+ "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
 
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
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": "NOT_ALIVE",
257
  "97": "NON_PARTICIPATING",
258
+ "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5946426,
268
+ 5946443
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": 5946293,
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 sha256:8855382fcf0e82476ca96789665a343784a80ff518885fe5ac9f96fd898d8d7b
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67203f494303f28862aa80490b1b7a75380df8acf12ee5a28aae04d8d68c4584
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06b00412090f779474d5a0e8343007723bc67df323dbdde96f073e38bb70e718
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea80f5ecc996a3f0960008419250181d0935b525c5d9ce1a4c6b396f13e08c93
3
  size 4400216536