ncaagcc commited on
Commit
996ef0c
·
verified ·
1 Parent(s): 7aee544

Run 5. Outer Step 108. 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
@@ -7,8 +7,8 @@
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
- "103": "NOT_ALIVE",
11
- "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
@@ -24,9 +24,9 @@
24
  "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
- "119": "NON_PARTICIPATING",
28
- "12": "NON_PARTICIPATING",
29
- "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
@@ -40,12 +40,12 @@
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": "SUCCESS",
47
- "137": "NOT_ALIVE",
48
- "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "SUCCESS",
51
  "140": "NOT_ALIVE",
@@ -55,7 +55,7 @@
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": "NOT_ALIVE",
@@ -64,26 +64,26 @@
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
  "154": "SUCCESS",
67
- "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
- "157": "NOT_ALIVE",
70
- "158": "NON_PARTICIPATING",
71
- "159": "SUCCESS",
72
- "16": "NOT_ALIVE",
73
- "160": "NOT_ALIVE",
74
- "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
- "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
- "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
- "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
- "172": "NOT_ALIVE",
87
  "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
@@ -95,26 +95,26 @@
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
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": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
- "196": "NON_PARTICIPATING",
113
- "197": "SUCCESS",
114
- "198": "NON_PARTICIPATING",
115
- "199": "NON_PARTICIPATING",
116
- "2": "NOT_ALIVE",
117
- "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
@@ -129,10 +129,10 @@
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
- "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
- "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
@@ -153,84 +153,84 @@
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
- "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
- "237": "SUCCESS",
159
- "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
- "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NOT_ALIVE",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
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": "NOT_ALIVE",
175
- "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
- "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
- "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "SUCCESS",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
- "38": "NON_PARTICIPATING",
193
- "39": "NOT_ALIVE",
194
  "4": "NON_PARTICIPATING",
195
  "40": "NON_PARTICIPATING",
196
- "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
- "44": "NOT_ALIVE",
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": "NOT_ALIVE",
209
- "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
- "56": "NON_PARTICIPATING",
213
- "57": "NOT_ALIVE",
214
- "58": "NON_PARTICIPATING",
215
  "59": "SUCCESS",
216
  "6": "NON_PARTICIPATING",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
- "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
- "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
- "68": "NON_PARTICIPATING",
226
  "69": "NOT_ALIVE",
227
- "7": "NOT_ALIVE",
228
- "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
- "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
@@ -244,17 +244,17 @@
244
  "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
- "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
- "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
- "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NOT_ALIVE"
260
  },
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5966018,
268
- 5966032
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": 40,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5964830,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
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",
 
24
  "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
+ "119": "NOT_ALIVE",
28
+ "12": "NOT_ALIVE",
29
+ "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
 
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NON_PARTICIPATING",
43
+ "133": "NOT_ALIVE",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "SUCCESS",
47
+ "137": "NON_PARTICIPATING",
48
+ "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "SUCCESS",
51
  "140": "NOT_ALIVE",
 
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": "NOT_ALIVE",
 
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
  "154": "SUCCESS",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
+ "157": "NON_PARTICIPATING",
70
+ "158": "NOT_ALIVE",
71
+ "159": "NON_PARTICIPATING",
72
+ "16": "NON_PARTICIPATING",
73
+ "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
+ "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
+ "168": "NOT_ALIVE",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
+ "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
+ "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
 
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": "NON_PARTICIPATING",
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": "NOT_ALIVE",
113
+ "197": "NON_PARTICIPATING",
114
+ "198": "NOT_ALIVE",
115
+ "199": "NOT_ALIVE",
116
+ "2": "NON_PARTICIPATING",
117
+ "20": "NON_PARTICIPATING",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
 
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": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
 
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
+ "237": "FAIL",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
+ "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
  "241": "NOT_ALIVE",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NON_PARTICIPATING",
168
+ "246": "NOT_ALIVE",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
+ "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
+ "26": "NOT_ALIVE",
180
  "27": "SUCCESS",
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": "SUCCESS",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
+ "38": "SUCCESS",
193
+ "39": "NON_PARTICIPATING",
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": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
+ "53": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
+ "56": "FAIL",
213
+ "57": "NON_PARTICIPATING",
214
+ "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
  "6": "NON_PARTICIPATING",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
+ "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
+ "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
227
+ "7": "NON_PARTICIPATING",
228
+ "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
+ "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
 
244
  "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
+ "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
+ "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
+ "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NOT_ALIVE"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5966107,
268
+ 5966122
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": 5966042,
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 sha256:2e04d9a0887407f4259eef368ea396d5a7fb516be96f12ca6e8088c6f550b123
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c6f138062e60f03b17473800d6f2f34e8e371602b3b67e02a3b8ce391027d00
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cf407c095fbd609f824e7d48fe26bf383747cab77f5f90e97847652c65cbdfd
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0aa347761e958cb2cc66cf0209c6fd73a708e31c16a7d8d1807d68e4dc3999b
3
  size 4400216536