MBA4215 commited on
Commit
1d11f7a
·
verified ·
1 Parent(s): b4e8d94

Run 5. Outer Step 62. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +62 -62
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -5,11 +5,11 @@
5
  "1": "NON_PARTICIPATING",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
- "103": "SUCCESS",
11
  "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
@@ -26,13 +26,13 @@
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
- "120": "NON_PARTICIPATING",
30
- "121": "NON_PARTICIPATING",
31
  "122": "SUCCESS",
32
- "123": "SUCCESS",
33
  "124": "SUCCESS",
34
  "125": "NON_PARTICIPATING",
35
- "126": "NON_PARTICIPATING",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
@@ -41,16 +41,16 @@
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
- "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
- "139": "NOT_ALIVE",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "SUCCESS",
53
- "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
@@ -61,7 +61,7 @@
61
  "15": "NON_PARTICIPATING",
62
  "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
- "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
  "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
@@ -71,22 +71,22 @@
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NOT_ALIVE",
75
- "162": "NOT_ALIVE",
76
  "163": "NOT_ALIVE",
77
  "164": "SUCCESS",
78
- "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
- "169": "NOT_ALIVE",
83
- "17": "NOT_ALIVE",
84
- "170": "NOT_ALIVE",
85
  "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "SUCCESS",
89
- "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
@@ -102,22 +102,22 @@
102
  "187": "SUCCESS",
103
  "188": "NON_PARTICIPATING",
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": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NOT_ALIVE",
115
  "199": "NON_PARTICIPATING",
116
- "2": "NON_PARTICIPATING",
117
- "20": "NON_PARTICIPATING",
118
- "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
- "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
@@ -131,7 +131,7 @@
131
  "212": "NOT_ALIVE",
132
  "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
- "215": "SUCCESS",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
@@ -140,12 +140,12 @@
140
  "220": "SUCCESS",
141
  "221": "SUCCESS",
142
  "222": "NON_PARTICIPATING",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
- "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
  "227": "SUCCESS",
148
- "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
@@ -158,7 +158,7 @@
158
  "237": "NOT_ALIVE",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
- "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NOT_ALIVE",
164
  "242": "SUCCESS",
@@ -168,43 +168,43 @@
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": "NOT_ALIVE",
175
- "252": "NON_PARTICIPATING",
176
- "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
- "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
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": "SUCCESS",
189
  "35": "NOT_ALIVE",
190
- "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "SUCCESS",
193
  "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
- "40": "NOT_ALIVE",
196
  "41": "SUCCESS",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
- "46": "NOT_ALIVE",
202
- "47": "NON_PARTICIPATING",
203
  "48": "SUCCESS",
204
  "49": "NOT_ALIVE",
205
- "5": "NON_PARTICIPATING",
206
- "50": "NON_PARTICIPATING",
207
- "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NOT_ALIVE",
210
  "54": "SUCCESS",
@@ -213,27 +213,27 @@
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
- "6": "NON_PARTICIPATING",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
- "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
- "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
- "68": "NON_PARTICIPATING",
226
  "69": "SUCCESS",
227
  "7": "SUCCESS",
228
- "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NON_PARTICIPATING",
231
  "73": "SUCCESS",
232
  "74": "SUCCESS",
233
- "75": "SUCCESS",
234
- "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
- "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
@@ -249,14 +249,14 @@
249
  "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
  "91": "NON_PARTICIPATING",
252
- "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
  "98": "SUCCESS",
259
- "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5901981,
268
- 5902010
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": 22,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5900841,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
5
  "1": "NON_PARTICIPATING",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
+ "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
+ "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
 
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
+ "120": "NOT_ALIVE",
30
+ "121": "NOT_ALIVE",
31
  "122": "SUCCESS",
32
+ "123": "NOT_ALIVE",
33
  "124": "SUCCESS",
34
  "125": "NON_PARTICIPATING",
35
+ "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
 
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
+ "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
  "136": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "SUCCESS",
53
+ "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
 
61
  "15": "NON_PARTICIPATING",
62
  "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
+ "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
  "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
 
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
+ "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "SUCCESS",
78
+ "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
+ "169": "NON_PARTICIPATING",
83
+ "17": "NON_PARTICIPATING",
84
+ "170": "NON_PARTICIPATING",
85
  "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "SUCCESS",
89
+ "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
 
102
  "187": "SUCCESS",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
+ "19": "NON_PARTICIPATING",
106
+ "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
+ "192": "SUCCESS",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NOT_ALIVE",
115
  "199": "NON_PARTICIPATING",
116
+ "2": "NOT_ALIVE",
117
+ "20": "NOT_ALIVE",
118
+ "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
+ "202": "NOT_ALIVE",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
 
131
  "212": "NOT_ALIVE",
132
  "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
 
140
  "220": "SUCCESS",
141
  "221": "SUCCESS",
142
  "222": "NON_PARTICIPATING",
143
+ "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
+ "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
  "227": "SUCCESS",
148
+ "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
 
158
  "237": "NOT_ALIVE",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
+ "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NOT_ALIVE",
164
  "242": "SUCCESS",
 
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
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": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
+ "27": "SUCCESS",
181
  "28": "SUCCESS",
182
+ "29": "NOT_ALIVE",
183
+ "3": "NON_PARTICIPATING",
184
+ "30": "NOT_ALIVE",
185
  "31": "NON_PARTICIPATING",
186
+ "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
  "35": "NOT_ALIVE",
190
+ "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "SUCCESS",
193
  "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
  "41": "SUCCESS",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NON_PARTICIPATING",
202
+ "47": "NOT_ALIVE",
203
  "48": "SUCCESS",
204
  "49": "NOT_ALIVE",
205
+ "5": "NOT_ALIVE",
206
+ "50": "NOT_ALIVE",
207
+ "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NOT_ALIVE",
210
  "54": "SUCCESS",
 
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
+ "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
+ "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NON_PARTICIPATING",
225
+ "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
  "7": "SUCCESS",
228
+ "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "SUCCESS",
233
+ "75": "NOT_ALIVE",
234
+ "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
+ "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
 
249
  "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
  "91": "NON_PARTICIPATING",
252
+ "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
  "98": "SUCCESS",
259
+ "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5902080,
268
+ 5902145
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": 5901986,
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:b9fc580deba311744fcc24e730ee85e2e5be9baf7b851f5beed71cfebbf07bd3
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6610d5b93d8a6e0dcbab0d1cad510e1043622c6489bbaf85b4df72564a201f4
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40678224aa6b1903629f55d9ace475dce13e45d5e0eb6e70c2ac2957bc0c306d
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ae97a068ff313f4d4c5f3646f3140d985b563270431d8bbac5d107d0c35180
3
  size 4400216536