MBA4215 commited on
Commit
dcd974d
·
verified ·
1 Parent(s): a1c6e60

Run 5. Outer Step 76. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +64 -64
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -12,7 +12,7 @@
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
- "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
@@ -21,13 +21,13 @@
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
- "116": "NON_PARTICIPATING",
25
- "117": "NOT_ALIVE",
26
- "118": "NOT_ALIVE",
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",
@@ -39,9 +39,9 @@
39
  "13": "NON_PARTICIPATING",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
- "132": "NON_PARTICIPATING",
43
  "133": "NON_PARTICIPATING",
44
- "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
@@ -49,14 +49,14 @@
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
- "141": "NOT_ALIVE",
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",
62
  "150": "NON_PARTICIPATING",
@@ -64,7 +64,7 @@
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
- "155": "NON_PARTICIPATING",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
@@ -73,57 +73,57 @@
73
  "160": "NON_PARTICIPATING",
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": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
- "172": "NON_PARTICIPATING",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "NON_PARTICIPATING",
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": "SUCCESS",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
- "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
- "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
- "197": "NOT_ALIVE",
114
  "198": "NOT_ALIVE",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
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": "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",
@@ -136,10 +136,10 @@
136
  "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
- "22": "NON_PARTICIPATING",
140
- "220": "NOT_ALIVE",
141
  "221": "NON_PARTICIPATING",
142
- "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
@@ -147,7 +147,7 @@
147
  "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
- "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
@@ -162,54 +162,54 @@
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
- "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
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": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
- "27": "NOT_ALIVE",
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": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
- "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
  "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
- "40": "NOT_ALIVE",
196
  "41": "SUCCESS",
197
  "42": "NON_PARTICIPATING",
198
- "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NOT_ALIVE",
202
- "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
- "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
- "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
@@ -217,46 +217,46 @@
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
- "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
- "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "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": "NOT_ALIVE",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
- "86": "NON_PARTICIPATING",
246
- "87": "NOT_ALIVE",
247
- "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
- "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
- "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
- "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
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
- 5919963,
268
- 5920096
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": 30,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5918862,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
+ "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
 
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
+ "116": "NOT_ALIVE",
25
+ "117": "NON_PARTICIPATING",
26
+ "118": "NON_PARTICIPATING",
27
  "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
+ "120": "NOT_ALIVE",
30
+ "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
 
39
  "13": "NON_PARTICIPATING",
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": "NOT_ALIVE",
 
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
+ "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
+ "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
 
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
+ "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
 
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": "NOT_ALIVE",
80
+ "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
+ "172": "NOT_ALIVE",
87
+ "173": "SUCCESS",
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": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
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": "NON_PARTICIPATING",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
+ "192": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
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": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
 
136
  "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
+ "22": "NOT_ALIVE",
140
+ "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
+ "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
 
147
  "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
+ "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
 
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
+ "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
+ "246": "NOT_ALIVE",
169
  "247": "NON_PARTICIPATING",
170
+ "248": "NOT_ALIVE",
171
+ "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
+ "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
+ "27": "NON_PARTICIPATING",
181
+ "28": "NON_PARTICIPATING",
182
+ "29": "NOT_ALIVE",
183
  "3": "NON_PARTICIPATING",
184
  "30": "SUCCESS",
185
+ "31": "NOT_ALIVE",
186
+ "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
  "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
+ "37": "NON_PARTICIPATING",
192
  "38": "SUCCESS",
193
  "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
  "41": "SUCCESS",
197
  "42": "NON_PARTICIPATING",
198
+ "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NOT_ALIVE",
202
+ "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
+ "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
+ "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
 
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
+ "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
+ "73": "NOT_ALIVE",
232
+ "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
+ "78": "NOT_ALIVE",
237
+ "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
+ "86": "NOT_ALIVE",
246
+ "87": "NON_PARTICIPATING",
247
+ "88": "NOT_ALIVE",
248
  "89": "NON_PARTICIPATING",
249
+ "9": "NON_PARTICIPATING",
250
  "90": "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": "NON_PARTICIPATING",
259
+ "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5920171,
268
+ 5920199
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": 5920032,
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:ee5460d8fa6daea720bb08b3a5baab1facb673605bf08379ace884f9307fab0f
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b80d91cf06181b24f0bda35ddda4a13ba2173f65447e78e676f954ca2ec2a29
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cb079d1efb856c0403b802e7e2318bb4c8654a645d623e7d9a2e2441fb44bd0
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b283e92e2f9180d8bad07a8fa0c06b184ed59954119366c2b09f2b0ff01895b0
3
  size 4400216536