thieu86 commited on
Commit
8cd9da2
·
verified ·
1 Parent(s): 1bb5bf6

Run 5. Outer Step 109. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +68 -68
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -15,20 +15,20 @@
15
  "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
  "11": "NON_PARTICIPATING",
18
- "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
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": "NOT_ALIVE",
29
- "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
- "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
@@ -39,14 +39,14 @@
39
  "13": "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",
52
  "141": "NOT_ALIVE",
@@ -55,36 +55,36 @@
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",
62
- "150": "NON_PARTICIPATING",
63
  "151": "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",
90
  "176": "NOT_ALIVE",
@@ -95,10 +95,10 @@
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",
@@ -109,12 +109,12 @@
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",
@@ -123,7 +123,7 @@
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
- "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
@@ -132,15 +132,15 @@
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",
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",
@@ -155,42 +155,42 @@
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",
@@ -200,44 +200,44 @@
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",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
- "80": "NON_PARTICIPATING",
240
- "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5967229,
268
- 5967272
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": 39,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5966042,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
15
  "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
  "11": "NON_PARTICIPATING",
18
+ "110": "SUCCESS",
19
  "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
+ "116": "NOT_ALIVE",
25
+ "117": "NON_PARTICIPATING",
26
  "118": "NOT_ALIVE",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
+ "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
+ "122": "NOT_ALIVE",
32
  "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
 
39
  "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
+ "132": "SUCCESS",
43
+ "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "SUCCESS",
47
+ "137": "SUCCESS",
48
+ "138": "NOT_ALIVE",
49
+ "139": "NOT_ALIVE",
50
  "14": "SUCCESS",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
 
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",
62
+ "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
+ "154": "NOT_ALIVE",
67
+ "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
+ "158": "NON_PARTICIPATING",
71
+ "159": "SUCCESS",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
+ "164": "NOT_ALIVE",
78
+ "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
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": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
 
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
+ "183": "NOT_ALIVE",
99
+ "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
+ "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
 
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
+ "196": "NON_PARTICIPATING",
113
+ "197": "NOT_ALIVE",
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",
 
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
+ "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
 
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
+ "216": "NON_PARTICIPATING",
136
+ "217": "NOT_ALIVE",
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": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
 
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
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": "NOT_ALIVE",
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": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "SUCCESS",
179
+ "26": "NON_PARTICIPATING",
180
+ "27": "NON_PARTICIPATING",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
+ "30": "SUCCESS",
185
+ "31": "NOT_ALIVE",
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": "NON_PARTICIPATING",
193
+ "39": "SUCCESS",
194
  "4": "NON_PARTICIPATING",
195
  "40": "NON_PARTICIPATING",
196
  "41": "SUCCESS",
 
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
+ "48": "SUCCESS",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "NON_PARTICIPATING",
209
+ "53": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
+ "68": "SUCCESS",
226
  "69": "NOT_ALIVE",
227
+ "7": "SUCCESS",
228
+ "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
+ "73": "NOT_ALIVE",
232
+ "74": "NON_PARTICIPATING",
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": "NOT_ALIVE",
240
+ "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5967360,
268
+ 5967440
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": 5967299,
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 sha256:055114b23d7840270260a6b892a59a08a711c4bc56366ec03d2ea6973f2b511e
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8c3acdf73aa1c36b7621044d5f63386b1880c8ac50297e4754cf40ac0b7e33
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93b7214ff1205f0dfeae4a9369004cbf0a0b5eed2e7264870f3664991ac3e4bb
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3582791c1326386234ae0d2cff3b6e3cc055a9a5b8ccd40b1bb9670a7d8a074
3
  size 4400216536