thieu86 commited on
Commit
548c4ea
·
verified ·
1 Parent(s): c905df4

Run 5. Outer Step 100. 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
@@ -3,51 +3,51 @@
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
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": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
- "11": "FAIL",
18
- "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "FAIL",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NOT_ALIVE",
25
  "117": "FAIL",
26
  "118": "NOT_ALIVE",
27
- "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
33
  "124": "NOT_ALIVE",
34
- "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
- "129": "NON_PARTICIPATING",
39
  "13": "NON_PARTICIPATING",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NON_PARTICIPATING",
43
- "133": "FAIL",
44
  "134": "NON_PARTICIPATING",
45
- "135": "NON_PARTICIPATING",
46
- "136": "NON_PARTICIPATING",
47
  "137": "SUCCESS",
48
- "138": "FAIL",
49
  "139": "NON_PARTICIPATING",
50
- "14": "SUCCESS",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
@@ -57,45 +57,45 @@
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
- "149": "NOT_ALIVE",
61
- "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "FAIL",
66
- "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NOT_ALIVE",
71
- "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
- "164": "FAIL",
78
  "165": "FAIL",
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": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
- "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "SUCCESS",
99
  "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
@@ -110,17 +110,17 @@
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": "NOT_ALIVE",
117
  "20": "NON_PARTICIPATING",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
- "204": "NON_PARTICIPATING",
123
- "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
@@ -131,9 +131,9 @@
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
- "215": "FAIL",
135
  "216": "NON_PARTICIPATING",
136
- "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
@@ -146,9 +146,9 @@
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
- "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
- "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
@@ -156,17 +156,17 @@
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
- "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
- "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
- "244": "NON_PARTICIPATING",
167
- "245": "NON_PARTICIPATING",
168
  "246": "NOT_ALIVE",
169
- "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
@@ -178,7 +178,7 @@
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
- "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
  "30": "NOT_ALIVE",
@@ -186,62 +186,62 @@
186
  "32": "FAIL",
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": "FAIL",
194
- "4": "NOT_ALIVE",
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": "NOT_ALIVE",
203
- "48": "NOT_ALIVE",
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": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
- "56": "FAIL",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
- "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
- "63": "FAIL",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
- "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
- "68": "SUCCESS",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
- "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
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": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
- "84": "NON_PARTICIPATING",
244
- "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
@@ -249,7 +249,7 @@
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
- "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5953152,
268
- 5953180
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": 33,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5951984,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NON_PARTICIPATING",
6
+ "10": "NOT_ALIVE",
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",
15
  "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
+ "11": "NON_PARTICIPATING",
18
+ "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
  "112": "FAIL",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NON_PARTICIPATING",
25
  "117": "FAIL",
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",
33
  "124": "NOT_ALIVE",
34
+ "125": "NON_PARTICIPATING",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
+ "129": "NOT_ALIVE",
39
  "13": "NON_PARTICIPATING",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NON_PARTICIPATING",
43
+ "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
+ "135": "NOT_ALIVE",
46
+ "136": "SUCCESS",
47
  "137": "SUCCESS",
48
+ "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
+ "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
 
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
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": "NOT_ALIVE",
66
+ "154": "SUCCESS",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NON_PARTICIPATING",
71
+ "159": "FAIL",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
+ "164": "NON_PARTICIPATING",
78
  "165": "FAIL",
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": "SUCCESS",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
+ "179": "NOT_ALIVE",
94
  "18": "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": "NON_PARTICIPATING",
 
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
113
+ "197": "SUCCESS",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
+ "2": "NON_PARTICIPATING",
117
  "20": "NON_PARTICIPATING",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
+ "204": "NOT_ALIVE",
123
+ "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
 
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
+ "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
 
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
+ "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
 
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
+ "238": "FAIL",
160
  "239": "NOT_ALIVE",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
+ "244": "NOT_ALIVE",
167
+ "245": "SUCCESS",
168
  "246": "NOT_ALIVE",
169
+ "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
 
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
+ "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
  "30": "NOT_ALIVE",
 
186
  "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
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": "SUCCESS",
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": "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": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
+ "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
+ "68": "NOT_ALIVE",
226
+ "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
238
+ "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
+ "84": "NOT_ALIVE",
244
+ "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
 
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
+ "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5953280,
268
+ 5953356
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": 5953208,
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 sha256:8ac55ad5a94d35e041b1df8da1868506bbcdf9c57fe44f087dd19a3b26ff2530
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a082268eda0a262765ba16cb28eb0147521eb214c0968cf3df81a5dc1c02202a
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a04886ed7aa5978fae9a0401dfa1a6005c6168179af9f665512bedd3cd45eddf
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c4279aa08fc44987a8ba9cc231e83d9377f5a1a4ed47563564f496ef8265194
3
  size 4400216536