ShinyUser commited on
Commit
8e86133
·
verified ·
1 Parent(s): 9198258

Run 11. Outer Step 70. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +53 -53
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -6,27 +6,27 @@
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
- "102": "SUCCESS",
10
  "103": "NOT_ALIVE",
11
- "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
- "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
- "115": "NOT_ALIVE",
24
- "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
- "118": "NOT_ALIVE",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
- "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
  "123": "NON_PARTICIPATING",
@@ -36,17 +36,17 @@
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
- "13": "NON_PARTICIPATING",
40
  "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
  "134": "SUCCESS",
45
- "135": "FAIL",
46
  "136": "NOT_ALIVE",
47
  "137": "SUCCESS",
48
  "138": "NOT_ALIVE",
49
- "139": "SUCCESS",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
@@ -59,18 +59,18 @@
59
  "148": "NOT_ALIVE",
60
  "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
- "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
- "157": "SUCCESS",
70
  "158": "SUCCESS",
71
  "159": "SUCCESS",
72
- "16": "NON_PARTICIPATING",
73
- "160": "NOT_ALIVE",
74
  "161": "SUCCESS",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
@@ -85,19 +85,19 @@
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
- "174": "NON_PARTICIPATING",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NON_PARTICIPATING",
95
- "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
@@ -108,24 +108,24 @@
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
- "195": "NOT_ALIVE",
112
  "196": "NON_PARTICIPATING",
113
  "197": "SUCCESS",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
- "20": "SUCCESS",
118
- "200": "NOT_ALIVE",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "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",
130
  "211": "NOT_ALIVE",
131
  "212": "SUCCESS",
@@ -138,12 +138,12 @@
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
- "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "SUCCESS",
146
- "226": "SUCCESS",
147
  "227": "NOT_ALIVE",
148
  "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
@@ -152,13 +152,13 @@
152
  "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
- "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
159
- "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
- "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
@@ -167,7 +167,7 @@
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
- "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
@@ -187,10 +187,10 @@
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
  "35": "NOT_ALIVE",
190
- "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
- "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
@@ -200,57 +200,57 @@
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
- "48": "NON_PARTICIPATING",
204
  "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
- "52": "NON_PARTICIPATING",
209
  "53": "SUCCESS",
210
- "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
- "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
- "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
- "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
- "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
- "75": "NOT_ALIVE",
234
- "76": "NOT_ALIVE",
235
- "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
- "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
- "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
- "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "NON_PARTICIPATING",
251
  "91": "SUCCESS",
252
- "92": "SUCCESS",
253
- "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6580346,
268
- 6580376
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
@@ -274,9 +274,9 @@
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
- "inner_step": 45,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6579999,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
+ "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
+ "104": "SUCCESS",
12
+ "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
+ "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
+ "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
  "117": "SUCCESS",
26
+ "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
+ "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
  "123": "NON_PARTICIPATING",
 
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
+ "13": "SUCCESS",
40
  "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
  "134": "SUCCESS",
45
+ "135": "NOT_ALIVE",
46
  "136": "NOT_ALIVE",
47
  "137": "SUCCESS",
48
  "138": "NOT_ALIVE",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
 
59
  "148": "NOT_ALIVE",
60
  "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
+ "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
+ "157": "NON_PARTICIPATING",
70
  "158": "SUCCESS",
71
  "159": "SUCCESS",
72
+ "16": "NOT_ALIVE",
73
+ "160": "NON_PARTICIPATING",
74
  "161": "SUCCESS",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
 
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
+ "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NON_PARTICIPATING",
95
+ "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
+ "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
 
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
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": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
+ "205": "NOT_ALIVE",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
+ "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "SUCCESS",
 
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "SUCCESS",
146
+ "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
  "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
 
152
  "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
+ "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
159
+ "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
+ "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
 
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
+ "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
 
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
  "35": "NOT_ALIVE",
190
+ "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
+ "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
 
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
+ "48": "NOT_ALIVE",
204
  "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "SUCCESS",
209
  "53": "SUCCESS",
210
+ "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
+ "58": "NON_PARTICIPATING",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
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": "NOT_ALIVE",
226
+ "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
+ "75": "NON_PARTICIPATING",
234
+ "76": "SUCCESS",
235
+ "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
+ "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
+ "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
+ "87": "NOT_ALIVE",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "SUCCESS",
251
  "91": "SUCCESS",
252
+ "92": "NON_PARTICIPATING",
253
+ "93": "SUCCESS",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6580461,
268
+ 6580490
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
 
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
+ "inner_step": 9,
278
  "intermediate_size": 5632,
279
+ "last_allreduce_block": 6580399,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3facfabd048d7b8697bc0a524bb588e218d23dfe36a23728ad82c2abe9f46f98
3
  size 88390091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fc345683e8c28c20d6f6826e515f0b053c588b8fa60b4249ecfc778e88896a5
3
  size 88390091
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1065453549ef309076493573ed1a48a036f52d5596ca6255e63efeba7dc87421
3
  size 4924928111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd17ddff151c9f01a3291691e8aa499b8d2d84904641045e923e6883e0b53758
3
  size 4924928111
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03e06bc0e2e42e2332c2189539c15029633ab7e5b3e67f89290c4f4c41268a4c
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:726124a37e36b58c361109abe5e11846d250f0642f8e0ed3281dadb9421ba58d
3
  size 4400216536