ShinyUser commited on
Commit
a9147f7
·
verified ·
1 Parent(s): 0671c6a

Run 11. Outer Step 61. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +57 -57
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -10,18 +10,18 @@
10
  "103": "NOT_ALIVE",
11
  "104": "SUCCESS",
12
  "105": "SUCCESS",
13
- "106": "NOT_ALIVE",
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": "NON_PARTICIPATING",
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",
@@ -29,25 +29,25 @@
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
- "123": "SUCCESS",
33
  "124": "SUCCESS",
34
- "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
  "136": "NOT_ALIVE",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
  "139": "SUCCESS",
50
- "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
@@ -66,43 +66,43 @@
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
- "157": "NOT_ALIVE",
70
  "158": "SUCCESS",
71
  "159": "SUCCESS",
72
  "16": "SUCCESS",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NOT_ALIVE",
75
- "162": "NOT_ALIVE",
76
- "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
- "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
  "168": "SUCCESS",
82
- "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
- "18": "SUCCESS",
95
- "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "NOT_ALIVE",
99
- "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
- "188": "NOT_ALIVE",
104
  "189": "NON_PARTICIPATING",
105
- "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
@@ -110,7 +110,7 @@
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
  "196": "NON_PARTICIPATING",
113
- "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
@@ -121,14 +121,14 @@
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": "SUCCESS",
129
- "210": "SUCCESS",
130
  "211": "NOT_ALIVE",
131
- "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
@@ -138,15 +138,15 @@
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
- "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
- "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
@@ -154,9 +154,9 @@
154
  "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
- "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
159
- "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "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": "SUCCESS",
@@ -187,10 +187,10 @@
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
  "35": "SUCCESS",
190
- "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
- "38": "NOT_ALIVE",
193
- "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
@@ -198,13 +198,13 @@
198
  "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
- "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
- "48": "NON_PARTICIPATING",
204
  "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
- "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
@@ -214,32 +214,32 @@
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "NOT_ALIVE",
218
  "61": "SUCCESS",
219
- "62": "NON_PARTICIPATING",
220
  "63": "NOT_ALIVE",
221
  "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
- "69": "SUCCESS",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "NON_PARTICIPATING",
233
- "75": "NOT_ALIVE",
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": "NOT_ALIVE",
242
- "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
@@ -247,10 +247,10 @@
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "NON_PARTICIPATING",
251
  "91": "SUCCESS",
252
  "92": "SUCCESS",
253
- "93": "SUCCESS",
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
- 6576286,
268
- 6576321
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": 58,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6575861,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
10
  "103": "NOT_ALIVE",
11
  "104": "SUCCESS",
12
  "105": "SUCCESS",
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": "SUCCESS",
20
+ "112": "NOT_ALIVE",
21
+ "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
+ "115": "SUCCESS",
24
+ "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
 
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
+ "123": "NON_PARTICIPATING",
33
  "124": "SUCCESS",
34
+ "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
  "13": "NON_PARTICIPATING",
40
+ "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "NOT_ALIVE",
44
  "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
  "136": "NOT_ALIVE",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
  "139": "SUCCESS",
50
+ "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "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": "SUCCESS",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
+ "162": "NON_PARTICIPATING",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
  "168": "SUCCESS",
82
+ "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
+ "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
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": "NOT_ALIVE",
100
+ "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "NON_PARTICIPATING",
105
+ "19": "NON_PARTICIPATING",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
 
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
  "196": "NON_PARTICIPATING",
113
+ "197": "SUCCESS",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
 
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
+ "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
+ "21": "NON_PARTICIPATING",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
+ "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
 
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
+ "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
 
154
  "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
+ "236": "NOT_ALIVE",
158
  "237": "SUCCESS",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
 
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
+ "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
 
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
  "35": "SUCCESS",
190
+ "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
 
198
  "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
+ "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
+ "48": "SUCCESS",
204
  "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
+ "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
 
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
+ "62": "SUCCESS",
220
  "63": "NOT_ALIVE",
221
  "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
+ "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "NON_PARTICIPATING",
233
+ "75": "SUCCESS",
234
+ "76": "SUCCESS",
235
+ "77": "NON_PARTICIPATING",
236
+ "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
+ "8": "SUCCESS",
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",
 
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "NOT_ALIVE",
251
  "91": "SUCCESS",
252
  "92": "SUCCESS",
253
+ "93": "NON_PARTICIPATING",
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
+ 6576412,
268
+ 6576442
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": 6576346,
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:cae757c444babccb53531f2e8a4ecb1b85d484091cddac39cb42780e2f56bd81
3
  size 88390091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ddcd141b0865ab0a7363904d20551c439951585bae77f0b46fec69d75d4097f
3
  size 88390091
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5827d73854a6f4a4e90d436547debbe0ba0d62543e904465a4b3e6a047cdac3
3
  size 4924928111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ff8afc1a18fe251ecd7560142ed5b0e5ae0f4a152ebd33be12733c64ed9510
3
  size 4924928111
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34a47e53e048c5984708dab3212187d329fafd9754612412f98dfca08761db99
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:442825343dcfa387d4b2345f173ede68cde3b38c6e84d801444965030ca1817f
3
  size 4400216536