ShinyUser commited on
Commit
6f99c0b
·
verified ·
1 Parent(s): 7323693

Run 11. Outer Step 214. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +54 -54
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -7,35 +7,35 @@
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
- "103": "FAIL",
11
  "104": "NON_PARTICIPATING",
12
- "105": "SUCCESS",
13
- "106": "SUCCESS",
14
- "107": "NON_PARTICIPATING",
15
- "108": "SUCCESS",
16
  "109": "FAIL",
17
  "11": "NOT_ALIVE",
18
- "110": "NON_PARTICIPATING",
19
- "111": "SUCCESS",
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
  "115": "SUCCESS",
24
- "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
- "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
- "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
- "127": "SUCCESS",
37
- "128": "NOT_ALIVE",
38
- "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
@@ -46,23 +46,23 @@
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
- "139": "FAIL",
50
  "14": "NON_PARTICIPATING",
51
- "140": "NOT_ALIVE",
52
  "141": "SUCCESS",
53
  "142": "NOT_ALIVE",
54
  "143": "FAIL",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
- "146": "NOT_ALIVE",
58
- "147": "SUCCESS",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
@@ -72,19 +72,19 @@
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
- "162": "SUCCESS",
76
  "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
82
- "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
- "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
@@ -96,9 +96,9 @@
96
  "181": "NOT_ALIVE",
97
  "182": "SUCCESS",
98
  "183": "NOT_ALIVE",
99
- "184": "SUCCESS",
100
- "185": "NOT_ALIVE",
101
- "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
@@ -106,13 +106,13 @@
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
- "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
- "195": "SUCCESS",
112
  "196": "NOT_ALIVE",
113
- "197": "SUCCESS",
114
  "198": "NOT_ALIVE",
115
- "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
@@ -126,10 +126,10 @@
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
- "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
@@ -143,19 +143,19 @@
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
- "226": "SUCCESS",
147
  "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
- "234": "SUCCESS",
156
- "235": "NOT_ALIVE",
157
- "236": "NON_PARTICIPATING",
158
- "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
@@ -164,15 +164,15 @@
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "SUCCESS",
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": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
@@ -189,11 +189,11 @@
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
192
- "38": "FAIL",
193
  "39": "NOT_ALIVE",
194
  "4": "NON_PARTICIPATING",
195
  "40": "NOT_ALIVE",
196
- "41": "SUCCESS",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
@@ -204,7 +204,7 @@
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
- "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
@@ -214,7 +214,7 @@
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": "NON_PARTICIPATING",
@@ -222,11 +222,11 @@
222
  "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
- "68": "SUCCESS",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
- "71": "SUCCESS",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
@@ -238,9 +238,9 @@
238
  "8": "SUCCESS",
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
- "82": "NOT_ALIVE",
242
- "83": "SUCCESS",
243
- "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
@@ -251,10 +251,10 @@
251
  "91": "NON_PARTICIPATING",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
- "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
- "97": "SUCCESS",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6664450,
268
- 6664475
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": 53,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6664151,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
+ "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
+ "105": "FAIL",
13
+ "106": "FAIL",
14
+ "107": "NOT_ALIVE",
15
+ "108": "FAIL",
16
  "109": "FAIL",
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": "SUCCESS",
24
+ "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
+ "119": "FAIL",
28
  "12": "NOT_ALIVE",
29
+ "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
+ "127": "NON_PARTICIPATING",
37
+ "128": "NON_PARTICIPATING",
38
+ "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
 
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
+ "140": "SUCCESS",
52
  "141": "SUCCESS",
53
  "142": "NOT_ALIVE",
54
  "143": "FAIL",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "NON_PARTICIPATING",
58
+ "147": "FAIL",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "FAIL",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
 
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
+ "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
+ "173": "FAIL",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
 
96
  "181": "NOT_ALIVE",
97
  "182": "SUCCESS",
98
  "183": "NOT_ALIVE",
99
+ "184": "NON_PARTICIPATING",
100
+ "185": "SUCCESS",
101
+ "186": "NON_PARTICIPATING",
102
  "187": "SUCCESS",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
 
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
+ "193": "FAIL",
110
  "194": "NOT_ALIVE",
111
+ "195": "FAIL",
112
  "196": "NOT_ALIVE",
113
+ "197": "FAIL",
114
  "198": "NOT_ALIVE",
115
+ "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
 
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
+ "210": "NOT_ALIVE",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
+ "213": "NOT_ALIVE",
133
  "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
 
143
  "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
+ "226": "FAIL",
147
  "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
+ "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
+ "234": "NOT_ALIVE",
156
+ "235": "NON_PARTICIPATING",
157
+ "236": "SUCCESS",
158
+ "237": "NOT_ALIVE",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
 
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "FAIL",
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": "NON_PARTICIPATING",
175
+ "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
 
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
  "4": "NON_PARTICIPATING",
195
  "40": "NOT_ALIVE",
196
+ "41": "FAIL",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
 
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
+ "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
 
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
 
222
  "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
+ "68": "FAIL",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
+ "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
 
238
  "8": "SUCCESS",
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
+ "82": "NON_PARTICIPATING",
242
+ "83": "FAIL",
243
+ "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
 
251
  "91": "NON_PARTICIPATING",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
+ "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6664560,
268
+ 6664578
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": 6664526,
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 sha256:38597b79be6f0b70b58dfa8b433463a6dc1b05e4a6815bd3def967297cc8d196
3
  size 88390091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5a10f81c763ba93b8e53410e10405cd0d5ea396c81d90bb431f326c52442274
3
  size 88390091
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bd1152581edc44202cecf56f394f85d62e6d38ce5da335ed8dc418c75c402d2
3
  size 4924928111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6b9b0e5a8dd3228d62e70e46136b120e80f3c5fa330e03dd94e5e29478fa0e8
3
  size 4924928111
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7dd491431703538d30c9ab2643e2e58408f36a7d02c8872c6088b4908871411
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb38f82b3314da3e2da5d32cd30c7acf1a4b0ec822a48ff129fb7c9f5c3f9d88
3
  size 4400216536