ncaagcc commited on
Commit
e968506
·
verified ·
1 Parent(s): ad2c9f5

Run 8. Outer Step 40. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +73 -73
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -5,12 +5,12 @@
5
  "1": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "FAIL",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
  "105": "SUCCESS",
13
- "106": "FAIL",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
@@ -28,121 +28,121 @@
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "FAIL",
31
- "122": "FAIL",
32
- "123": "FAIL",
33
- "124": "SUCCESS",
34
  "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
- "128": "FAIL",
38
- "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
- "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
- "132": "SUCCESS",
43
  "133": "SUCCESS",
44
- "134": "SUCCESS",
45
  "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "SUCCESS",
49
- "139": "NOT_ALIVE",
50
  "14": "SUCCESS",
51
  "140": "FAIL",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
  "143": "FAIL",
55
- "144": "FAIL",
56
- "145": "FAIL",
57
  "146": "SUCCESS",
58
  "147": "SUCCESS",
59
- "148": "SUCCESS",
60
  "149": "SUCCESS",
61
  "15": "SUCCESS",
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "FAIL",
66
- "154": "NON_PARTICIPATING",
67
- "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "FAIL",
71
- "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
  "160": "NOT_ALIVE",
74
  "161": "FAIL",
75
  "162": "NOT_ALIVE",
76
- "163": "SUCCESS",
77
- "164": "NOT_ALIVE",
78
  "165": "FAIL",
79
  "166": "SUCCESS",
80
  "167": "NON_PARTICIPATING",
81
  "168": "FAIL",
82
- "169": "FAIL",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
- "173": "SUCCESS",
88
- "174": "FAIL",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
- "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
- "180": "NOT_ALIVE",
96
  "181": "FAIL",
97
  "182": "NOT_ALIVE",
98
- "183": "SUCCESS",
99
  "184": "NOT_ALIVE",
100
- "185": "FAIL",
101
- "186": "SUCCESS",
102
  "187": "SUCCESS",
103
- "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "SUCCESS",
108
  "192": "SUCCESS",
109
- "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
111
- "195": "SUCCESS",
112
- "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
- "199": "FAIL",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "SUCCESS",
122
- "204": "SUCCESS",
123
- "205": "SUCCESS",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "SUCCESS",
127
  "209": "FAIL",
128
- "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
- "211": "NON_PARTICIPATING",
131
- "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
- "214": "NON_PARTICIPATING",
134
  "215": "SUCCESS",
135
  "216": "SUCCESS",
136
- "217": "SUCCESS",
137
  "218": "FAIL",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
- "221": "NON_PARTICIPATING",
142
- "222": "SUCCESS",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
- "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
@@ -154,31 +154,31 @@
154
  "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
- "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "FAIL",
161
  "24": "SUCCESS",
162
- "240": "FAIL",
163
- "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
- "245": "NOT_ALIVE",
168
- "246": "SUCCESS",
169
- "247": "FAIL",
170
  "248": "NOT_ALIVE",
171
- "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
- "252": "SUCCESS",
176
- "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
- "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
@@ -189,17 +189,17 @@
189
  "35": "FAIL",
190
  "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
- "38": "FAIL",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "SUCCESS",
197
  "42": "NOT_ALIVE",
198
- "43": "NON_PARTICIPATING",
199
- "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
- "46": "SUCCESS",
202
- "47": "FAIL",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
  "5": "FAIL",
@@ -212,7 +212,7 @@
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
- "59": "FAIL",
216
  "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
@@ -222,9 +222,9 @@
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
- "68": "NOT_ALIVE",
226
- "69": "FAIL",
227
- "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
@@ -243,7 +243,7 @@
243
  "84": "FAIL",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
- "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
@@ -254,8 +254,8 @@
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
- "97": "NOT_ALIVE",
258
- "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,18 +264,18 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6361388,
268
- 6361401,
269
- 6361414
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
- "inner_step": 78,
277
  "intermediate_size": 5632,
278
- "last_allreduce_block": 6360880,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
 
5
  "1": "SUCCESS",
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": "SUCCESS",
13
+ "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
 
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "FAIL",
31
+ "122": "NON_PARTICIPATING",
32
+ "123": "SUCCESS",
33
+ "124": "FAIL",
34
  "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
+ "128": "SUCCESS",
38
+ "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
+ "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "FAIL",
43
  "133": "SUCCESS",
44
+ "134": "NOT_ALIVE",
45
  "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "FAIL",
49
+ "139": "SUCCESS",
50
  "14": "SUCCESS",
51
  "140": "FAIL",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
  "143": "FAIL",
55
+ "144": "SUCCESS",
56
+ "145": "SUCCESS",
57
  "146": "SUCCESS",
58
  "147": "SUCCESS",
59
+ "148": "NON_PARTICIPATING",
60
  "149": "SUCCESS",
61
  "15": "SUCCESS",
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "FAIL",
66
+ "154": "NOT_ALIVE",
67
+ "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "SUCCESS",
71
+ "159": "NOT_ALIVE",
72
  "16": "SUCCESS",
73
  "160": "NOT_ALIVE",
74
  "161": "FAIL",
75
  "162": "NOT_ALIVE",
76
+ "163": "FAIL",
77
+ "164": "NON_PARTICIPATING",
78
  "165": "FAIL",
79
  "166": "SUCCESS",
80
  "167": "NON_PARTICIPATING",
81
  "168": "FAIL",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "FAIL",
88
+ "174": "NON_PARTICIPATING",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
+ "177": "FAIL",
92
  "178": "NON_PARTICIPATING",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
  "181": "FAIL",
97
  "182": "NOT_ALIVE",
98
+ "183": "FAIL",
99
  "184": "NOT_ALIVE",
100
+ "185": "SUCCESS",
101
+ "186": "NON_PARTICIPATING",
102
  "187": "SUCCESS",
103
+ "188": "FAIL",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "SUCCESS",
108
  "192": "SUCCESS",
109
+ "193": "SUCCESS",
110
  "194": "SUCCESS",
111
+ "195": "FAIL",
112
+ "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "FAIL",
122
+ "204": "FAIL",
123
+ "205": "FAIL",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "SUCCESS",
127
  "209": "FAIL",
128
+ "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "FAIL",
131
+ "212": "FAIL",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "SUCCESS",
134
  "215": "SUCCESS",
135
  "216": "SUCCESS",
136
+ "217": "FAIL",
137
  "218": "FAIL",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
+ "220": "FAIL",
141
+ "221": "FAIL",
142
+ "222": "FAIL",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "FAIL",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
 
154
  "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
+ "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "FAIL",
161
  "24": "SUCCESS",
162
+ "240": "SUCCESS",
163
+ "241": "FAIL",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
+ "245": "NON_PARTICIPATING",
168
+ "246": "NON_PARTICIPATING",
169
+ "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
+ "249": "FAIL",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
+ "252": "FAIL",
176
+ "253": "FAIL",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
+ "28": "FAIL",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
 
189
  "35": "FAIL",
190
  "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
+ "38": "SUCCESS",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "SUCCESS",
197
  "42": "NOT_ALIVE",
198
+ "43": "FAIL",
199
+ "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
+ "46": "FAIL",
202
+ "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
  "5": "FAIL",
 
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
+ "59": "SUCCESS",
216
  "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
 
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
+ "68": "NON_PARTICIPATING",
226
+ "69": "SUCCESS",
227
+ "7": "FAIL",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
 
243
  "84": "FAIL",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
+ "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
 
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
+ "97": "FAIL",
258
+ "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6361572,
268
+ 6361589,
269
+ 6361602
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
+ "inner_step": 4,
277
  "intermediate_size": 5632,
278
+ "last_allreduce_block": 6361535,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cba48f74d07fcd24c95677b9f59b93a7d562350b9112a92bca82507c4611bd9a
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ea1d9e73ad06e449a52178ee6ab6bdd482a27ab3fa775d452cece0929b375a
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff6ad9f14e87e1e49e1a1a37e513894a660d8eb437b45fe5478255f136f0f90c
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62e1ff0f5d8c7d02281732d050df1e9514a05aacc4a9a9db55d2432d6cefc330
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cc7bc4d7df35e76374d51b6fb6bb72b728011ee94f2133625a4a566acc16ce4
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38ff6c72bcf2ef4eabaf2111674919d953ffddd003b61c37ac7b3faf4c1d8852
3
  size 4400216536