ncaagcc commited on
Commit
f8fe67e
·
verified ·
1 Parent(s): a864b44

Run 8. Outer Step 40. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +91 -91
  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": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
  "105": "SUCCESS",
13
- "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
@@ -20,96 +20,96 @@
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
- "115": "SUCCESS",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "SUCCESS",
31
- "122": "FAIL",
32
- "123": "FAIL",
33
  "124": "FAIL",
34
  "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
- "128": "FAIL",
38
- "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
- "130": "SUCCESS",
41
- "131": "NOT_ALIVE",
42
- "132": "SUCCESS",
43
  "133": "SUCCESS",
44
- "134": "FAIL",
45
- "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "SUCCESS",
49
- "139": "FAIL",
50
  "14": "SUCCESS",
51
  "140": "FAIL",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
  "143": "FAIL",
55
  "144": "SUCCESS",
56
- "145": "FAIL",
57
  "146": "SUCCESS",
58
- "147": "NON_PARTICIPATING",
59
- "148": "SUCCESS",
60
  "149": "SUCCESS",
61
  "15": "SUCCESS",
62
- "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "FAIL",
66
- "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "SUCCESS",
71
- "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
- "160": "NON_PARTICIPATING",
74
- "161": "NOT_ALIVE",
75
- "162": "SUCCESS",
76
- "163": "SUCCESS",
77
  "164": "NON_PARTICIPATING",
78
  "165": "FAIL",
79
  "166": "SUCCESS",
80
  "167": "NON_PARTICIPATING",
81
- "168": "NON_PARTICIPATING",
82
- "169": "FAIL",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
- "172": "NOT_ALIVE",
87
- "173": "SUCCESS",
88
- "174": "SUCCESS",
89
- "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
- "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
- "181": "SUCCESS",
97
  "182": "NOT_ALIVE",
98
  "183": "FAIL",
99
  "184": "NOT_ALIVE",
100
- "185": "FAIL",
101
- "186": "SUCCESS",
102
- "187": "FAIL",
103
- "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
- "191": "NON_PARTICIPATING",
108
  "192": "SUCCESS",
109
- "193": "FAIL",
110
- "194": "FAIL",
111
- "195": "SUCCESS",
112
- "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "SUCCESS",
@@ -118,34 +118,34 @@
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "SUCCESS",
122
- "204": "SUCCESS",
123
- "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "SUCCESS",
127
- "209": "NOT_ALIVE",
128
- "21": "FAIL",
129
  "210": "NON_PARTICIPATING",
130
- "211": "SUCCESS",
131
- "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
  "216": "SUCCESS",
136
- "217": "SUCCESS",
137
  "218": "FAIL",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "FAIL",
141
  "221": "FAIL",
142
- "222": "SUCCESS",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
- "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
- "228": "SUCCESS",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "FAIL",
@@ -154,49 +154,49 @@
154
  "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
- "236": "FAIL",
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "FAIL",
161
  "24": "SUCCESS",
162
- "240": "FAIL",
163
  "241": "FAIL",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NON_PARTICIPATING",
168
- "246": "SUCCESS",
169
- "247": "SUCCESS",
170
  "248": "NOT_ALIVE",
171
  "249": "FAIL",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
- "252": "SUCCESS",
176
- "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "FAIL",
180
- "27": "NOT_ALIVE",
181
- "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
- "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "SUCCESS",
190
- "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
- "38": "FAIL",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "FAIL",
197
  "42": "NOT_ALIVE",
198
- "43": "NON_PARTICIPATING",
199
- "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
  "46": "FAIL",
202
  "47": "SUCCESS",
@@ -204,34 +204,34 @@
204
  "49": "NON_PARTICIPATING",
205
  "5": "FAIL",
206
  "50": "NOT_ALIVE",
207
- "51": "NON_PARTICIPATING",
208
- "52": "NOT_ALIVE",
209
- "53": "FAIL",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
- "58": "FAIL",
215
- "59": "FAIL",
216
  "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
- "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
- "69": "NON_PARTICIPATING",
227
- "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
- "74": "FAIL",
233
  "75": "NOT_ALIVE",
234
- "76": "NOT_ALIVE",
235
  "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
  "79": "FAIL",
@@ -240,21 +240,21 @@
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
- "84": "SUCCESS",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "FAIL",
247
- "88": "SUCCESS",
248
- "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "FAIL",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
- "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
- "97": "SUCCESS",
258
  "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
@@ -264,18 +264,18 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6361370,
268
- 6361395,
269
- 6361406
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": 82,
277
  "intermediate_size": 5632,
278
- "last_allreduce_block": 6360216,
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",
 
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
+ "115": "FAIL",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
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",
 
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",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "FAIL",
 
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",
185
  "31": "NON_PARTICIPATING",
186
  "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
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",
 
204
  "49": "NON_PARTICIPATING",
205
  "5": "FAIL",
206
  "50": "NOT_ALIVE",
207
+ "51": "NOT_ALIVE",
208
+ "52": "SUCCESS",
209
+ "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
+ "58": "SUCCESS",
215
+ "59": "SUCCESS",
216
  "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
+ "64": "SUCCESS",
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",
231
  "73": "NOT_ALIVE",
232
+ "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
234
+ "76": "FAIL",
235
  "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
  "79": "FAIL",
 
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "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",
250
  "90": "NOT_ALIVE",
251
  "91": "FAIL",
252
  "92": "NOT_ALIVE",
253
  "93": "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
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6361572,
268
+ 6361589,
269
+ 6361604
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:d0ac02b768683b85c6dce79a16df29c5cb946bc3a713e175d4c9a2da7c31ffed
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a595799ffcd421b21cec4b5d94c70983eda17bec0e3e1e01f85759cbc80bf38
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a859d7d952921d511caeb96650dbdf05d13b05e8c1b88c1887ba6f0ea346f67b
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab568f0b7af0292acd734b4a76c4686a8564d0fcf3307908d38b203982c20f8d
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:507e3cd0bd1de0b560cf52a5ad1926bdcf01bfbc45c1d40a0812be1942d5b168
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5848621b478694699fe39d340db3c1e31c9522e68b96ce5f6ecc381ff4f04b80
3
  size 4400216536