ncaagcc commited on
Commit
e084939
·
verified ·
1 Parent(s): 27c87f9

Run 8. Outer Step 75. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +126 -125
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -4,84 +4,84 @@
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
- "100": "NON_PARTICIPATING",
8
- "101": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
- "103": "NON_PARTICIPATING",
11
- "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
- "106": "FAIL",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
- "111": "FAIL",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
- "115": "FAIL",
24
- "116": "NON_PARTICIPATING",
25
- "117": "FAIL",
26
- "118": "FAIL",
27
- "119": "FAIL",
28
  "12": "NOT_ALIVE",
29
- "120": "NON_PARTICIPATING",
30
- "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
- "123": "NOT_ALIVE",
33
- "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
- "126": "NON_PARTICIPATING",
36
  "127": "SUCCESS",
37
  "128": "SUCCESS",
38
- "129": "FAIL",
39
  "13": "SUCCESS",
40
  "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
- "132": "FAIL",
43
  "133": "SUCCESS",
44
- "134": "FAIL",
45
- "135": "FAIL",
46
- "136": "SUCCESS",
47
  "137": "FAIL",
48
- "138": "NOT_ALIVE",
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
- "141": "NON_PARTICIPATING",
53
  "142": "SUCCESS",
54
- "143": "FAIL",
55
  "144": "NON_PARTICIPATING",
56
  "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
- "147": "NON_PARTICIPATING",
59
- "148": "NOT_ALIVE",
60
- "149": "FAIL",
61
  "15": "NOT_ALIVE",
62
- "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
- "154": "SUCCESS",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
- "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
- "160": "NON_PARTICIPATING",
74
- "161": "FAIL",
75
- "162": "FAIL",
76
  "163": "NON_PARTICIPATING",
77
- "164": "FAIL",
78
- "165": "SUCCESS",
79
- "166": "NOT_ALIVE",
80
- "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
- "169": "FAIL",
83
  "17": "NOT_ALIVE",
84
- "170": "SUCCESS",
85
  "171": "SUCCESS",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NOT_ALIVE",
@@ -90,171 +90,171 @@
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
- "179": "SUCCESS",
94
- "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
  "181": "NON_PARTICIPATING",
97
- "182": "SUCCESS",
98
  "183": "SUCCESS",
99
- "184": "SUCCESS",
100
- "185": "SUCCESS",
101
- "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
- "188": "SUCCESS",
104
- "189": "FAIL",
105
  "19": "NOT_ALIVE",
106
- "190": "NON_PARTICIPATING",
107
- "191": "FAIL",
108
- "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
- "195": "SUCCESS",
112
- "196": "FAIL",
113
  "197": "NON_PARTICIPATING",
114
  "198": "SUCCESS",
115
  "199": "SUCCESS",
116
- "2": "SUCCESS",
117
- "20": "NOT_ALIVE",
118
- "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
  "202": "SUCCESS",
121
- "203": "FAIL",
122
- "204": "FAIL",
123
  "205": "SUCCESS",
124
- "206": "NON_PARTICIPATING",
125
- "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
- "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
- "214": "SUCCESS",
134
- "215": "SUCCESS",
135
- "216": "FAIL",
136
  "217": "SUCCESS",
137
- "218": "SUCCESS",
138
- "219": "NON_PARTICIPATING",
139
- "22": "NOT_ALIVE",
140
  "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
- "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
- "225": "SUCCESS",
146
- "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
- "229": "FAIL",
150
- "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
- "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
- "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
- "24": "SUCCESS",
162
- "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
- "244": "SUCCESS",
167
  "245": "SUCCESS",
168
  "246": "SUCCESS",
169
- "247": "FAIL",
170
  "248": "NON_PARTICIPATING",
171
- "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
- "252": "SUCCESS",
176
  "253": "SUCCESS",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
- "26": "FAIL",
180
- "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "NOT_ALIVE",
184
- "30": "NOT_ALIVE",
185
- "31": "NON_PARTICIPATING",
186
  "32": "SUCCESS",
187
- "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
- "35": "SUCCESS",
190
- "36": "FAIL",
191
- "37": "NON_PARTICIPATING",
192
- "38": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "SUCCESS",
196
- "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
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": "NON_PARTICIPATING",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
  "55": "SUCCESS",
212
- "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
- "61": "NON_PARTICIPATING",
219
  "62": "SUCCESS",
220
- "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
- "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "SUCCESS",
226
  "69": "SUCCESS",
227
- "7": "FAIL",
228
  "70": "NOT_ALIVE",
229
- "71": "NON_PARTICIPATING",
230
- "72": "FAIL",
231
  "73": "NON_PARTICIPATING",
232
- "74": "FAIL",
233
- "75": "NON_PARTICIPATING",
234
  "76": "SUCCESS",
235
  "77": "SUCCESS",
236
- "78": "NON_PARTICIPATING",
237
- "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
- "80": "NON_PARTICIPATING",
240
- "81": "NOT_ALIVE",
241
- "82": "SUCCESS",
242
- "83": "FAIL",
243
  "84": "SUCCESS",
244
- "85": "FAIL",
245
- "86": "NOT_ALIVE",
246
  "87": "SUCCESS",
247
- "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "NON_PARTICIPATING",
251
  "91": "NON_PARTICIPATING",
252
- "92": "SUCCESS",
253
- "93": "FAIL",
254
  "94": "NON_PARTICIPATING",
255
  "95": "SUCCESS",
256
- "96": "FAIL",
257
- "97": "SUCCESS",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
@@ -264,17 +264,18 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6396633,
268
- 6396645
 
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
- "inner_step": 169,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6395861,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
+ "100": "NOT_ALIVE",
8
+ "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
+ "103": "SUCCESS",
11
+ "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "SUCCESS",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
+ "115": "SUCCESS",
24
+ "116": "SUCCESS",
25
+ "117": "SUCCESS",
26
+ "118": "NON_PARTICIPATING",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
+ "120": "FAIL",
30
+ "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "SUCCESS",
33
+ "124": "SUCCESS",
34
  "125": "NOT_ALIVE",
35
+ "126": "FAIL",
36
  "127": "SUCCESS",
37
  "128": "SUCCESS",
38
+ "129": "SUCCESS",
39
  "13": "SUCCESS",
40
  "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "SUCCESS",
43
  "133": "SUCCESS",
44
+ "134": "SUCCESS",
45
+ "135": "NON_PARTICIPATING",
46
+ "136": "NON_PARTICIPATING",
47
  "137": "FAIL",
48
+ "138": "FAIL",
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
+ "141": "SUCCESS",
53
  "142": "SUCCESS",
54
+ "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
+ "147": "FAIL",
59
+ "148": "NON_PARTICIPATING",
60
+ "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
+ "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
+ "157": "FAIL",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
+ "160": "SUCCESS",
74
+ "161": "SUCCESS",
75
+ "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
+ "164": "SUCCESS",
78
+ "165": "NON_PARTICIPATING",
79
+ "166": "NON_PARTICIPATING",
80
+ "167": "SUCCESS",
81
  "168": "SUCCESS",
82
+ "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
+ "170": "FAIL",
85
  "171": "SUCCESS",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NOT_ALIVE",
 
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
+ "179": "NOT_ALIVE",
94
+ "18": "FAIL",
95
  "180": "SUCCESS",
96
  "181": "NON_PARTICIPATING",
97
+ "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
+ "184": "FAIL",
100
+ "185": "FAIL",
101
+ "186": "FAIL",
102
  "187": "NON_PARTICIPATING",
103
+ "188": "FAIL",
104
+ "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
+ "191": "SUCCESS",
108
+ "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
+ "195": "NON_PARTICIPATING",
112
+ "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "SUCCESS",
115
  "199": "SUCCESS",
116
+ "2": "FAIL",
117
+ "20": "SUCCESS",
118
+ "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "SUCCESS",
121
+ "203": "SUCCESS",
122
+ "204": "SUCCESS",
123
  "205": "SUCCESS",
124
+ "206": "NOT_ALIVE",
125
+ "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
+ "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "FAIL",
134
+ "215": "FAIL",
135
+ "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "FAIL",
138
+ "219": "SUCCESS",
139
+ "22": "SUCCESS",
140
  "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
+ "222": "NON_PARTICIPATING",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "FAIL",
146
+ "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "SUCCESS",
150
+ "23": "SUCCESS",
151
  "230": "NON_PARTICIPATING",
152
+ "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
+ "233": "FAIL",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
+ "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
+ "24": "FAIL",
162
+ "240": "SUCCESS",
163
  "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
+ "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "SUCCESS",
169
+ "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
+ "249": "FAIL",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
+ "252": "NON_PARTICIPATING",
176
  "253": "SUCCESS",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
+ "26": "SUCCESS",
180
+ "27": "NON_PARTICIPATING",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "NOT_ALIVE",
184
+ "30": "SUCCESS",
185
+ "31": "SUCCESS",
186
  "32": "SUCCESS",
187
+ "33": "NON_PARTICIPATING",
188
  "34": "SUCCESS",
189
+ "35": "NOT_ALIVE",
190
+ "36": "NON_PARTICIPATING",
191
+ "37": "SUCCESS",
192
+ "38": "FAIL",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "SUCCESS",
196
+ "41": "SUCCESS",
197
  "42": "SUCCESS",
198
+ "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
+ "45": "NON_PARTICIPATING",
201
+ "46": "NOT_ALIVE",
202
+ "47": "NON_PARTICIPATING",
203
  "48": "SUCCESS",
204
+ "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "FAIL",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
  "55": "SUCCESS",
212
+ "56": "NON_PARTICIPATING",
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
+ "61": "NOT_ALIVE",
219
  "62": "SUCCESS",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
+ "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "SUCCESS",
226
  "69": "SUCCESS",
227
+ "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
+ "71": "SUCCESS",
230
+ "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "SUCCESS",
233
+ "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
  "77": "SUCCESS",
236
+ "78": "FAIL",
237
+ "79": "NON_PARTICIPATING",
238
  "8": "NOT_ALIVE",
239
+ "80": "SUCCESS",
240
+ "81": "NON_PARTICIPATING",
241
+ "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
+ "85": "SUCCESS",
245
+ "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
+ "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "FAIL",
251
  "91": "NON_PARTICIPATING",
252
+ "92": "FAIL",
253
+ "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "SUCCESS",
256
+ "96": "NON_PARTICIPATING",
257
+ "97": "FAIL",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6396709,
268
+ 6396717,
269
+ 6396724
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": 6396547,
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 sha256:6d93b749c843243f60b128a4f20419f88b1bac92ea04fa60a1f761f1d5b82a78
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3aefa03e97726f0269ee1b3c6aa99201e72beeba63a8f0c054242a7e85938c1
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7b7ed4b27d1238fd99f8d82a2664e74baaba4c050bc6010d7f8b2d0f175c46f
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36f6b246ad6988b8297648ac6584ac53277368b9f9d277d19342bba4ee426ff
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fb4dab18dec0fa61e9009ed94b9a617f239b88d45847ed3d2ed3c66025004e0
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4abee6da830fb2f26cdda6f3fdbd565b1d6e3b811abf62fcfe08d69544040158
3
  size 4400216536