mujerry commited on
Commit
8a50502
·
verified ·
1 Parent(s): 3f443c6

Run 11. Outer Step 34. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +75 -75
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -10,19 +10,19 @@
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
- "106": "FAIL",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
- "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
- "110": "SUCCESS",
19
- "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "NON_PARTICIPATING",
22
- "114": "NOT_ALIVE",
23
  "115": "SUCCESS",
24
- "116": "FAIL",
25
- "117": "FAIL",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
@@ -30,9 +30,9 @@
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
  "123": "SUCCESS",
33
- "124": "SUCCESS",
34
- "125": "NON_PARTICIPATING",
35
- "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
@@ -41,7 +41,7 @@
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
- "134": "SUCCESS",
45
  "135": "SUCCESS",
46
  "136": "NOT_ALIVE",
47
  "137": "NON_PARTICIPATING",
@@ -51,32 +51,32 @@
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
- "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
  "148": "NOT_ALIVE",
60
- "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
- "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
- "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
- "155": "NON_PARTICIPATING",
68
- "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "SUCCESS",
71
  "159": "SUCCESS",
72
- "16": "SUCCESS",
73
- "160": "SUCCESS",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
- "166": "NOT_ALIVE",
80
  "167": "FAIL",
81
  "168": "SUCCESS",
82
  "169": "SUCCESS",
@@ -84,28 +84,28 @@
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
  "175": "SUCCESS",
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": "NON_PARTICIPATING",
100
- "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
- "19": "SUCCESS",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
- "192": "NON_PARTICIPATING",
109
  "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
@@ -120,80 +120,80 @@
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "SUCCESS",
124
- "206": "NOT_ALIVE",
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": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
- "217": "FAIL",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
- "222": "NOT_ALIVE",
143
- "223": "FAIL",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "FAIL",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
  "229": "SUCCESS",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
- "231": "NON_PARTICIPATING",
153
  "232": "NON_PARTICIPATING",
154
  "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
159
- "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NOT_ALIVE",
164
  "242": "NOT_ALIVE",
165
- "243": "SUCCESS",
166
  "244": "NOT_ALIVE",
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": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
- "252": "FAIL",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
- "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
- "3": "SUCCESS",
184
  "30": "SUCCESS",
185
- "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
- "35": "FAIL",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
- "38": "NON_PARTICIPATING",
193
- "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
- "41": "FAIL",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
@@ -206,22 +206,22 @@
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
- "53": "FAIL",
210
- "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
- "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
- "61": "FAIL",
219
- "62": "SUCCESS",
220
- "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "SUCCESS",
224
- "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
  "7": "NON_PARTICIPATING",
@@ -230,32 +230,32 @@
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "NON_PARTICIPATING",
233
- "75": "SUCCESS",
234
  "76": "NON_PARTICIPATING",
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": "FAIL",
243
  "84": "NON_PARTICIPATING",
244
  "85": "SUCCESS",
245
- "86": "NOT_ALIVE",
246
- "87": "NOT_ALIVE",
247
- "88": "NON_PARTICIPATING",
248
- "89": "SUCCESS",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
- "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
- "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6562063,
268
- 6562091
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": 40,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6561785,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "SUCCESS",
13
+ "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
+ "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
+ "110": "NON_PARTICIPATING",
19
+ "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "NON_PARTICIPATING",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "SUCCESS",
24
+ "116": "NON_PARTICIPATING",
25
+ "117": "NOT_ALIVE",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
 
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
  "123": "SUCCESS",
33
+ "124": "NON_PARTICIPATING",
34
+ "125": "NOT_ALIVE",
35
+ "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
  "129": "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",
 
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
+ "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
  "148": "NOT_ALIVE",
60
+ "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
+ "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
+ "152": "NOT_ALIVE",
65
  "153": "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": "NON_PARTICIPATING",
73
+ "160": "NOT_ALIVE",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "NON_PARTICIPATING",
80
  "167": "FAIL",
81
  "168": "SUCCESS",
82
  "169": "SUCCESS",
 
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "NOT_ALIVE",
88
  "174": "NON_PARTICIPATING",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
+ "178": "NON_PARTICIPATING",
93
+ "179": "NON_PARTICIPATING",
94
+ "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
  "183": "NOT_ALIVE",
99
+ "184": "FAIL",
100
+ "185": "NOT_ALIVE",
101
  "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
+ "19": "NON_PARTICIPATING",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
+ "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
 
120
  "202": "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": "SUCCESS",
129
+ "210": "SUCCESS",
130
  "211": "NOT_ALIVE",
131
  "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
+ "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
  "221": "NON_PARTICIPATING",
142
+ "222": "NON_PARTICIPATING",
143
+ "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
  "229": "SUCCESS",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
+ "231": "NOT_ALIVE",
153
  "232": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
163
  "241": "NOT_ALIVE",
164
  "242": "NOT_ALIVE",
165
+ "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
+ "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
+ "248": "FAIL",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
+ "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
+ "26": "SUCCESS",
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
+ "3": "FAIL",
184
  "30": "SUCCESS",
185
+ "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "SUCCESS",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
+ "41": "SUCCESS",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
 
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
+ "53": "SUCCESS",
210
+ "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
+ "57": "SUCCESS",
214
  "58": "NON_PARTICIPATING",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "NOT_ALIVE",
218
+ "61": "SUCCESS",
219
+ "62": "NOT_ALIVE",
220
+ "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "SUCCESS",
224
+ "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
  "7": "NON_PARTICIPATING",
 
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": "NON_PARTICIPATING",
237
+ "79": "SUCCESS",
238
+ "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
+ "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "SUCCESS",
245
+ "86": "SUCCESS",
246
+ "87": "SUCCESS",
247
+ "88": "NOT_ALIVE",
248
+ "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
+ "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
+ "98": "NON_PARTICIPATING",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6562210,
268
+ 6562237
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": 8,
278
  "intermediate_size": 5632,
279
+ "last_allreduce_block": 6562161,
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 sha256:779f1ea67ae2449e7eb97258625c3047db0f37ff814b6078b1db843d2ecf65ce
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9d736843a46f9712e6d9f8f816b8662d96d97f4d953a2e8bc1912cbddb0b68f
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c73d9489d5703cd8105c24715fe955cf70a1ad5556af97352eb0ba52433ba0ab
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19bfd08a18b43061dc0e354edb4558653d9bbd637fa5f37cc7b771b33a56412b
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e98e32c2b85d87c216fe4f2a4e1a2cc009a793f12ef3566094bb9dc7f6d81e3a
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee7e16dd0657fa1d9e4bb9d5b1ec8edf7cede50bea2f92ba4a4638c1b881f1a
3
  size 4400216536