pruning commited on
Commit
0257eb0
·
verified ·
1 Parent(s): 50a0e0e

Run 11. Outer Step 404. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +41 -41
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -9,19 +9,19 @@
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "SUCCESS",
12
- "105": "NOT_ALIVE",
13
  "106": "NOT_ALIVE",
14
- "107": "SUCCESS",
15
- "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "SUCCESS",
19
  "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
- "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
@@ -36,17 +36,17 @@
36
  "127": "SUCCESS",
37
  "128": "SUCCESS",
38
  "129": "NOT_ALIVE",
39
- "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
- "134": "SUCCESS",
45
- "135": "SUCCESS",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
- "139": "SUCCESS",
50
  "14": "NON_PARTICIPATING",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
@@ -90,25 +90,25 @@
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
- "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "SUCCESS",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
- "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
- "187": "SUCCESS",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
- "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
- "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
@@ -121,7 +121,7 @@
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
- "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
@@ -131,14 +131,14 @@
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NOT_ALIVE",
134
- "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
- "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
@@ -151,14 +151,14 @@
151
  "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
- "237": "NOT_ALIVE",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
- "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
  "241": "SUCCESS",
164
  "242": "NOT_ALIVE",
@@ -171,12 +171,12 @@
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",
179
- "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
@@ -193,7 +193,7 @@
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
- "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
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": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
@@ -214,19 +214,19 @@
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
- "60": "NOT_ALIVE",
218
  "61": "SUCCESS",
219
- "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "SUCCESS",
226
- "69": "NON_PARTICIPATING",
227
- "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
- "71": "SUCCESS",
230
  "72": "SUCCESS",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
@@ -234,7 +234,7 @@
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
- "79": "NOT_ALIVE",
238
  "8": "SUCCESS",
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
@@ -243,18 +243,18 @@
243
  "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
- "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
- "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
- "91": "SUCCESS",
252
  "92": "SUCCESS",
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
  },
@@ -264,9 +264,6 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6748433,
268
- 6748466,
269
- 6748498,
270
  6748531,
271
  6748561,
272
  6748596,
@@ -274,7 +271,10 @@
274
  6748661,
275
  6748684,
276
  6748716,
277
- 6748740
 
 
 
278
  ],
279
  "bos_token_id": 1,
280
  "dtype": "float32",
@@ -283,9 +283,9 @@
283
  "hidden_act": "silu",
284
  "hidden_size": 2048,
285
  "initializer_range": 0.02,
286
- "inner_step": 339,
287
  "intermediate_size": 5632,
288
- "last_allreduce_block": 6744461,
289
  "max_position_embeddings": 2048,
290
  "mlp_bias": false,
291
  "model_type": "llama",
 
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "SUCCESS",
12
+ "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
+ "107": "NOT_ALIVE",
15
+ "108": "NOT_ALIVE",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "SUCCESS",
19
  "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
+ "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
 
36
  "127": "SUCCESS",
37
  "128": "SUCCESS",
38
  "129": "NOT_ALIVE",
39
+ "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
+ "134": "NON_PARTICIPATING",
45
+ "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "NOT_ALIVE",
50
  "14": "NON_PARTICIPATING",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
 
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
+ "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "SUCCESS",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
+ "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
+ "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
+ "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
 
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
 
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NOT_ALIVE",
134
+ "215": "SUCCESS",
135
  "216": "NON_PARTICIPATING",
136
  "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
 
151
  "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
+ "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
+ "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "SUCCESS",
164
  "242": "NOT_ALIVE",
 
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
+ "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
+ "255": "NON_PARTICIPATING",
179
+ "26": "NOT_ALIVE",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
 
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
 
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
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
+ "62": "SUCCESS",
220
  "63": "NOT_ALIVE",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "SUCCESS",
226
+ "69": "NOT_ALIVE",
227
+ "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
+ "71": "NOT_ALIVE",
230
  "72": "SUCCESS",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
 
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
+ "79": "SUCCESS",
238
  "8": "SUCCESS",
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
 
243
  "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
+ "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
+ "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
+ "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
+ "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
 
 
 
267
  6748531,
268
  6748561,
269
  6748596,
 
271
  6748661,
272
  6748684,
273
  6748716,
274
+ 6748739,
275
+ 6748771,
276
+ 6748791,
277
+ 6748857
278
  ],
279
  "bos_token_id": 1,
280
  "dtype": "float32",
 
283
  "hidden_act": "silu",
284
  "hidden_size": 2048,
285
  "initializer_range": 0.02,
286
+ "inner_step": 4,
287
  "intermediate_size": 5632,
288
+ "last_allreduce_block": 6748777,
289
  "max_position_embeddings": 2048,
290
  "mlp_bias": false,
291
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15e267d61c7a8cee213dc4f8058f54251024ef74bf43ce6e1ad7c029c95ff5f5
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ea4f746d8f5c9e42ea1d76a287bc2ce1dbd4b2d770a9d9e57a4601bac3bcb2b
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70f917e97b5432125334a805f896f84fcf3d7051fbe2413e90822581deaebf4f
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39797493c60b49fa49e6edc8d7a21159617f2b0e0f2adeb3ecd10ad1d7604498
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0657e792836841db60245872ca6e258125b6345f0a5e9b788c300d8385a31805
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bf1a07f3a4e218ce469c1c08a6a52d2f8a97e707fed3d74f4f91792c6e10d4f
3
  size 4400216536