pruning commited on
Commit
dee50cb
·
verified ·
1 Parent(s): ee50aa5

Run 11. Outer Step 410. 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
@@ -5,49 +5,49 @@
5
  "1": "NOT_ALIVE",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
- "101": "SUCCESS",
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "SUCCESS",
12
- "105": "NOT_ALIVE",
13
  "106": "NOT_ALIVE",
14
- "107": "NON_PARTICIPATING",
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "SUCCESS",
19
  "111": "NON_PARTICIPATING",
20
- "112": "SUCCESS",
21
- "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
- "115": "NOT_ALIVE",
24
- "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
- "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "NOT_ALIVE",
32
- "123": "NOT_ALIVE",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
- "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
- "13": "NON_PARTICIPATING",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
- "134": "NOT_ALIVE",
45
- "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
- "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "NOT_ALIVE",
@@ -79,22 +79,22 @@
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "NON_PARTICIPATING",
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": "SUCCESS",
@@ -112,8 +112,8 @@
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NOT_ALIVE",
115
- "199": "SUCCESS",
116
- "2": "SUCCESS",
117
  "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
@@ -124,11 +124,11 @@
124
  "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
- "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
  "211": "SUCCESS",
131
- "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NOT_ALIVE",
134
  "215": "NON_PARTICIPATING",
@@ -148,19 +148,19 @@
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
- "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
- "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
- "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
@@ -175,11 +175,11 @@
175
  "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
- "255": "NON_PARTICIPATING",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
- "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
@@ -193,7 +193,7 @@
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
@@ -210,7 +210,7 @@
210
  "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
- "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
@@ -227,16 +227,16 @@
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
- "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "SUCCESS",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
- "79": "NOT_ALIVE",
238
  "8": "SUCCESS",
239
- "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "SUCCESS",
@@ -248,8 +248,8 @@
248
  "89": "NON_PARTICIPATING",
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",
@@ -264,9 +264,6 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6750600,
268
- 6750651,
269
- 6750685,
270
  6750709,
271
  6750741,
272
  6750780,
@@ -274,7 +271,10 @@
274
  6750847,
275
  6750881,
276
  6750914,
277
- 6750954
 
 
 
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": 45,
287
  "intermediate_size": 5632,
288
- "last_allreduce_block": 6750582,
289
  "max_position_embeddings": 2048,
290
  "mlp_bias": false,
291
  "model_type": "llama",
 
5
  "1": "NOT_ALIVE",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
+ "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "SUCCESS",
12
+ "105": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
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": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "NOT_ALIVE",
32
+ "123": "NON_PARTICIPATING",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
+ "128": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
50
+ "14": "NON_PARTICIPATING",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "NOT_ALIVE",
 
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
82
+ "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
+ "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
+ "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
+ "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
  "185": "SUCCESS",
 
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NOT_ALIVE",
115
+ "199": "NOT_ALIVE",
116
+ "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
 
124
  "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
  "211": "SUCCESS",
131
+ "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NOT_ALIVE",
134
  "215": "NON_PARTICIPATING",
 
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
+ "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
+ "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
+ "241": "SUCCESS",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "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",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
 
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
 
210
  "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
+ "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
 
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
+ "72": "SUCCESS",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "SUCCESS",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
+ "79": "SUCCESS",
238
  "8": "SUCCESS",
239
+ "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "SUCCESS",
 
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
+ "91": "NOT_ALIVE",
252
+ "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
 
 
 
267
  6750709,
268
  6750741,
269
  6750780,
 
271
  6750847,
272
  6750881,
273
  6750914,
274
+ 6750954,
275
+ 6750993,
276
+ 6751000,
277
+ 6751053
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": 6750947,
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 sha256:69b88082ef50cf47fdc779b33ed48d5629820e8bb7c27fbfd3bebeae5fe89a6b
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:888bcb5a9cf149e3b436206836e5d8f1405048f031ba72c1b1fbe015e8fd6b02
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e4a19244bf2ca7dbdc809fba734cad5c131e34676f84ea157d04bb58ba9955a
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2d149185ef1bd36d58f016f06d1252d5ba94ea3dbe0fafc1ba675e38dc8349
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1936be31550ef1c150dc190660366fabdb2d9334a3c05747a1a43b20e5db4388
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd068f3f8f99d12b6302776eeeaa40c43610d08262c3b66df77a9b182b974a8f
3
  size 4400216536