mujerry commited on
Commit
1592ac8
·
verified ·
1 Parent(s): 2de72ae

Run 11. Outer Step 409. Inner Step 9.

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
@@ -8,50 +8,50 @@
8
  "101": "SUCCESS",
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
- "104": "NOT_ALIVE",
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": "SUCCESS",
21
- "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
- "115": "NON_PARTICIPATING",
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": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
- "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
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": "NON_PARTICIPATING",
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",
54
- "143": "SUCCESS",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NOT_ALIVE",
@@ -62,7 +62,7 @@
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
@@ -79,7 +79,7 @@
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",
@@ -90,16 +90,16 @@
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": "NOT_ALIVE",
101
- "186": "SUCCESS",
102
- "187": "SUCCESS",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
@@ -111,7 +111,7 @@
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
- "198": "NON_PARTICIPATING",
115
  "199": "SUCCESS",
116
  "2": "SUCCESS",
117
  "20": "SUCCESS",
@@ -127,18 +127,18 @@
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
- "211": "NOT_ALIVE",
131
- "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NOT_ALIVE",
134
- "215": "SUCCESS",
135
  "216": "NON_PARTICIPATING",
136
  "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
- "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
- "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
@@ -148,19 +148,19 @@
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": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
- "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "SUCCESS",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
@@ -192,7 +192,7 @@
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
- "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
@@ -212,7 +212,7 @@
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
@@ -222,19 +222,19 @@
222
  "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
- "68": "NOT_ALIVE",
226
  "69": "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": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
@@ -254,9 +254,9 @@
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
- "97": "NOT_ALIVE",
258
- "98": "NOT_ALIVE",
259
- "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6750500,
268
- 6750530
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": 45,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6749479,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
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",
54
+ "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NOT_ALIVE",
 
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
 
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",
 
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",
101
+ "186": "NOT_ALIVE",
102
+ "187": "NOT_ALIVE",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
 
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
+ "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "SUCCESS",
117
  "20": "SUCCESS",
 
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",
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",
 
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",
 
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
 
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
+ "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "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": "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",
 
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
+ "97": "SUCCESS",
258
+ "98": "SUCCESS",
259
+ "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6750600,
268
+ 6750641
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": 9,
278
  "intermediate_size": 5632,
279
+ "last_allreduce_block": 6750582,
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 sha256:85fe2511f010f9f7657656687f03c2f37b719bf85eb1f0e85ff7a9670222681e
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aeaae5b5d6d5344d0d9262ffa9beee7659d6ea9ffff02ef28e32380ef838399
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26e9790d84d2816d462b3ff1890cd73a365934a2fff6eb139eee63dc160dd4bc
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84ad05f6d9b0d23063f28e974b3fa2468edcaa1390b61000a276a997d7ea3345
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb049d6d7dbdfd4c802332b70aa571050074048cd8c04149b0a3153980762e32
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a178b1ce3fb5860c2558646dee685e09dbbbba6622d968b82bdf4df5654e85
3
  size 4400216536