Alir332 commited on
Commit
61daecc
·
verified ·
1 Parent(s): 3c517c8

Run 11. Outer Step 210. Inner Step 0.

Browse files
Files changed (4) hide show
  1. config.json +40 -41
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -5,14 +5,14 @@
5
  "1": "SUCCESS",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
- "101": "SUCCESS",
9
  "102": "NOT_ALIVE",
10
- "103": "NON_PARTICIPATING",
11
- "104": "SUCCESS",
12
  "105": "NON_PARTICIPATING",
13
- "106": "SUCCESS",
14
- "107": "NON_PARTICIPATING",
15
- "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
@@ -20,7 +20,7 @@
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
- "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
@@ -35,7 +35,7 @@
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
  "128": "SUCCESS",
38
- "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
@@ -51,10 +51,10 @@
51
  "140": "NOT_ALIVE",
52
  "141": "SUCCESS",
53
  "142": "NON_PARTICIPATING",
54
- "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
- "146": "NOT_ALIVE",
58
  "147": "SUCCESS",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
@@ -63,14 +63,14 @@
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
- "154": "NON_PARTICIPATING",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
- "157": "FAIL",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
- "16": "NOT_ALIVE",
73
- "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "SUCCESS",
76
  "163": "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": "NON_PARTICIPATING",
@@ -97,8 +97,8 @@
97
  "182": "SUCCESS",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
- "185": "NOT_ALIVE",
101
- "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
@@ -114,23 +114,23 @@
114
  "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
- "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
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",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
- "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
@@ -138,13 +138,13 @@
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
- "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "SUCCESS",
147
- "227": "SUCCESS",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
@@ -152,15 +152,15 @@
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
- "234": "NON_PARTICIPATING",
156
- "235": "NOT_ALIVE",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
- "241": "NOT_ALIVE",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
@@ -189,7 +189,7 @@
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
192
- "38": "SUCCESS",
193
  "39": "NOT_ALIVE",
194
  "4": "NON_PARTICIPATING",
195
  "40": "NOT_ALIVE",
@@ -222,7 +222,7 @@
222
  "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
- "68": "SUCCESS",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
@@ -231,30 +231,30 @@
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
- "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
- "79": "SUCCESS",
238
- "8": "NOT_ALIVE",
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
- "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "NON_PARTICIPATING",
251
  "91": "NON_PARTICIPATING",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
- "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
- "97": "SUCCESS",
258
  "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
@@ -264,8 +264,7 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6662743,
268
- 6662772
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
@@ -274,9 +273,9 @@
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
- "inner_step": 67,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6660612,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
5
  "1": "SUCCESS",
6
  "10": "SUCCESS",
7
  "100": "NOT_ALIVE",
8
+ "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
+ "103": "SUCCESS",
11
+ "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "FAIL",
14
+ "107": "SUCCESS",
15
+ "108": "NOT_ALIVE",
16
  "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
 
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
+ "115": "SUCCESS",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
 
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
  "128": "SUCCESS",
38
+ "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
 
51
  "140": "NOT_ALIVE",
52
  "141": "SUCCESS",
53
  "142": "NON_PARTICIPATING",
54
+ "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "SUCCESS",
58
  "147": "SUCCESS",
59
  "148": "SUCCESS",
60
  "149": "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",
69
+ "157": "SUCCESS",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
+ "16": "NON_PARTICIPATING",
73
+ "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
  "162": "SUCCESS",
76
  "163": "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": "NON_PARTICIPATING",
 
97
  "182": "SUCCESS",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
+ "185": "SUCCESS",
101
+ "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
 
114
  "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
+ "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
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": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
 
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
+ "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "SUCCESS",
147
+ "227": "NOT_ALIVE",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
 
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
+ "234": "NOT_ALIVE",
156
+ "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
 
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
  "4": "NON_PARTICIPATING",
195
  "40": "NOT_ALIVE",
 
222
  "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
+ "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
 
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
+ "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
+ "79": "NON_PARTICIPATING",
238
+ "8": "SUCCESS",
239
  "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
+ "82": "NOT_ALIVE",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
+ "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
  "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
+ "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6662850
 
268
  ],
269
  "bos_token_id": 1,
270
  "dtype": "float32",
 
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
+ "inner_step": 0,
277
  "intermediate_size": 5632,
278
+ "last_allreduce_block": 6662808,
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 sha256:85ced907eda34a740a7cf8b32a3774fda527da9e3a0262f9418b65c381202590
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94748012abf5d45d80ffda4943b2a1b600dd8a5f1385e6b961c1f8d4e1b0aaea
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07eff261fee4bde4adbe315f818bd9abffe584d03b94610d6e3610eda8ec2bf1
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:476e5033e929364d4af081fdea974a97dbe6d7cba289358170e2ed3dc524eac5
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a53861306d972f27aba3c38cbbc38e5edd288084bebbb904043e041e1a61f76
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a767a8221ea870f06986bd2c3c385a38e8fb4b57c4153142514c509791e92d63
3
  size 4400216536