mujerry commited on
Commit
c331224
·
verified ·
1 Parent(s): bd0162d

Run 11. Outer Step 199. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +52 -52
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -8,8 +8,8 @@
8
  "101": "SUCCESS",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
- "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "SUCCESS",
@@ -20,50 +20,50 @@
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
- "115": "NON_PARTICIPATING",
24
- "116": "SUCCESS",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
- "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
- "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
- "128": "NOT_ALIVE",
38
- "129": "SUCCESS",
39
- "13": "FAIL",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
- "134": "FAIL",
45
  "135": "SUCCESS",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
- "14": "NOT_ALIVE",
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",
61
  "15": "NOT_ALIVE",
62
- "150": "NOT_ALIVE",
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": "SUCCESS",
@@ -72,10 +72,10 @@
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
- "162": "SUCCESS",
76
  "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
- "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
  "168": "NOT_ALIVE",
@@ -89,30 +89,30 @@
89
  "175": "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": "SUCCESS",
100
- "185": "FAIL",
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": "FAIL",
110
  "194": "NOT_ALIVE",
111
- "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
- "197": "FAIL",
114
  "198": "NOT_ALIVE",
115
- "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
@@ -121,40 +121,40 @@
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",
128
  "21": "NOT_ALIVE",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
- "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
- "216": "NON_PARTICIPATING",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
- "220": "NOT_ALIVE",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
- "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
- "226": "FAIL",
147
- "227": "NOT_ALIVE",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "SUCCESS",
151
  "230": "SUCCESS",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "SUCCESS",
155
- "234": "NOT_ALIVE",
156
- "235": "NOT_ALIVE",
157
- "236": "NOT_ALIVE",
158
  "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
@@ -176,7 +176,7 @@
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
- "26": "FAIL",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
@@ -189,12 +189,12 @@
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "SUCCESS",
192
- "38": "FAIL",
193
  "39": "NOT_ALIVE",
194
  "4": "NON_PARTICIPATING",
195
  "40": "NOT_ALIVE",
196
- "41": "SUCCESS",
197
- "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
  "45": "SUCCESS",
@@ -206,8 +206,8 @@
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
- "53": "NOT_ALIVE",
210
- "54": "FAIL",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
@@ -216,10 +216,10 @@
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
- "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
- "65": "FAIL",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "SUCCESS",
@@ -236,11 +236,11 @@
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
238
  "8": "SUCCESS",
239
- "80": "NON_PARTICIPATING",
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",
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6658514,
268
- 6658550
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": 31,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6658306,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
8
  "101": "SUCCESS",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
+ "104": "NON_PARTICIPATING",
12
+ "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "SUCCESS",
 
20
  "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
+ "115": "NOT_ALIVE",
24
+ "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
+ "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "NOT_ALIVE",
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": "NON_PARTICIPATING",
40
  "130": "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": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
+ "14": "NON_PARTICIPATING",
51
+ "140": "SUCCESS",
52
  "141": "SUCCESS",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "NON_PARTICIPATING",
58
  "147": "SUCCESS",
59
+ "148": "NOT_ALIVE",
60
  "149": "NOT_ALIVE",
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": "SUCCESS",
 
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
+ "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
+ "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
  "168": "NOT_ALIVE",
 
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
+ "178": "NON_PARTICIPATING",
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": "SUCCESS",
101
  "186": "SUCCESS",
102
+ "187": "NOT_ALIVE",
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": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
+ "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
+ "197": "SUCCESS",
114
  "198": "NOT_ALIVE",
115
+ "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
 
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": "SUCCESS",
130
  "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
+ "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
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": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "SUCCESS",
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": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "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": "NOT_ALIVE",
 
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",
196
+ "41": "NON_PARTICIPATING",
197
+ "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
  "45": "SUCCESS",
 
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
+ "53": "NON_PARTICIPATING",
210
+ "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
 
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
+ "62": "NON_PARTICIPATING",
220
  "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
+ "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "SUCCESS",
 
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
238
  "8": "SUCCESS",
239
+ "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "SUCCESS",
243
+ "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6658711,
268
+ 6658741
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": 6658685,
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:edffbc1bfacae9ab27d88129db7a306acfd45787ddcf0cf43a136e52838a4c17
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b5c71dfe8ca0ee3250e14bf178a94330a8c067362bcc88682474d57a9ca37ed
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dca1537790713e2ff2d8a8c4e049e72d8b33013a695da6f53066d82523d7b34
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d57ab82cb0b65863d3592c88e9d75c7bbe5dbccaff973b3f9e9d7daf2c6a0f
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1af5bf5b215aabe5034a9caa985589298620084b93a472cd8e8aa9d73a5464f
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59fca958ab55b4edaa52028319092a083f03458a5467e2dafe1b8564158d9753
3
  size 4400216536