ncaagcc commited on
Commit
608d667
·
verified ·
1 Parent(s): 9113ce3

Run 5. Outer Step 69. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +67 -68
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,39 +1,39 @@
1
  {
2
- "_name_or_path": "ncaagcc/tensor3",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NON_PARTICIPATING",
6
- "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
  "103": "SUCCESS",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
- "107": "NOT_ALIVE",
15
- "108": "NOT_ALIVE",
16
- "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "SUCCESS",
19
  "111": "NON_PARTICIPATING",
20
- "112": "NOT_ALIVE",
21
- "113": "NOT_ALIVE",
22
- "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
- "117": "NOT_ALIVE",
26
- "118": "NON_PARTICIPATING",
27
  "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NON_PARTICIPATING",
30
- "121": "NON_PARTICIPATING",
31
  "122": "SUCCESS",
32
- "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
- "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NON_PARTICIPATING",
@@ -41,16 +41,16 @@
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
- "134": "NON_PARTICIPATING",
45
  "135": "NOT_ALIVE",
46
  "136": "SUCCESS",
47
- "137": "NOT_ALIVE",
48
- "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
- "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
@@ -58,27 +58,27 @@
58
  "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
  "149": "NON_PARTICIPATING",
61
- "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
- "153": "SUCCESS",
66
  "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
- "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "SUCCESS",
78
- "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
- "168": "SUCCESS",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
@@ -88,27 +88,27 @@
88
  "174": "NON_PARTICIPATING",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
- "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "SUCCESS",
95
- "180": "NON_PARTICIPATING",
96
  "181": "SUCCESS",
97
- "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
- "184": "NOT_ALIVE",
100
- "185": "NOT_ALIVE",
101
- "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
- "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
- "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
- "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
@@ -116,7 +116,7 @@
116
  "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
- "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
@@ -127,14 +127,14 @@
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "SUCCESS",
130
- "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
- "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
  "215": "SUCCESS",
135
  "216": "NON_PARTICIPATING",
136
- "217": "NON_PARTICIPATING",
137
- "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
@@ -144,31 +144,31 @@
144
  "224": "NOT_ALIVE",
145
  "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
- "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
- "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NON_PARTICIPATING",
154
- "233": "NON_PARTICIPATING",
155
  "234": "NOT_ALIVE",
156
  "235": "NOT_ALIVE",
157
- "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
- "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
- "248": "NOT_ALIVE",
171
- "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
@@ -179,7 +179,7 @@
179
  "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
- "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
  "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
@@ -195,13 +195,13 @@
195
  "40": "SUCCESS",
196
  "41": "SUCCESS",
197
  "42": "NON_PARTICIPATING",
198
- "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
- "48": "NOT_ALIVE",
204
- "49": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
@@ -209,25 +209,25 @@
209
  "53": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
- "56": "SUCCESS",
213
- "57": "NOT_ALIVE",
214
- "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
- "6": "NON_PARTICIPATING",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
- "62": "SUCCESS",
220
- "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NON_PARTICIPATING",
229
- "71": "NON_PARTICIPATING",
230
- "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
  "75": "SUCCESS",
@@ -237,16 +237,16 @@
237
  "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
- "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
- "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
- "86": "SUCCESS",
246
  "87": "NON_PARTICIPATING",
247
- "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
- "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
@@ -264,17 +264,16 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5910046,
268
- 5910046
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
- "inner_step": 28,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5909477,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NON_PARTICIPATING",
6
+ "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
+ "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "SUCCESS",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
+ "107": "NON_PARTICIPATING",
15
+ "108": "NON_PARTICIPATING",
16
+ "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "SUCCESS",
19
  "111": "NON_PARTICIPATING",
20
+ "112": "NON_PARTICIPATING",
21
+ "113": "NON_PARTICIPATING",
22
+ "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "NON_PARTICIPATING",
26
+ "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NON_PARTICIPATING",
30
+ "121": "NOT_ALIVE",
31
  "122": "SUCCESS",
32
+ "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
+ "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NON_PARTICIPATING",
 
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
+ "134": "NOT_ALIVE",
45
  "135": "NOT_ALIVE",
46
  "136": "SUCCESS",
47
+ "137": "NON_PARTICIPATING",
48
+ "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
+ "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
 
58
  "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
+ "153": "NOT_ALIVE",
66
  "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NON_PARTICIPATING",
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
+ "160": "NOT_ALIVE",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "SUCCESS",
78
+ "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
+ "168": "NOT_ALIVE",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
 
88
  "174": "NON_PARTICIPATING",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
+ "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "SUCCESS",
95
+ "180": "NOT_ALIVE",
96
  "181": "SUCCESS",
97
+ "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
+ "184": "NON_PARTICIPATING",
100
+ "185": "NON_PARTICIPATING",
101
+ "186": "NON_PARTICIPATING",
102
  "187": "NON_PARTICIPATING",
103
+ "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
+ "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
 
116
  "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
+ "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
 
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "SUCCESS",
130
+ "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
+ "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "SUCCESS",
135
  "216": "NON_PARTICIPATING",
136
+ "217": "NOT_ALIVE",
137
+ "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
 
144
  "224": "NOT_ALIVE",
145
  "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
+ "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
+ "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NON_PARTICIPATING",
154
+ "233": "NOT_ALIVE",
155
  "234": "NOT_ALIVE",
156
  "235": "NOT_ALIVE",
157
+ "236": "NON_PARTICIPATING",
158
  "237": "NOT_ALIVE",
159
+ "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
+ "241": "NOT_ALIVE",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
+ "248": "NON_PARTICIPATING",
171
+ "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
 
179
  "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
+ "29": "NOT_ALIVE",
183
  "3": "NON_PARTICIPATING",
184
  "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
 
195
  "40": "SUCCESS",
196
  "41": "SUCCESS",
197
  "42": "NON_PARTICIPATING",
198
+ "43": "SUCCESS",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
+ "48": "NON_PARTICIPATING",
204
+ "49": "NON_PARTICIPATING",
205
  "5": "NON_PARTICIPATING",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
 
209
  "53": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
+ "56": "NOT_ALIVE",
213
+ "57": "NON_PARTICIPATING",
214
+ "58": "SUCCESS",
215
  "59": "NON_PARTICIPATING",
216
+ "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
+ "62": "NOT_ALIVE",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "NON_PARTICIPATING",
229
+ "71": "NOT_ALIVE",
230
+ "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
  "75": "SUCCESS",
 
237
  "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
+ "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
+ "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
+ "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
+ "88": "NOT_ALIVE",
248
  "89": "NON_PARTICIPATING",
249
+ "9": "NON_PARTICIPATING",
250
  "90": "SUCCESS",
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5911377
 
268
  ],
269
  "bos_token_id": 1,
270
  "eos_token_id": 2,
271
  "hidden_act": "silu",
272
  "hidden_size": 2048,
273
  "initializer_range": 0.02,
274
+ "inner_step": 0,
275
  "intermediate_size": 5632,
276
+ "last_allreduce_block": 5910694,
277
  "max_position_embeddings": 2048,
278
  "mlp_bias": false,
279
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:985fd1eb62d3397179f968dc9e900fc3e8a8afb46796112abba39dcc4579accb
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd499e9187384c9e0c01cec69cd190f1ce9eb9e7c8bb8e24c9ed841c30989438
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:202ca3d7256f81f400ebbfd97b3a9ec5a444e941fbc6f4e143241af1577923ad
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb739567e18dc1f327b36f5aaa9f6e31ddcb9fdb5321462030c9aedc48a9296
3
  size 4400216536