ncaagcc commited on
Commit
caedac0
·
verified ·
1 Parent(s): 75b856b

Run 10. Outer Step 5. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +106 -106
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,78 +2,78 @@
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": "NOT_ALIVE",
9
  "102": "FAIL",
10
- "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "FAIL",
13
- "106": "FAIL",
14
- "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
- "109": "FAIL",
17
- "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
- "113": "NOT_ALIVE",
22
- "114": "NON_PARTICIPATING",
23
  "115": "FAIL",
24
- "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
- "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
- "120": "SUCCESS",
30
  "121": "NOT_ALIVE",
31
  "122": "FAIL",
32
- "123": "NON_PARTICIPATING",
33
- "124": "FAIL",
34
  "125": "NON_PARTICIPATING",
35
- "126": "NON_PARTICIPATING",
36
- "127": "NOT_ALIVE",
37
- "128": "FAIL",
38
- "129": "NON_PARTICIPATING",
39
- "13": "NON_PARTICIPATING",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
- "132": "NON_PARTICIPATING",
43
- "133": "NON_PARTICIPATING",
44
  "134": "SUCCESS",
45
- "135": "FAIL",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NOT_ALIVE",
50
- "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
- "142": "FAIL",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
- "148": "NON_PARTICIPATING",
60
- "149": "NOT_ALIVE",
61
- "15": "NON_PARTICIPATING",
62
- "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
  "154": "FAIL",
67
- "155": "NOT_ALIVE",
68
- "156": "NON_PARTICIPATING",
69
- "157": "NON_PARTICIPATING",
70
- "158": "NOT_ALIVE",
71
  "159": "NON_PARTICIPATING",
72
- "16": "SUCCESS",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
@@ -85,61 +85,61 @@
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
- "174": "FAIL",
89
  "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
- "177": "FAIL",
92
  "178": "NOT_ALIVE",
93
- "179": "FAIL",
94
  "18": "NON_PARTICIPATING",
95
- "180": "NON_PARTICIPATING",
96
- "181": "NON_PARTICIPATING",
97
- "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
- "184": "NON_PARTICIPATING",
100
- "185": "NON_PARTICIPATING",
101
- "186": "NOT_ALIVE",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
- "19": "NON_PARTICIPATING",
106
- "190": "SUCCESS",
107
  "191": "NON_PARTICIPATING",
108
- "192": "NON_PARTICIPATING",
109
- "193": "FAIL",
110
- "194": "FAIL",
111
- "195": "NOT_ALIVE",
112
  "196": "NON_PARTICIPATING",
113
- "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
  "199": "FAIL",
116
- "2": "NON_PARTICIPATING",
117
- "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
- "201": "SUCCESS",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "FAIL",
124
- "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
- "208": "SUCCESS",
127
- "209": "NON_PARTICIPATING",
128
  "21": "FAIL",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
- "212": "NON_PARTICIPATING",
132
- "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
- "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
- "221": "FAIL",
142
- "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "FAIL",
@@ -151,54 +151,54 @@
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NON_PARTICIPATING",
154
- "233": "FAIL",
155
- "234": "FAIL",
156
- "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
- "241": "NON_PARTICIPATING",
164
- "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "FAIL",
168
  "246": "FAIL",
169
- "247": "NON_PARTICIPATING",
170
- "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
  "252": "FAIL",
176
  "253": "FAIL",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NON_PARTICIPATING",
180
- "27": "NON_PARTICIPATING",
181
- "28": "FAIL",
182
- "29": "FAIL",
183
  "3": "FAIL",
184
- "30": "SUCCESS",
185
- "31": "NON_PARTICIPATING",
186
- "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
- "35": "FAIL",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
- "4": "NON_PARTICIPATING",
195
  "40": "NON_PARTICIPATING",
196
- "41": "NOT_ALIVE",
197
- "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
- "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
- "46": "FAIL",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
@@ -214,44 +214,44 @@
214
  "58": "NOT_ALIVE",
215
  "59": "FAIL",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
  "61": "FAIL",
219
- "62": "NOT_ALIVE",
220
- "63": "NON_PARTICIPATING",
221
- "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
- "69": "SUCCESS",
227
  "7": "NON_PARTICIPATING",
228
- "70": "NON_PARTICIPATING",
229
  "71": "NOT_ALIVE",
230
- "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
- "74": "SUCCESS",
233
- "75": "NON_PARTICIPATING",
234
- "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
- "79": "SUCCESS",
238
- "8": "NON_PARTICIPATING",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NON_PARTICIPATING",
243
- "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
- "86": "FAIL",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
- "89": "FAIL",
249
  "9": "NON_PARTICIPATING",
250
  "90": "FAIL",
251
  "91": "NON_PARTICIPATING",
252
  "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
- "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6465993,
268
- 6466007
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": 65,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6464980,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "FAIL",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
  "102": "FAIL",
10
+ "103": "FAIL",
11
  "104": "NOT_ALIVE",
12
+ "105": "NON_PARTICIPATING",
13
+ "106": "NON_PARTICIPATING",
14
+ "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
+ "109": "NOT_ALIVE",
17
+ "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
+ "113": "FAIL",
22
+ "114": "NOT_ALIVE",
23
  "115": "FAIL",
24
+ "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
+ "119": "FAIL",
28
  "12": "NOT_ALIVE",
29
+ "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "FAIL",
32
+ "123": "FAIL",
33
+ "124": "SUCCESS",
34
  "125": "NON_PARTICIPATING",
35
+ "126": "NOT_ALIVE",
36
+ "127": "FAIL",
37
+ "128": "NON_PARTICIPATING",
38
+ "129": "NOT_ALIVE",
39
+ "13": "FAIL",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
+ "132": "NOT_ALIVE",
43
+ "133": "FAIL",
44
  "134": "SUCCESS",
45
+ "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NOT_ALIVE",
50
+ "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
+ "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "NOT_ALIVE",
60
+ "149": "NON_PARTICIPATING",
61
+ "15": "FAIL",
62
+ "150": "FAIL",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "FAIL",
66
  "154": "FAIL",
67
+ "155": "SUCCESS",
68
+ "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
+ "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
+ "16": "NON_PARTICIPATING",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
 
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
+ "174": "NON_PARTICIPATING",
89
  "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
+ "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
+ "179": "NON_PARTICIPATING",
94
  "18": "NON_PARTICIPATING",
95
+ "180": "FAIL",
96
+ "181": "NOT_ALIVE",
97
+ "182": "FAIL",
98
  "183": "NON_PARTICIPATING",
99
+ "184": "FAIL",
100
+ "185": "NOT_ALIVE",
101
+ "186": "FAIL",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
+ "19": "NOT_ALIVE",
106
+ "190": "FAIL",
107
  "191": "NON_PARTICIPATING",
108
+ "192": "NOT_ALIVE",
109
+ "193": "SUCCESS",
110
+ "194": "NON_PARTICIPATING",
111
+ "195": "SUCCESS",
112
  "196": "NON_PARTICIPATING",
113
+ "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "FAIL",
116
+ "2": "NOT_ALIVE",
117
+ "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
119
+ "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
+ "205": "NOT_ALIVE",
124
+ "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
+ "208": "NON_PARTICIPATING",
127
+ "209": "FAIL",
128
  "21": "FAIL",
129
+ "210": "FAIL",
130
  "211": "NON_PARTICIPATING",
131
+ "212": "NOT_ALIVE",
132
+ "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
+ "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "NON_PARTICIPATING",
142
+ "222": "FAIL",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "FAIL",
 
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NON_PARTICIPATING",
154
+ "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
+ "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
+ "241": "NOT_ALIVE",
164
+ "242": "FAIL",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NOT_ALIVE",
168
  "246": "FAIL",
169
+ "247": "NOT_ALIVE",
170
+ "248": "FAIL",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
  "252": "FAIL",
176
  "253": "FAIL",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "FAIL",
180
+ "27": "NOT_ALIVE",
181
+ "28": "NON_PARTICIPATING",
182
+ "29": "NON_PARTICIPATING",
183
  "3": "FAIL",
184
+ "30": "NON_PARTICIPATING",
185
+ "31": "NOT_ALIVE",
186
+ "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
+ "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "SUCCESS",
197
+ "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
+ "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
+ "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
 
214
  "58": "NOT_ALIVE",
215
  "59": "FAIL",
216
  "6": "NOT_ALIVE",
217
+ "60": "NOT_ALIVE",
218
  "61": "FAIL",
219
+ "62": "NON_PARTICIPATING",
220
+ "63": "FAIL",
221
+ "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
+ "69": "FAIL",
227
  "7": "NON_PARTICIPATING",
228
+ "70": "FAIL",
229
  "71": "NOT_ALIVE",
230
+ "72": "FAIL",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "FAIL",
233
+ "75": "NOT_ALIVE",
234
+ "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
+ "79": "NON_PARTICIPATING",
238
+ "8": "FAIL",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NON_PARTICIPATING",
243
+ "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "NON_PARTICIPATING",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
+ "89": "SUCCESS",
249
  "9": "NON_PARTICIPATING",
250
  "90": "FAIL",
251
  "91": "NON_PARTICIPATING",
252
  "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6466300,
268
+ 6466324
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": 5,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6466263,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a10142457a51b7076b254afa5d12812d91dbf0ddaca9b0460eee172911f19c12
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99033430b95d620c780dd4d1d587d8a8a0c0234cf30a6f005ed89779ea7abe28
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfb7e379a7bd581e3cd618d855783ca598343957cffd0521d524b6748fee572e
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca91e35c7754f2aad3627181e979a67d2c9fd994405cffc135f1ee914428a4ed
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06cd2e6e0351155e3769a18291d40633e53dc997d28959bdb428a8beb7f4f918
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63df78781ea0112dfebb447c264132217dcde7c8dfef4b5bcb32b12e1ecdd1bc
3
  size 4400216536