ncaagcc commited on
Commit
5d8bea0
·
verified ·
1 Parent(s): 9f687d7

Run 8. Outer Step 61. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +92 -92
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,45 +2,45 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
- "104": "NON_PARTICIPATING",
12
  "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
- "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NOT_ALIVE",
20
- "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
- "117": "FAIL",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
- "121": "SUCCESS",
31
  "122": "SUCCESS",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
- "126": "FAIL",
36
- "127": "SUCCESS",
37
  "128": "SUCCESS",
38
- "129": "NOT_ALIVE",
39
- "13": "NOT_ALIVE",
40
- "130": "NOT_ALIVE",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
- "133": "SUCCESS",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
@@ -48,17 +48,17 @@
48
  "138": "NON_PARTICIPATING",
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
- "140": "NOT_ALIVE",
52
- "141": "NOT_ALIVE",
53
- "142": "SUCCESS",
54
- "143": "SUCCESS",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
- "146": "SUCCESS",
58
  "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
- "149": "NOT_ALIVE",
61
- "15": "SUCCESS",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
@@ -67,13 +67,13 @@
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
- "161": "FAIL",
75
  "162": "NON_PARTICIPATING",
76
- "163": "SUCCESS",
77
  "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
@@ -83,28 +83,28 @@
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "SUCCESS",
86
- "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
- "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
- "178": "NON_PARTICIPATING",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
- "182": "NOT_ALIVE",
98
- "183": "SUCCESS",
99
- "184": "NON_PARTICIPATING",
100
- "185": "FAIL",
101
- "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
- "188": "NON_PARTICIPATING",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
- "191": "FAIL",
108
  "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
@@ -112,32 +112,32 @@
112
  "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
- "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "FAIL",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "FAIL",
122
  "204": "SUCCESS",
123
- "205": "SUCCESS",
124
  "206": "SUCCESS",
125
- "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
- "209": "FAIL",
128
  "21": "SUCCESS",
129
- "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
- "212": "NOT_ALIVE",
132
- "213": "NOT_ALIVE",
133
  "214": "SUCCESS",
134
- "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "NOT_ALIVE",
138
- "219": "SUCCESS",
139
  "22": "SUCCESS",
140
- "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
@@ -148,114 +148,114 @@
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
  "233": "SUCCESS",
155
- "234": "SUCCESS",
156
- "235": "NOT_ALIVE",
157
  "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
- "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
- "242": "FAIL",
165
- "243": "NOT_ALIVE",
166
  "244": "SUCCESS",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
- "247": "SUCCESS",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "FAIL",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
  "30": "FAIL",
185
  "31": "SUCCESS",
186
- "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
- "34": "FAIL",
189
- "35": "FAIL",
190
  "36": "SUCCESS",
191
- "37": "NON_PARTICIPATING",
192
- "38": "NOT_ALIVE",
193
- "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "FAIL",
197
- "42": "FAIL",
198
- "43": "NON_PARTICIPATING",
199
- "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
- "5": "SUCCESS",
206
- "50": "SUCCESS",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "SUCCESS",
211
- "55": "FAIL",
212
- "56": "NON_PARTICIPATING",
213
- "57": "FAIL",
214
  "58": "SUCCESS",
215
- "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
- "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
- "7": "FAIL",
228
  "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
- "72": "FAIL",
231
  "73": "NON_PARTICIPATING",
232
- "74": "FAIL",
233
  "75": "NON_PARTICIPATING",
234
- "76": "SUCCESS",
235
  "77": "SUCCESS",
236
- "78": "FAIL",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
- "81": "NOT_ALIVE",
241
- "82": "FAIL",
242
  "83": "SUCCESS",
243
- "84": "FAIL",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
- "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
- "90": "SUCCESS",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
- "93": "NON_PARTICIPATING",
254
  "94": "NOT_ALIVE",
255
- "95": "FAIL",
256
  "96": "SUCCESS",
257
- "97": "FAIL",
258
- "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,18 +264,18 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6383098,
268
- 6383123,
269
- 6383144
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
- "inner_step": 122,
277
  "intermediate_size": 5632,
278
- "last_allreduce_block": 6382220,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
+ "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
+ "104": "FAIL",
12
  "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
+ "109": "NOT_ALIVE",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NOT_ALIVE",
20
+ "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
  "118": "NOT_ALIVE",
27
  "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
+ "121": "NON_PARTICIPATING",
31
  "122": "SUCCESS",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
+ "126": "SUCCESS",
36
+ "127": "FAIL",
37
  "128": "SUCCESS",
38
+ "129": "NON_PARTICIPATING",
39
+ "13": "SUCCESS",
40
+ "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
+ "133": "NON_PARTICIPATING",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
 
48
  "138": "NON_PARTICIPATING",
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
+ "140": "NON_PARTICIPATING",
52
+ "141": "NON_PARTICIPATING",
53
+ "142": "FAIL",
54
+ "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
+ "146": "NOT_ALIVE",
58
  "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "FAIL",
61
+ "15": "FAIL",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
 
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NOT_ALIVE",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "SUCCESS",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
 
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "SUCCESS",
86
+ "172": "FAIL",
87
  "173": "SUCCESS",
88
+ "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
+ "178": "FAIL",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
+ "182": "SUCCESS",
98
+ "183": "FAIL",
99
+ "184": "SUCCESS",
100
+ "185": "NON_PARTICIPATING",
101
+ "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
+ "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "SUCCESS",
108
  "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
 
112
  "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "FAIL",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "SUCCESS",
122
  "204": "SUCCESS",
123
+ "205": "NON_PARTICIPATING",
124
  "206": "SUCCESS",
125
+ "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "SUCCESS",
128
  "21": "SUCCESS",
129
+ "210": "NOT_ALIVE",
130
  "211": "SUCCESS",
131
+ "212": "FAIL",
132
+ "213": "SUCCESS",
133
  "214": "SUCCESS",
134
+ "215": "NOT_ALIVE",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "SUCCESS",
138
+ "219": "FAIL",
139
  "22": "SUCCESS",
140
+ "220": "SUCCESS",
141
  "221": "SUCCESS",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
 
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
+ "230": "FAIL",
152
  "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
  "233": "SUCCESS",
155
+ "234": "FAIL",
156
+ "235": "SUCCESS",
157
  "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
+ "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "SUCCESS",
165
+ "243": "NON_PARTICIPATING",
166
  "244": "SUCCESS",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "FAIL",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "SUCCESS",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
  "30": "FAIL",
185
  "31": "SUCCESS",
186
+ "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
+ "34": "NOT_ALIVE",
189
+ "35": "NOT_ALIVE",
190
  "36": "SUCCESS",
191
+ "37": "SUCCESS",
192
+ "38": "NON_PARTICIPATING",
193
+ "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "SUCCESS",
197
+ "42": "SUCCESS",
198
+ "43": "NOT_ALIVE",
199
+ "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "FAIL",
206
+ "50": "FAIL",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "SUCCESS",
211
+ "55": "NON_PARTICIPATING",
212
+ "56": "SUCCESS",
213
+ "57": "SUCCESS",
214
  "58": "SUCCESS",
215
+ "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
+ "62": "SUCCESS",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
+ "7": "SUCCESS",
228
  "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "FAIL",
235
  "77": "SUCCESS",
236
+ "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
+ "81": "NON_PARTICIPATING",
241
+ "82": "SUCCESS",
242
  "83": "SUCCESS",
243
+ "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
+ "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
+ "90": "FAIL",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
+ "93": "NOT_ALIVE",
254
  "94": "NOT_ALIVE",
255
+ "95": "NON_PARTICIPATING",
256
  "96": "SUCCESS",
257
+ "97": "SUCCESS",
258
+ "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6383208,
268
+ 6383222,
269
+ 6383237
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
+ "inner_step": 5,
277
  "intermediate_size": 5632,
278
+ "last_allreduce_block": 6382929,
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 sha256:7fc4401c5ffb21787f18980b69d7f0e3537a21e89aaeb4c0b4629571143c33ea
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0a4dc59a46322bc6a6f9f6bc865e864600a03c408ca0a51371afe2ece9dfd24
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea991ef7074714ac767c07222d543ce80e7c08367ffdbac91ab9edfe561b9f6a
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3513823d96f18273d5eecc97eee318351f22fe40c5284b2fd71776a50cd57570
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7126f79e9e20e7c600ac4191466365516d50725cddc2c669e1dc961385472b63
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67d0d1568c25c1e84f29566cba815863d46c4574ac50a840a0c479a4f9618ef9
3
  size 4400216536