ncaagcc commited on
Commit
d7fbb88
·
verified ·
1 Parent(s): 38cfd48

Run 5. Outer Step 133. Inner Step 1.

Browse files
Files changed (4) hide show
  1. config.json +86 -86
  2. gradients.pt +3 -0
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,83 +2,83 @@
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": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
- "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
- "108": "SUCCESS",
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
- "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
- "112": "NOT_ALIVE",
21
- "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
- "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
- "122": "NOT_ALIVE",
32
  "123": "NOT_ALIVE",
33
- "124": "FAIL",
34
  "125": "NON_PARTICIPATING",
35
- "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
- "128": "NOT_ALIVE",
38
- "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
- "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
- "133": "NOT_ALIVE",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
- "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
- "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
- "148": "FAIL",
60
- "149": "NOT_ALIVE",
61
- "15": "NOT_ALIVE",
62
- "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
- "154": "SUCCESS",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NOT_ALIVE",
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": "NOT_ALIVE",
80
- "167": "NOT_ALIVE",
81
- "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
@@ -99,46 +99,46 @@
99
  "184": "NON_PARTICIPATING",
100
  "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
102
- "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
- "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
- "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
- "196": "NON_PARTICIPATING",
113
- "197": "NOT_ALIVE",
114
- "198": "NOT_ALIVE",
115
- "199": "NOT_ALIVE",
116
  "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
- "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
- "204": "SUCCESS",
123
- "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
- "210": "NOT_ALIVE",
130
- "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
- "213": "FAIL",
133
- "214": "NOT_ALIVE",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
- "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
@@ -146,7 +146,7 @@
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
- "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
@@ -159,62 +159,62 @@
159
  "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
- "240": "NOT_ALIVE",
163
- "241": "NOT_ALIVE",
164
- "242": "NOT_ALIVE",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
- "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
- "248": "NOT_ALIVE",
171
- "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
- "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
- "29": "NOT_ALIVE",
183
  "3": "NON_PARTICIPATING",
184
- "30": "SUCCESS",
185
  "31": "NOT_ALIVE",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
- "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
- "38": "NON_PARTICIPATING",
193
- "39": "FAIL",
194
  "4": "NON_PARTICIPATING",
195
- "40": "NOT_ALIVE",
196
- "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
- "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
204
- "49": "NOT_ALIVE",
205
- "5": "NON_PARTICIPATING",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
- "52": "SUCCESS",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
- "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NON_PARTICIPATING",
217
- "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
@@ -227,35 +227,35 @@
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NON_PARTICIPATING",
231
- "73": "NOT_ALIVE",
232
- "74": "NON_PARTICIPATING",
233
- "75": "NON_PARTICIPATING",
234
- "76": "NON_PARTICIPATING",
235
- "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
- "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
- "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
- "9": "NOT_ALIVE",
250
- "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
- "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
- "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
- "98": "NON_PARTICIPATING",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5994296,
268
- 5994331
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": 30,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5992468,
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": "NON_PARTICIPATING",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
+ "106": "NOT_ALIVE",
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": "SUCCESS",
21
+ "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
+ "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
33
+ "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
+ "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
+ "128": "NON_PARTICIPATING",
38
+ "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
+ "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
+ "136": "SUCCESS",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
+ "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "SUCCESS",
60
+ "149": "NON_PARTICIPATING",
61
+ "15": "SUCCESS",
62
+ "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
+ "16": "NOT_ALIVE",
73
+ "160": "NON_PARTICIPATING",
74
+ "161": "NOT_ALIVE",
75
+ "162": "NOT_ALIVE",
76
  "163": "NOT_ALIVE",
77
+ "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
+ "166": "NON_PARTICIPATING",
80
+ "167": "NON_PARTICIPATING",
81
+ "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
 
99
  "184": "NON_PARTICIPATING",
100
  "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
102
+ "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
+ "190": "NON_PARTICIPATING",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
+ "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
+ "196": "NOT_ALIVE",
113
+ "197": "NON_PARTICIPATING",
114
+ "198": "NON_PARTICIPATING",
115
+ "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
+ "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
+ "204": "NOT_ALIVE",
123
+ "205": "NON_PARTICIPATING",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
+ "210": "NON_PARTICIPATING",
130
+ "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
+ "213": "SUCCESS",
133
+ "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
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": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
 
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
 
159
  "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
+ "240": "NON_PARTICIPATING",
163
+ "241": "NON_PARTICIPATING",
164
+ "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
+ "246": "NOT_ALIVE",
169
  "247": "NON_PARTICIPATING",
170
+ "248": "NON_PARTICIPATING",
171
+ "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
+ "254": "SUCCESS",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
+ "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
+ "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
+ "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
+ "39": "SUCCESS",
194
  "4": "NON_PARTICIPATING",
195
+ "40": "SUCCESS",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
+ "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
+ "49": "NON_PARTICIPATING",
205
+ "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
+ "52": "FAIL",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
+ "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NON_PARTICIPATING",
217
+ "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
  "63": "NON_PARTICIPATING",
 
227
  "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NOT_ALIVE",
231
+ "73": "NON_PARTICIPATING",
232
+ "74": "NOT_ALIVE",
233
+ "75": "NOT_ALIVE",
234
+ "76": "NOT_ALIVE",
235
+ "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
237
+ "79": "NON_PARTICIPATING",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
+ "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
+ "9": "NON_PARTICIPATING",
250
+ "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
+ "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
+ "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6004035,
268
+ 6004058
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": 1,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6003212,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
gradients.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91367e36f2995d71ea86aae850d6fac84c794c85da0ec39b7d85e432e77ddfaa
3
+ size 44585978
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3249de78e3d0baa8edb9b131af1c7c5221250ca28e78525fa70c6320736c681
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b1c7d86b6b6b70db5a64b18f344091f7e9691f08370471250e4c93a843c786
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80e95a4cc43d427e776b9bcc2aa3628edd91d53be8a33628f3e7e98d52d47c1b
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9355ed218934b233d28a1d01073586702875d0d5d9c648d1b84fbcb3249c522
3
  size 4400216536