aalv2 commited on
Commit
163a30e
·
verified ·
1 Parent(s): 5d086b6

Run 5. Outer Step 99. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +81 -84
  2. inner_optimizer.pt +2 -2
  3. model.safetensors +1 -1
config.json CHANGED
@@ -2,52 +2,52 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NOT_ALIVE",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
- "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
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": "NOT_ALIVE",
20
  "112": "FAIL",
21
  "113": "NOT_ALIVE",
22
- "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
- "117": "NON_PARTICIPATING",
26
- "118": "NON_PARTICIPATING",
27
- "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
- "122": "NOT_ALIVE",
32
  "123": "NOT_ALIVE",
33
- "124": "NON_PARTICIPATING",
34
- "125": "NON_PARTICIPATING",
35
  "126": "NOT_ALIVE",
36
- "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NON_PARTICIPATING",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
- "132": "NOT_ALIVE",
43
- "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
- "137": "NOT_ALIVE",
48
- "138": "SUCCESS",
49
- "139": "NOT_ALIVE",
50
- "14": "FAIL",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
@@ -56,65 +56,65 @@
56
  "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
- "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "FAIL",
66
- "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NON_PARTICIPATING",
77
- "164": "NOT_ALIVE",
78
  "165": "FAIL",
79
- "166": "NOT_ALIVE",
80
- "167": "NON_PARTICIPATING",
81
- "168": "NOT_ALIVE",
82
  "169": "NOT_ALIVE",
83
- "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
- "172": "SUCCESS",
87
- "173": "SUCCESS",
88
- "174": "NON_PARTICIPATING",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
- "18": "NON_PARTICIPATING",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
- "185": "FAIL",
101
  "186": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
113
- "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
- "199": "NOT_ALIVE",
116
- "2": "NON_PARTICIPATING",
117
- "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
@@ -126,14 +126,14 @@
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
- "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "FAIL",
135
  "216": "NON_PARTICIPATING",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
@@ -146,9 +146,9 @@
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": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
@@ -156,24 +156,24 @@
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
- "238": "FAIL",
160
- "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
- "241": "NOT_ALIVE",
164
- "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
- "245": "SUCCESS",
168
- "246": "NON_PARTICIPATING",
169
- "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
- "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
@@ -181,43 +181,43 @@
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
- "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
  "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
- "38": "FAIL",
193
- "39": "NON_PARTICIPATING",
194
- "4": "NON_PARTICIPATING",
195
- "40": "NOT_ALIVE",
196
- "41": "NON_PARTICIPATING",
197
- "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
- "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
- "47": "NON_PARTICIPATING",
203
- "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
- "5": "FAIL",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
- "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
- "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
  "56": "FAIL",
213
- "57": "NOT_ALIVE",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
- "6": "NON_PARTICIPATING",
217
- "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
- "62": "NOT_ALIVE",
220
- "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
@@ -237,19 +237,19 @@
237
  "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
- "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NOT_ALIVE",
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": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
@@ -263,18 +263,15 @@
263
  ],
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
- "block_list": [
267
- 5951919,
268
- 5951923
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": 183,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5950870,
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": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
+ "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
+ "11": "FAIL",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "FAIL",
21
  "113": "NOT_ALIVE",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
+ "117": "FAIL",
26
+ "118": "NOT_ALIVE",
27
+ "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
+ "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
33
+ "124": "NOT_ALIVE",
34
+ "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
+ "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NON_PARTICIPATING",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
+ "132": "NON_PARTICIPATING",
43
+ "133": "FAIL",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
+ "137": "SUCCESS",
48
+ "138": "FAIL",
49
+ "139": "NON_PARTICIPATING",
50
+ "14": "SUCCESS",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
 
56
  "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "FAIL",
66
+ "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NOT_ALIVE",
71
+ "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "NOT_ALIVE",
77
+ "164": "FAIL",
78
  "165": "FAIL",
79
+ "166": "NON_PARTICIPATING",
80
+ "167": "NOT_ALIVE",
81
+ "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
83
+ "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
+ "172": "NON_PARTICIPATING",
87
+ "173": "NON_PARTICIPATING",
88
+ "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
+ "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
+ "183": "SUCCESS",
99
  "184": "NON_PARTICIPATING",
100
+ "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
113
+ "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "NON_PARTICIPATING",
116
+ "2": "NOT_ALIVE",
117
+ "20": "NON_PARTICIPATING",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
 
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "FAIL",
135
  "216": "NON_PARTICIPATING",
136
+ "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
 
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
+ "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
 
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
+ "238": "SUCCESS",
160
+ "239": "NOT_ALIVE",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
+ "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
+ "245": "NON_PARTICIPATING",
168
+ "246": "NOT_ALIVE",
169
+ "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
+ "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
 
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
+ "30": "NOT_ALIVE",
185
  "31": "NON_PARTICIPATING",
186
  "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "SUCCESS",
193
+ "39": "FAIL",
194
+ "4": "NOT_ALIVE",
195
+ "40": "NON_PARTICIPATING",
196
+ "41": "SUCCESS",
197
+ "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
+ "47": "NOT_ALIVE",
203
+ "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "NON_PARTICIPATING",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
+ "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "FAIL",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
+ "6": "NOT_ALIVE",
217
+ "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
+ "62": "NON_PARTICIPATING",
220
+ "63": "FAIL",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
 
237
  "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
+ "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NON_PARTICIPATING",
243
+ "84": "NON_PARTICIPATING",
244
+ "85": "NOT_ALIVE",
245
+ "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
+ "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
+ "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
 
263
  ],
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
+ "block_list": [],
 
 
 
267
  "bos_token_id": 1,
268
  "eos_token_id": 2,
269
  "hidden_act": "silu",
270
  "hidden_size": 2048,
271
  "initializer_range": 0.02,
272
+ "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 5951984,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11f20adacf64c41bd4c616bd7e79a05931067c41e2c52bb5e48723c3d03f4893
3
- size 8800564561
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51899347f4e0e32048e9b6ad2eac80a3d2d1aea93726efa0535519c293052811
3
+ size 2269
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9605a10bd863fd72c71f23ca94be29d2359c5b71655dc488471b8b4b6dabb668
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b18eb8605dba41b504ab2ec46eec9842c91f26e16758cd69dedc702ad43bd2
3
  size 4400216536