penguin102 commited on
Commit
1f7774c
·
verified ·
1 Parent(s): b24d39a

Run 5. Outer Step 46. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +68 -68
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -2,7 +2,7 @@
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": "NOT_ALIVE",
@@ -13,12 +13,12 @@
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
- "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
- "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
@@ -27,17 +27,17 @@
27
  "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
- "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
- "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
38
- "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
- "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
@@ -46,7 +46,7 @@
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
- "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "SUCCESS",
@@ -55,46 +55,46 @@
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
- "147": "NON_PARTICIPATING",
59
- "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NON_PARTICIPATING",
62
- "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
- "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
- "155": "NON_PARTICIPATING",
68
- "156": "NON_PARTICIPATING",
69
  "157": "NOT_ALIVE",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
- "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
77
  "164": "SUCCESS",
78
- "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
- "167": "NON_PARTICIPATING",
81
- "168": "NOT_ALIVE",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
- "170": "NON_PARTICIPATING",
85
  "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "SUCCESS",
89
- "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "SUCCESS",
95
  "180": "NOT_ALIVE",
96
  "181": "NON_PARTICIPATING",
97
- "182": "NOT_ALIVE",
98
  "183": "SUCCESS",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
@@ -104,48 +104,48 @@
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
- "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
- "196": "NON_PARTICIPATING",
113
- "197": "NON_PARTICIPATING",
114
  "198": "NOT_ALIVE",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
- "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
- "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
- "211": "NOT_ALIVE",
131
  "212": "NOT_ALIVE",
132
- "213": "NOT_ALIVE",
133
- "214": "NOT_ALIVE",
134
- "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
139
  "22": "NON_PARTICIPATING",
140
- "220": "NON_PARTICIPATING",
141
- "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
- "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
- "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
@@ -154,59 +154,59 @@
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
- "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
- "240": "NON_PARTICIPATING",
163
  "241": "NOT_ALIVE",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
- "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
- "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
- "250": "NOT_ALIVE",
174
- "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
- "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
- "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
- "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
- "41": "SUCCESS",
197
- "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
- "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NOT_ALIVE",
208
  "52": "NON_PARTICIPATING",
209
- "53": "NOT_ALIVE",
210
  "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
  "56": "SUCCESS",
@@ -220,18 +220,18 @@
220
  "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
- "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
- "69": "NOT_ALIVE",
227
  "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
- "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
- "74": "NON_PARTICIPATING",
233
- "75": "SUCCESS",
234
- "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
@@ -243,7 +243,7 @@
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
- "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
@@ -251,11 +251,11 @@
251
  "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
254
- "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
- "98": "SUCCESS",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5881524,
268
- 5881553
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": 88,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5877003,
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": "NOT_ALIVE",
 
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
+ "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
+ "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
 
27
  "119": "NOT_ALIVE",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
+ "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
+ "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
+ "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
+ "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
 
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "SUCCESS",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "SUCCESS",
 
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
+ "147": "NOT_ALIVE",
59
+ "148": "SUCCESS",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NON_PARTICIPATING",
62
+ "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
+ "152": "NON_PARTICIPATING",
65
+ "153": "NOT_ALIVE",
66
  "154": "NOT_ALIVE",
67
+ "155": "SUCCESS",
68
+ "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "SUCCESS",
75
+ "162": "NON_PARTICIPATING",
76
  "163": "SUCCESS",
77
  "164": "SUCCESS",
78
+ "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
+ "167": "SUCCESS",
81
+ "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
+ "170": "NOT_ALIVE",
85
  "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "SUCCESS",
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": "NON_PARTICIPATING",
97
+ "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
 
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
+ "196": "NOT_ALIVE",
113
+ "197": "NOT_ALIVE",
114
  "198": "NOT_ALIVE",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
+ "20": "NON_PARTICIPATING",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
+ "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
+ "213": "NON_PARTICIPATING",
133
+ "214": "NON_PARTICIPATING",
134
+ "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
+ "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
139
  "22": "NON_PARTICIPATING",
140
+ "220": "SUCCESS",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
+ "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
+ "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
 
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
+ "236": "NON_PARTICIPATING",
158
  "237": "NOT_ALIVE",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
+ "240": "NOT_ALIVE",
163
  "241": "NOT_ALIVE",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "SUCCESS",
170
  "248": "NON_PARTICIPATING",
171
+ "249": "SUCCESS",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
+ "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
+ "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
+ "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "SUCCESS",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
+ "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
+ "41": "NOT_ALIVE",
197
+ "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
  "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
+ "48": "SUCCESS",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NOT_ALIVE",
208
  "52": "NON_PARTICIPATING",
209
+ "53": "NON_PARTICIPATING",
210
  "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
  "56": "SUCCESS",
 
220
  "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
+ "66": "SUCCESS",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
+ "69": "SUCCESS",
227
  "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
+ "71": "SUCCESS",
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
+ "74": "NOT_ALIVE",
233
+ "75": "NOT_ALIVE",
234
+ "76": "SUCCESS",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
 
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
+ "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
 
251
  "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
+ "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5881611,
268
+ 5881624
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": 2,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5881510,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1402e951cf7ef9144298f50101e9ab16fe20a9cb024937b02ad8a25929786bf
3
  size 8800564561
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28937963a5555d639fad997eff9b4160e883d5e69165bdb4ce597f0ed68e0355
3
  size 8800564561
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca04fe6eb0d860384efd8d0b8dc9b7ac602673a20b3434fe86aa04413c129891
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a46c34a5ad5c9db3d1bbe193888bf1dbd8ed0e4c177f1e9341c5d54ccfa39f8
3
  size 4400216536