tensor-tech commited on
Commit
69236b0
·
verified ·
1 Parent(s): 656eef1

Run 5. Outer Step 57. Inner Step 1.

Browse files
Files changed (3) hide show
  1. config.json +175 -175
  2. inner_optimizer.pt +2 -2
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,230 +1,230 @@
1
  {
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
- "0": "SUCCESS",
5
  "1": "SUCCESS",
6
  "10": "SUCCESS",
7
- "100": "SUCCESS",
8
- "101": "SUCCESS",
9
- "102": "SUCCESS",
10
- "103": "SUCCESS",
11
- "104": "SUCCESS",
12
- "105": "SUCCESS",
13
- "106": "SUCCESS",
14
- "107": "SUCCESS",
15
- "108": "SUCCESS",
16
- "109": "SUCCESS",
17
  "11": "SUCCESS",
18
- "110": "SUCCESS",
19
- "111": "SUCCESS",
20
  "112": "SUCCESS",
21
- "113": "SUCCESS",
22
- "114": "SUCCESS",
23
- "115": "SUCCESS",
24
- "116": "SUCCESS",
25
  "117": "SUCCESS",
26
- "118": "SUCCESS",
27
- "119": "SUCCESS",
28
  "12": "SUCCESS",
29
- "120": "SUCCESS",
30
- "121": "SUCCESS",
31
- "122": "SUCCESS",
32
- "123": "SUCCESS",
33
- "124": "SUCCESS",
34
- "125": "SUCCESS",
35
  "126": "SUCCESS",
36
- "127": "SUCCESS",
37
- "128": "SUCCESS",
38
- "129": "SUCCESS",
39
- "13": "SUCCESS",
40
- "130": "SUCCESS",
41
- "131": "SUCCESS",
42
- "132": "SUCCESS",
43
- "133": "SUCCESS",
44
- "134": "SUCCESS",
45
- "135": "SUCCESS",
46
- "136": "SUCCESS",
47
- "137": "SUCCESS",
48
- "138": "SUCCESS",
49
- "139": "SUCCESS",
50
  "14": "SUCCESS",
51
- "140": "SUCCESS",
52
- "141": "SUCCESS",
53
- "142": "SUCCESS",
54
- "143": "SUCCESS",
55
- "144": "SUCCESS",
56
- "145": "SUCCESS",
57
- "146": "SUCCESS",
58
- "147": "SUCCESS",
59
- "148": "SUCCESS",
60
- "149": "SUCCESS",
61
  "15": "SUCCESS",
62
- "150": "SUCCESS",
63
- "151": "SUCCESS",
64
- "152": "SUCCESS",
65
- "153": "SUCCESS",
66
- "154": "SUCCESS",
67
- "155": "SUCCESS",
68
- "156": "SUCCESS",
69
- "157": "SUCCESS",
70
- "158": "SUCCESS",
71
- "159": "SUCCESS",
72
  "16": "SUCCESS",
73
- "160": "SUCCESS",
74
- "161": "SUCCESS",
75
- "162": "SUCCESS",
76
- "163": "SUCCESS",
77
- "164": "SUCCESS",
78
- "165": "SUCCESS",
79
  "166": "SUCCESS",
80
- "167": "SUCCESS",
81
- "168": "SUCCESS",
82
- "169": "SUCCESS",
83
  "17": "SUCCESS",
84
- "170": "SUCCESS",
85
- "171": "SUCCESS",
86
- "172": "SUCCESS",
87
- "173": "SUCCESS",
88
- "174": "SUCCESS",
89
- "175": "SUCCESS",
90
- "176": "SUCCESS",
91
- "177": "SUCCESS",
92
- "178": "SUCCESS",
93
- "179": "SUCCESS",
94
- "18": "SUCCESS",
95
- "180": "SUCCESS",
96
- "181": "SUCCESS",
97
- "182": "SUCCESS",
98
- "183": "SUCCESS",
99
- "184": "SUCCESS",
100
- "185": "SUCCESS",
101
- "186": "SUCCESS",
102
- "187": "SUCCESS",
103
- "188": "SUCCESS",
104
- "189": "SUCCESS",
105
- "19": "SUCCESS",
106
- "190": "SUCCESS",
107
- "191": "SUCCESS",
108
- "192": "SUCCESS",
109
- "193": "SUCCESS",
110
- "194": "SUCCESS",
111
- "195": "SUCCESS",
112
- "196": "SUCCESS",
113
- "197": "SUCCESS",
114
- "198": "SUCCESS",
115
- "199": "SUCCESS",
116
  "2": "SUCCESS",
117
- "20": "SUCCESS",
118
- "200": "SUCCESS",
119
- "201": "SUCCESS",
120
- "202": "SUCCESS",
121
  "203": "SUCCESS",
122
- "204": "SUCCESS",
123
- "205": "SUCCESS",
124
- "206": "SUCCESS",
125
- "207": "SUCCESS",
126
- "208": "SUCCESS",
127
- "209": "SUCCESS",
128
  "21": "SUCCESS",
129
  "210": "SUCCESS",
130
- "211": "SUCCESS",
131
- "212": "SUCCESS",
132
- "213": "SUCCESS",
133
- "214": "SUCCESS",
134
- "215": "SUCCESS",
135
- "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "SUCCESS",
138
- "219": "SUCCESS",
139
  "22": "SUCCESS",
140
- "220": "SUCCESS",
141
- "221": "SUCCESS",
142
- "222": "SUCCESS",
143
  "223": "SUCCESS",
144
- "224": "SUCCESS",
145
- "225": "SUCCESS",
146
- "226": "SUCCESS",
147
- "227": "SUCCESS",
148
- "228": "SUCCESS",
149
- "229": "SUCCESS",
150
  "23": "SUCCESS",
151
- "230": "SUCCESS",
152
- "231": "SUCCESS",
153
  "232": "SUCCESS",
154
- "233": "SUCCESS",
155
- "234": "SUCCESS",
156
- "235": "SUCCESS",
157
- "236": "SUCCESS",
158
- "237": "SUCCESS",
159
- "238": "SUCCESS",
160
- "239": "SUCCESS",
161
  "24": "SUCCESS",
162
- "240": "SUCCESS",
163
- "241": "SUCCESS",
164
- "242": "SUCCESS",
165
- "243": "SUCCESS",
166
- "244": "SUCCESS",
167
- "245": "SUCCESS",
168
- "246": "SUCCESS",
169
- "247": "SUCCESS",
170
- "248": "SUCCESS",
171
- "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
- "251": "SUCCESS",
175
- "252": "SUCCESS",
176
- "253": "SUCCESS",
177
- "254": "SUCCESS",
178
- "255": "SUCCESS",
179
  "26": "SUCCESS",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
- "30": "SUCCESS",
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
- "33": "SUCCESS",
188
  "34": "SUCCESS",
189
  "35": "SUCCESS",
190
  "36": "SUCCESS",
191
  "37": "SUCCESS",
192
- "38": "SUCCESS",
193
  "39": "SUCCESS",
194
  "4": "SUCCESS",
195
- "40": "SUCCESS",
196
- "41": "SUCCESS",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
- "44": "SUCCESS",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
- "47": "SUCCESS",
203
- "48": "SUCCESS",
204
  "49": "SUCCESS",
205
  "5": "SUCCESS",
206
  "50": "SUCCESS",
207
- "51": "SUCCESS",
208
- "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "SUCCESS",
211
  "55": "SUCCESS",
212
  "56": "SUCCESS",
213
- "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "SUCCESS",
216
- "6": "SUCCESS",
217
  "60": "SUCCESS",
218
- "61": "SUCCESS",
219
  "62": "SUCCESS",
220
- "63": "SUCCESS",
221
- "64": "SUCCESS",
222
  "65": "SUCCESS",
223
- "66": "SUCCESS",
224
  "67": "SUCCESS",
225
  "68": "SUCCESS",
226
  "69": "SUCCESS",
227
- "7": "SUCCESS",
228
  "70": "SUCCESS",
229
  "71": "SUCCESS",
230
  "72": "SUCCESS",
@@ -232,10 +232,10 @@
232
  "74": "SUCCESS",
233
  "75": "SUCCESS",
234
  "76": "SUCCESS",
235
- "77": "SUCCESS",
236
  "78": "SUCCESS",
237
  "79": "SUCCESS",
238
- "8": "SUCCESS",
239
  "80": "SUCCESS",
240
  "81": "SUCCESS",
241
  "82": "SUCCESS",
@@ -246,7 +246,7 @@
246
  "87": "SUCCESS",
247
  "88": "SUCCESS",
248
  "89": "SUCCESS",
249
- "9": "SUCCESS",
250
  "90": "SUCCESS",
251
  "91": "SUCCESS",
252
  "92": "SUCCESS",
@@ -254,7 +254,7 @@
254
  "94": "SUCCESS",
255
  "95": "SUCCESS",
256
  "96": "SUCCESS",
257
- "97": "SUCCESS",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
@@ -264,16 +264,16 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5782350
268
  ],
269
  "bos_token_id": 1,
270
  "eos_token_id": 2,
271
  "hidden_act": "silu",
272
  "hidden_size": 2048,
273
  "initializer_range": 0.02,
274
- "inner_step": 4,
275
  "intermediate_size": 5632,
276
- "last_allreduce_block": 5699671,
277
  "max_position_embeddings": 2048,
278
  "mlp_bias": false,
279
  "model_type": "llama",
 
1
  {
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
+ "0": "NON_PARTICIPATING",
5
  "1": "SUCCESS",
6
  "10": "SUCCESS",
7
+ "100": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
15
+ "108": "NON_PARTICIPATING",
16
+ "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
+ "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
+ "113": "NON_PARTICIPATING",
22
+ "114": "NON_PARTICIPATING",
23
+ "115": "NON_PARTICIPATING",
24
+ "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
+ "118": "NON_PARTICIPATING",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "SUCCESS",
29
+ "120": "NON_PARTICIPATING",
30
+ "121": "NON_PARTICIPATING",
31
+ "122": "NON_PARTICIPATING",
32
+ "123": "NON_PARTICIPATING",
33
+ "124": "NON_PARTICIPATING",
34
+ "125": "NON_PARTICIPATING",
35
  "126": "SUCCESS",
36
+ "127": "NON_PARTICIPATING",
37
+ "128": "NON_PARTICIPATING",
38
+ "129": "NON_PARTICIPATING",
39
+ "13": "NON_PARTICIPATING",
40
+ "130": "NON_PARTICIPATING",
41
+ "131": "NON_PARTICIPATING",
42
+ "132": "NON_PARTICIPATING",
43
+ "133": "NON_PARTICIPATING",
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": "SUCCESS",
51
+ "140": "NON_PARTICIPATING",
52
+ "141": "NON_PARTICIPATING",
53
+ "142": "NON_PARTICIPATING",
54
+ "143": "NON_PARTICIPATING",
55
+ "144": "NON_PARTICIPATING",
56
+ "145": "NON_PARTICIPATING",
57
+ "146": "NON_PARTICIPATING",
58
+ "147": "NON_PARTICIPATING",
59
+ "148": "NON_PARTICIPATING",
60
+ "149": "NON_PARTICIPATING",
61
  "15": "SUCCESS",
62
+ "150": "NON_PARTICIPATING",
63
+ "151": "NON_PARTICIPATING",
64
+ "152": "NON_PARTICIPATING",
65
+ "153": "NON_PARTICIPATING",
66
+ "154": "NON_PARTICIPATING",
67
+ "155": "NON_PARTICIPATING",
68
+ "156": "NON_PARTICIPATING",
69
+ "157": "NON_PARTICIPATING",
70
+ "158": "NON_PARTICIPATING",
71
+ "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
+ "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
+ "162": "NON_PARTICIPATING",
76
+ "163": "NON_PARTICIPATING",
77
+ "164": "NON_PARTICIPATING",
78
+ "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
+ "167": "NON_PARTICIPATING",
81
+ "168": "NON_PARTICIPATING",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "SUCCESS",
84
+ "170": "NON_PARTICIPATING",
85
+ "171": "NON_PARTICIPATING",
86
+ "172": "NON_PARTICIPATING",
87
+ "173": "NON_PARTICIPATING",
88
+ "174": "NON_PARTICIPATING",
89
+ "175": "NON_PARTICIPATING",
90
+ "176": "NON_PARTICIPATING",
91
+ "177": "NON_PARTICIPATING",
92
+ "178": "NON_PARTICIPATING",
93
+ "179": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
102
+ "187": "NON_PARTICIPATING",
103
+ "188": "NON_PARTICIPATING",
104
+ "189": "NON_PARTICIPATING",
105
+ "19": "FAIL",
106
+ "190": "NON_PARTICIPATING",
107
+ "191": "NON_PARTICIPATING",
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": "SUCCESS",
117
+ "20": "NON_PARTICIPATING",
118
+ "200": "NON_PARTICIPATING",
119
+ "201": "NON_PARTICIPATING",
120
+ "202": "NON_PARTICIPATING",
121
  "203": "SUCCESS",
122
+ "204": "NON_PARTICIPATING",
123
+ "205": "NON_PARTICIPATING",
124
+ "206": "NON_PARTICIPATING",
125
+ "207": "NON_PARTICIPATING",
126
+ "208": "NON_PARTICIPATING",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "SUCCESS",
130
+ "211": "NON_PARTICIPATING",
131
+ "212": "NON_PARTICIPATING",
132
+ "213": "NON_PARTICIPATING",
133
+ "214": "NON_PARTICIPATING",
134
+ "215": "NON_PARTICIPATING",
135
+ "216": "NON_PARTICIPATING",
136
  "217": "SUCCESS",
137
+ "218": "NON_PARTICIPATING",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
+ "220": "NON_PARTICIPATING",
141
+ "221": "NON_PARTICIPATING",
142
+ "222": "NON_PARTICIPATING",
143
  "223": "SUCCESS",
144
+ "224": "NON_PARTICIPATING",
145
+ "225": "NON_PARTICIPATING",
146
+ "226": "NON_PARTICIPATING",
147
+ "227": "NON_PARTICIPATING",
148
+ "228": "NON_PARTICIPATING",
149
+ "229": "NON_PARTICIPATING",
150
  "23": "SUCCESS",
151
+ "230": "NON_PARTICIPATING",
152
+ "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
+ "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
+ "235": "NON_PARTICIPATING",
157
+ "236": "NON_PARTICIPATING",
158
+ "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
+ "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
+ "240": "NON_PARTICIPATING",
163
+ "241": "NON_PARTICIPATING",
164
+ "242": "NON_PARTICIPATING",
165
+ "243": "NON_PARTICIPATING",
166
+ "244": "NON_PARTICIPATING",
167
+ "245": "NON_PARTICIPATING",
168
+ "246": "NON_PARTICIPATING",
169
+ "247": "NON_PARTICIPATING",
170
+ "248": "NON_PARTICIPATING",
171
+ "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
+ "251": "NON_PARTICIPATING",
175
+ "252": "NON_PARTICIPATING",
176
+ "253": "NON_PARTICIPATING",
177
+ "254": "NON_PARTICIPATING",
178
+ "255": "NON_PARTICIPATING",
179
  "26": "SUCCESS",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
+ "33": "NON_PARTICIPATING",
188
  "34": "SUCCESS",
189
  "35": "SUCCESS",
190
  "36": "SUCCESS",
191
  "37": "SUCCESS",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
194
  "4": "SUCCESS",
195
+ "40": "NON_PARTICIPATING",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
+ "44": "NON_PARTICIPATING",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
+ "47": "NON_PARTICIPATING",
203
+ "48": "NON_PARTICIPATING",
204
  "49": "SUCCESS",
205
  "5": "SUCCESS",
206
  "50": "SUCCESS",
207
+ "51": "FAIL",
208
+ "52": "NON_PARTICIPATING",
209
  "53": "SUCCESS",
210
  "54": "SUCCESS",
211
  "55": "SUCCESS",
212
  "56": "SUCCESS",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "SUCCESS",
215
  "59": "SUCCESS",
216
+ "6": "NON_PARTICIPATING",
217
  "60": "SUCCESS",
218
+ "61": "NON_PARTICIPATING",
219
  "62": "SUCCESS",
220
+ "63": "NON_PARTICIPATING",
221
+ "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
+ "66": "NON_PARTICIPATING",
224
  "67": "SUCCESS",
225
  "68": "SUCCESS",
226
  "69": "SUCCESS",
227
+ "7": "NON_PARTICIPATING",
228
  "70": "SUCCESS",
229
  "71": "SUCCESS",
230
  "72": "SUCCESS",
 
232
  "74": "SUCCESS",
233
  "75": "SUCCESS",
234
  "76": "SUCCESS",
235
+ "77": "NON_PARTICIPATING",
236
  "78": "SUCCESS",
237
  "79": "SUCCESS",
238
+ "8": "NON_PARTICIPATING",
239
  "80": "SUCCESS",
240
  "81": "SUCCESS",
241
  "82": "SUCCESS",
 
246
  "87": "SUCCESS",
247
  "88": "SUCCESS",
248
  "89": "SUCCESS",
249
+ "9": "NON_PARTICIPATING",
250
  "90": "SUCCESS",
251
  "91": "SUCCESS",
252
  "92": "SUCCESS",
 
254
  "94": "SUCCESS",
255
  "95": "SUCCESS",
256
  "96": "SUCCESS",
257
+ "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5782413
268
  ],
269
  "bos_token_id": 1,
270
  "eos_token_id": 2,
271
  "hidden_act": "silu",
272
  "hidden_size": 2048,
273
  "initializer_range": 0.02,
274
+ "inner_step": 1,
275
  "intermediate_size": 5632,
276
+ "last_allreduce_block": 5781479,
277
  "max_position_embeddings": 2048,
278
  "mlp_bias": false,
279
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38f7378845ca376c95936156705357d328dff98c6552d9b8bec84182a6a8f0cb
3
- size 8800564012
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7447a3208576c9a3d51cd61988c910f7ab66351f25efba0793f120e00f3386d3
3
+ size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:819e1e2dfa2a1a742de3d3f467776eb4ede4c75061ad2c105c5ba692539a1fd5
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d89ec26e88862eae8f5c275374bf68469262051aa5698b5b42ae1770823116
3
  size 4400216536