thieu86 commited on
Commit
a1afbb4
·
verified ·
1 Parent(s): dddcdac

Run 5. Outer Step 60. Inner Step 3.

Browse files
Files changed (3) hide show
  1. config.json +59 -59
  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": "NON_PARTICIPATING",
@@ -15,55 +15,55 @@
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
- "110": "SUCCESS",
19
  "111": "SUCCESS",
20
  "112": "NOT_ALIVE",
21
- "113": "NOT_ALIVE",
22
- "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
- "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
- "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
- "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
- "121": "NON_PARTICIPATING",
31
  "122": "SUCCESS",
32
  "123": "NOT_ALIVE",
33
  "124": "SUCCESS",
34
- "125": "NOT_ALIVE",
35
- "126": "NOT_ALIVE",
36
- "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
38
- "129": "NON_PARTICIPATING",
39
- "13": "NON_PARTICIPATING",
40
  "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
- "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
  "136": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
- "139": "NOT_ALIVE",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
- "141": "NOT_ALIVE",
53
  "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
57
- "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
- "148": "SUCCESS",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NON_PARTICIPATING",
62
  "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
- "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
@@ -71,19 +71,19 @@
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
- "168": "NOT_ALIVE",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "SUCCESS",
86
- "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "SUCCESS",
89
  "175": "NOT_ALIVE",
@@ -97,7 +97,7 @@
97
  "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
  "184": "NOT_ALIVE",
100
- "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
  "188": "NON_PARTICIPATING",
@@ -111,9 +111,9 @@
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
- "198": "NOT_ALIVE",
115
- "199": "NOT_ALIVE",
116
- "2": "NOT_ALIVE",
117
  "20": "NON_PARTICIPATING",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
@@ -123,7 +123,7 @@
123
  "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
- "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
128
  "21": "SUCCESS",
129
  "210": "SUCCESS",
@@ -134,10 +134,10 @@
134
  "215": "SUCCESS",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
- "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
  "22": "NON_PARTICIPATING",
140
- "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
  "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
@@ -145,21 +145,21 @@
145
  "225": "NON_PARTICIPATING",
146
  "226": "NOT_ALIVE",
147
  "227": "SUCCESS",
148
- "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
- "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NOT_ALIVE",
159
- "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
- "240": "NOT_ALIVE",
163
  "241": "NOT_ALIVE",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
@@ -172,15 +172,15 @@
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
- "252": "NOT_ALIVE",
176
- "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "SUCCESS",
180
  "27": "SUCCESS",
181
- "28": "NOT_ALIVE",
182
- "29": "NOT_ALIVE",
183
- "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NON_PARTICIPATING",
@@ -190,25 +190,25 @@
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "SUCCESS",
193
- "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
  "40": "SUCCESS",
196
- "41": "NON_PARTICIPATING",
197
- "42": "SUCCESS",
198
  "43": "SUCCESS",
199
- "44": "NOT_ALIVE",
200
- "45": "NON_PARTICIPATING",
201
- "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
- "48": "SUCCESS",
204
  "49": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
- "50": "NON_PARTICIPATING",
207
- "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NOT_ALIVE",
210
  "54": "SUCCESS",
211
- "55": "NON_PARTICIPATING",
212
  "56": "SUCCESS",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
@@ -227,7 +227,7 @@
227
  "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NON_PARTICIPATING",
231
  "73": "SUCCESS",
232
  "74": "SUCCESS",
233
  "75": "SUCCESS",
@@ -235,22 +235,22 @@
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
- "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
- "86": "SUCCESS",
246
  "87": "NON_PARTICIPATING",
247
- "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
- "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
- "93": "NON_PARTICIPATING",
254
  "94": "NOT_ALIVE",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5899290,
268
- 5899307
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": 99,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5898013,
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",
 
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
+ "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
  "112": "NOT_ALIVE",
21
+ "113": "NON_PARTICIPATING",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
+ "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
+ "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
+ "12": "NON_PARTICIPATING",
29
  "120": "NON_PARTICIPATING",
30
+ "121": "NOT_ALIVE",
31
  "122": "SUCCESS",
32
  "123": "NOT_ALIVE",
33
  "124": "SUCCESS",
34
+ "125": "NON_PARTICIPATING",
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",
44
+ "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
+ "141": "SUCCESS",
53
  "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NON_PARTICIPATING",
57
+ "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NON_PARTICIPATING",
62
  "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
+ "154": "NOT_ALIVE",
67
  "155": "SUCCESS",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
 
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "SUCCESS",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "SUCCESS",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "SUCCESS",
86
+ "172": "NON_PARTICIPATING",
87
  "173": "NOT_ALIVE",
88
  "174": "SUCCESS",
89
  "175": "NOT_ALIVE",
 
97
  "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
  "184": "NOT_ALIVE",
100
+ "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
  "188": "NON_PARTICIPATING",
 
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
+ "198": "NON_PARTICIPATING",
115
+ "199": "NON_PARTICIPATING",
116
+ "2": "NON_PARTICIPATING",
117
  "20": "NON_PARTICIPATING",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
 
123
  "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
+ "208": "NON_PARTICIPATING",
127
  "209": "SUCCESS",
128
  "21": "SUCCESS",
129
  "210": "SUCCESS",
 
134
  "215": "SUCCESS",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
+ "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
139
  "22": "NON_PARTICIPATING",
140
+ "220": "SUCCESS",
141
  "221": "SUCCESS",
142
  "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
 
145
  "225": "NON_PARTICIPATING",
146
  "226": "NOT_ALIVE",
147
  "227": "SUCCESS",
148
+ "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
+ "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NOT_ALIVE",
159
+ "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
+ "240": "NON_PARTICIPATING",
163
  "241": "NOT_ALIVE",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
 
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": "SUCCESS",
181
+ "28": "SUCCESS",
182
+ "29": "NON_PARTICIPATING",
183
+ "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NON_PARTICIPATING",
 
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "SUCCESS",
193
+ "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "SUCCESS",
196
+ "41": "SUCCESS",
197
+ "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
+ "44": "NON_PARTICIPATING",
200
+ "45": "SUCCESS",
201
+ "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
+ "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
+ "50": "NOT_ALIVE",
207
+ "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NOT_ALIVE",
210
  "54": "SUCCESS",
211
+ "55": "SUCCESS",
212
  "56": "SUCCESS",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
 
227
  "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
  "74": "SUCCESS",
233
  "75": "SUCCESS",
 
235
  "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
+ "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
+ "88": "NOT_ALIVE",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
+ "91": "NON_PARTICIPATING",
252
  "92": "SUCCESS",
253
+ "93": "NOT_ALIVE",
254
  "94": "NOT_ALIVE",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5899463,
268
+ 5899531
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": 3,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5899216,
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 sha256:7782f5b2b1de2bea763eaf8ebaf9e78d8b20818aef1c6ed366744cbaea4760ae
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5768aec8ccf895f0ec8298f8ee8829b4dc327c0da91807027c61b44d75597133
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d8392d14e0ac3c774eae0e2da463d375a7c82aec02a40eab9373ea92b346932
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c3cb000a4229fdf11377df2f55ef7f04a18cfac7bf5b7437d6748da61d747b9
3
  size 4400216536