thieu86 commited on
Commit
c0306a0
·
verified ·
1 Parent(s): 2ef51e2

Run 5. Outer Step 98. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +80 -80
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -2,26 +2,26 @@
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": "NOT_ALIVE",
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": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
- "111": "NON_PARTICIPATING",
20
- "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
- "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
@@ -29,7 +29,7 @@
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
- "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
  "126": "NOT_ALIVE",
@@ -39,67 +39,67 @@
39
  "13": "NON_PARTICIPATING",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
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": "NOT_ALIVE",
50
- "14": "SUCCESS",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
- "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
58
- "147": "NOT_ALIVE",
59
- "148": "NON_PARTICIPATING",
60
- "149": "NON_PARTICIPATING",
61
  "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
- "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NOT_ALIVE",
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": "SUCCESS",
78
- "165": "NON_PARTICIPATING",
79
- "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
- "168": "NON_PARTICIPATING",
82
  "169": "NOT_ALIVE",
83
  "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
- "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
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": "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": "NOT_ALIVE",
103
  "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
@@ -111,19 +111,19 @@
111
  "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
113
  "197": "NOT_ALIVE",
114
- "198": "NOT_ALIVE",
115
- "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
- "20": "NON_PARTICIPATING",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
- "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
- "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
@@ -131,8 +131,8 @@
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
- "215": "SUCCESS",
135
- "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
@@ -146,7 +146,7 @@
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
- "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
@@ -155,12 +155,12 @@
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
- "237": "NON_PARTICIPATING",
159
- "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
- "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
@@ -177,85 +177,85 @@
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
- "27": "NON_PARTICIPATING",
181
- "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
  "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
- "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "NOT_ALIVE",
190
- "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
- "38": "SUCCESS",
193
- "39": "SUCCESS",
194
- "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
- "41": "NOT_ALIVE",
197
- "42": "SUCCESS",
198
  "43": "NON_PARTICIPATING",
199
- "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
- "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
- "5": "SUCCESS",
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": "SUCCESS",
213
- "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
- "59": "SUCCESS",
216
  "6": "NON_PARTICIPATING",
217
- "60": "NOT_ALIVE",
218
- "61": "NOT_ALIVE",
219
- "62": "SUCCESS",
220
- "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
- "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
- "7": "SUCCESS",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
233
- "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
  "8": "NON_PARTICIPATING",
239
- "80": "NOT_ALIVE",
240
- "81": "NON_PARTICIPATING",
241
- "82": "NOT_ALIVE",
242
- "83": "NON_PARTICIPATING",
243
  "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
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",
256
  "96": "NOT_ALIVE",
257
  "97": "NON_PARTICIPATING",
258
- "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5950879,
268
- 5950907
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": 55,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5948952,
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": "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",
 
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",
 
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",
54
  "143": "NON_PARTICIPATING",
55
+ "144": "NON_PARTICIPATING",
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",
 
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",
121
+ "203": "NOT_ALIVE",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
+ "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
 
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",
 
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",
 
155
  "234": "NON_PARTICIPATING",
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",
 
177
  "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
+ "27": "NOT_ALIVE",
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",
224
  "67": "NOT_ALIVE",
225
+ "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
+ "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
233
+ "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
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",
256
  "96": "NOT_ALIVE",
257
  "97": "NON_PARTICIPATING",
258
+ "98": "NON_PARTICIPATING",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5951072,
268
+ 5951098
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": 5950870,
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:c631760854ace8ad0bbe4dbb622c6aade338ed39f6e4235abdb9d07d71516a37
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5e28bf166304a60058eb80cba58452403ad86529213a7c3b4473d3ca2b93119
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd74715bae0e400bef073fb4ee2343b59473129f2527a60c190e2e1af459ad7e
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21aed827e47331dae21b44e96d581c7bf386e7afb91a39441eb1bbb8fe02aec
3
  size 4400216536