zeras141a commited on
Commit
fd14aa3
·
verified ·
1 Parent(s): 72c2314

Run 6. Outer Step 100. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +52 -52
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. 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": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
@@ -16,21 +16,21 @@
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
- "111": "NON_PARTICIPATING",
20
- "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
- "115": "SUCCESS",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
- "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
- "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
@@ -40,13 +40,13 @@
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
- "133": "NON_PARTICIPATING",
44
  "134": "NOT_ALIVE",
45
  "135": "NOT_ALIVE",
46
- "136": "NOT_ALIVE",
47
  "137": "NON_PARTICIPATING",
48
- "138": "SUCCESS",
49
- "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
@@ -56,10 +56,10 @@
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
- "148": "NON_PARTICIPATING",
60
- "149": "NON_PARTICIPATING",
61
- "15": "SUCCESS",
62
- "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
@@ -70,31 +70,31 @@
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
- "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
- "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
- "168": "NOT_ALIVE",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
- "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
- "178": "NON_PARTICIPATING",
93
- "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
- "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
@@ -104,9 +104,9 @@
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": "NOT_ALIVE",
@@ -130,11 +130,11 @@
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
- "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
- "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
@@ -163,25 +163,25 @@
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
- "244": "NOT_ALIVE",
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
- "253": "NON_PARTICIPATING",
177
- "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
184
- "30": "SUCCESS",
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
@@ -192,58 +192,58 @@
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
- "43": "NON_PARTICIPATING",
199
- "44": "SUCCESS",
200
- "45": "NON_PARTICIPATING",
201
- "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
- "52": "SUCCESS",
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
- "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
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": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
- "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
- "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
- "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
- "86": "NOT_ALIVE",
246
- "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6200166,
268
- 6200179
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": 80,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6199538,
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": "FAIL",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
 
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
+ "111": "NOT_ALIVE",
20
+ "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
+ "115": "FAIL",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
+ "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
+ "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
 
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "FAIL",
44
  "134": "NOT_ALIVE",
45
  "135": "NOT_ALIVE",
46
+ "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "NON_PARTICIPATING",
49
+ "139": "FAIL",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
 
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
+ "148": "NOT_ALIVE",
60
+ "149": "NOT_ALIVE",
61
+ "15": "NOT_ALIVE",
62
+ "150": "FAIL",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
 
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
+ "160": "NOT_ALIVE",
74
+ "161": "FAIL",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
+ "166": "FAIL",
80
  "167": "NOT_ALIVE",
81
+ "168": "NON_PARTICIPATING",
82
+ "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
+ "173": "FAIL",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
+ "178": "NOT_ALIVE",
93
+ "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
+ "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
 
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
+ "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "FAIL",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
 
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
+ "214": "FAIL",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
+ "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
 
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
+ "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
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": "NOT_ALIVE",
176
+ "253": "NOT_ALIVE",
177
+ "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
184
+ "30": "FAIL",
185
  "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
 
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "NOT_ALIVE",
196
  "41": "NOT_ALIVE",
197
  "42": "NON_PARTICIPATING",
198
+ "43": "NOT_ALIVE",
199
+ "44": "FAIL",
200
+ "45": "NOT_ALIVE",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
+ "52": "FAIL",
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
+ "59": "FAIL",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
+ "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
+ "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
+ "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
+ "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
+ "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
+ "77": "FAIL",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
+ "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
+ "86": "NON_PARTICIPATING",
246
+ "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6200272,
268
+ 6200289
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": 5,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6200206,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2823189f320c63390bf421a5572e987083e0c2632efb415fc02165affc64df1b
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66393151279b007808957a533f601545f0e26e94dff88ef7769cfa7566708c48
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63be730b60b13b1102f3f138cdda9e088cd6043db77e7389af71566edde08882
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa77149ab1158c9f5bcb3bc7d42e9c51e0bfd7676e5527ebf41754519ab77f66
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b055f16dfd55879cf1d1f2a37dba9ee4977683f91eb491f1cbc284ce2408c7ac
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afa38fe8c74c13c9a5c9dcfa3269ea996ae653da99a788d4e766d8f71000c394
3
  size 4400216536