mizzaay commited on
Commit
278bd43
·
verified ·
1 Parent(s): d5ddd38

Run 6. Outer Step 66. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +47 -47
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,11 +2,11 @@
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",
9
- "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
@@ -27,31 +27,31 @@
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
- "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
  "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
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",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "NOT_ALIVE",
54
- "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
@@ -60,14 +60,14 @@
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
- "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
- "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
- "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
@@ -75,31 +75,31 @@
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
- "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
- "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
- "172": "NOT_ALIVE",
87
- "173": "NOT_ALIVE",
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": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NOT_ALIVE",
101
- "186": "NON_PARTICIPATING",
102
- "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
  "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
@@ -128,14 +128,14 @@
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
- "212": "NOT_ALIVE",
132
- "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
- "216": "NOT_ALIVE",
136
- "217": "NOT_ALIVE",
137
- "218": "NOT_ALIVE",
138
- "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
@@ -157,13 +157,13 @@
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
- "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
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",
@@ -177,28 +177,28 @@
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
- "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
- "32": "NOT_ALIVE",
187
- "33": "NON_PARTICIPATING",
188
- "34": "NOT_ALIVE",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
- "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
@@ -217,29 +217,29 @@
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
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": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
- "70": "NON_PARTICIPATING",
229
- "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
- "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
- "77": "NOT_ALIVE",
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": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
@@ -251,9 +251,9 @@
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
- "94": "NOT_ALIVE",
255
  "95": "NON_PARTICIPATING",
256
- "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "SUCCESS"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6173301,
268
- 6173333
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": 33,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6172668,
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": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
9
+ "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
 
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
+ "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
  "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "NOT_ALIVE",
54
+ "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
 
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
+ "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "SUCCESS",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
+ "158": "NOT_ALIVE",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
 
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
+ "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
80
+ "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
+ "172": "NON_PARTICIPATING",
87
+ "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
+ "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NOT_ALIVE",
101
+ "186": "NOT_ALIVE",
102
+ "187": "SUCCESS",
103
  "188": "NOT_ALIVE",
104
  "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
 
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
+ "212": "NON_PARTICIPATING",
132
+ "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
+ "216": "NON_PARTICIPATING",
136
+ "217": "NON_PARTICIPATING",
137
+ "218": "NON_PARTICIPATING",
138
+ "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
 
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
+ "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
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",
 
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
+ "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
+ "32": "NON_PARTICIPATING",
187
+ "33": "NOT_ALIVE",
188
+ "34": "NON_PARTICIPATING",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
 
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
+ "63": "NOT_ALIVE",
221
+ "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
+ "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
+ "70": "NOT_ALIVE",
229
+ "71": "SUCCESS",
230
  "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
+ "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
+ "77": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
 
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
+ "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "SUCCESS"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6173465,
268
+ 6173494
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": 6173336,
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 sha256:95874539f080f3618e19c6902b10615dab63f6d54b1d1a4726ee990d67824c23
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddc111f2251b6b5e95e6434e3acb8763948b1cdb0ef6b3ea46db24ac72cbe9d5
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1afff7428c000f4a7809a4f7751845a84dd11b70ab1aaf725be0cd67b51df4b9
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:286a9c4067b73b642a4f78cad862d8aa1d0c2ca963d666f28b2a115c2ab5aeef
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dc973db81f584d082c339c19d3dcd862fe8c465b052690fde3ac549760eda35
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377946a25cd24db087a6d79452f5199f8f4fb0eae7882dd1ee8853869b5b0cc1
3
  size 4400216536