sevalish commited on
Commit
990e6c3
·
verified ·
1 Parent(s): 62f83bf

Run 4. Outer Step 19. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +57 -58
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "_name_or_path": "sevalish/subnet38",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
6
- "1": "SUCCESS",
7
  "10": "SUCCESS",
8
  "100": "NON_PARTICIPATING",
9
- "101": "NON_PARTICIPATING",
10
  "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
  "104": "NON_PARTICIPATING",
@@ -24,26 +24,26 @@
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
26
  "117": "NON_PARTICIPATING",
27
- "118": "NON_PARTICIPATING",
28
  "119": "NON_PARTICIPATING",
29
  "12": "SUCCESS",
30
  "120": "SUCCESS",
31
  "121": "NON_PARTICIPATING",
32
- "122": "NON_PARTICIPATING",
33
- "123": "NON_PARTICIPATING",
34
  "124": "NON_PARTICIPATING",
35
  "125": "NON_PARTICIPATING",
36
  "126": "NON_PARTICIPATING",
37
- "127": "SUCCESS",
38
  "128": "NON_PARTICIPATING",
39
- "129": "SUCCESS",
40
  "13": "NON_PARTICIPATING",
41
  "130": "NON_PARTICIPATING",
42
  "131": "NON_PARTICIPATING",
43
  "132": "SUCCESS",
44
  "133": "NON_PARTICIPATING",
45
  "134": "NON_PARTICIPATING",
46
- "135": "SUCCESS",
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
  "138": "NON_PARTICIPATING",
@@ -58,19 +58,19 @@
58
  "146": "NON_PARTICIPATING",
59
  "147": "SUCCESS",
60
  "148": "SUCCESS",
61
- "149": "SUCCESS",
62
  "15": "SUCCESS",
63
- "150": "NON_PARTICIPATING",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
  "153": "NON_PARTICIPATING",
67
- "154": "SUCCESS",
68
- "155": "SUCCESS",
69
  "156": "SUCCESS",
70
  "157": "NON_PARTICIPATING",
71
  "158": "NON_PARTICIPATING",
72
  "159": "NON_PARTICIPATING",
73
- "16": "NON_PARTICIPATING",
74
  "160": "SUCCESS",
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
@@ -78,8 +78,8 @@
78
  "164": "NON_PARTICIPATING",
79
  "165": "NON_PARTICIPATING",
80
  "166": "NON_PARTICIPATING",
81
- "167": "NON_PARTICIPATING",
82
- "168": "NON_PARTICIPATING",
83
  "169": "NON_PARTICIPATING",
84
  "17": "SUCCESS",
85
  "170": "SUCCESS",
@@ -87,27 +87,27 @@
87
  "172": "SUCCESS",
88
  "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
- "175": "NON_PARTICIPATING",
91
  "176": "NON_PARTICIPATING",
92
  "177": "NON_PARTICIPATING",
93
  "178": "NON_PARTICIPATING",
94
  "179": "NON_PARTICIPATING",
95
- "18": "NON_PARTICIPATING",
96
  "180": "NON_PARTICIPATING",
97
  "181": "NON_PARTICIPATING",
98
  "182": "NON_PARTICIPATING",
99
  "183": "NON_PARTICIPATING",
100
- "184": "NON_PARTICIPATING",
101
  "185": "NON_PARTICIPATING",
102
- "186": "NON_PARTICIPATING",
103
  "187": "SUCCESS",
104
  "188": "NON_PARTICIPATING",
105
  "189": "NON_PARTICIPATING",
106
  "19": "NON_PARTICIPATING",
107
  "190": "NON_PARTICIPATING",
108
- "191": "NON_PARTICIPATING",
109
- "192": "NON_PARTICIPATING",
110
- "193": "NON_PARTICIPATING",
111
  "194": "NON_PARTICIPATING",
112
  "195": "SUCCESS",
113
  "196": "NON_PARTICIPATING",
@@ -119,31 +119,31 @@
119
  "200": "SUCCESS",
120
  "201": "SUCCESS",
121
  "202": "NON_PARTICIPATING",
122
- "203": "NON_PARTICIPATING",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
125
  "206": "NON_PARTICIPATING",
126
  "207": "NON_PARTICIPATING",
127
  "208": "NON_PARTICIPATING",
128
  "209": "NON_PARTICIPATING",
129
- "21": "NON_PARTICIPATING",
130
  "210": "NON_PARTICIPATING",
131
  "211": "NON_PARTICIPATING",
132
  "212": "NON_PARTICIPATING",
133
  "213": "NON_PARTICIPATING",
134
  "214": "SUCCESS",
135
- "215": "NON_PARTICIPATING",
136
  "216": "NON_PARTICIPATING",
137
  "217": "NON_PARTICIPATING",
138
  "218": "SUCCESS",
139
  "219": "NON_PARTICIPATING",
140
- "22": "NON_PARTICIPATING",
141
  "220": "NON_PARTICIPATING",
142
- "221": "NON_PARTICIPATING",
143
  "222": "NON_PARTICIPATING",
144
- "223": "NON_PARTICIPATING",
145
  "224": "NON_PARTICIPATING",
146
- "225": "FAIL",
147
  "226": "SUCCESS",
148
  "227": "NON_PARTICIPATING",
149
  "228": "NON_PARTICIPATING",
@@ -159,17 +159,17 @@
159
  "237": "NON_PARTICIPATING",
160
  "238": "NON_PARTICIPATING",
161
  "239": "NON_PARTICIPATING",
162
- "24": "NON_PARTICIPATING",
163
  "240": "NON_PARTICIPATING",
164
  "241": "SUCCESS",
165
  "242": "NON_PARTICIPATING",
166
  "243": "NON_PARTICIPATING",
167
- "244": "NON_PARTICIPATING",
168
  "245": "NON_PARTICIPATING",
169
  "246": "NON_PARTICIPATING",
170
- "247": "NON_PARTICIPATING",
171
  "248": "NON_PARTICIPATING",
172
- "249": "NON_PARTICIPATING",
173
  "25": "SUCCESS",
174
  "250": "SUCCESS",
175
  "251": "NON_PARTICIPATING",
@@ -179,10 +179,10 @@
179
  "255": "NON_PARTICIPATING",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
- "28": "NON_PARTICIPATING",
183
  "29": "SUCCESS",
184
  "3": "NON_PARTICIPATING",
185
- "30": "SUCCESS",
186
  "31": "NON_PARTICIPATING",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
@@ -193,12 +193,12 @@
193
  "38": "NON_PARTICIPATING",
194
  "39": "NON_PARTICIPATING",
195
  "4": "NON_PARTICIPATING",
196
- "40": "NON_PARTICIPATING",
197
- "41": "NON_PARTICIPATING",
198
  "42": "NON_PARTICIPATING",
199
- "43": "NON_PARTICIPATING",
200
- "44": "NON_PARTICIPATING",
201
- "45": "NON_PARTICIPATING",
202
  "46": "SUCCESS",
203
  "47": "SUCCESS",
204
  "48": "NON_PARTICIPATING",
@@ -214,18 +214,18 @@
214
  "57": "SUCCESS",
215
  "58": "NON_PARTICIPATING",
216
  "59": "NON_PARTICIPATING",
217
- "6": "SUCCESS",
218
  "60": "NON_PARTICIPATING",
219
  "61": "NON_PARTICIPATING",
220
  "62": "NON_PARTICIPATING",
221
  "63": "SUCCESS",
222
- "64": "FAIL",
223
  "65": "NON_PARTICIPATING",
224
  "66": "NON_PARTICIPATING",
225
- "67": "NON_PARTICIPATING",
226
- "68": "NON_PARTICIPATING",
227
  "69": "NON_PARTICIPATING",
228
- "7": "NON_PARTICIPATING",
229
  "70": "NON_PARTICIPATING",
230
  "71": "NON_PARTICIPATING",
231
  "72": "NON_PARTICIPATING",
@@ -241,19 +241,19 @@
241
  "81": "NON_PARTICIPATING",
242
  "82": "SUCCESS",
243
  "83": "NON_PARTICIPATING",
244
- "84": "NON_PARTICIPATING",
245
- "85": "SUCCESS",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
249
- "89": "NON_PARTICIPATING",
250
  "9": "NON_PARTICIPATING",
251
  "90": "NON_PARTICIPATING",
252
  "91": "SUCCESS",
253
  "92": "NON_PARTICIPATING",
254
  "93": "NON_PARTICIPATING",
255
  "94": "NON_PARTICIPATING",
256
- "95": "NON_PARTICIPATING",
257
  "96": "SUCCESS",
258
  "97": "NON_PARTICIPATING",
259
  "98": "NON_PARTICIPATING",
@@ -268,21 +268,20 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5522510,
272
- 5522514,
273
- 5522518,
274
- 5522521,
275
- 5522525,
276
- 5522529
277
  ],
278
  "block_size": 1024,
279
  "bos_token_id": 50256,
280
  "embd_pdrop": 0.1,
281
  "eos_token_id": 50256,
282
  "initializer_range": 0.02,
283
- "inner_step": 52,
284
  "inner_steps": 0,
285
- "last_allreduce_block": 5509976,
286
  "layer_norm_epsilon": 1e-05,
287
  "model_type": "gpt_optimized",
288
  "n_embd": 1280,
 
1
  {
2
+ "_name_or_path": "distributed/optimized-gpt2-1b",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
6
+ "1": "NON_PARTICIPATING",
7
  "10": "SUCCESS",
8
  "100": "NON_PARTICIPATING",
9
+ "101": "SUCCESS",
10
  "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
  "104": "NON_PARTICIPATING",
 
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
26
  "117": "NON_PARTICIPATING",
27
+ "118": "SUCCESS",
28
  "119": "NON_PARTICIPATING",
29
  "12": "SUCCESS",
30
  "120": "SUCCESS",
31
  "121": "NON_PARTICIPATING",
32
+ "122": "SUCCESS",
33
+ "123": "SUCCESS",
34
  "124": "NON_PARTICIPATING",
35
  "125": "NON_PARTICIPATING",
36
  "126": "NON_PARTICIPATING",
37
+ "127": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
39
+ "129": "NON_PARTICIPATING",
40
  "13": "NON_PARTICIPATING",
41
  "130": "NON_PARTICIPATING",
42
  "131": "NON_PARTICIPATING",
43
  "132": "SUCCESS",
44
  "133": "NON_PARTICIPATING",
45
  "134": "NON_PARTICIPATING",
46
+ "135": "NON_PARTICIPATING",
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
  "138": "NON_PARTICIPATING",
 
58
  "146": "NON_PARTICIPATING",
59
  "147": "SUCCESS",
60
  "148": "SUCCESS",
61
+ "149": "NON_PARTICIPATING",
62
  "15": "SUCCESS",
63
+ "150": "SUCCESS",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
  "153": "NON_PARTICIPATING",
67
+ "154": "NON_PARTICIPATING",
68
+ "155": "NON_PARTICIPATING",
69
  "156": "SUCCESS",
70
  "157": "NON_PARTICIPATING",
71
  "158": "NON_PARTICIPATING",
72
  "159": "NON_PARTICIPATING",
73
+ "16": "SUCCESS",
74
  "160": "SUCCESS",
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
 
78
  "164": "NON_PARTICIPATING",
79
  "165": "NON_PARTICIPATING",
80
  "166": "NON_PARTICIPATING",
81
+ "167": "SUCCESS",
82
+ "168": "SUCCESS",
83
  "169": "NON_PARTICIPATING",
84
  "17": "SUCCESS",
85
  "170": "SUCCESS",
 
87
  "172": "SUCCESS",
88
  "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
+ "175": "SUCCESS",
91
  "176": "NON_PARTICIPATING",
92
  "177": "NON_PARTICIPATING",
93
  "178": "NON_PARTICIPATING",
94
  "179": "NON_PARTICIPATING",
95
+ "18": "SUCCESS",
96
  "180": "NON_PARTICIPATING",
97
  "181": "NON_PARTICIPATING",
98
  "182": "NON_PARTICIPATING",
99
  "183": "NON_PARTICIPATING",
100
+ "184": "SUCCESS",
101
  "185": "NON_PARTICIPATING",
102
+ "186": "SUCCESS",
103
  "187": "SUCCESS",
104
  "188": "NON_PARTICIPATING",
105
  "189": "NON_PARTICIPATING",
106
  "19": "NON_PARTICIPATING",
107
  "190": "NON_PARTICIPATING",
108
+ "191": "SUCCESS",
109
+ "192": "SUCCESS",
110
+ "193": "SUCCESS",
111
  "194": "NON_PARTICIPATING",
112
  "195": "SUCCESS",
113
  "196": "NON_PARTICIPATING",
 
119
  "200": "SUCCESS",
120
  "201": "SUCCESS",
121
  "202": "NON_PARTICIPATING",
122
+ "203": "SUCCESS",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
125
  "206": "NON_PARTICIPATING",
126
  "207": "NON_PARTICIPATING",
127
  "208": "NON_PARTICIPATING",
128
  "209": "NON_PARTICIPATING",
129
+ "21": "SUCCESS",
130
  "210": "NON_PARTICIPATING",
131
  "211": "NON_PARTICIPATING",
132
  "212": "NON_PARTICIPATING",
133
  "213": "NON_PARTICIPATING",
134
  "214": "SUCCESS",
135
+ "215": "SUCCESS",
136
  "216": "NON_PARTICIPATING",
137
  "217": "NON_PARTICIPATING",
138
  "218": "SUCCESS",
139
  "219": "NON_PARTICIPATING",
140
+ "22": "SUCCESS",
141
  "220": "NON_PARTICIPATING",
142
+ "221": "SUCCESS",
143
  "222": "NON_PARTICIPATING",
144
+ "223": "SUCCESS",
145
  "224": "NON_PARTICIPATING",
146
+ "225": "SUCCESS",
147
  "226": "SUCCESS",
148
  "227": "NON_PARTICIPATING",
149
  "228": "NON_PARTICIPATING",
 
159
  "237": "NON_PARTICIPATING",
160
  "238": "NON_PARTICIPATING",
161
  "239": "NON_PARTICIPATING",
162
+ "24": "SUCCESS",
163
  "240": "NON_PARTICIPATING",
164
  "241": "SUCCESS",
165
  "242": "NON_PARTICIPATING",
166
  "243": "NON_PARTICIPATING",
167
+ "244": "SUCCESS",
168
  "245": "NON_PARTICIPATING",
169
  "246": "NON_PARTICIPATING",
170
+ "247": "SUCCESS",
171
  "248": "NON_PARTICIPATING",
172
+ "249": "SUCCESS",
173
  "25": "SUCCESS",
174
  "250": "SUCCESS",
175
  "251": "NON_PARTICIPATING",
 
179
  "255": "NON_PARTICIPATING",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
+ "28": "SUCCESS",
183
  "29": "SUCCESS",
184
  "3": "NON_PARTICIPATING",
185
+ "30": "NON_PARTICIPATING",
186
  "31": "NON_PARTICIPATING",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
 
193
  "38": "NON_PARTICIPATING",
194
  "39": "NON_PARTICIPATING",
195
  "4": "NON_PARTICIPATING",
196
+ "40": "SUCCESS",
197
+ "41": "SUCCESS",
198
  "42": "NON_PARTICIPATING",
199
+ "43": "SUCCESS",
200
+ "44": "SUCCESS",
201
+ "45": "SUCCESS",
202
  "46": "SUCCESS",
203
  "47": "SUCCESS",
204
  "48": "NON_PARTICIPATING",
 
214
  "57": "SUCCESS",
215
  "58": "NON_PARTICIPATING",
216
  "59": "NON_PARTICIPATING",
217
+ "6": "NON_PARTICIPATING",
218
  "60": "NON_PARTICIPATING",
219
  "61": "NON_PARTICIPATING",
220
  "62": "NON_PARTICIPATING",
221
  "63": "SUCCESS",
222
+ "64": "NON_PARTICIPATING",
223
  "65": "NON_PARTICIPATING",
224
  "66": "NON_PARTICIPATING",
225
+ "67": "SUCCESS",
226
+ "68": "SUCCESS",
227
  "69": "NON_PARTICIPATING",
228
+ "7": "SUCCESS",
229
  "70": "NON_PARTICIPATING",
230
  "71": "NON_PARTICIPATING",
231
  "72": "NON_PARTICIPATING",
 
241
  "81": "NON_PARTICIPATING",
242
  "82": "SUCCESS",
243
  "83": "NON_PARTICIPATING",
244
+ "84": "SUCCESS",
245
+ "85": "NON_PARTICIPATING",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
249
+ "89": "SUCCESS",
250
  "9": "NON_PARTICIPATING",
251
  "90": "NON_PARTICIPATING",
252
  "91": "SUCCESS",
253
  "92": "NON_PARTICIPATING",
254
  "93": "NON_PARTICIPATING",
255
  "94": "NON_PARTICIPATING",
256
+ "95": "SUCCESS",
257
  "96": "SUCCESS",
258
  "97": "NON_PARTICIPATING",
259
  "98": "NON_PARTICIPATING",
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5522592,
272
+ 5522596,
273
+ 5522599,
274
+ 5522603,
275
+ 5522606
 
276
  ],
277
  "block_size": 1024,
278
  "bos_token_id": 50256,
279
  "embd_pdrop": 0.1,
280
  "eos_token_id": 50256,
281
  "initializer_range": 0.02,
282
+ "inner_step": 0,
283
  "inner_steps": 0,
284
+ "last_allreduce_block": 5522512,
285
  "layer_norm_epsilon": 1e-05,
286
  "model_type": "gpt_optimized",
287
  "n_embd": 1280,
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:597dfd3d787a658aae4e44d33039dd974c9002988c18a6031b69d8ca350052c9
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d590dda39e8aa6b30a146fed8530f0afc4827313387e8570a8d517c0f4d82355
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:812097082daba3d03e10d0718b57029c4b330d2b753d9229d28ad44d1669f76d
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48fb515b34ae99a3eb34583d35ec6984ce8bac4f2c30837ced3b2c53ef09bea5
3
  size 4040701744