sevalish commited on
Commit
0aa878d
·
verified ·
1 Parent(s): e65b62f

Run 4. Outer Step 54. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +78 -80
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,65 +1,65 @@
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": "SUCCESS",
10
  "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
  "104": "NON_PARTICIPATING",
13
  "105": "NON_PARTICIPATING",
14
- "106": "SUCCESS",
15
- "107": "SUCCESS",
16
  "108": "NON_PARTICIPATING",
17
  "109": "NON_PARTICIPATING",
18
- "11": "NON_PARTICIPATING",
19
- "110": "SUCCESS",
20
- "111": "SUCCESS",
21
  "112": "NON_PARTICIPATING",
22
- "113": "NON_PARTICIPATING",
23
- "114": "SUCCESS",
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
26
  "117": "NON_PARTICIPATING",
27
- "118": "SUCCESS",
28
  "119": "NON_PARTICIPATING",
29
  "12": "SUCCESS",
30
  "120": "NON_PARTICIPATING",
31
- "121": "SUCCESS",
32
- "122": "SUCCESS",
33
- "123": "SUCCESS",
34
  "124": "NON_PARTICIPATING",
35
  "125": "NON_PARTICIPATING",
36
  "126": "NON_PARTICIPATING",
37
- "127": "SUCCESS",
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": "SUCCESS",
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
  "138": "NON_PARTICIPATING",
50
  "139": "NON_PARTICIPATING",
51
- "14": "NON_PARTICIPATING",
52
  "140": "NON_PARTICIPATING",
53
  "141": "NON_PARTICIPATING",
54
- "142": "SUCCESS",
55
  "143": "NON_PARTICIPATING",
56
  "144": "NON_PARTICIPATING",
57
  "145": "NON_PARTICIPATING",
58
  "146": "NON_PARTICIPATING",
59
  "147": "NON_PARTICIPATING",
60
- "148": "NON_PARTICIPATING",
61
- "149": "SUCCESS",
62
- "15": "SUCCESS",
63
  "150": "NON_PARTICIPATING",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
@@ -69,22 +69,22 @@
69
  "156": "SUCCESS",
70
  "157": "NON_PARTICIPATING",
71
  "158": "NON_PARTICIPATING",
72
- "159": "SUCCESS",
73
  "16": "SUCCESS",
74
- "160": "SUCCESS",
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
77
  "163": "NON_PARTICIPATING",
78
  "164": "NON_PARTICIPATING",
79
  "165": "NON_PARTICIPATING",
80
  "166": "NON_PARTICIPATING",
81
- "167": "SUCCESS",
82
  "168": "NON_PARTICIPATING",
83
  "169": "NON_PARTICIPATING",
84
  "17": "SUCCESS",
85
- "170": "SUCCESS",
86
  "171": "NON_PARTICIPATING",
87
- "172": "SUCCESS",
88
  "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
  "175": "SUCCESS",
@@ -94,31 +94,31 @@
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": "NON_PARTICIPATING",
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": "SUCCESS",
111
  "194": "NON_PARTICIPATING",
112
- "195": "SUCCESS",
113
  "196": "NON_PARTICIPATING",
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
116
  "199": "NON_PARTICIPATING",
117
  "2": "SUCCESS",
118
  "20": "SUCCESS",
119
- "200": "SUCCESS",
120
  "201": "SUCCESS",
121
- "202": "NON_PARTICIPATING",
122
  "203": "SUCCESS",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
@@ -131,25 +131,25 @@
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": "SUCCESS",
140
  "22": "SUCCESS",
141
- "220": "NON_PARTICIPATING",
142
  "221": "NON_PARTICIPATING",
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",
150
  "229": "NON_PARTICIPATING",
151
  "23": "SUCCESS",
152
- "230": "NON_PARTICIPATING",
153
  "231": "NON_PARTICIPATING",
154
  "232": "NON_PARTICIPATING",
155
  "233": "NON_PARTICIPATING",
@@ -157,19 +157,19 @@
157
  "235": "NON_PARTICIPATING",
158
  "236": "NON_PARTICIPATING",
159
  "237": "NON_PARTICIPATING",
160
- "238": "NON_PARTICIPATING",
161
  "239": "NON_PARTICIPATING",
162
  "24": "SUCCESS",
163
  "240": "NON_PARTICIPATING",
164
  "241": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
175
  "251": "NON_PARTICIPATING",
@@ -181,64 +181,64 @@
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",
189
  "34": "SUCCESS",
190
  "35": "NON_PARTICIPATING",
191
- "36": "NON_PARTICIPATING",
192
  "37": "SUCCESS",
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",
205
  "49": "SUCCESS",
206
- "5": "NON_PARTICIPATING",
207
  "50": "SUCCESS",
208
  "51": "SUCCESS",
209
- "52": "NON_PARTICIPATING",
210
- "53": "NON_PARTICIPATING",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
214
  "57": "SUCCESS",
215
  "58": "NON_PARTICIPATING",
216
- "59": "NON_PARTICIPATING",
217
  "6": "NON_PARTICIPATING",
218
  "60": "SUCCESS",
219
  "61": "NON_PARTICIPATING",
220
  "62": "SUCCESS",
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",
232
  "73": "NON_PARTICIPATING",
233
- "74": "NON_PARTICIPATING",
234
  "75": "SUCCESS",
235
- "76": "NON_PARTICIPATING",
236
- "77": "NON_PARTICIPATING",
237
- "78": "NON_PARTICIPATING",
238
  "79": "NON_PARTICIPATING",
239
  "8": "SUCCESS",
240
  "80": "SUCCESS",
241
- "81": "NON_PARTICIPATING",
242
  "82": "SUCCESS",
243
  "83": "NON_PARTICIPATING",
244
  "84": "SUCCESS",
@@ -250,12 +250,12 @@
250
  "9": "NON_PARTICIPATING",
251
  "90": "NON_PARTICIPATING",
252
  "91": "SUCCESS",
253
- "92": "NON_PARTICIPATING",
254
  "93": "NON_PARTICIPATING",
255
  "94": "SUCCESS",
256
  "95": "SUCCESS",
257
  "96": "SUCCESS",
258
- "97": "NON_PARTICIPATING",
259
  "98": "SUCCESS",
260
  "99": "SUCCESS"
261
  },
@@ -268,22 +268,20 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5575370,
272
- 5575374,
273
- 5575378,
274
- 5575382,
275
- 5575386,
276
- 5575390,
277
- 5575394
278
  ],
279
  "block_size": 1024,
280
  "bos_token_id": 50256,
281
  "embd_pdrop": 0.1,
282
  "eos_token_id": 50256,
283
  "initializer_range": 0.02,
284
- "inner_step": 19,
285
  "inner_steps": 0,
286
- "last_allreduce_block": 5523943,
287
  "layer_norm_epsilon": 1e-05,
288
  "model_type": "gpt_optimized",
289
  "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": "SUCCESS",
7
+ "10": "NON_PARTICIPATING",
8
  "100": "NON_PARTICIPATING",
9
+ "101": "NON_PARTICIPATING",
10
  "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
  "104": "NON_PARTICIPATING",
13
  "105": "NON_PARTICIPATING",
14
+ "106": "NON_PARTICIPATING",
15
+ "107": "NON_PARTICIPATING",
16
  "108": "NON_PARTICIPATING",
17
  "109": "NON_PARTICIPATING",
18
+ "11": "SUCCESS",
19
+ "110": "NON_PARTICIPATING",
20
+ "111": "NON_PARTICIPATING",
21
  "112": "NON_PARTICIPATING",
22
+ "113": "SUCCESS",
23
+ "114": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
39
  "129": "NON_PARTICIPATING",
40
+ "13": "SUCCESS",
41
  "130": "NON_PARTICIPATING",
42
  "131": "NON_PARTICIPATING",
43
+ "132": "NON_PARTICIPATING",
44
  "133": "NON_PARTICIPATING",
45
  "134": "NON_PARTICIPATING",
46
+ "135": "NON_PARTICIPATING",
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
  "138": "NON_PARTICIPATING",
50
  "139": "NON_PARTICIPATING",
51
+ "14": "SUCCESS",
52
  "140": "NON_PARTICIPATING",
53
  "141": "NON_PARTICIPATING",
54
+ "142": "NON_PARTICIPATING",
55
  "143": "NON_PARTICIPATING",
56
  "144": "NON_PARTICIPATING",
57
  "145": "NON_PARTICIPATING",
58
  "146": "NON_PARTICIPATING",
59
  "147": "NON_PARTICIPATING",
60
+ "148": "SUCCESS",
61
+ "149": "NON_PARTICIPATING",
62
+ "15": "NON_PARTICIPATING",
63
  "150": "NON_PARTICIPATING",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
 
69
  "156": "SUCCESS",
70
  "157": "NON_PARTICIPATING",
71
  "158": "NON_PARTICIPATING",
72
+ "159": "NON_PARTICIPATING",
73
  "16": "SUCCESS",
74
+ "160": "NON_PARTICIPATING",
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
77
  "163": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
86
  "171": "NON_PARTICIPATING",
87
+ "172": "NON_PARTICIPATING",
88
  "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
  "175": "SUCCESS",
 
94
  "179": "NON_PARTICIPATING",
95
  "18": "SUCCESS",
96
  "180": "NON_PARTICIPATING",
97
+ "181": "SUCCESS",
98
  "182": "NON_PARTICIPATING",
99
  "183": "NON_PARTICIPATING",
100
  "184": "SUCCESS",
101
+ "185": "SUCCESS",
102
+ "186": "NON_PARTICIPATING",
103
+ "187": "SUCCESS",
104
  "188": "NON_PARTICIPATING",
105
  "189": "NON_PARTICIPATING",
106
+ "19": "SUCCESS",
107
+ "190": "SUCCESS",
108
  "191": "NON_PARTICIPATING",
109
  "192": "NON_PARTICIPATING",
110
+ "193": "NON_PARTICIPATING",
111
  "194": "NON_PARTICIPATING",
112
+ "195": "NON_PARTICIPATING",
113
  "196": "NON_PARTICIPATING",
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
116
  "199": "NON_PARTICIPATING",
117
  "2": "SUCCESS",
118
  "20": "SUCCESS",
119
+ "200": "NON_PARTICIPATING",
120
  "201": "SUCCESS",
121
+ "202": "SUCCESS",
122
  "203": "SUCCESS",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
 
131
  "211": "NON_PARTICIPATING",
132
  "212": "NON_PARTICIPATING",
133
  "213": "NON_PARTICIPATING",
134
+ "214": "NON_PARTICIPATING",
135
+ "215": "NON_PARTICIPATING",
136
  "216": "NON_PARTICIPATING",
137
  "217": "NON_PARTICIPATING",
138
+ "218": "NON_PARTICIPATING",
139
  "219": "SUCCESS",
140
  "22": "SUCCESS",
141
+ "220": "SUCCESS",
142
  "221": "NON_PARTICIPATING",
143
  "222": "NON_PARTICIPATING",
144
+ "223": "NON_PARTICIPATING",
145
  "224": "NON_PARTICIPATING",
146
  "225": "SUCCESS",
147
+ "226": "NON_PARTICIPATING",
148
  "227": "NON_PARTICIPATING",
149
  "228": "NON_PARTICIPATING",
150
  "229": "NON_PARTICIPATING",
151
  "23": "SUCCESS",
152
+ "230": "SUCCESS",
153
  "231": "NON_PARTICIPATING",
154
  "232": "NON_PARTICIPATING",
155
  "233": "NON_PARTICIPATING",
 
157
  "235": "NON_PARTICIPATING",
158
  "236": "NON_PARTICIPATING",
159
  "237": "NON_PARTICIPATING",
160
+ "238": "SUCCESS",
161
  "239": "NON_PARTICIPATING",
162
  "24": "SUCCESS",
163
  "240": "NON_PARTICIPATING",
164
  "241": "NON_PARTICIPATING",
165
  "242": "NON_PARTICIPATING",
166
  "243": "NON_PARTICIPATING",
167
+ "244": "NON_PARTICIPATING",
168
  "245": "NON_PARTICIPATING",
169
  "246": "NON_PARTICIPATING",
170
  "247": "SUCCESS",
171
  "248": "NON_PARTICIPATING",
172
+ "249": "NON_PARTICIPATING",
173
  "25": "SUCCESS",
174
  "250": "NON_PARTICIPATING",
175
  "251": "NON_PARTICIPATING",
 
181
  "27": "SUCCESS",
182
  "28": "SUCCESS",
183
  "29": "SUCCESS",
184
+ "3": "SUCCESS",
185
+ "30": "SUCCESS",
186
  "31": "NON_PARTICIPATING",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
189
  "34": "SUCCESS",
190
  "35": "NON_PARTICIPATING",
191
+ "36": "SUCCESS",
192
  "37": "SUCCESS",
193
+ "38": "SUCCESS",
194
+ "39": "SUCCESS",
195
+ "4": "SUCCESS",
196
  "40": "SUCCESS",
197
  "41": "SUCCESS",
198
  "42": "NON_PARTICIPATING",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
202
+ "46": "NON_PARTICIPATING",
203
+ "47": "NON_PARTICIPATING",
204
  "48": "NON_PARTICIPATING",
205
  "49": "SUCCESS",
206
+ "5": "SUCCESS",
207
  "50": "SUCCESS",
208
  "51": "SUCCESS",
209
+ "52": "SUCCESS",
210
+ "53": "SUCCESS",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
214
  "57": "SUCCESS",
215
  "58": "NON_PARTICIPATING",
216
+ "59": "SUCCESS",
217
  "6": "NON_PARTICIPATING",
218
  "60": "SUCCESS",
219
  "61": "NON_PARTICIPATING",
220
  "62": "SUCCESS",
221
  "63": "SUCCESS",
222
  "64": "NON_PARTICIPATING",
223
+ "65": "SUCCESS",
224
+ "66": "SUCCESS",
225
  "67": "SUCCESS",
226
  "68": "SUCCESS",
227
+ "69": "SUCCESS",
228
  "7": "SUCCESS",
229
  "70": "NON_PARTICIPATING",
230
  "71": "NON_PARTICIPATING",
231
+ "72": "SUCCESS",
232
  "73": "NON_PARTICIPATING",
233
+ "74": "SUCCESS",
234
  "75": "SUCCESS",
235
+ "76": "SUCCESS",
236
+ "77": "SUCCESS",
237
+ "78": "SUCCESS",
238
  "79": "NON_PARTICIPATING",
239
  "8": "SUCCESS",
240
  "80": "SUCCESS",
241
+ "81": "SUCCESS",
242
  "82": "SUCCESS",
243
  "83": "NON_PARTICIPATING",
244
  "84": "SUCCESS",
 
250
  "9": "NON_PARTICIPATING",
251
  "90": "NON_PARTICIPATING",
252
  "91": "SUCCESS",
253
+ "92": "SUCCESS",
254
  "93": "NON_PARTICIPATING",
255
  "94": "SUCCESS",
256
  "95": "SUCCESS",
257
  "96": "SUCCESS",
258
+ "97": "SUCCESS",
259
  "98": "SUCCESS",
260
  "99": "SUCCESS"
261
  },
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5579390,
272
+ 5579395,
273
+ 5579399,
274
+ 5579404,
275
+ 5579409
 
 
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": 5577515,
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:b3ba02b1e92045d92c6e54671935f8294c453a09fd9632006461756ca59e0867
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3840ee545fcf0a3739f53927f05b1830da50b59c661a1958747032baedfbf77
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98035700220ec65f07eef48c43deb374ed2e9046292e877ae5744ad9923b11d2
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de3de475cc7f3ce5d617cd2e4e54980c916e8edebeda0cbf87510e43696c4a1
3
  size 4040701744