tensor-tech commited on
Commit
249fa40
·
verified ·
1 Parent(s): 075364b

Run 4. Outer Step 0. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +166 -166
  2. inner_optimizer.pt +2 -2
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,193 +1,193 @@
1
  {
2
- "_name_or_path": "tensor-tech/sn38-11",
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": "SUCCESS",
16
- "108": "NON_PARTICIPATING",
17
  "109": "SUCCESS",
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": "SUCCESS",
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": "SUCCESS",
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",
66
- "153": "NON_PARTICIPATING",
67
- "154": "NON_PARTICIPATING",
68
- "155": "NON_PARTICIPATING",
69
- "156": "NON_PARTICIPATING",
70
- "157": "NON_PARTICIPATING",
71
- "158": "NON_PARTICIPATING",
72
  "159": "SUCCESS",
73
  "16": "SUCCESS",
74
- "160": "NON_PARTICIPATING",
75
- "161": "NON_PARTICIPATING",
76
  "162": "SUCCESS",
77
- "163": "NON_PARTICIPATING",
78
  "164": "SUCCESS",
79
  "165": "SUCCESS",
80
- "166": "NON_PARTICIPATING",
81
- "167": "NON_PARTICIPATING",
82
- "168": "NON_PARTICIPATING",
83
  "169": "SUCCESS",
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",
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": "SUCCESS",
98
- "182": "NON_PARTICIPATING",
99
- "183": "NON_PARTICIPATING",
100
- "184": "NON_PARTICIPATING",
101
  "185": "SUCCESS",
102
- "186": "NON_PARTICIPATING",
103
- "187": "NON_PARTICIPATING",
104
- "188": "NON_PARTICIPATING",
105
- "189": "NON_PARTICIPATING",
106
  "19": "SUCCESS",
107
- "190": "NON_PARTICIPATING",
108
  "191": "SUCCESS",
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": "NON_PARTICIPATING",
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": "SUCCESS",
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": "NON_PARTICIPATING",
135
- "215": "NON_PARTICIPATING",
136
- "216": "NON_PARTICIPATING",
137
- "217": "NON_PARTICIPATING",
138
- "218": "NON_PARTICIPATING",
139
- "219": "NON_PARTICIPATING",
140
  "22": "SUCCESS",
141
- "220": "NON_PARTICIPATING",
142
- "221": "NON_PARTICIPATING",
143
- "222": "NON_PARTICIPATING",
144
- "223": "NON_PARTICIPATING",
145
- "224": "NON_PARTICIPATING",
146
- "225": "NON_PARTICIPATING",
147
- "226": "NON_PARTICIPATING",
148
- "227": "NON_PARTICIPATING",
149
- "228": "NON_PARTICIPATING",
150
  "229": "SUCCESS",
151
  "23": "SUCCESS",
152
  "230": "SUCCESS",
153
- "231": "NON_PARTICIPATING",
154
  "232": "SUCCESS",
155
- "233": "NON_PARTICIPATING",
156
- "234": "NON_PARTICIPATING",
157
- "235": "NON_PARTICIPATING",
158
- "236": "NON_PARTICIPATING",
159
- "237": "NON_PARTICIPATING",
160
  "238": "SUCCESS",
161
  "239": "SUCCESS",
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": "SUCCESS",
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",
176
- "252": "NON_PARTICIPATING",
177
- "253": "NON_PARTICIPATING",
178
- "254": "NON_PARTICIPATING",
179
- "255": "NON_PARTICIPATING",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
  "28": "SUCCESS",
183
  "29": "SUCCESS",
184
  "3": "SUCCESS",
185
- "30": "NON_PARTICIPATING",
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",
@@ -195,13 +195,13 @@
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": "SUCCESS",
204
- "48": "NON_PARTICIPATING",
205
  "49": "SUCCESS",
206
  "5": "SUCCESS",
207
  "50": "SUCCESS",
@@ -212,46 +212,46 @@
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": "NON_PARTICIPATING",
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",
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": "SUCCESS",
254
- "93": "NON_PARTICIPATING",
255
  "94": "SUCCESS",
256
  "95": "SUCCESS",
257
  "96": "SUCCESS",
@@ -268,20 +268,20 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5603474,
272
- 5603481,
273
- 5603488,
274
- 5603494,
275
- 5603501
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": 24,
283
  "inner_steps": 0,
284
- "last_allreduce_block": 5576204,
285
  "layer_norm_epsilon": 1e-05,
286
  "model_type": "gpt_optimized",
287
  "n_embd": 1280,
 
1
  {
2
+ "_name_or_path": "distributed/optimized-gpt2-1b",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
+ "0": "SUCCESS",
6
  "1": "SUCCESS",
7
+ "10": "SUCCESS",
8
+ "100": "SUCCESS",
9
+ "101": "SUCCESS",
10
+ "102": "SUCCESS",
11
+ "103": "SUCCESS",
12
+ "104": "SUCCESS",
13
+ "105": "SUCCESS",
14
+ "106": "SUCCESS",
15
  "107": "SUCCESS",
16
+ "108": "SUCCESS",
17
  "109": "SUCCESS",
18
  "11": "SUCCESS",
19
+ "110": "SUCCESS",
20
+ "111": "SUCCESS",
21
+ "112": "SUCCESS",
22
  "113": "SUCCESS",
23
+ "114": "SUCCESS",
24
+ "115": "SUCCESS",
25
+ "116": "SUCCESS",
26
+ "117": "SUCCESS",
27
+ "118": "SUCCESS",
28
+ "119": "SUCCESS",
29
  "12": "SUCCESS",
30
+ "120": "SUCCESS",
31
+ "121": "SUCCESS",
32
+ "122": "SUCCESS",
33
+ "123": "SUCCESS",
34
+ "124": "SUCCESS",
35
+ "125": "SUCCESS",
36
  "126": "SUCCESS",
37
+ "127": "SUCCESS",
38
+ "128": "SUCCESS",
39
+ "129": "SUCCESS",
40
  "13": "SUCCESS",
41
+ "130": "SUCCESS",
42
+ "131": "SUCCESS",
43
+ "132": "SUCCESS",
44
+ "133": "SUCCESS",
45
+ "134": "SUCCESS",
46
+ "135": "SUCCESS",
47
+ "136": "SUCCESS",
48
+ "137": "SUCCESS",
49
  "138": "SUCCESS",
50
+ "139": "SUCCESS",
51
  "14": "SUCCESS",
52
+ "140": "SUCCESS",
53
+ "141": "SUCCESS",
54
+ "142": "SUCCESS",
55
+ "143": "SUCCESS",
56
+ "144": "SUCCESS",
57
+ "145": "SUCCESS",
58
+ "146": "SUCCESS",
59
+ "147": "SUCCESS",
60
  "148": "SUCCESS",
61
+ "149": "SUCCESS",
62
+ "15": "SUCCESS",
63
+ "150": "SUCCESS",
64
+ "151": "SUCCESS",
65
+ "152": "SUCCESS",
66
+ "153": "SUCCESS",
67
+ "154": "SUCCESS",
68
+ "155": "SUCCESS",
69
+ "156": "SUCCESS",
70
+ "157": "SUCCESS",
71
+ "158": "SUCCESS",
72
  "159": "SUCCESS",
73
  "16": "SUCCESS",
74
+ "160": "SUCCESS",
75
+ "161": "SUCCESS",
76
  "162": "SUCCESS",
77
+ "163": "SUCCESS",
78
  "164": "SUCCESS",
79
  "165": "SUCCESS",
80
+ "166": "SUCCESS",
81
+ "167": "SUCCESS",
82
+ "168": "SUCCESS",
83
  "169": "SUCCESS",
84
  "17": "SUCCESS",
85
+ "170": "SUCCESS",
86
+ "171": "SUCCESS",
87
+ "172": "SUCCESS",
88
+ "173": "SUCCESS",
89
+ "174": "SUCCESS",
90
  "175": "SUCCESS",
91
+ "176": "SUCCESS",
92
+ "177": "SUCCESS",
93
+ "178": "SUCCESS",
94
+ "179": "SUCCESS",
95
  "18": "SUCCESS",
96
+ "180": "SUCCESS",
97
  "181": "SUCCESS",
98
+ "182": "SUCCESS",
99
+ "183": "SUCCESS",
100
+ "184": "SUCCESS",
101
  "185": "SUCCESS",
102
+ "186": "SUCCESS",
103
+ "187": "SUCCESS",
104
+ "188": "SUCCESS",
105
+ "189": "SUCCESS",
106
  "19": "SUCCESS",
107
+ "190": "SUCCESS",
108
  "191": "SUCCESS",
109
+ "192": "SUCCESS",
110
+ "193": "SUCCESS",
111
+ "194": "SUCCESS",
112
+ "195": "SUCCESS",
113
+ "196": "SUCCESS",
114
+ "197": "SUCCESS",
115
+ "198": "SUCCESS",
116
+ "199": "SUCCESS",
117
  "2": "SUCCESS",
118
  "20": "SUCCESS",
119
+ "200": "SUCCESS",
120
+ "201": "SUCCESS",
121
+ "202": "SUCCESS",
122
+ "203": "SUCCESS",
123
+ "204": "SUCCESS",
124
+ "205": "SUCCESS",
125
+ "206": "SUCCESS",
126
+ "207": "SUCCESS",
127
  "208": "SUCCESS",
128
+ "209": "SUCCESS",
129
  "21": "SUCCESS",
130
+ "210": "SUCCESS",
131
+ "211": "SUCCESS",
132
+ "212": "SUCCESS",
133
+ "213": "SUCCESS",
134
+ "214": "SUCCESS",
135
+ "215": "SUCCESS",
136
+ "216": "SUCCESS",
137
+ "217": "SUCCESS",
138
+ "218": "SUCCESS",
139
+ "219": "SUCCESS",
140
  "22": "SUCCESS",
141
+ "220": "SUCCESS",
142
+ "221": "SUCCESS",
143
+ "222": "SUCCESS",
144
+ "223": "SUCCESS",
145
+ "224": "SUCCESS",
146
+ "225": "SUCCESS",
147
+ "226": "SUCCESS",
148
+ "227": "SUCCESS",
149
+ "228": "SUCCESS",
150
  "229": "SUCCESS",
151
  "23": "SUCCESS",
152
  "230": "SUCCESS",
153
+ "231": "SUCCESS",
154
  "232": "SUCCESS",
155
+ "233": "SUCCESS",
156
+ "234": "SUCCESS",
157
+ "235": "SUCCESS",
158
+ "236": "SUCCESS",
159
+ "237": "SUCCESS",
160
  "238": "SUCCESS",
161
  "239": "SUCCESS",
162
  "24": "SUCCESS",
163
+ "240": "SUCCESS",
164
+ "241": "SUCCESS",
165
+ "242": "SUCCESS",
166
+ "243": "SUCCESS",
167
+ "244": "SUCCESS",
168
  "245": "SUCCESS",
169
+ "246": "SUCCESS",
170
+ "247": "SUCCESS",
171
+ "248": "SUCCESS",
172
+ "249": "SUCCESS",
173
  "25": "SUCCESS",
174
  "250": "SUCCESS",
175
+ "251": "SUCCESS",
176
+ "252": "SUCCESS",
177
+ "253": "SUCCESS",
178
+ "254": "SUCCESS",
179
+ "255": "SUCCESS",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
  "28": "SUCCESS",
183
  "29": "SUCCESS",
184
  "3": "SUCCESS",
185
+ "30": "SUCCESS",
186
+ "31": "SUCCESS",
187
  "32": "SUCCESS",
188
+ "33": "SUCCESS",
189
  "34": "SUCCESS",
190
+ "35": "SUCCESS",
191
  "36": "SUCCESS",
192
  "37": "SUCCESS",
193
  "38": "SUCCESS",
 
195
  "4": "SUCCESS",
196
  "40": "SUCCESS",
197
  "41": "SUCCESS",
198
+ "42": "SUCCESS",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
202
+ "46": "SUCCESS",
203
  "47": "SUCCESS",
204
+ "48": "SUCCESS",
205
  "49": "SUCCESS",
206
  "5": "SUCCESS",
207
  "50": "SUCCESS",
 
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
214
  "57": "SUCCESS",
215
+ "58": "SUCCESS",
216
  "59": "SUCCESS",
217
+ "6": "SUCCESS",
218
  "60": "SUCCESS",
219
+ "61": "SUCCESS",
220
  "62": "SUCCESS",
221
  "63": "SUCCESS",
222
+ "64": "SUCCESS",
223
  "65": "SUCCESS",
224
  "66": "SUCCESS",
225
  "67": "SUCCESS",
226
  "68": "SUCCESS",
227
  "69": "SUCCESS",
228
+ "7": "SUCCESS",
229
+ "70": "SUCCESS",
230
+ "71": "SUCCESS",
231
  "72": "SUCCESS",
232
+ "73": "SUCCESS",
233
  "74": "SUCCESS",
234
  "75": "SUCCESS",
235
  "76": "SUCCESS",
236
  "77": "SUCCESS",
237
  "78": "SUCCESS",
238
+ "79": "SUCCESS",
239
  "8": "SUCCESS",
240
  "80": "SUCCESS",
241
  "81": "SUCCESS",
242
  "82": "SUCCESS",
243
+ "83": "SUCCESS",
244
  "84": "SUCCESS",
245
+ "85": "SUCCESS",
246
+ "86": "SUCCESS",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
249
  "89": "SUCCESS",
250
+ "9": "SUCCESS",
251
+ "90": "SUCCESS",
252
  "91": "SUCCESS",
253
  "92": "SUCCESS",
254
+ "93": "SUCCESS",
255
  "94": "SUCCESS",
256
  "95": "SUCCESS",
257
  "96": "SUCCESS",
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5603547,
272
+ 5603554,
273
+ 5603561,
274
+ 5603568,
275
+ 5603575
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": 5470731,
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 sha256:7e55795c5edb66e45b9cd0dff88b0658495182843f765cdc314956749bc2255d
3
- size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50852309c11bba1c68b1fc599de303950b01245d3f8e70c6ec061ebf1229b0c3
3
+ size 2944
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ee5ed8f3cbf889d1b68d0660b12f263f2ea2f99ca3c2ea8d7f94fb49cc62928
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:365a8be76326501ea811276a569f0cc28ad07a1bacda5111d7247e4a758ad97f
3
  size 4040701744