jockibaba commited on
Commit
b019e3f
·
verified ·
1 Parent(s): af633fc

Run 4. Outer Step 50. Inner Step 66.

Browse files
Files changed (3) hide show
  1. config.json +49 -49
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "distributed/optimized-gpt2-1b",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
@@ -7,19 +7,19 @@
7
  "10": "NON_PARTICIPATING",
8
  "100": "NON_PARTICIPATING",
9
  "101": "NON_PARTICIPATING",
10
- "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
  "104": "SUCCESS",
13
  "105": "NON_PARTICIPATING",
14
- "106": "SUCCESS",
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": "NON_PARTICIPATING",
23
  "114": "NON_PARTICIPATING",
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
@@ -27,13 +27,13 @@
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",
@@ -50,15 +50,15 @@
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": "NON_PARTICIPATING",
61
- "149": "NON_PARTICIPATING",
62
  "15": "SUCCESS",
63
  "150": "NON_PARTICIPATING",
64
  "151": "NON_PARTICIPATING",
@@ -71,23 +71,23 @@
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": "SUCCESS",
87
  "172": "NON_PARTICIPATING",
88
  "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
- "175": "SUCCESS",
91
  "176": "NON_PARTICIPATING",
92
  "177": "SUCCESS",
93
  "178": "NON_PARTICIPATING",
@@ -95,7 +95,7 @@
95
  "18": "SUCCESS",
96
  "180": "NON_PARTICIPATING",
97
  "181": "NON_PARTICIPATING",
98
- "182": "SUCCESS",
99
  "183": "NON_PARTICIPATING",
100
  "184": "NON_PARTICIPATING",
101
  "185": "NON_PARTICIPATING",
@@ -103,7 +103,7 @@
103
  "187": "NON_PARTICIPATING",
104
  "188": "NON_PARTICIPATING",
105
  "189": "NON_PARTICIPATING",
106
- "19": "SUCCESS",
107
  "190": "NON_PARTICIPATING",
108
  "191": "NON_PARTICIPATING",
109
  "192": "NON_PARTICIPATING",
@@ -113,19 +113,19 @@
113
  "196": "NON_PARTICIPATING",
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
116
- "199": "SUCCESS",
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",
@@ -143,33 +143,33 @@
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": "SUCCESS",
150
  "229": "NON_PARTICIPATING",
151
  "23": "SUCCESS",
152
  "230": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
161
- "239": "SUCCESS",
162
  "24": "SUCCESS",
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": "SUCCESS",
170
  "247": "NON_PARTICIPATING",
171
  "248": "NON_PARTICIPATING",
172
- "249": "SUCCESS",
173
  "25": "SUCCESS",
174
  "250": "NON_PARTICIPATING",
175
  "251": "NON_PARTICIPATING",
@@ -182,11 +182,11 @@
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": "NON_PARTICIPATING",
190
  "35": "SUCCESS",
191
  "36": "SUCCESS",
192
  "37": "SUCCESS",
@@ -205,13 +205,13 @@
205
  "49": "SUCCESS",
206
  "5": "SUCCESS",
207
  "50": "SUCCESS",
208
- "51": "FAIL",
209
- "52": "NON_PARTICIPATING",
210
  "53": "SUCCESS",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
214
- "57": "NON_PARTICIPATING",
215
  "58": "NON_PARTICIPATING",
216
  "59": "SUCCESS",
217
  "6": "NON_PARTICIPATING",
@@ -219,20 +219,20 @@
219
  "61": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
231
  "72": "SUCCESS",
232
  "73": "NON_PARTICIPATING",
233
  "74": "SUCCESS",
234
  "75": "SUCCESS",
235
- "76": "NON_PARTICIPATING",
236
  "77": "SUCCESS",
237
  "78": "SUCCESS",
238
  "79": "NON_PARTICIPATING",
@@ -240,10 +240,10 @@
240
  "80": "SUCCESS",
241
  "81": "SUCCESS",
242
  "82": "SUCCESS",
243
- "83": "SUCCESS",
244
  "84": "SUCCESS",
245
  "85": "NON_PARTICIPATING",
246
- "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
249
  "89": "SUCCESS",
@@ -268,20 +268,20 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5622018,
272
- 5622022,
273
- 5622026,
274
- 5622030,
275
- 5622035
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": 96,
283
  "inner_steps": 0,
284
- "last_allreduce_block": 5613899,
285
  "layer_norm_epsilon": 1e-05,
286
  "model_type": "gpt_optimized",
287
  "n_embd": 1280,
 
1
  {
2
+ "_name_or_path": "jockibaba/jockibaba1",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
 
7
  "10": "NON_PARTICIPATING",
8
  "100": "NON_PARTICIPATING",
9
  "101": "NON_PARTICIPATING",
10
+ "102": "SUCCESS",
11
  "103": "NON_PARTICIPATING",
12
  "104": "SUCCESS",
13
  "105": "NON_PARTICIPATING",
14
+ "106": "NON_PARTICIPATING",
15
  "107": "NON_PARTICIPATING",
16
  "108": "NON_PARTICIPATING",
17
  "109": "NON_PARTICIPATING",
18
+ "11": "NON_PARTICIPATING",
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",
 
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": "SUCCESS",
37
  "127": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
39
  "129": "NON_PARTICIPATING",
 
50
  "139": "NON_PARTICIPATING",
51
  "14": "SUCCESS",
52
  "140": "NON_PARTICIPATING",
53
+ "141": "SUCCESS",
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": "SUCCESS",
62
  "15": "SUCCESS",
63
  "150": "NON_PARTICIPATING",
64
  "151": "NON_PARTICIPATING",
 
71
  "158": "NON_PARTICIPATING",
72
  "159": "NON_PARTICIPATING",
73
  "16": "SUCCESS",
74
+ "160": "SUCCESS",
75
  "161": "NON_PARTICIPATING",
76
+ "162": "SUCCESS",
77
  "163": "NON_PARTICIPATING",
78
  "164": "NON_PARTICIPATING",
79
+ "165": "SUCCESS",
80
  "166": "NON_PARTICIPATING",
81
  "167": "NON_PARTICIPATING",
82
  "168": "NON_PARTICIPATING",
83
+ "169": "SUCCESS",
84
+ "17": "NON_PARTICIPATING",
85
  "170": "NON_PARTICIPATING",
86
+ "171": "NON_PARTICIPATING",
87
  "172": "NON_PARTICIPATING",
88
  "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
+ "175": "NON_PARTICIPATING",
91
  "176": "NON_PARTICIPATING",
92
  "177": "SUCCESS",
93
  "178": "NON_PARTICIPATING",
 
95
  "18": "SUCCESS",
96
  "180": "NON_PARTICIPATING",
97
  "181": "NON_PARTICIPATING",
98
+ "182": "NON_PARTICIPATING",
99
  "183": "NON_PARTICIPATING",
100
  "184": "NON_PARTICIPATING",
101
  "185": "NON_PARTICIPATING",
 
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",
 
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": "NON_PARTICIPATING",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
125
  "206": "NON_PARTICIPATING",
126
  "207": "NON_PARTICIPATING",
127
+ "208": "NON_PARTICIPATING",
128
+ "209": "SUCCESS",
129
  "21": "SUCCESS",
130
  "210": "NON_PARTICIPATING",
131
  "211": "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": "NON_PARTICIPATING",
153
  "231": "NON_PARTICIPATING",
154
+ "232": "NON_PARTICIPATING",
155
  "233": "NON_PARTICIPATING",
156
  "234": "NON_PARTICIPATING",
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": "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": "NON_PARTICIPATING",
175
  "251": "NON_PARTICIPATING",
 
182
  "28": "SUCCESS",
183
  "29": "SUCCESS",
184
  "3": "SUCCESS",
185
+ "30": "SUCCESS",
186
+ "31": "SUCCESS",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
189
+ "34": "SUCCESS",
190
  "35": "SUCCESS",
191
  "36": "SUCCESS",
192
  "37": "SUCCESS",
 
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",
 
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",
 
240
  "80": "SUCCESS",
241
  "81": "SUCCESS",
242
  "82": "SUCCESS",
243
+ "83": "NON_PARTICIPATING",
244
  "84": "SUCCESS",
245
  "85": "NON_PARTICIPATING",
246
+ "86": "SUCCESS",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
249
  "89": "SUCCESS",
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5622123,
272
+ 5622127,
273
+ 5622131,
274
+ 5622136,
275
+ 5622140
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": 66,
283
  "inner_steps": 0,
284
+ "last_allreduce_block": 5556551,
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:eff91f739ab18fea74f5f674074e9d494dff3a09c38d1304497ab10fc97dcc23
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35480871f9b1b4f11556d67bd1dcef988021f8cbb32702960755ec6da4aced5f
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e65c8ece8d0244eebc2d12df14c21062af8ac0dbc7a758d03df860cfd7064208
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2229598af101c19965169d0eabbc3485f60f99d3f990a467de61301f501b5c8b
3
  size 4040701744