jockibaba commited on
Commit
3344572
·
verified ·
1 Parent(s): 081a295

Run 4. Outer Step 53. Inner Step 44.

Browse files
Files changed (3) hide show
  1. config.json +46 -46
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,19 +1,19 @@
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": "SUCCESS",
10
  "102": "NON_PARTICIPATING",
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": "SUCCESS",
19
  "110": "NON_PARTICIPATING",
@@ -24,34 +24,34 @@
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": "NON_PARTICIPATING",
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": "SUCCESS",
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": "SUCCESS",
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",
@@ -64,7 +64,7 @@
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
  "153": "SUCCESS",
67
- "154": "SUCCESS",
68
  "155": "NON_PARTICIPATING",
69
  "156": "NON_PARTICIPATING",
70
  "157": "NON_PARTICIPATING",
@@ -76,24 +76,24 @@
76
  "162": "NON_PARTICIPATING",
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": "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": "NON_PARTICIPATING",
98
  "182": "NON_PARTICIPATING",
99
  "183": "NON_PARTICIPATING",
@@ -116,7 +116,7 @@
116
  "199": "NON_PARTICIPATING",
117
  "2": "SUCCESS",
118
  "20": "SUCCESS",
119
- "200": "SUCCESS",
120
  "201": "NON_PARTICIPATING",
121
  "202": "NON_PARTICIPATING",
122
  "203": "NON_PARTICIPATING",
@@ -125,9 +125,9 @@
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",
@@ -135,41 +135,41 @@
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": "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": "SUCCESS",
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": "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": "NON_PARTICIPATING",
175
  "251": "NON_PARTICIPATING",
@@ -182,15 +182,15 @@
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": "SUCCESS",
191
  "36": "SUCCESS",
192
  "37": "SUCCESS",
193
- "38": "NON_PARTICIPATING",
194
  "39": "SUCCESS",
195
  "4": "SUCCESS",
196
  "40": "SUCCESS",
@@ -200,17 +200,17 @@
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": "NON_PARTICIPATING",
213
- "56": "NON_PARTICIPATING",
214
  "57": "SUCCESS",
215
  "58": "NON_PARTICIPATING",
216
  "59": "SUCCESS",
@@ -249,7 +249,7 @@
249
  "89": "SUCCESS",
250
  "9": "SUCCESS",
251
  "90": "SUCCESS",
252
- "91": "NON_PARTICIPATING",
253
  "92": "SUCCESS",
254
  "93": "NON_PARTICIPATING",
255
  "94": "SUCCESS",
@@ -257,7 +257,7 @@
257
  "96": "SUCCESS",
258
  "97": "SUCCESS",
259
  "98": "SUCCESS",
260
- "99": "NON_PARTICIPATING"
261
  },
262
  "architectures": [
263
  "GPTOptim"
@@ -268,20 +268,20 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5586998,
272
- 5587002,
273
- 5587005,
274
- 5587009,
275
- 5587013
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": 32,
283
  "inner_steps": 0,
284
- "last_allreduce_block": 5583387,
285
  "layer_norm_epsilon": 1e-05,
286
  "model_type": "gpt_optimized",
287
  "n_embd": 1280,
 
1
  {
2
+ "_name_or_path": "jockibaba/jockibaba2",
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": "SUCCESS",
17
  "109": "NON_PARTICIPATING",
18
  "11": "SUCCESS",
19
  "110": "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": "SUCCESS",
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": "NON_PARTICIPATING",
50
  "139": "NON_PARTICIPATING",
51
  "14": "NON_PARTICIPATING",
52
  "140": "NON_PARTICIPATING",
53
  "141": "NON_PARTICIPATING",
54
+ "142": "NON_PARTICIPATING",
55
  "143": "NON_PARTICIPATING",
56
  "144": "NON_PARTICIPATING",
57
  "145": "NON_PARTICIPATING",
 
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
  "153": "SUCCESS",
67
+ "154": "NON_PARTICIPATING",
68
  "155": "NON_PARTICIPATING",
69
  "156": "NON_PARTICIPATING",
70
  "157": "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": "SUCCESS",
83
+ "169": "NON_PARTICIPATING",
84
  "17": "SUCCESS",
85
  "170": "NON_PARTICIPATING",
86
+ "171": "SUCCESS",
87
  "172": "NON_PARTICIPATING",
88
+ "173": "SUCCESS",
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": "SUCCESS",
96
+ "180": "SUCCESS",
97
  "181": "NON_PARTICIPATING",
98
  "182": "NON_PARTICIPATING",
99
  "183": "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",
 
125
  "206": "NON_PARTICIPATING",
126
  "207": "NON_PARTICIPATING",
127
  "208": "SUCCESS",
128
+ "209": "SUCCESS",
129
  "21": "SUCCESS",
130
+ "210": "SUCCESS",
131
  "211": "NON_PARTICIPATING",
132
  "212": "NON_PARTICIPATING",
133
  "213": "NON_PARTICIPATING",
 
135
  "215": "NON_PARTICIPATING",
136
  "216": "NON_PARTICIPATING",
137
  "217": "NON_PARTICIPATING",
138
+ "218": "SUCCESS",
139
  "219": "NON_PARTICIPATING",
140
  "22": "SUCCESS",
141
  "220": "SUCCESS",
142
+ "221": "SUCCESS",
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": "NON_PARTICIPATING",
153
+ "231": "SUCCESS",
154
  "232": "NON_PARTICIPATING",
155
  "233": "NON_PARTICIPATING",
156
  "234": "NON_PARTICIPATING",
157
  "235": "NON_PARTICIPATING",
158
+ "236": "SUCCESS",
159
  "237": "NON_PARTICIPATING",
160
+ "238": "SUCCESS",
161
  "239": "NON_PARTICIPATING",
162
  "24": "SUCCESS",
163
  "240": "NON_PARTICIPATING",
164
+ "241": "NON_PARTICIPATING",
165
+ "242": "SUCCESS",
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": "SUCCESS",
173
  "25": "SUCCESS",
174
  "250": "NON_PARTICIPATING",
175
  "251": "NON_PARTICIPATING",
 
182
  "28": "SUCCESS",
183
  "29": "SUCCESS",
184
  "3": "SUCCESS",
185
+ "30": "NON_PARTICIPATING",
186
+ "31": "SUCCESS",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
189
  "34": "SUCCESS",
190
  "35": "SUCCESS",
191
  "36": "SUCCESS",
192
  "37": "SUCCESS",
193
+ "38": "SUCCESS",
194
  "39": "SUCCESS",
195
  "4": "SUCCESS",
196
  "40": "SUCCESS",
 
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
202
  "46": "NON_PARTICIPATING",
203
+ "47": "SUCCESS",
204
  "48": "NON_PARTICIPATING",
205
  "49": "SUCCESS",
206
+ "5": "NON_PARTICIPATING",
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",
 
249
  "89": "SUCCESS",
250
  "9": "SUCCESS",
251
  "90": "SUCCESS",
252
+ "91": "SUCCESS",
253
  "92": "SUCCESS",
254
  "93": "NON_PARTICIPATING",
255
  "94": "SUCCESS",
 
257
  "96": "SUCCESS",
258
  "97": "SUCCESS",
259
  "98": "SUCCESS",
260
+ "99": "SUCCESS"
261
  },
262
  "architectures": [
263
  "GPTOptim"
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5587040,
272
+ 5587080,
273
+ 5587084,
274
+ 5587088,
275
+ 5587092
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": 44,
283
  "inner_steps": 0,
284
+ "last_allreduce_block": 5570305,
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 sha256:22450f590d5fca4edaf25c04e5ee075d02d6030701406521d2820b73ba24986d
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37feaaf06ab49149ba238040831ac3344b04575207021f271905c8ce332c1ae0
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abe24de186655ef428303656a6e4930c5d77388c2c3af48173ef939448d7d0d3
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e71d6be97d2d11723e52cb20bf8b9482cc85d63cc1ef82299ffc9310b5192de
3
  size 4040701744