jockibaba commited on
Commit
9c7689e
·
verified ·
1 Parent(s): 0260b2a

Run 4. Outer Step 98. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +78 -78
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "_name_or_path": "jockibaba/jockibaba12",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
6
- "1": "NON_PARTICIPATING",
7
  "10": "NON_PARTICIPATING",
8
  "100": "NON_PARTICIPATING",
9
- "101": "NON_PARTICIPATING",
10
  "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
  "104": "NON_PARTICIPATING",
@@ -15,7 +15,7 @@
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",
@@ -36,19 +36,19 @@
36
  "126": "NON_PARTICIPATING",
37
  "127": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
39
- "129": "SUCCESS",
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": "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": "NON_PARTICIPATING",
@@ -57,7 +57,7 @@
57
  "145": "NON_PARTICIPATING",
58
  "146": "NON_PARTICIPATING",
59
  "147": "NON_PARTICIPATING",
60
- "148": "NON_PARTICIPATING",
61
  "149": "NON_PARTICIPATING",
62
  "15": "NON_PARTICIPATING",
63
  "150": "NON_PARTICIPATING",
@@ -66,11 +66,11 @@
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": "NON_PARTICIPATING",
74
  "160": "NON_PARTICIPATING",
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
@@ -78,21 +78,21 @@
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": "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": "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",
@@ -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",
@@ -114,14 +114,14 @@
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
116
  "199": "NON_PARTICIPATING",
117
- "2": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
@@ -134,10 +134,10 @@
134
  "214": "NON_PARTICIPATING",
135
  "215": "NON_PARTICIPATING",
136
  "216": "NON_PARTICIPATING",
137
- "217": "SUCCESS",
138
  "218": "NON_PARTICIPATING",
139
  "219": "NON_PARTICIPATING",
140
- "22": "NON_PARTICIPATING",
141
  "220": "NON_PARTICIPATING",
142
  "221": "NON_PARTICIPATING",
143
  "222": "NON_PARTICIPATING",
@@ -148,18 +148,18 @@
148
  "227": "NON_PARTICIPATING",
149
  "228": "NON_PARTICIPATING",
150
  "229": "NON_PARTICIPATING",
151
- "23": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
163
  "240": "NON_PARTICIPATING",
164
  "241": "NON_PARTICIPATING",
165
  "242": "NON_PARTICIPATING",
@@ -168,7 +168,7 @@
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",
@@ -180,83 +180,83 @@
180
  "26": "NON_PARTICIPATING",
181
  "27": "SUCCESS",
182
  "28": "SUCCESS",
183
- "29": "NON_PARTICIPATING",
184
- "3": "NON_PARTICIPATING",
185
  "30": "NON_PARTICIPATING",
186
- "31": "NON_PARTICIPATING",
187
- "32": "NON_PARTICIPATING",
188
  "33": "NON_PARTICIPATING",
189
- "34": "SUCCESS",
190
- "35": "NON_PARTICIPATING",
191
  "36": "NON_PARTICIPATING",
192
- "37": "NON_PARTICIPATING",
193
- "38": "SUCCESS",
194
  "39": "SUCCESS",
195
  "4": "NON_PARTICIPATING",
196
- "40": "SUCCESS",
197
  "41": "NON_PARTICIPATING",
198
- "42": "SUCCESS",
199
  "43": "NON_PARTICIPATING",
200
- "44": "SUCCESS",
201
- "45": "NON_PARTICIPATING",
202
- "46": "NON_PARTICIPATING",
203
  "47": "NON_PARTICIPATING",
204
  "48": "NON_PARTICIPATING",
205
  "49": "NON_PARTICIPATING",
206
- "5": "SUCCESS",
207
- "50": "NON_PARTICIPATING",
208
  "51": "SUCCESS",
209
- "52": "SUCCESS",
210
- "53": "NON_PARTICIPATING",
211
- "54": "NON_PARTICIPATING",
212
  "55": "NON_PARTICIPATING",
213
  "56": "NON_PARTICIPATING",
214
- "57": "NON_PARTICIPATING",
215
  "58": "NON_PARTICIPATING",
216
- "59": "SUCCESS",
217
- "6": "NON_PARTICIPATING",
218
  "60": "SUCCESS",
219
- "61": "NON_PARTICIPATING",
220
- "62": "NON_PARTICIPATING",
221
  "63": "SUCCESS",
222
- "64": "SUCCESS",
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": "SUCCESS",
231
  "72": "NON_PARTICIPATING",
232
- "73": "NON_PARTICIPATING",
233
  "74": "NON_PARTICIPATING",
234
  "75": "NON_PARTICIPATING",
235
- "76": "NON_PARTICIPATING",
236
- "77": "SUCCESS",
237
- "78": "NON_PARTICIPATING",
238
  "79": "NON_PARTICIPATING",
239
- "8": "SUCCESS",
240
  "80": "NON_PARTICIPATING",
241
- "81": "NON_PARTICIPATING",
242
  "82": "NON_PARTICIPATING",
243
  "83": "NON_PARTICIPATING",
244
- "84": "NON_PARTICIPATING",
245
- "85": "SUCCESS",
246
  "86": "NON_PARTICIPATING",
247
- "87": "NON_PARTICIPATING",
248
- "88": "NON_PARTICIPATING",
249
- "89": "NON_PARTICIPATING",
250
- "9": "SUCCESS",
251
- "90": "NON_PARTICIPATING",
252
  "91": "SUCCESS",
253
  "92": "NON_PARTICIPATING",
254
- "93": "NON_PARTICIPATING",
255
- "94": "NON_PARTICIPATING",
256
- "95": "SUCCESS",
257
  "96": "NON_PARTICIPATING",
258
  "97": "NON_PARTICIPATING",
259
- "98": "NON_PARTICIPATING",
260
  "99": "NON_PARTICIPATING"
261
  },
262
  "architectures": [
@@ -268,17 +268,17 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5687863,
272
- 5687893
273
  ],
274
  "block_size": 1024,
275
  "bos_token_id": 50256,
276
  "embd_pdrop": 0.1,
277
  "eos_token_id": 50256,
278
  "initializer_range": 0.02,
279
- "inner_step": 58,
280
  "inner_steps": 0,
281
- "last_allreduce_block": 5672513,
282
  "layer_norm_epsilon": 1e-05,
283
  "model_type": "gpt_optimized",
284
  "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": "SUCCESS",
10
  "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
  "104": "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",
 
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": "SUCCESS",
50
  "139": "NON_PARTICIPATING",
51
+ "14": "SUCCESS",
52
  "140": "NON_PARTICIPATING",
53
  "141": "NON_PARTICIPATING",
54
  "142": "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",
 
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": "NON_PARTICIPATING",
73
+ "16": "SUCCESS",
74
  "160": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
83
  "169": "NON_PARTICIPATING",
84
+ "17": "SUCCESS",
85
  "170": "NON_PARTICIPATING",
86
  "171": "NON_PARTICIPATING",
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": "SUCCESS",
95
+ "18": "SUCCESS",
96
  "180": "NON_PARTICIPATING",
97
  "181": "NON_PARTICIPATING",
98
  "182": "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",
 
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
116
  "199": "NON_PARTICIPATING",
117
+ "2": "SUCCESS",
118
+ "20": "NON_PARTICIPATING",
119
+ "200": "SUCCESS",
120
  "201": "NON_PARTICIPATING",
121
  "202": "NON_PARTICIPATING",
122
  "203": "NON_PARTICIPATING",
123
  "204": "NON_PARTICIPATING",
124
+ "205": "SUCCESS",
125
  "206": "NON_PARTICIPATING",
126
  "207": "NON_PARTICIPATING",
127
  "208": "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",
 
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": "SUCCESS",
155
  "233": "NON_PARTICIPATING",
156
  "234": "NON_PARTICIPATING",
157
  "235": "NON_PARTICIPATING",
158
+ "236": "SUCCESS",
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",
 
168
  "245": "NON_PARTICIPATING",
169
  "246": "NON_PARTICIPATING",
170
  "247": "NON_PARTICIPATING",
171
+ "248": "SUCCESS",
172
  "249": "NON_PARTICIPATING",
173
  "25": "SUCCESS",
174
  "250": "NON_PARTICIPATING",
 
180
  "26": "NON_PARTICIPATING",
181
  "27": "SUCCESS",
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": "NON_PARTICIPATING",
190
+ "35": "SUCCESS",
191
  "36": "NON_PARTICIPATING",
192
+ "37": "SUCCESS",
193
+ "38": "NON_PARTICIPATING",
194
  "39": "SUCCESS",
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": "SUCCESS",
202
+ "46": "SUCCESS",
203
  "47": "NON_PARTICIPATING",
204
  "48": "NON_PARTICIPATING",
205
  "49": "NON_PARTICIPATING",
206
+ "5": "NON_PARTICIPATING",
207
+ "50": "SUCCESS",
208
  "51": "SUCCESS",
209
+ "52": "NON_PARTICIPATING",
210
+ "53": "SUCCESS",
211
+ "54": "SUCCESS",
212
  "55": "NON_PARTICIPATING",
213
  "56": "NON_PARTICIPATING",
214
+ "57": "SUCCESS",
215
  "58": "NON_PARTICIPATING",
216
+ "59": "NON_PARTICIPATING",
217
+ "6": "SUCCESS",
218
  "60": "SUCCESS",
219
+ "61": "SUCCESS",
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": "SUCCESS",
228
+ "7": "SUCCESS",
229
  "70": "NON_PARTICIPATING",
230
+ "71": "NON_PARTICIPATING",
231
  "72": "NON_PARTICIPATING",
232
+ "73": "SUCCESS",
233
  "74": "NON_PARTICIPATING",
234
  "75": "NON_PARTICIPATING",
235
+ "76": "SUCCESS",
236
+ "77": "NON_PARTICIPATING",
237
+ "78": "SUCCESS",
238
  "79": "NON_PARTICIPATING",
239
+ "8": "NON_PARTICIPATING",
240
  "80": "NON_PARTICIPATING",
241
+ "81": "SUCCESS",
242
  "82": "NON_PARTICIPATING",
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": "SUCCESS",
252
  "91": "SUCCESS",
253
  "92": "NON_PARTICIPATING",
254
+ "93": "SUCCESS",
255
+ "94": "SUCCESS",
256
+ "95": "NON_PARTICIPATING",
257
  "96": "NON_PARTICIPATING",
258
  "97": "NON_PARTICIPATING",
259
+ "98": "SUCCESS",
260
  "99": "NON_PARTICIPATING"
261
  },
262
  "architectures": [
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5693325,
272
+ 5693355
273
  ],
274
  "block_size": 1024,
275
  "bos_token_id": 50256,
276
  "embd_pdrop": 0.1,
277
  "eos_token_id": 50256,
278
  "initializer_range": 0.02,
279
+ "inner_step": 2,
280
  "inner_steps": 0,
281
+ "last_allreduce_block": 5692898,
282
  "layer_norm_epsilon": 1e-05,
283
  "model_type": "gpt_optimized",
284
  "n_embd": 1280,
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c69a56f940b51cc595b3c3eb3efe448f1538045ccea6370616c7599eff95b49c
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14f0b781f62f4d8fc3827df67b31aa33bbc5944d6dcb1e45e79e7f3e7ab78fde
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:840d1d9936821b3dc90703286eb6e3580626dd99ac539ef7808f8d7077b33622
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ca9744f51e239e9f828f85f379d30f609768e192f5437f484e4a0ac0dce2c8
3
  size 4040701744