philip324mark commited on
Commit
e09d68c
·
verified ·
1 Parent(s): 66a9692

Run 4. Outer Step 61. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +68 -68
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "philip324mark/mark6",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
@@ -9,14 +9,14 @@
9
  "101": "SUCCESS",
10
  "102": "SUCCESS",
11
  "103": "NON_PARTICIPATING",
12
- "104": "NON_PARTICIPATING",
13
- "105": "NON_PARTICIPATING",
14
- "106": "SUCCESS",
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": "NON_PARTICIPATING",
@@ -24,46 +24,46 @@
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": "SUCCESS",
31
  "121": "NON_PARTICIPATING",
32
  "122": "SUCCESS",
33
- "123": "NON_PARTICIPATING",
34
  "124": "NON_PARTICIPATING",
35
  "125": "SUCCESS",
36
- "126": "NON_PARTICIPATING",
37
  "127": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
39
- "129": "SUCCESS",
40
- "13": "FAIL",
41
  "130": "SUCCESS",
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",
58
  "146": "NON_PARTICIPATING",
59
- "147": "SUCCESS",
60
  "148": "NON_PARTICIPATING",
61
  "149": "NON_PARTICIPATING",
62
- "15": "SUCCESS",
63
- "150": "SUCCESS",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
- "153": "SUCCESS",
67
  "154": "NON_PARTICIPATING",
68
  "155": "NON_PARTICIPATING",
69
  "156": "NON_PARTICIPATING",
@@ -85,17 +85,17 @@
85
  "170": "NON_PARTICIPATING",
86
  "171": "SUCCESS",
87
  "172": "NON_PARTICIPATING",
88
- "173": "FAIL",
89
- "174": "FAIL",
90
  "175": "NON_PARTICIPATING",
91
  "176": "NON_PARTICIPATING",
92
- "177": "FAIL",
93
  "178": "NON_PARTICIPATING",
94
  "179": "NON_PARTICIPATING",
95
  "18": "SUCCESS",
96
  "180": "NON_PARTICIPATING",
97
- "181": "SUCCESS",
98
- "182": "SUCCESS",
99
  "183": "NON_PARTICIPATING",
100
  "184": "NON_PARTICIPATING",
101
  "185": "NON_PARTICIPATING",
@@ -106,8 +106,8 @@
106
  "19": "NON_PARTICIPATING",
107
  "190": "NON_PARTICIPATING",
108
  "191": "NON_PARTICIPATING",
109
- "192": "SUCCESS",
110
- "193": "SUCCESS",
111
  "194": "NON_PARTICIPATING",
112
  "195": "NON_PARTICIPATING",
113
  "196": "NON_PARTICIPATING",
@@ -115,26 +115,26 @@
115
  "198": "NON_PARTICIPATING",
116
  "199": "NON_PARTICIPATING",
117
  "2": "SUCCESS",
118
- "20": "NON_PARTICIPATING",
119
  "200": "NON_PARTICIPATING",
120
  "201": "NON_PARTICIPATING",
121
- "202": "NON_PARTICIPATING",
122
- "203": "SUCCESS",
123
  "204": "NON_PARTICIPATING",
124
- "205": "SUCCESS",
125
  "206": "NON_PARTICIPATING",
126
  "207": "NON_PARTICIPATING",
127
  "208": "NON_PARTICIPATING",
128
  "209": "NON_PARTICIPATING",
129
  "21": "SUCCESS",
130
- "210": "SUCCESS",
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": "SUCCESS",
138
  "218": "NON_PARTICIPATING",
139
  "219": "NON_PARTICIPATING",
140
  "22": "SUCCESS",
@@ -143,28 +143,28 @@
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": "NON_PARTICIPATING",
152
- "230": "NON_PARTICIPATING",
153
  "231": "NON_PARTICIPATING",
154
- "232": "SUCCESS",
155
  "233": "SUCCESS",
156
  "234": "NON_PARTICIPATING",
157
  "235": "NON_PARTICIPATING",
158
- "236": "SUCCESS",
159
  "237": "NON_PARTICIPATING",
160
  "238": "NON_PARTICIPATING",
161
- "239": "FAIL",
162
  "24": "SUCCESS",
163
  "240": "NON_PARTICIPATING",
164
  "241": "NON_PARTICIPATING",
165
  "242": "NON_PARTICIPATING",
166
  "243": "SUCCESS",
167
- "244": "NON_PARTICIPATING",
168
  "245": "NON_PARTICIPATING",
169
  "246": "SUCCESS",
170
  "247": "NON_PARTICIPATING",
@@ -175,7 +175,7 @@
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",
@@ -183,31 +183,31 @@
183
  "29": "SUCCESS",
184
  "3": "SUCCESS",
185
  "30": "NON_PARTICIPATING",
186
- "31": "NON_PARTICIPATING",
187
- "32": "NON_PARTICIPATING",
188
  "33": "NON_PARTICIPATING",
189
  "34": "NON_PARTICIPATING",
190
  "35": "SUCCESS",
191
  "36": "NON_PARTICIPATING",
192
- "37": "NON_PARTICIPATING",
193
  "38": "SUCCESS",
194
- "39": "NON_PARTICIPATING",
195
- "4": "SUCCESS",
196
- "40": "NON_PARTICIPATING",
197
  "41": "SUCCESS",
198
  "42": "SUCCESS",
199
  "43": "SUCCESS",
200
- "44": "FAIL",
201
  "45": "SUCCESS",
202
  "46": "NON_PARTICIPATING",
203
  "47": "SUCCESS",
204
  "48": "NON_PARTICIPATING",
205
  "49": "SUCCESS",
206
  "5": "SUCCESS",
207
- "50": "NON_PARTICIPATING",
208
  "51": "SUCCESS",
209
  "52": "NON_PARTICIPATING",
210
- "53": "NON_PARTICIPATING",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
@@ -216,29 +216,29 @@
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": "NON_PARTICIPATING",
227
- "69": "NON_PARTICIPATING",
228
  "7": "SUCCESS",
229
  "70": "SUCCESS",
230
- "71": "FAIL",
231
  "72": "NON_PARTICIPATING",
232
  "73": "NON_PARTICIPATING",
233
  "74": "SUCCESS",
234
  "75": "SUCCESS",
235
  "76": "NON_PARTICIPATING",
236
  "77": "SUCCESS",
237
- "78": "NON_PARTICIPATING",
238
  "79": "NON_PARTICIPATING",
239
- "8": "NON_PARTICIPATING",
240
- "80": "SUCCESS",
241
- "81": "NON_PARTICIPATING",
242
  "82": "SUCCESS",
243
  "83": "SUCCESS",
244
  "84": "SUCCESS",
@@ -246,10 +246,10 @@
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
249
- "89": "FAIL",
250
  "9": "SUCCESS",
251
  "90": "SUCCESS",
252
- "91": "NON_PARTICIPATING",
253
  "92": "SUCCESS",
254
  "93": "NON_PARTICIPATING",
255
  "94": "SUCCESS",
@@ -268,17 +268,17 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5640935,
272
- 5640964
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": 49,
280
  "inner_steps": 0,
281
- "last_allreduce_block": 5636912,
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",
 
9
  "101": "SUCCESS",
10
  "102": "SUCCESS",
11
  "103": "NON_PARTICIPATING",
12
+ "104": "SUCCESS",
13
+ "105": "SUCCESS",
14
+ "106": "NON_PARTICIPATING",
15
  "107": "NON_PARTICIPATING",
16
  "108": "NON_PARTICIPATING",
17
  "109": "NON_PARTICIPATING",
18
+ "11": "SUCCESS",
19
+ "110": "SUCCESS",
20
  "111": "NON_PARTICIPATING",
21
  "112": "NON_PARTICIPATING",
22
  "113": "NON_PARTICIPATING",
 
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": "NON_PARTICIPATING",
32
  "122": "SUCCESS",
33
+ "123": "SUCCESS",
34
  "124": "NON_PARTICIPATING",
35
  "125": "SUCCESS",
36
+ "126": "SUCCESS",
37
  "127": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
39
+ "129": "NON_PARTICIPATING",
40
+ "13": "SUCCESS",
41
  "130": "SUCCESS",
42
  "131": "NON_PARTICIPATING",
43
  "132": "NON_PARTICIPATING",
44
  "133": "NON_PARTICIPATING",
45
+ "134": "SUCCESS",
46
  "135": "NON_PARTICIPATING",
47
  "136": "NON_PARTICIPATING",
48
+ "137": "SUCCESS",
49
+ "138": "SUCCESS",
50
+ "139": "SUCCESS",
51
  "14": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
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",
 
85
  "170": "NON_PARTICIPATING",
86
  "171": "SUCCESS",
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",
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": "NON_PARTICIPATING",
101
  "185": "NON_PARTICIPATING",
 
106
  "19": "NON_PARTICIPATING",
107
  "190": "NON_PARTICIPATING",
108
  "191": "NON_PARTICIPATING",
109
+ "192": "NON_PARTICIPATING",
110
+ "193": "NON_PARTICIPATING",
111
  "194": "NON_PARTICIPATING",
112
  "195": "NON_PARTICIPATING",
113
  "196": "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": "SUCCESS",
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": "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": "SUCCESS",
137
+ "217": "NON_PARTICIPATING",
138
  "218": "NON_PARTICIPATING",
139
  "219": "NON_PARTICIPATING",
140
  "22": "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": "NON_PARTICIPATING",
151
+ "23": "SUCCESS",
152
+ "230": "SUCCESS",
153
  "231": "NON_PARTICIPATING",
154
+ "232": "NON_PARTICIPATING",
155
  "233": "SUCCESS",
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": "SUCCESS",
167
+ "244": "SUCCESS",
168
  "245": "NON_PARTICIPATING",
169
  "246": "SUCCESS",
170
  "247": "NON_PARTICIPATING",
 
175
  "251": "NON_PARTICIPATING",
176
  "252": "NON_PARTICIPATING",
177
  "253": "NON_PARTICIPATING",
178
+ "254": "SUCCESS",
179
  "255": "NON_PARTICIPATING",
180
  "26": "SUCCESS",
181
  "27": "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": "SUCCESS",
194
+ "39": "SUCCESS",
195
+ "4": "NON_PARTICIPATING",
196
+ "40": "SUCCESS",
197
  "41": "SUCCESS",
198
  "42": "SUCCESS",
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",
208
  "51": "SUCCESS",
209
  "52": "NON_PARTICIPATING",
210
+ "53": "SUCCESS",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
 
216
  "59": "NON_PARTICIPATING",
217
  "6": "NON_PARTICIPATING",
218
  "60": "SUCCESS",
219
+ "61": "SUCCESS",
220
  "62": "SUCCESS",
221
  "63": "SUCCESS",
222
+ "64": "SUCCESS",
223
  "65": "NON_PARTICIPATING",
224
  "66": "NON_PARTICIPATING",
225
+ "67": "NON_PARTICIPATING",
226
+ "68": "SUCCESS",
227
+ "69": "SUCCESS",
228
  "7": "SUCCESS",
229
  "70": "SUCCESS",
230
+ "71": "SUCCESS",
231
  "72": "NON_PARTICIPATING",
232
  "73": "NON_PARTICIPATING",
233
  "74": "SUCCESS",
234
  "75": "SUCCESS",
235
  "76": "NON_PARTICIPATING",
236
  "77": "SUCCESS",
237
+ "78": "SUCCESS",
238
  "79": "NON_PARTICIPATING",
239
+ "8": "SUCCESS",
240
+ "80": "NON_PARTICIPATING",
241
+ "81": "SUCCESS",
242
  "82": "SUCCESS",
243
  "83": "SUCCESS",
244
  "84": "SUCCESS",
 
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
249
+ "89": "SUCCESS",
250
  "9": "SUCCESS",
251
  "90": "SUCCESS",
252
+ "91": "FAIL",
253
  "92": "SUCCESS",
254
  "93": "NON_PARTICIPATING",
255
  "94": "SUCCESS",
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5641128,
272
+ 5641158
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": 5641040,
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:b28664533f0d72a64555e18c84191b537557fe0dce30a63c59d325df438f83a1
3
  size 8081782503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac97edc7805ac915b71db2372e14e89b94868b016a171c4865aeafed084c3b0
3
  size 8081782503
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84fd95d4c3516694485d5c92d091ffc8a22d8f00683111f45f00b4da98c8216f
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45e1908b54d3d796f8157469a5025432cb8459c1ffa66e1dc3b2a33e4674178
3
  size 4040701744