philip324mark commited on
Commit
d176205
·
verified ·
1 Parent(s): 2fd4d30

Run 4. Outer Step 56. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +53 -53
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "philip324mark/mark3",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
@@ -7,38 +7,38 @@
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",
@@ -46,20 +46,20 @@
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",
@@ -69,45 +69,45 @@
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",
@@ -116,15 +116,15 @@
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",
@@ -140,16 +140,16 @@
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",
@@ -157,21 +157,21 @@
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",
@@ -183,7 +183,7 @@
183
  "29": "SUCCESS",
184
  "3": "SUCCESS",
185
  "30": "NON_PARTICIPATING",
186
- "31": "NON_PARTICIPATING",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
189
  "34": "SUCCESS",
@@ -195,7 +195,7 @@
195
  "4": "SUCCESS",
196
  "40": "SUCCESS",
197
  "41": "SUCCESS",
198
- "42": "NON_PARTICIPATING",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
@@ -206,7 +206,7 @@
206
  "5": "SUCCESS",
207
  "50": "SUCCESS",
208
  "51": "SUCCESS",
209
- "52": "SUCCESS",
210
  "53": "SUCCESS",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
@@ -225,7 +225,7 @@
225
  "67": "SUCCESS",
226
  "68": "SUCCESS",
227
  "69": "SUCCESS",
228
- "7": "NON_PARTICIPATING",
229
  "70": "NON_PARTICIPATING",
230
  "71": "NON_PARTICIPATING",
231
  "72": "SUCCESS",
@@ -234,7 +234,7 @@
234
  "75": "SUCCESS",
235
  "76": "SUCCESS",
236
  "77": "SUCCESS",
237
- "78": "SUCCESS",
238
  "79": "NON_PARTICIPATING",
239
  "8": "SUCCESS",
240
  "80": "SUCCESS",
@@ -245,10 +245,10 @@
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",
@@ -268,20 +268,20 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5599387,
272
- 5599391,
273
- 5599396,
274
- 5599401,
275
- 5599406
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": 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": "NON_PARTICIPATING",
 
7
  "10": "NON_PARTICIPATING",
8
  "100": "NON_PARTICIPATING",
9
  "101": "NON_PARTICIPATING",
10
+ "102": "SUCCESS",
11
  "103": "NON_PARTICIPATING",
12
  "104": "NON_PARTICIPATING",
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",
20
  "111": "NON_PARTICIPATING",
21
  "112": "NON_PARTICIPATING",
22
+ "113": "NON_PARTICIPATING",
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": "FAIL",
30
  "120": "NON_PARTICIPATING",
31
  "121": "NON_PARTICIPATING",
32
+ "122": "SUCCESS",
33
  "123": "NON_PARTICIPATING",
34
+ "124": "SUCCESS",
35
  "125": "NON_PARTICIPATING",
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",
 
46
  "135": "NON_PARTICIPATING",
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
+ "138": "NON_PARTICIPATING",
50
  "139": "NON_PARTICIPATING",
51
  "14": "SUCCESS",
52
  "140": "NON_PARTICIPATING",
53
  "141": "NON_PARTICIPATING",
54
  "142": "NON_PARTICIPATING",
55
+ "143": "SUCCESS",
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",
65
  "152": "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",
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": "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",
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": "SUCCESS",
102
+ "186": "SUCCESS",
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": "SUCCESS",
110
+ "193": "SUCCESS",
111
  "194": "NON_PARTICIPATING",
112
  "195": "NON_PARTICIPATING",
113
  "196": "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": "NON_PARTICIPATING",
129
  "21": "SUCCESS",
130
  "210": "NON_PARTICIPATING",
 
140
  "22": "SUCCESS",
141
  "220": "NON_PARTICIPATING",
142
  "221": "NON_PARTICIPATING",
143
+ "222": "SUCCESS",
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": "NON_PARTICIPATING",
153
  "231": "NON_PARTICIPATING",
154
  "232": "SUCCESS",
155
  "233": "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": "SUCCESS",
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": "SUCCESS",
173
  "25": "SUCCESS",
174
+ "250": "NON_PARTICIPATING",
175
  "251": "NON_PARTICIPATING",
176
  "252": "NON_PARTICIPATING",
177
  "253": "NON_PARTICIPATING",
 
183
  "29": "SUCCESS",
184
  "3": "SUCCESS",
185
  "30": "NON_PARTICIPATING",
186
+ "31": "SUCCESS",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
189
  "34": "SUCCESS",
 
195
  "4": "SUCCESS",
196
  "40": "SUCCESS",
197
  "41": "SUCCESS",
198
+ "42": "SUCCESS",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
 
206
  "5": "SUCCESS",
207
  "50": "SUCCESS",
208
  "51": "SUCCESS",
209
+ "52": "NON_PARTICIPATING",
210
  "53": "SUCCESS",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
 
225
  "67": "SUCCESS",
226
  "68": "SUCCESS",
227
  "69": "SUCCESS",
228
+ "7": "SUCCESS",
229
  "70": "NON_PARTICIPATING",
230
  "71": "NON_PARTICIPATING",
231
  "72": "SUCCESS",
 
234
  "75": "SUCCESS",
235
  "76": "SUCCESS",
236
  "77": "SUCCESS",
237
+ "78": "NON_PARTICIPATING",
238
  "79": "NON_PARTICIPATING",
239
  "8": "SUCCESS",
240
  "80": "SUCCESS",
 
245
  "85": "NON_PARTICIPATING",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
+ "88": "NON_PARTICIPATING",
249
  "89": "SUCCESS",
250
+ "9": "SUCCESS",
251
+ "90": "SUCCESS",
252
  "91": "SUCCESS",
253
  "92": "SUCCESS",
254
  "93": "NON_PARTICIPATING",
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5599541,
272
+ 5599546,
273
+ 5599551,
274
+ 5599556,
275
+ 5599561
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": 5599463,
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 sha256:353b03b084766a6ecc8cfa7ef24c4b840518d926e90ccec4d4bd4fec71da4f37
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d002f1d19d255167035b990d4cde595c0c99e63a22f33f98cc6c403560fbc0ea
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd8e7279d59a64356f22c3c781f4b17713d63476872b0e93f282d7ad640263a1
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60c473da30b7c93e82dd80d1e7e66ee8fc9142612a376e04ec556c6f98a2da9a
3
  size 4040701744