philip324mark commited on
Commit
03681db
·
verified ·
1 Parent(s): c05e049

Run 4. Outer Step 60. Inner Step 2.

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
@@ -1,21 +1,21 @@
1
  {
2
- "_name_or_path": "philip324mark/mark16",
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": "SUCCESS",
15
  "107": "SUCCESS",
16
  "108": "NON_PARTICIPATING",
17
- "109": "FAIL",
18
- "11": "SUCCESS",
19
  "110": "NON_PARTICIPATING",
20
  "111": "SUCCESS",
21
  "112": "NON_PARTICIPATING",
@@ -23,31 +23,31 @@
23
  "114": "NON_PARTICIPATING",
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
26
- "117": "SUCCESS",
27
  "118": "SUCCESS",
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": "SUCCESS",
40
  "13": "SUCCESS",
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": "SUCCESS",
51
  "14": "NON_PARTICIPATING",
52
  "140": "NON_PARTICIPATING",
53
  "141": "SUCCESS",
@@ -56,14 +56,14 @@
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": "SUCCESS",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
- "153": "NON_PARTICIPATING",
67
  "154": "NON_PARTICIPATING",
68
  "155": "NON_PARTICIPATING",
69
  "156": "NON_PARTICIPATING",
@@ -75,7 +75,7 @@
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",
@@ -85,9 +85,9 @@
85
  "170": "NON_PARTICIPATING",
86
  "171": "NON_PARTICIPATING",
87
  "172": "NON_PARTICIPATING",
88
- "173": "SUCCESS",
89
- "174": "FAIL",
90
- "175": "NON_PARTICIPATING",
91
  "176": "NON_PARTICIPATING",
92
  "177": "NON_PARTICIPATING",
93
  "178": "NON_PARTICIPATING",
@@ -95,10 +95,10 @@
95
  "18": "SUCCESS",
96
  "180": "NON_PARTICIPATING",
97
  "181": "NON_PARTICIPATING",
98
- "182": "SUCCESS",
99
  "183": "NON_PARTICIPATING",
100
  "184": "NON_PARTICIPATING",
101
- "185": "FAIL",
102
  "186": "NON_PARTICIPATING",
103
  "187": "NON_PARTICIPATING",
104
  "188": "NON_PARTICIPATING",
@@ -106,11 +106,11 @@
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",
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
116
  "199": "NON_PARTICIPATING",
@@ -133,10 +133,10 @@
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",
141
  "220": "NON_PARTICIPATING",
142
  "221": "NON_PARTICIPATING",
@@ -146,20 +146,20 @@
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": "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": "NON_PARTICIPATING",
162
- "24": "FAIL",
163
  "240": "NON_PARTICIPATING",
164
  "241": "NON_PARTICIPATING",
165
  "242": "NON_PARTICIPATING",
@@ -175,7 +175,7 @@
175
  "251": "NON_PARTICIPATING",
176
  "252": "NON_PARTICIPATING",
177
  "253": "NON_PARTICIPATING",
178
- "254": "FAIL",
179
  "255": "NON_PARTICIPATING",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
@@ -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": "NON_PARTICIPATING",
@@ -198,16 +198,16 @@
198
  "42": "SUCCESS",
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
- "45": "FAIL",
202
  "46": "NON_PARTICIPATING",
203
  "47": "SUCCESS",
204
  "48": "NON_PARTICIPATING",
205
- "49": "FAIL",
206
  "5": "SUCCESS",
207
  "50": "SUCCESS",
208
  "51": "SUCCESS",
209
  "52": "NON_PARTICIPATING",
210
- "53": "NON_PARTICIPATING",
211
  "54": "SUCCESS",
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
@@ -216,16 +216,16 @@
216
  "59": "NON_PARTICIPATING",
217
  "6": "NON_PARTICIPATING",
218
  "60": "SUCCESS",
219
- "61": "NON_PARTICIPATING",
220
  "62": "SUCCESS",
221
- "63": "FAIL",
222
  "64": "NON_PARTICIPATING",
223
  "65": "NON_PARTICIPATING",
224
  "66": "NON_PARTICIPATING",
225
  "67": "SUCCESS",
226
  "68": "SUCCESS",
227
  "69": "SUCCESS",
228
- "7": "FAIL",
229
  "70": "SUCCESS",
230
  "71": "SUCCESS",
231
  "72": "NON_PARTICIPATING",
@@ -245,7 +245,7 @@
245
  "85": "NON_PARTICIPATING",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
- "88": "FAIL",
249
  "89": "SUCCESS",
250
  "9": "SUCCESS",
251
  "90": "SUCCESS",
@@ -268,17 +268,17 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5639589,
272
- 5639616
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": 46,
280
  "inner_steps": 0,
281
- "last_allreduce_block": 5638171,
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": "NON_PARTICIPATING",
10
  "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
  "104": "SUCCESS",
13
  "105": "NON_PARTICIPATING",
14
+ "106": "NON_PARTICIPATING",
15
  "107": "SUCCESS",
16
  "108": "NON_PARTICIPATING",
17
+ "109": "NON_PARTICIPATING",
18
+ "11": "NON_PARTICIPATING",
19
  "110": "NON_PARTICIPATING",
20
  "111": "SUCCESS",
21
  "112": "NON_PARTICIPATING",
 
23
  "114": "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": "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",
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": "SUCCESS",
49
  "138": "NON_PARTICIPATING",
50
+ "139": "NON_PARTICIPATING",
51
  "14": "NON_PARTICIPATING",
52
  "140": "NON_PARTICIPATING",
53
  "141": "SUCCESS",
 
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": "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",
 
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
77
  "163": "NON_PARTICIPATING",
78
+ "164": "SUCCESS",
79
  "165": "NON_PARTICIPATING",
80
  "166": "NON_PARTICIPATING",
81
  "167": "NON_PARTICIPATING",
 
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",
 
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",
102
  "186": "NON_PARTICIPATING",
103
  "187": "NON_PARTICIPATING",
104
  "188": "NON_PARTICIPATING",
 
106
  "19": "NON_PARTICIPATING",
107
  "190": "NON_PARTICIPATING",
108
  "191": "NON_PARTICIPATING",
109
+ "192": "FAIL",
110
+ "193": "SUCCESS",
111
  "194": "NON_PARTICIPATING",
112
  "195": "NON_PARTICIPATING",
113
+ "196": "SUCCESS",
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
116
  "199": "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": "SUCCESS",
140
  "22": "SUCCESS",
141
  "220": "NON_PARTICIPATING",
142
  "221": "NON_PARTICIPATING",
 
146
  "225": "SUCCESS",
147
  "226": "NON_PARTICIPATING",
148
  "227": "NON_PARTICIPATING",
149
+ "228": "SUCCESS",
150
  "229": "NON_PARTICIPATING",
151
  "23": "SUCCESS",
152
+ "230": "SUCCESS",
153
  "231": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
161
+ "239": "SUCCESS",
162
+ "24": "SUCCESS",
163
  "240": "NON_PARTICIPATING",
164
  "241": "NON_PARTICIPATING",
165
  "242": "NON_PARTICIPATING",
 
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
  "29": "SUCCESS",
184
  "3": "SUCCESS",
185
  "30": "NON_PARTICIPATING",
186
+ "31": "SUCCESS",
187
  "32": "SUCCESS",
188
  "33": "NON_PARTICIPATING",
189
  "34": "NON_PARTICIPATING",
 
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": "NON_PARTICIPATING",
223
  "65": "NON_PARTICIPATING",
224
  "66": "NON_PARTICIPATING",
225
  "67": "SUCCESS",
226
  "68": "SUCCESS",
227
  "69": "SUCCESS",
228
+ "7": "SUCCESS",
229
  "70": "SUCCESS",
230
  "71": "SUCCESS",
231
  "72": "NON_PARTICIPATING",
 
245
  "85": "NON_PARTICIPATING",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
+ "88": "SUCCESS",
249
  "89": "SUCCESS",
250
  "9": "SUCCESS",
251
  "90": "SUCCESS",
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5639720,
272
+ 5639746
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": 5639485,
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:c2fb808c55dbe8702577b4488665c9122ea1068cd38896d84855e83145cd5363
3
  size 8081782503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:448d1715494891705bc33aae5469a455b0665c8790ae81fa6a42e261d585f205
3
  size 8081782503
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7df194c41e00268e6173c4c14b363dd45e1b428a0046dc0abeb546399da06c5f
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b9299875d9f10ce919017065b1eb8a380f7f9fe7af96829a81f11954f28c09
3
  size 4040701744