ncaagcc commited on
Commit
1082cd9
·
verified ·
1 Parent(s): e480dd5

Run 4. Outer Step 24. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +51 -55
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -7,19 +7,19 @@
7
  "10": "SUCCESS",
8
  "100": "NON_PARTICIPATING",
9
  "101": "SUCCESS",
10
- "102": "NON_PARTICIPATING",
11
  "103": "NON_PARTICIPATING",
12
  "104": "NON_PARTICIPATING",
13
  "105": "NON_PARTICIPATING",
14
  "106": "SUCCESS",
15
  "107": "SUCCESS",
16
  "108": "NON_PARTICIPATING",
17
- "109": "SUCCESS",
18
  "11": "NON_PARTICIPATING",
19
  "110": "SUCCESS",
20
- "111": "NON_PARTICIPATING",
21
  "112": "NON_PARTICIPATING",
22
- "113": "NON_PARTICIPATING",
23
  "114": "SUCCESS",
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
@@ -34,13 +34,13 @@
34
  "124": "NON_PARTICIPATING",
35
  "125": "NON_PARTICIPATING",
36
  "126": "NON_PARTICIPATING",
37
- "127": "NON_PARTICIPATING",
38
  "128": "NON_PARTICIPATING",
39
- "129": "SUCCESS",
40
  "13": "NON_PARTICIPATING",
41
  "130": "NON_PARTICIPATING",
42
  "131": "NON_PARTICIPATING",
43
- "132": "NON_PARTICIPATING",
44
  "133": "NON_PARTICIPATING",
45
  "134": "NON_PARTICIPATING",
46
  "135": "NON_PARTICIPATING",
@@ -54,9 +54,9 @@
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": "SUCCESS",
61
  "149": "NON_PARTICIPATING",
62
  "15": "SUCCESS",
@@ -64,14 +64,14 @@
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
  "153": "NON_PARTICIPATING",
67
- "154": "SUCCESS",
68
  "155": "NON_PARTICIPATING",
69
  "156": "SUCCESS",
70
  "157": "NON_PARTICIPATING",
71
  "158": "NON_PARTICIPATING",
72
- "159": "SUCCESS",
73
  "16": "SUCCESS",
74
- "160": "SUCCESS",
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
77
  "163": "NON_PARTICIPATING",
@@ -79,17 +79,17 @@
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": "SUCCESS",
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": "SUCCESS",
@@ -97,34 +97,34 @@
97
  "181": "NON_PARTICIPATING",
98
  "182": "NON_PARTICIPATING",
99
  "183": "NON_PARTICIPATING",
100
- "184": "SUCCESS",
101
- "185": "SUCCESS",
102
  "186": "SUCCESS",
103
- "187": "NON_PARTICIPATING",
104
  "188": "NON_PARTICIPATING",
105
  "189": "NON_PARTICIPATING",
106
  "19": "NON_PARTICIPATING",
107
  "190": "NON_PARTICIPATING",
108
- "191": "SUCCESS",
109
- "192": "SUCCESS",
110
  "193": "NON_PARTICIPATING",
111
  "194": "NON_PARTICIPATING",
112
- "195": "SUCCESS",
113
  "196": "NON_PARTICIPATING",
114
  "197": "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": "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",
@@ -135,8 +135,8 @@
135
  "215": "NON_PARTICIPATING",
136
  "216": "NON_PARTICIPATING",
137
  "217": "NON_PARTICIPATING",
138
- "218": "SUCCESS",
139
- "219": "SUCCESS",
140
  "22": "SUCCESS",
141
  "220": "NON_PARTICIPATING",
142
  "221": "NON_PARTICIPATING",
@@ -148,8 +148,8 @@
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",
@@ -159,9 +159,9 @@
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",
166
  "243": "NON_PARTICIPATING",
167
  "244": "SUCCESS",
@@ -169,9 +169,9 @@
169
  "246": "NON_PARTICIPATING",
170
  "247": "NON_PARTICIPATING",
171
  "248": "NON_PARTICIPATING",
172
- "249": "SUCCESS",
173
  "25": "SUCCESS",
174
- "250": "SUCCESS",
175
  "251": "NON_PARTICIPATING",
176
  "252": "NON_PARTICIPATING",
177
  "253": "NON_PARTICIPATING",
@@ -179,15 +179,15 @@
179
  "255": "NON_PARTICIPATING",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
- "28": "SUCCESS",
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": "NON_PARTICIPATING",
191
  "36": "NON_PARTICIPATING",
192
  "37": "SUCCESS",
193
  "38": "NON_PARTICIPATING",
@@ -199,7 +199,7 @@
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
202
- "46": "SUCCESS",
203
  "47": "SUCCESS",
204
  "48": "NON_PARTICIPATING",
205
  "49": "SUCCESS",
@@ -212,13 +212,13 @@
212
  "55": "NON_PARTICIPATING",
213
  "56": "SUCCESS",
214
  "57": "SUCCESS",
215
- "58": "SUCCESS",
216
  "59": "NON_PARTICIPATING",
217
  "6": "NON_PARTICIPATING",
218
  "60": "SUCCESS",
219
  "61": "NON_PARTICIPATING",
220
  "62": "SUCCESS",
221
- "63": "NON_PARTICIPATING",
222
  "64": "NON_PARTICIPATING",
223
  "65": "SUCCESS",
224
  "66": "NON_PARTICIPATING",
@@ -234,10 +234,10 @@
234
  "75": "SUCCESS",
235
  "76": "NON_PARTICIPATING",
236
  "77": "NON_PARTICIPATING",
237
- "78": "NON_PARTICIPATING",
238
  "79": "NON_PARTICIPATING",
239
  "8": "SUCCESS",
240
- "80": "NON_PARTICIPATING",
241
  "81": "NON_PARTICIPATING",
242
  "82": "SUCCESS",
243
  "83": "NON_PARTICIPATING",
@@ -249,8 +249,8 @@
249
  "89": "SUCCESS",
250
  "9": "NON_PARTICIPATING",
251
  "90": "SUCCESS",
252
- "91": "SUCCESS",
253
- "92": "NON_PARTICIPATING",
254
  "93": "NON_PARTICIPATING",
255
  "94": "SUCCESS",
256
  "95": "SUCCESS",
@@ -268,24 +268,20 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5531626,
272
- 5531628,
273
- 5531631,
274
- 5531634,
275
- 5531636,
276
- 5531638,
277
- 5531641,
278
- 5531644,
279
- 5531646
280
  ],
281
  "block_size": 1024,
282
  "bos_token_id": 50256,
283
  "embd_pdrop": 0.1,
284
  "eos_token_id": 50256,
285
  "initializer_range": 0.02,
286
- "inner_step": 24,
287
  "inner_steps": 0,
288
- "last_allreduce_block": 5529444,
289
  "layer_norm_epsilon": 1e-05,
290
  "model_type": "gpt_optimized",
291
  "n_embd": 1280,
 
7
  "10": "SUCCESS",
8
  "100": "NON_PARTICIPATING",
9
  "101": "SUCCESS",
10
+ "102": "FAIL",
11
  "103": "NON_PARTICIPATING",
12
  "104": "NON_PARTICIPATING",
13
  "105": "NON_PARTICIPATING",
14
  "106": "SUCCESS",
15
  "107": "SUCCESS",
16
  "108": "NON_PARTICIPATING",
17
+ "109": "NON_PARTICIPATING",
18
  "11": "NON_PARTICIPATING",
19
  "110": "SUCCESS",
20
+ "111": "SUCCESS",
21
  "112": "NON_PARTICIPATING",
22
+ "113": "SUCCESS",
23
  "114": "SUCCESS",
24
  "115": "NON_PARTICIPATING",
25
  "116": "NON_PARTICIPATING",
 
34
  "124": "NON_PARTICIPATING",
35
  "125": "NON_PARTICIPATING",
36
  "126": "NON_PARTICIPATING",
37
+ "127": "SUCCESS",
38
  "128": "NON_PARTICIPATING",
39
+ "129": "NON_PARTICIPATING",
40
  "13": "NON_PARTICIPATING",
41
  "130": "NON_PARTICIPATING",
42
  "131": "NON_PARTICIPATING",
43
+ "132": "SUCCESS",
44
  "133": "NON_PARTICIPATING",
45
  "134": "NON_PARTICIPATING",
46
  "135": "NON_PARTICIPATING",
 
54
  "142": "NON_PARTICIPATING",
55
  "143": "SUCCESS",
56
  "144": "NON_PARTICIPATING",
57
+ "145": "SUCCESS",
58
  "146": "NON_PARTICIPATING",
59
+ "147": "SUCCESS",
60
  "148": "SUCCESS",
61
  "149": "NON_PARTICIPATING",
62
  "15": "SUCCESS",
 
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
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": "SUCCESS",
74
+ "160": "NON_PARTICIPATING",
75
  "161": "NON_PARTICIPATING",
76
  "162": "NON_PARTICIPATING",
77
  "163": "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": "SUCCESS",
86
+ "171": "SUCCESS",
87
  "172": "NON_PARTICIPATING",
88
  "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
+ "175": "SUCCESS",
91
  "176": "NON_PARTICIPATING",
92
+ "177": "SUCCESS",
93
  "178": "NON_PARTICIPATING",
94
  "179": "NON_PARTICIPATING",
95
  "18": "SUCCESS",
 
97
  "181": "NON_PARTICIPATING",
98
  "182": "NON_PARTICIPATING",
99
  "183": "NON_PARTICIPATING",
100
+ "184": "NON_PARTICIPATING",
101
+ "185": "NON_PARTICIPATING",
102
  "186": "SUCCESS",
103
+ "187": "SUCCESS",
104
  "188": "NON_PARTICIPATING",
105
  "189": "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",
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
116
  "199": "NON_PARTICIPATING",
117
  "2": "SUCCESS",
118
  "20": "SUCCESS",
119
+ "200": "SUCCESS",
120
  "201": "NON_PARTICIPATING",
121
  "202": "NON_PARTICIPATING",
122
+ "203": "SUCCESS",
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",
 
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",
 
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": "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": "SUCCESS",
 
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",
176
  "252": "NON_PARTICIPATING",
177
  "253": "NON_PARTICIPATING",
 
179
  "255": "NON_PARTICIPATING",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
+ "28": "NON_PARTICIPATING",
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",
 
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
202
+ "46": "NON_PARTICIPATING",
203
  "47": "SUCCESS",
204
  "48": "NON_PARTICIPATING",
205
  "49": "SUCCESS",
 
212
  "55": "NON_PARTICIPATING",
213
  "56": "SUCCESS",
214
  "57": "SUCCESS",
215
+ "58": "NON_PARTICIPATING",
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": "SUCCESS",
224
  "66": "NON_PARTICIPATING",
 
234
  "75": "SUCCESS",
235
  "76": "NON_PARTICIPATING",
236
  "77": "NON_PARTICIPATING",
237
+ "78": "SUCCESS",
238
  "79": "NON_PARTICIPATING",
239
  "8": "SUCCESS",
240
+ "80": "SUCCESS",
241
  "81": "NON_PARTICIPATING",
242
  "82": "SUCCESS",
243
  "83": "NON_PARTICIPATING",
 
249
  "89": "SUCCESS",
250
  "9": "NON_PARTICIPATING",
251
  "90": "SUCCESS",
252
+ "91": "NON_PARTICIPATING",
253
+ "92": "FAIL",
254
  "93": "NON_PARTICIPATING",
255
  "94": "SUCCESS",
256
  "95": "SUCCESS",
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5531680,
272
+ 5531721,
273
+ 5531723,
274
+ 5531725,
275
+ 5531727
 
 
 
 
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": 5531651,
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:ba9871130c0e79ab0fa1c25989ea40fd90a454bca923e189e4dba633624c6f0b
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:048b9da0e5898c0cfce94d8666acc2e674e6b390ed47b2bffd536a33cd1d9d74
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7e208dcce4daf3f4d943d8b3eac167c009ec823f1d3c3a6725914755e72ab98
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7db6d25b10796e315ce334c07d90d0790680ac49b93d3c165fd65c8cd647bb5
3
  size 4040701744