ncaagcc commited on
Commit
1040d0a
·
verified ·
1 Parent(s): d87b00c

Run 4. Outer Step 21. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +51 -60
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -14,23 +14,23 @@
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": "NON_PARTICIPATING",
23
  "114": "SUCCESS",
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": "SUCCESS",
32
- "122": "SUCCESS",
33
- "123": "SUCCESS",
34
  "124": "NON_PARTICIPATING",
35
  "125": "NON_PARTICIPATING",
36
  "126": "NON_PARTICIPATING",
@@ -43,7 +43,7 @@
43
  "132": "SUCCESS",
44
  "133": "NON_PARTICIPATING",
45
  "134": "NON_PARTICIPATING",
46
- "135": "SUCCESS",
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
  "138": "NON_PARTICIPATING",
@@ -56,38 +56,38 @@
56
  "144": "NON_PARTICIPATING",
57
  "145": "NON_PARTICIPATING",
58
  "146": "NON_PARTICIPATING",
59
- "147": "NON_PARTICIPATING",
60
- "148": "NON_PARTICIPATING",
61
  "149": "SUCCESS",
62
  "15": "SUCCESS",
63
- "150": "NON_PARTICIPATING",
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",
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": "SUCCESS",
86
  "171": "NON_PARTICIPATING",
87
  "172": "SUCCESS",
88
  "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
- "175": "SUCCESS",
91
  "176": "NON_PARTICIPATING",
92
  "177": "NON_PARTICIPATING",
93
  "178": "NON_PARTICIPATING",
@@ -100,16 +100,16 @@
100
  "184": "SUCCESS",
101
  "185": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
109
- "192": "NON_PARTICIPATING",
110
  "193": "SUCCESS",
111
  "194": "NON_PARTICIPATING",
112
- "195": "SUCCESS",
113
  "196": "NON_PARTICIPATING",
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
@@ -119,7 +119,7 @@
119
  "200": "SUCCESS",
120
  "201": "SUCCESS",
121
  "202": "NON_PARTICIPATING",
122
- "203": "SUCCESS",
123
  "204": "NON_PARTICIPATING",
124
  "205": "NON_PARTICIPATING",
125
  "206": "NON_PARTICIPATING",
@@ -127,30 +127,30 @@
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": "SUCCESS",
135
- "215": "SUCCESS",
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",
143
  "222": "NON_PARTICIPATING",
144
- "223": "SUCCESS",
145
  "224": "NON_PARTICIPATING",
146
- "225": "SUCCESS",
147
  "226": "SUCCESS",
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": "NON_PARTICIPATING",
155
  "233": "NON_PARTICIPATING",
156
  "234": "NON_PARTICIPATING",
@@ -180,8 +180,8 @@
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
  "28": "SUCCESS",
183
- "29": "SUCCESS",
184
- "3": "NON_PARTICIPATING",
185
  "30": "NON_PARTICIPATING",
186
  "31": "NON_PARTICIPATING",
187
  "32": "SUCCESS",
@@ -212,32 +212,32 @@
212
  "55": "SUCCESS",
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": "NON_PARTICIPATING",
224
  "66": "NON_PARTICIPATING",
225
  "67": "SUCCESS",
226
- "68": "SUCCESS",
227
  "69": "NON_PARTICIPATING",
228
  "7": "SUCCESS",
229
  "70": "NON_PARTICIPATING",
230
  "71": "NON_PARTICIPATING",
231
  "72": "NON_PARTICIPATING",
232
  "73": "NON_PARTICIPATING",
233
- "74": "NON_PARTICIPATING",
234
  "75": "SUCCESS",
235
  "76": "NON_PARTICIPATING",
236
  "77": "NON_PARTICIPATING",
237
  "78": "NON_PARTICIPATING",
238
  "79": "NON_PARTICIPATING",
239
- "8": "SUCCESS",
240
- "80": "SUCCESS",
241
  "81": "NON_PARTICIPATING",
242
  "82": "SUCCESS",
243
  "83": "NON_PARTICIPATING",
@@ -268,29 +268,20 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5525386,
272
- 5525388,
273
- 5525390,
274
- 5525391,
275
- 5525393,
276
- 5525394,
277
- 5525396,
278
- 5525397,
279
- 5525399,
280
- 5525400,
281
- 5525401,
282
- 5525403,
283
- 5525404,
284
- 5525407
285
  ],
286
  "block_size": 1024,
287
  "bos_token_id": 50256,
288
  "embd_pdrop": 0.1,
289
  "eos_token_id": 50256,
290
  "initializer_range": 0.02,
291
- "inner_step": 27,
292
  "inner_steps": 0,
293
- "last_allreduce_block": 5523943,
294
  "layer_norm_epsilon": 1e-05,
295
  "model_type": "gpt_optimized",
296
  "n_embd": 1280,
 
14
  "106": "SUCCESS",
15
  "107": "SUCCESS",
16
  "108": "NON_PARTICIPATING",
17
+ "109": "SUCCESS",
18
  "11": "NON_PARTICIPATING",
19
+ "110": "NON_PARTICIPATING",
20
+ "111": "NON_PARTICIPATING",
21
  "112": "NON_PARTICIPATING",
22
  "113": "NON_PARTICIPATING",
23
  "114": "SUCCESS",
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": "NON_PARTICIPATING",
33
+ "123": "NON_PARTICIPATING",
34
  "124": "NON_PARTICIPATING",
35
  "125": "NON_PARTICIPATING",
36
  "126": "NON_PARTICIPATING",
 
43
  "132": "SUCCESS",
44
  "133": "NON_PARTICIPATING",
45
  "134": "NON_PARTICIPATING",
46
+ "135": "NON_PARTICIPATING",
47
  "136": "NON_PARTICIPATING",
48
  "137": "NON_PARTICIPATING",
49
  "138": "NON_PARTICIPATING",
 
56
  "144": "NON_PARTICIPATING",
57
  "145": "NON_PARTICIPATING",
58
  "146": "NON_PARTICIPATING",
59
+ "147": "SUCCESS",
60
+ "148": "SUCCESS",
61
  "149": "SUCCESS",
62
  "15": "SUCCESS",
63
+ "150": "SUCCESS",
64
  "151": "NON_PARTICIPATING",
65
  "152": "NON_PARTICIPATING",
66
  "153": "NON_PARTICIPATING",
67
  "154": "SUCCESS",
68
+ "155": "SUCCESS",
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": "NON_PARTICIPATING",
77
  "163": "NON_PARTICIPATING",
78
  "164": "NON_PARTICIPATING",
79
  "165": "NON_PARTICIPATING",
80
  "166": "NON_PARTICIPATING",
81
+ "167": "NON_PARTICIPATING",
82
+ "168": "FAIL",
83
  "169": "NON_PARTICIPATING",
84
  "17": "SUCCESS",
85
+ "170": "NON_PARTICIPATING",
86
  "171": "NON_PARTICIPATING",
87
  "172": "SUCCESS",
88
  "173": "NON_PARTICIPATING",
89
  "174": "NON_PARTICIPATING",
90
+ "175": "NON_PARTICIPATING",
91
  "176": "NON_PARTICIPATING",
92
  "177": "NON_PARTICIPATING",
93
  "178": "NON_PARTICIPATING",
 
100
  "184": "SUCCESS",
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": "SUCCESS",
109
+ "192": "SUCCESS",
110
  "193": "SUCCESS",
111
  "194": "NON_PARTICIPATING",
112
+ "195": "NON_PARTICIPATING",
113
  "196": "NON_PARTICIPATING",
114
  "197": "NON_PARTICIPATING",
115
  "198": "NON_PARTICIPATING",
 
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",
 
127
  "208": "NON_PARTICIPATING",
128
  "209": "NON_PARTICIPATING",
129
  "21": "SUCCESS",
130
+ "210": "SUCCESS",
131
+ "211": "SUCCESS",
132
  "212": "NON_PARTICIPATING",
133
+ "213": "SUCCESS",
134
  "214": "SUCCESS",
135
+ "215": "NON_PARTICIPATING",
136
  "216": "NON_PARTICIPATING",
137
  "217": "NON_PARTICIPATING",
138
+ "218": "NON_PARTICIPATING",
139
  "219": "SUCCESS",
140
  "22": "SUCCESS",
141
  "220": "NON_PARTICIPATING",
142
+ "221": "SUCCESS",
143
  "222": "NON_PARTICIPATING",
144
+ "223": "NON_PARTICIPATING",
145
  "224": "NON_PARTICIPATING",
146
+ "225": "NON_PARTICIPATING",
147
  "226": "SUCCESS",
148
  "227": "NON_PARTICIPATING",
149
  "228": "NON_PARTICIPATING",
150
  "229": "NON_PARTICIPATING",
151
  "23": "SUCCESS",
152
+ "230": "SUCCESS",
153
+ "231": "SUCCESS",
154
  "232": "NON_PARTICIPATING",
155
  "233": "NON_PARTICIPATING",
156
  "234": "NON_PARTICIPATING",
 
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
  "28": "SUCCESS",
183
+ "29": "NON_PARTICIPATING",
184
+ "3": "SUCCESS",
185
  "30": "NON_PARTICIPATING",
186
  "31": "NON_PARTICIPATING",
187
  "32": "SUCCESS",
 
212
  "55": "SUCCESS",
213
  "56": "SUCCESS",
214
  "57": "SUCCESS",
215
+ "58": "SUCCESS",
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": "SUCCESS",
224
  "66": "NON_PARTICIPATING",
225
  "67": "SUCCESS",
226
+ "68": "NON_PARTICIPATING",
227
  "69": "NON_PARTICIPATING",
228
  "7": "SUCCESS",
229
  "70": "NON_PARTICIPATING",
230
  "71": "NON_PARTICIPATING",
231
  "72": "NON_PARTICIPATING",
232
  "73": "NON_PARTICIPATING",
233
+ "74": "SUCCESS",
234
  "75": "SUCCESS",
235
  "76": "NON_PARTICIPATING",
236
  "77": "NON_PARTICIPATING",
237
  "78": "NON_PARTICIPATING",
238
  "79": "NON_PARTICIPATING",
239
+ "8": "FAIL",
240
+ "80": "NON_PARTICIPATING",
241
  "81": "NON_PARTICIPATING",
242
  "82": "SUCCESS",
243
  "83": "NON_PARTICIPATING",
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5525456,
272
+ 5525457,
273
+ 5525459,
274
+ 5525461,
275
+ 5525462
 
 
 
 
 
 
 
 
 
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": 5525369,
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 sha256:9f93899c987ab034866b43232b47e14a0456993aa5fa8545bb9c906e8b7772e9
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67bd6e0db6c2a34afd9b8e88815d323e13dfc2e83d5e0a37bc6ec62cb348935d
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f46c0ebbcdf5c7174dc68e482bbad3eaece4cd63a5d6804d5efd6bef26aa41f
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c125bbbaa5b77926501f473aefab3d7712828ca96f0a164f72c97ca09e8f6d
3
  size 4040701744