ncaagcc commited on
Commit
53c3366
·
verified ·
1 Parent(s): 2c7a1a8

Run 4. Outer Step 27. Inner Step 0.

Browse files
Files changed (3) hide show
  1. config.json +58 -66
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,42 +1,42 @@
1
  {
2
- "_name_or_path": "ncaagcc/v9a",
3
  "activation_function": "gelu_new",
4
  "all_reduce_scores": {
5
  "0": "NON_PARTICIPATING",
6
  "1": "SUCCESS",
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",
26
  "117": "NON_PARTICIPATING",
27
- "118": "SUCCESS",
28
  "119": "NON_PARTICIPATING",
29
  "12": "SUCCESS",
30
  "120": "SUCCESS",
31
- "121": "SUCCESS",
32
- "122": "NON_PARTICIPATING",
33
  "123": "SUCCESS",
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",
@@ -52,7 +52,7 @@
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",
@@ -66,12 +66,12 @@
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",
@@ -98,15 +98,15 @@
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",
@@ -128,27 +128,27 @@
128
  "209": "NON_PARTICIPATING",
129
  "21": "SUCCESS",
130
  "210": "NON_PARTICIPATING",
131
- "211": "NON_PARTICIPATING",
132
  "212": "NON_PARTICIPATING",
133
  "213": "SUCCESS",
134
- "214": "SUCCESS",
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",
143
  "222": "NON_PARTICIPATING",
144
  "223": "SUCCESS",
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": "NON_PARTICIPATING",
@@ -159,7 +159,7 @@
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",
@@ -167,16 +167,16 @@
167
  "244": "SUCCESS",
168
  "245": "NON_PARTICIPATING",
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",
178
  "254": "NON_PARTICIPATING",
179
- "255": "NON_PARTICIPATING",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
  "28": "SUCCESS",
@@ -184,14 +184,14 @@
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",
194
- "39": "NON_PARTICIPATING",
195
  "4": "NON_PARTICIPATING",
196
  "40": "SUCCESS",
197
  "41": "SUCCESS",
@@ -199,63 +199,63 @@
199
  "43": "SUCCESS",
200
  "44": "SUCCESS",
201
  "45": "SUCCESS",
202
- "46": "SUCCESS",
203
  "47": "SUCCESS",
204
  "48": "NON_PARTICIPATING",
205
  "49": "SUCCESS",
206
  "5": "NON_PARTICIPATING",
207
  "50": "SUCCESS",
208
  "51": "SUCCESS",
209
- "52": "NON_PARTICIPATING",
210
  "53": "NON_PARTICIPATING",
211
  "54": "SUCCESS",
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",
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": "SUCCESS",
240
- "80": "NON_PARTICIPATING",
241
  "81": "NON_PARTICIPATING",
242
  "82": "SUCCESS",
243
- "83": "NON_PARTICIPATING",
244
  "84": "SUCCESS",
245
- "85": "NON_PARTICIPATING",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
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",
257
  "96": "SUCCESS",
258
- "97": "NON_PARTICIPATING",
259
  "98": "SUCCESS",
260
  "99": "SUCCESS"
261
  },
@@ -268,28 +268,20 @@
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
- 5535751,
272
- 5535754,
273
- 5535756,
274
- 5535758,
275
- 5535760,
276
- 5535762,
277
- 5535764,
278
- 5535766,
279
- 5535769,
280
- 5535771,
281
- 5535773,
282
- 5535775,
283
- 5535776
284
  ],
285
  "block_size": 1024,
286
  "bos_token_id": 50256,
287
  "embd_pdrop": 0.1,
288
  "eos_token_id": 50256,
289
  "initializer_range": 0.02,
290
- "inner_step": 44,
291
  "inner_steps": 0,
292
- "last_allreduce_block": 5529444,
293
  "layer_norm_epsilon": 1e-05,
294
  "model_type": "gpt_optimized",
295
  "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": "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": "SUCCESS",
20
+ "111": "SUCCESS",
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": "SUCCESS",
31
+ "121": "NON_PARTICIPATING",
32
+ "122": "SUCCESS",
33
  "123": "SUCCESS",
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": "NON_PARTICIPATING",
41
  "130": "NON_PARTICIPATING",
42
  "131": "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",
 
66
  "153": "NON_PARTICIPATING",
67
  "154": "SUCCESS",
68
  "155": "NON_PARTICIPATING",
69
+ "156": "NON_PARTICIPATING",
70
  "157": "NON_PARTICIPATING",
71
+ "158": "SUCCESS",
72
  "159": "SUCCESS",
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": "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": "SUCCESS",
93
  "178": "NON_PARTICIPATING",
94
  "179": "NON_PARTICIPATING",
95
  "18": "SUCCESS",
 
98
  "182": "NON_PARTICIPATING",
99
  "183": "NON_PARTICIPATING",
100
  "184": "SUCCESS",
101
+ "185": "NON_PARTICIPATING",
102
+ "186": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
111
  "194": "NON_PARTICIPATING",
112
  "195": "SUCCESS",
 
128
  "209": "NON_PARTICIPATING",
129
  "21": "SUCCESS",
130
  "210": "NON_PARTICIPATING",
131
+ "211": "SUCCESS",
132
  "212": "NON_PARTICIPATING",
133
  "213": "SUCCESS",
134
+ "214": "NON_PARTICIPATING",
135
  "215": "NON_PARTICIPATING",
136
  "216": "NON_PARTICIPATING",
137
  "217": "NON_PARTICIPATING",
138
  "218": "SUCCESS",
139
+ "219": "NON_PARTICIPATING",
140
  "22": "SUCCESS",
141
  "220": "NON_PARTICIPATING",
142
  "221": "NON_PARTICIPATING",
143
  "222": "NON_PARTICIPATING",
144
  "223": "SUCCESS",
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": "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",
 
167
  "244": "SUCCESS",
168
  "245": "NON_PARTICIPATING",
169
  "246": "NON_PARTICIPATING",
170
+ "247": "SUCCESS",
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",
178
  "254": "NON_PARTICIPATING",
179
+ "255": "SUCCESS",
180
  "26": "SUCCESS",
181
  "27": "SUCCESS",
182
  "28": "SUCCESS",
 
184
  "3": "SUCCESS",
185
  "30": "NON_PARTICIPATING",
186
  "31": "NON_PARTICIPATING",
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",
194
+ "39": "SUCCESS",
195
  "4": "NON_PARTICIPATING",
196
  "40": "SUCCESS",
197
  "41": "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": "NON_PARTICIPATING",
207
  "50": "SUCCESS",
208
  "51": "SUCCESS",
209
+ "52": "SUCCESS",
210
  "53": "NON_PARTICIPATING",
211
  "54": "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": "SUCCESS",
225
  "67": "SUCCESS",
226
  "68": "NON_PARTICIPATING",
227
  "69": "NON_PARTICIPATING",
228
  "7": "SUCCESS",
229
  "70": "NON_PARTICIPATING",
230
  "71": "NON_PARTICIPATING",
231
+ "72": "SUCCESS",
232
  "73": "NON_PARTICIPATING",
233
  "74": "SUCCESS",
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": "SUCCESS",
244
  "84": "SUCCESS",
245
+ "85": "SUCCESS",
246
  "86": "NON_PARTICIPATING",
247
  "87": "SUCCESS",
248
  "88": "SUCCESS",
249
  "89": "SUCCESS",
250
  "9": "NON_PARTICIPATING",
251
  "90": "SUCCESS",
252
+ "91": "NON_PARTICIPATING",
253
+ "92": "SUCCESS",
254
  "93": "NON_PARTICIPATING",
255
  "94": "SUCCESS",
256
  "95": "SUCCESS",
257
  "96": "SUCCESS",
258
+ "97": "SUCCESS",
259
  "98": "SUCCESS",
260
  "99": "SUCCESS"
261
  },
 
268
  "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
269
  },
270
  "block_list": [
271
+ 5535861,
272
+ 5535919,
273
+ 5535921,
274
+ 5535923,
275
+ 5535926
 
 
 
 
 
 
 
 
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": 5535854,
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 sha256:29cc8bab9d220080cb596ec6e7f60b8eb10eb068be34bcb83f433d4b7243f79f
3
  size 8081782026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af981582bb8b7b2b54cfae3e8f9553f9b971a624a05c8684055777676feed48
3
  size 8081782026
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75f24fdb55c3164cff3c20f9c91bc677d431ad2902006d450a48fb4663cee9c8
3
  size 4040701744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15ee1ba3604bb1a80c135b5243c5c30d6a5b7279d94b02f4b20ae01f3954858d
3
  size 4040701744