penguin102 commited on
Commit
cfa1ac5
·
verified ·
1 Parent(s): f1734dd

Run 5. Outer Step 110. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +63 -63
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "_name_or_path": "penguin102/c67-h13",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NON_PARTICIPATING",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
@@ -14,18 +14,18 @@
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
- "11": "NON_PARTICIPATING",
18
- "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
- "116": "NOT_ALIVE",
25
- "117": "SUCCESS",
26
  "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
- "12": "NON_PARTICIPATING",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
@@ -37,12 +37,12 @@
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
- "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
- "132": "SUCCESS",
43
- "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
- "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "SUCCESS",
@@ -59,24 +59,24 @@
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
- "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
- "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
- "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
- "159": "SUCCESS",
72
- "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NOT_ALIVE",
75
- "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
- "164": "SUCCESS",
78
  "165": "NON_PARTICIPATING",
79
- "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
  "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
@@ -105,12 +105,12 @@
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
- "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
113
- "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
@@ -119,20 +119,20 @@
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
- "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
- "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
- "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "SUCCESS",
135
- "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
@@ -142,7 +142,7 @@
142
  "222": "NOT_ALIVE",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
- "225": "NON_PARTICIPATING",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
@@ -151,85 +151,85 @@
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
- "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
- "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
- "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NOT_ALIVE",
164
- "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
- "244": "NON_PARTICIPATING",
167
- "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
- "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
- "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
- "27": "NON_PARTICIPATING",
181
  "28": "NOT_ALIVE",
182
- "29": "NOT_ALIVE",
183
  "3": "NON_PARTICIPATING",
184
- "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "SUCCESS",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
- "39": "SUCCESS",
194
- "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
- "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
- "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
- "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
- "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
- "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
- "56": "NOT_ALIVE",
213
- "57": "NOT_ALIVE",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
- "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
- "62": "NON_PARTICIPATING",
220
  "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
- "68": "SUCCESS",
226
  "69": "NOT_ALIVE",
227
- "7": "SUCCESS",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "SUCCESS",
232
- "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
@@ -238,7 +238,7 @@
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
- "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
@@ -247,7 +247,7 @@
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
@@ -255,7 +255,7 @@
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
258
- "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5968781,
268
- 5968785
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
- "inner_step": 280,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5961214,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
 
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
+ "11": "NOT_ALIVE",
18
+ "110": "SUCCESS",
19
  "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
+ "116": "NON_PARTICIPATING",
25
+ "117": "NON_PARTICIPATING",
26
  "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
+ "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
 
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
+ "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
+ "132": "NON_PARTICIPATING",
43
+ "133": "FAIL",
44
  "134": "NON_PARTICIPATING",
45
+ "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "SUCCESS",
 
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
+ "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "SUCCESS",
66
+ "154": "SUCCESS",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "NON_PARTICIPATING",
72
+ "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
+ "162": "NOT_ALIVE",
76
  "163": "NOT_ALIVE",
77
+ "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
+ "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
  "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
 
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
+ "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
113
+ "197": "FAIL",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
 
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
+ "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
+ "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
+ "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "SUCCESS",
135
+ "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
 
142
  "222": "NOT_ALIVE",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
+ "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
 
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
+ "237": "SUCCESS",
159
  "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NOT_ALIVE",
164
+ "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
+ "244": "NOT_ALIVE",
167
+ "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
+ "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "FAIL",
179
  "26": "NON_PARTICIPATING",
180
+ "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
+ "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
+ "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
+ "39": "NOT_ALIVE",
194
+ "4": "NON_PARTICIPATING",
195
+ "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
+ "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
+ "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "NON_PARTICIPATING",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
+ "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
+ "56": "FAIL",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
+ "6": "NON_PARTICIPATING",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
+ "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "NOT_ALIVE",
227
+ "7": "NON_PARTICIPATING",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "SUCCESS",
232
+ "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
 
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
+ "82": "NOT_ALIVE",
242
  "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
 
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
 
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
258
+ "98": "NON_PARTICIPATING",
259
  "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5968831,
268
+ 5968834
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
+ "inner_step": 1,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5968672,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e777fa69885fa18472f4f2911286cc4b192a6b22834294b9fbcecfbf7fdd83b
3
  size 8800564561
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf393a030aaffc8e61d3ac10e89715aa3093a26d8e4007a6aabbe1ca158a0692
3
  size 8800564561
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2a6e8a321c798132e0f4d1e715ecaf859855924136ee26a8d4fa0435e3c822b
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084aaaeee7035f506d95a83e216b46dc21c4cf9781ed50861d5b91c117eef9bc
3
  size 4400216536