ncaagcc commited on
Commit
73f1dc3
·
verified ·
1 Parent(s): 9f0cc0b

Run 8. Outer Step 68. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +97 -96
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,22 +1,22 @@
1
  {
2
- "_name_or_path": "ncaagcc/naz1",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
- "100": "NON_PARTICIPATING",
8
  "101": "SUCCESS",
9
- "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
- "106": "SUCCESS",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
- "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
@@ -27,26 +27,26 @@
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
- "121": "SUCCESS",
31
- "122": "SUCCESS",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
- "126": "FAIL",
36
- "127": "SUCCESS",
37
  "128": "SUCCESS",
38
  "129": "SUCCESS",
39
  "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
- "132": "NON_PARTICIPATING",
43
  "133": "SUCCESS",
44
- "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
47
- "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
- "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
@@ -54,208 +54,208 @@
54
  "143": "SUCCESS",
55
  "144": "SUCCESS",
56
  "145": "NON_PARTICIPATING",
57
- "146": "NON_PARTICIPATING",
58
- "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
  "149": "SUCCESS",
61
- "15": "FAIL",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
- "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
- "157": "NOT_ALIVE",
70
  "158": "FAIL",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
- "162": "SUCCESS",
76
  "163": "NON_PARTICIPATING",
77
- "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "SUCCESS",
81
- "168": "SUCCESS",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
- "171": "SUCCESS",
86
- "172": "SUCCESS",
87
  "173": "NOT_ALIVE",
88
  "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "FAIL",
92
  "178": "SUCCESS",
93
  "179": "SUCCESS",
94
- "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
- "182": "SUCCESS",
98
  "183": "SUCCESS",
99
  "184": "SUCCESS",
100
- "185": "NOT_ALIVE",
101
- "186": "NOT_ALIVE",
102
- "187": "NON_PARTICIPATING",
103
- "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
- "191": "NOT_ALIVE",
108
  "192": "SUCCESS",
109
- "193": "NON_PARTICIPATING",
110
- "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
- "196": "NON_PARTICIPATING",
113
- "197": "NON_PARTICIPATING",
114
  "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
- "202": "NON_PARTICIPATING",
121
- "203": "SUCCESS",
122
- "204": "NON_PARTICIPATING",
123
- "205": "NON_PARTICIPATING",
124
  "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
- "208": "NON_PARTICIPATING",
127
  "209": "SUCCESS",
128
  "21": "SUCCESS",
129
  "210": "SUCCESS",
130
- "211": "NOT_ALIVE",
131
  "212": "SUCCESS",
132
  "213": "SUCCESS",
133
- "214": "FAIL",
134
- "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "FAIL",
138
- "219": "SUCCESS",
139
  "22": "SUCCESS",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
142
- "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
  "226": "NON_PARTICIPATING",
147
- "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
- "230": "FAIL",
152
  "231": "NON_PARTICIPATING",
153
- "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
  "234": "SUCCESS",
156
- "235": "SUCCESS",
157
  "236": "SUCCESS",
158
- "237": "FAIL",
159
- "238": "SUCCESS",
160
  "239": "SUCCESS",
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
- "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
- "246": "FAIL",
169
  "247": "NON_PARTICIPATING",
170
- "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
- "253": "FAIL",
177
  "254": "NOT_ALIVE",
178
- "255": "NON_PARTICIPATING",
179
- "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
- "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
- "3": "SUCCESS",
184
- "30": "FAIL",
185
- "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
  "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
- "37": "SUCCESS",
192
  "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
- "41": "SUCCESS",
197
  "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
  "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
- "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
- "5": "FAIL",
206
  "50": "FAIL",
207
- "51": "NOT_ALIVE",
208
- "52": "FAIL",
209
- "53": "FAIL",
210
  "54": "NON_PARTICIPATING",
211
- "55": "SUCCESS",
212
  "56": "NON_PARTICIPATING",
213
- "57": "NON_PARTICIPATING",
214
  "58": "SUCCESS",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
- "61": "SUCCESS",
219
  "62": "SUCCESS",
220
- "63": "NON_PARTICIPATING",
221
- "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NON_PARTICIPATING",
225
  "68": "SUCCESS",
226
- "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
- "71": "NON_PARTICIPATING",
230
  "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
  "76": "SUCCESS",
235
- "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
- "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
- "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "SUCCESS",
242
- "83": "SUCCESS",
243
  "84": "SUCCESS",
244
- "85": "NON_PARTICIPATING",
245
- "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
- "88": "NOT_ALIVE",
248
- "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
- "90": "SUCCESS",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
- "94": "NON_PARTICIPATING",
255
- "95": "FAIL",
256
  "96": "SUCCESS",
257
- "97": "SUCCESS",
258
- "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,17 +264,18 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6391946,
268
- 6391957
 
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": 87,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6391321,
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": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
+ "100": "NOT_ALIVE",
8
  "101": "SUCCESS",
9
+ "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "FAIL",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
  "109": "SUCCESS",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
 
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
+ "121": "NON_PARTICIPATING",
31
+ "122": "FAIL",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
+ "126": "NON_PARTICIPATING",
36
+ "127": "NOT_ALIVE",
37
  "128": "SUCCESS",
38
  "129": "SUCCESS",
39
  "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "SUCCESS",
43
  "133": "SUCCESS",
44
+ "134": "SUCCESS",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
47
+ "137": "SUCCESS",
48
  "138": "NOT_ALIVE",
49
+ "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
 
54
  "143": "SUCCESS",
55
  "144": "SUCCESS",
56
  "145": "NON_PARTICIPATING",
57
+ "146": "NOT_ALIVE",
58
+ "147": "FAIL",
59
  "148": "NON_PARTICIPATING",
60
  "149": "SUCCESS",
61
+ "15": "NOT_ALIVE",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
+ "157": "NON_PARTICIPATING",
70
  "158": "FAIL",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "SUCCESS",
75
+ "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
+ "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "SUCCESS",
81
+ "168": "FAIL",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
+ "171": "NON_PARTICIPATING",
86
+ "172": "NON_PARTICIPATING",
87
  "173": "NOT_ALIVE",
88
  "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
+ "177": "NON_PARTICIPATING",
92
  "178": "SUCCESS",
93
  "179": "SUCCESS",
94
+ "18": "SUCCESS",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
+ "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
  "184": "SUCCESS",
100
+ "185": "SUCCESS",
101
+ "186": "FAIL",
102
+ "187": "NOT_ALIVE",
103
+ "188": "FAIL",
104
  "189": "SUCCESS",
105
  "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "SUCCESS",
108
  "192": "SUCCESS",
109
+ "193": "SUCCESS",
110
+ "194": "NOT_ALIVE",
111
  "195": "SUCCESS",
112
+ "196": "NOT_ALIVE",
113
+ "197": "NOT_ALIVE",
114
  "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
+ "202": "FAIL",
121
+ "203": "FAIL",
122
+ "204": "FAIL",
123
+ "205": "FAIL",
124
  "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
+ "208": "SUCCESS",
127
  "209": "SUCCESS",
128
  "21": "SUCCESS",
129
  "210": "SUCCESS",
130
+ "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "SUCCESS",
133
+ "214": "SUCCESS",
134
+ "215": "FAIL",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "SUCCESS",
138
+ "219": "FAIL",
139
  "22": "SUCCESS",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
142
+ "222": "FAIL",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
  "226": "NON_PARTICIPATING",
147
+ "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
+ "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
+ "232": "SUCCESS",
154
  "233": "SUCCESS",
155
  "234": "SUCCESS",
156
+ "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
+ "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "SUCCESS",
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
+ "244": "FAIL",
167
  "245": "SUCCESS",
168
+ "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
+ "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
+ "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
+ "255": "NOT_ALIVE",
179
+ "26": "SUCCESS",
180
  "27": "SUCCESS",
181
+ "28": "SUCCESS",
182
  "29": "SUCCESS",
183
+ "3": "FAIL",
184
+ "30": "SUCCESS",
185
+ "31": "NOT_ALIVE",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
  "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
+ "37": "FAIL",
192
  "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
+ "40": "NOT_ALIVE",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
  "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "SUCCESS",
206
  "50": "FAIL",
207
+ "51": "NON_PARTICIPATING",
208
+ "52": "SUCCESS",
209
+ "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
+ "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
+ "61": "NOT_ALIVE",
219
  "62": "SUCCESS",
220
+ "63": "FAIL",
221
+ "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NOT_ALIVE",
225
  "68": "SUCCESS",
226
+ "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
+ "71": "NOT_ALIVE",
230
  "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
  "76": "SUCCESS",
235
+ "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
+ "79": "FAIL",
238
  "8": "NOT_ALIVE",
239
+ "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "SUCCESS",
242
+ "83": "NON_PARTICIPATING",
243
  "84": "SUCCESS",
244
+ "85": "SUCCESS",
245
+ "86": "NOT_ALIVE",
246
  "87": "SUCCESS",
247
+ "88": "NON_PARTICIPATING",
248
+ "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "FAIL",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
+ "94": "NOT_ALIVE",
255
+ "95": "SUCCESS",
256
  "96": "SUCCESS",
257
+ "97": "NON_PARTICIPATING",
258
+ "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6392017,
268
+ 6392021,
269
+ 6392032
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
+ "inner_step": 5,
277
  "intermediate_size": 5632,
278
+ "last_allreduce_block": 6391958,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a79383e8cabc3052a5537e777da94154fe63d710fd2c6a621641452f78dc1822
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:819069c9b9e6bbf0135ee28af1d6a6a819f9c1b9af7aef60cd20d1f4ef03f4eb
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00a9289ac3a20534c94fde4a49fec249521f7976b8f1549443235a03c8d44e95
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a32caefa5800ba7853a465e09cd993bafbbdc44604a2374d352745a5d5fe284a
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:680e584cb629319c22806f31b9cfc2df81bbd3d3ede659b04acda033d6bf8ac9
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6da700a8aacdefdccde97eb6364ffde478de35feab70971f96eff74fe944ba
3
  size 4400216536