ncaagcc commited on
Commit
f512e6c
·
verified ·
1 Parent(s): b179aff

Run 8. Outer Step 90. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +120 -120
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "ncaagcc/az2",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
@@ -7,13 +7,13 @@
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
- "103": "FAIL",
11
- "104": "FAIL",
12
- "105": "SUCCESS",
13
- "106": "FAIL",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
- "109": "FAIL",
17
  "11": "SUCCESS",
18
  "110": "SUCCESS",
19
  "111": "NOT_ALIVE",
@@ -21,105 +21,105 @@
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
- "116": "SUCCESS",
25
  "117": "NOT_ALIVE",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "FAIL",
30
- "121": "NON_PARTICIPATING",
31
  "122": "SUCCESS",
32
  "123": "SUCCESS",
33
  "124": "SUCCESS",
34
- "125": "FAIL",
35
- "126": "FAIL",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
- "129": "FAIL",
39
  "13": "NOT_ALIVE",
40
- "130": "FAIL",
41
- "131": "NON_PARTICIPATING",
42
- "132": "FAIL",
43
- "133": "NOT_ALIVE",
44
  "134": "FAIL",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
- "137": "NOT_ALIVE",
48
  "138": "SUCCESS",
49
- "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
- "140": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
53
  "142": "SUCCESS",
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
- "145": "FAIL",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
- "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
- "152": "SUCCESS",
65
- "153": "FAIL",
66
- "154": "SUCCESS",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
- "157": "NON_PARTICIPATING",
70
- "158": "NOT_ALIVE",
71
- "159": "FAIL",
72
- "16": "SUCCESS",
73
- "160": "NON_PARTICIPATING",
74
  "161": "SUCCESS",
75
- "162": "SUCCESS",
76
- "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
- "166": "FAIL",
80
  "167": "NON_PARTICIPATING",
81
- "168": "FAIL",
82
  "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
- "171": "NOT_ALIVE",
86
  "172": "FAIL",
87
- "173": "FAIL",
88
  "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
- "179": "FAIL",
94
  "18": "SUCCESS",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
- "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
- "184": "SUCCESS",
100
- "185": "NOT_ALIVE",
101
- "186": "FAIL",
102
  "187": "NON_PARTICIPATING",
103
- "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "FAIL",
107
  "191": "SUCCESS",
108
- "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
110
  "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
112
- "196": "NON_PARTICIPATING",
113
  "197": "NON_PARTICIPATING",
114
- "198": "FAIL",
115
- "199": "NON_PARTICIPATING",
116
- "2": "SUCCESS",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "FAIL",
122
- "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
@@ -127,136 +127,136 @@
127
  "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "SUCCESS",
130
- "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "SUCCESS",
135
- "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "SUCCESS",
138
- "219": "SUCCESS",
139
  "22": "SUCCESS",
140
- "220": "NOT_ALIVE",
141
  "221": "NON_PARTICIPATING",
142
- "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
- "224": "NOT_ALIVE",
145
  "225": "SUCCESS",
146
- "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
- "228": "NON_PARTICIPATING",
149
- "229": "SUCCESS",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
- "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
- "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
- "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
- "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
- "24": "SUCCESS",
162
- "240": "FAIL",
163
- "241": "NON_PARTICIPATING",
164
- "242": "SUCCESS",
165
- "243": "SUCCESS",
166
- "244": "SUCCESS",
167
- "245": "SUCCESS",
168
- "246": "SUCCESS",
169
- "247": "SUCCESS",
170
- "248": "NOT_ALIVE",
171
- "249": "FAIL",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
- "251": "NON_PARTICIPATING",
175
- "252": "SUCCESS",
176
- "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
- "26": "SUCCESS",
180
- "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
- "31": "FAIL",
186
- "32": "SUCCESS",
187
  "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
  "35": "FAIL",
190
- "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
- "38": "FAIL",
193
- "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
- "40": "NOT_ALIVE",
196
  "41": "FAIL",
197
- "42": "NON_PARTICIPATING",
198
- "43": "FAIL",
199
- "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
- "47": "FAIL",
203
  "48": "SUCCESS",
204
- "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
- "51": "SUCCESS",
208
  "52": "FAIL",
209
- "53": "SUCCESS",
210
- "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
- "56": "NON_PARTICIPATING",
213
- "57": "FAIL",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "SUCCESS",
218
- "61": "SUCCESS",
219
- "62": "SUCCESS",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
- "69": "NOT_ALIVE",
227
- "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
- "74": "NOT_ALIVE",
233
- "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
  "77": "SUCCESS",
236
- "78": "SUCCESS",
237
- "79": "NOT_ALIVE",
238
- "8": "SUCCESS",
239
  "80": "NOT_ALIVE",
240
- "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "SUCCESS",
244
  "85": "SUCCESS",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
- "89": "SUCCESS",
249
  "9": "SUCCESS",
250
  "90": "NON_PARTICIPATING",
251
- "91": "NOT_ALIVE",
252
- "92": "NOT_ALIVE",
253
- "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
  "95": "FAIL",
256
- "96": "SUCCESS",
257
- "97": "SUCCESS",
258
- "98": "NON_PARTICIPATING",
259
- "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,18 +264,18 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6408567,
268
- 6408580,
269
- 6408596
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": 120,
277
  "intermediate_size": 5632,
278
- "last_allreduce_block": 6406775,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
 
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
+ "103": "SUCCESS",
11
+ "104": "SUCCESS",
12
+ "105": "NOT_ALIVE",
13
+ "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
+ "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
  "110": "SUCCESS",
19
  "111": "NOT_ALIVE",
 
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
+ "116": "FAIL",
25
  "117": "NOT_ALIVE",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "FAIL",
30
+ "121": "NOT_ALIVE",
31
  "122": "SUCCESS",
32
  "123": "SUCCESS",
33
  "124": "SUCCESS",
34
+ "125": "SUCCESS",
35
+ "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
+ "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
+ "130": "SUCCESS",
41
+ "131": "NOT_ALIVE",
42
+ "132": "NOT_ALIVE",
43
+ "133": "SUCCESS",
44
  "134": "FAIL",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
+ "137": "FAIL",
48
  "138": "SUCCESS",
49
+ "139": "FAIL",
50
  "14": "NOT_ALIVE",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
  "142": "SUCCESS",
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
+ "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "FAIL",
65
+ "153": "SUCCESS",
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": "SUCCESS",
74
  "161": "SUCCESS",
75
+ "162": "FAIL",
76
+ "163": "FAIL",
77
  "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
+ "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "SUCCESS",
82
  "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
+ "171": "FAIL",
86
  "172": "FAIL",
87
+ "173": "NON_PARTICIPATING",
88
  "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
+ "179": "SUCCESS",
94
  "18": "SUCCESS",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
+ "182": "NOT_ALIVE",
98
  "183": "SUCCESS",
99
+ "184": "FAIL",
100
+ "185": "FAIL",
101
+ "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
+ "188": "FAIL",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
+ "190": "NON_PARTICIPATING",
107
  "191": "SUCCESS",
108
+ "192": "NON_PARTICIPATING",
109
  "193": "SUCCESS",
110
  "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
112
+ "196": "FAIL",
113
  "197": "NON_PARTICIPATING",
114
+ "198": "NON_PARTICIPATING",
115
+ "199": "FAIL",
116
+ "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "NOT_ALIVE",
122
+ "204": "SUCCESS",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
 
127
  "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "SUCCESS",
130
+ "211": "SUCCESS",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "SUCCESS",
135
+ "216": "FAIL",
136
  "217": "SUCCESS",
137
+ "218": "FAIL",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
+ "220": "FAIL",
141
  "221": "NON_PARTICIPATING",
142
+ "222": "SUCCESS",
143
  "223": "NON_PARTICIPATING",
144
+ "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
+ "226": "FAIL",
147
  "227": "NON_PARTICIPATING",
148
+ "228": "NOT_ALIVE",
149
+ "229": "FAIL",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
+ "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "NOT_ALIVE",
156
  "235": "NON_PARTICIPATING",
157
+ "236": "NON_PARTICIPATING",
158
  "237": "NOT_ALIVE",
159
+ "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
+ "24": "FAIL",
162
+ "240": "NON_PARTICIPATING",
163
+ "241": "SUCCESS",
164
+ "242": "NON_PARTICIPATING",
165
+ "243": "FAIL",
166
+ "244": "NOT_ALIVE",
167
+ "245": "NON_PARTICIPATING",
168
+ "246": "NOT_ALIVE",
169
+ "247": "NON_PARTICIPATING",
170
+ "248": "SUCCESS",
171
+ "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
+ "251": "SUCCESS",
175
+ "252": "NON_PARTICIPATING",
176
+ "253": "SUCCESS",
177
  "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
+ "26": "FAIL",
180
+ "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
+ "31": "SUCCESS",
186
+ "32": "FAIL",
187
  "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
  "35": "FAIL",
190
+ "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
+ "39": "FAIL",
194
  "4": "SUCCESS",
195
+ "40": "NON_PARTICIPATING",
196
  "41": "FAIL",
197
+ "42": "FAIL",
198
+ "43": "SUCCESS",
199
+ "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
+ "47": "SUCCESS",
203
  "48": "SUCCESS",
204
+ "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
+ "51": "FAIL",
208
  "52": "FAIL",
209
+ "53": "FAIL",
210
+ "54": "SUCCESS",
211
  "55": "NOT_ALIVE",
212
+ "56": "SUCCESS",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "NOT_ALIVE",
219
+ "62": "FAIL",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
+ "69": "FAIL",
227
+ "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "SUCCESS",
233
+ "75": "SUCCESS",
234
  "76": "SUCCESS",
235
  "77": "SUCCESS",
236
+ "78": "NON_PARTICIPATING",
237
+ "79": "NON_PARTICIPATING",
238
+ "8": "FAIL",
239
  "80": "NOT_ALIVE",
240
+ "81": "NON_PARTICIPATING",
241
+ "82": "NOT_ALIVE",
242
  "83": "NON_PARTICIPATING",
243
  "84": "SUCCESS",
244
  "85": "SUCCESS",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
+ "89": "FAIL",
249
  "9": "SUCCESS",
250
  "90": "NON_PARTICIPATING",
251
+ "91": "NON_PARTICIPATING",
252
+ "92": "NON_PARTICIPATING",
253
+ "93": "SUCCESS",
254
  "94": "SUCCESS",
255
  "95": "FAIL",
256
+ "96": "NON_PARTICIPATING",
257
+ "97": "NOT_ALIVE",
258
+ "98": "NOT_ALIVE",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6409059,
268
+ 6409075,
269
+ 6409089
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": 4,
277
  "intermediate_size": 5632,
278
+ "last_allreduce_block": 6409002,
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 sha256:8e2a1cb719009fb4a564d4d07359fbae9e6664c76a22c3e6f948c76fb4c7872b
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb397b5487cb49034cf41b7f186a09da39164d47ffc05e8718ad5b9cace5dfd0
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f153e76547c20de4ae34399619d55b959fc03442d97f40291e2a432c8fa7a3cb
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5639f029925931425700b1e418179aef653b9a26f8f8c068f60e13a0f4af2fa
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9be3106c356b0dc0c19bbbf8a0f0c7bb0af6ea80fd7b8ad5d08dafb5ceeabfb
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b78c6fea90e9f08a332e7b1e69ee2db43a2b57fd17ce5ef24a61b86cdfeaa7
3
  size 4400216536