ncaagcc commited on
Commit
9bedb05
·
verified ·
1 Parent(s): 2e8e585

Run 8. Outer Step 90. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +131 -131
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,261 +1,261 @@
1
  {
2
- "_name_or_path": "ncaagcc/naz4",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
- "100": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "SUCCESS",
11
  "104": "SUCCESS",
12
- "105": "SUCCESS",
13
- "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
- "109": "SUCCESS",
17
- "11": "NOT_ALIVE",
18
- "110": "NON_PARTICIPATING",
19
- "111": "FAIL",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
- "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
- "116": "SUCCESS",
25
  "117": "NOT_ALIVE",
26
- "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
- "120": "SUCCESS",
30
- "121": "NON_PARTICIPATING",
31
  "122": "SUCCESS",
32
  "123": "SUCCESS",
33
- "124": "NOT_ALIVE",
34
  "125": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
- "129": "FAIL",
39
  "13": "NOT_ALIVE",
40
- "130": "NON_PARTICIPATING",
41
- "131": "NON_PARTICIPATING",
42
- "132": "SUCCESS",
43
  "133": "SUCCESS",
44
  "134": "FAIL",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "FAIL",
48
- "138": "NOT_ALIVE",
49
- "139": "NOT_ALIVE",
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": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
- "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
- "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
- "154": "SUCCESS",
67
- "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
- "157": "FAIL",
70
- "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
- "16": "SUCCESS",
73
  "160": "SUCCESS",
74
- "161": "NOT_ALIVE",
75
- "162": "SUCCESS",
76
- "163": "NOT_ALIVE",
77
- "164": "SUCCESS",
78
  "165": "SUCCESS",
79
- "166": "SUCCESS",
80
- "167": "FAIL",
81
  "168": "SUCCESS",
82
- "169": "FAIL",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
- "171": "NOT_ALIVE",
86
  "172": "FAIL",
87
- "173": "SUCCESS",
88
- "174": "NON_PARTICIPATING",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
  "179": "SUCCESS",
94
- "18": "FAIL",
95
- "180": "NOT_ALIVE",
96
  "181": "SUCCESS",
97
- "182": "NON_PARTICIPATING",
98
- "183": "FAIL",
99
- "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
- "186": "FAIL",
102
  "187": "NON_PARTICIPATING",
103
- "188": "NOT_ALIVE",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "FAIL",
107
- "191": "FAIL",
108
- "192": "SUCCESS",
109
  "193": "SUCCESS",
110
  "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
112
- "196": "NOT_ALIVE",
113
- "197": "FAIL",
114
- "198": "FAIL",
115
- "199": "SUCCESS",
116
- "2": "SUCCESS",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "SUCCESS",
122
  "204": "SUCCESS",
123
- "205": "NOT_ALIVE",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
- "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
- "210": "NOT_ALIVE",
130
- "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
- "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "SUCCESS",
135
- "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
- "22": "FAIL",
140
- "220": "NOT_ALIVE",
141
- "221": "NOT_ALIVE",
142
- "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "NOT_ALIVE",
155
- "234": "SUCCESS",
156
- "235": "NOT_ALIVE",
157
- "236": "SUCCESS",
158
  "237": "NOT_ALIVE",
159
- "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
- "24": "SUCCESS",
162
- "240": "SUCCESS",
163
- "241": "FAIL",
164
  "242": "NON_PARTICIPATING",
165
- "243": "SUCCESS",
166
- "244": "FAIL",
167
- "245": "NOT_ALIVE",
168
  "246": "NOT_ALIVE",
169
- "247": "SUCCESS",
170
- "248": "NOT_ALIVE",
171
- "249": "SUCCESS",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
- "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
  "253": "SUCCESS",
177
  "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
- "26": "SUCCESS",
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
- "32": "SUCCESS",
187
  "33": "NON_PARTICIPATING",
188
- "34": "NOT_ALIVE",
189
- "35": "SUCCESS",
190
- "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
- "38": "SUCCESS",
193
- "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
  "40": "NON_PARTICIPATING",
196
- "41": "SUCCESS",
197
  "42": "FAIL",
198
- "43": "FAIL",
199
  "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
- "47": "FAIL",
203
- "48": "FAIL",
204
  "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "FAIL",
208
- "52": "SUCCESS",
209
  "53": "FAIL",
210
- "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
- "56": "NON_PARTICIPATING",
213
- "57": "SUCCESS",
214
- "58": "NOT_ALIVE",
215
- "59": "SUCCESS",
216
- "6": "SUCCESS",
217
- "60": "SUCCESS",
218
- "61": "SUCCESS",
219
- "62": "SUCCESS",
220
  "63": "NON_PARTICIPATING",
221
- "64": "NOT_ALIVE",
222
- "65": "NOT_ALIVE",
223
- "66": "SUCCESS",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
233
- "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
  "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
- "79": "NOT_ALIVE",
238
- "8": "SUCCESS",
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
- "82": "NON_PARTICIPATING",
242
- "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
  "85": "SUCCESS",
245
  "86": "NON_PARTICIPATING",
246
- "87": "FAIL",
247
  "88": "NOT_ALIVE",
248
- "89": "NOT_ALIVE",
249
- "9": "NOT_ALIVE",
250
- "90": "NOT_ALIVE",
251
  "91": "NON_PARTICIPATING",
252
  "92": "NON_PARTICIPATING",
253
- "93": "NOT_ALIVE",
254
  "94": "SUCCESS",
255
- "95": "NON_PARTICIPATING",
256
- "96": "FAIL",
257
- "97": "FAIL",
258
- "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,18 +264,18 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6409002,
268
- 6409018,
269
- 6409021
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": 194,
277
  "intermediate_size": 5632,
278
- "last_allreduce_block": 6406083,
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",
6
  "10": "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",
20
  "112": "NON_PARTICIPATING",
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",
126
+ "208": "SUCCESS",
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": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6409059,
268
+ 6409066,
269
+ 6409091
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:a3d3eb221097f4f5657d2225bd9016f2f5b7dd4823299dc47a1dc09760104332
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4782364f114e15e480f13d91d01198b538fd8d3d721b864673d10ad6bee2a12f
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b0f1bdb6199f0b3bba900311e40ca72d9abf9fc1f9ce9b8183ae29cf8b085ba
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76fbd120becc591f02da603e11c0dff00701b49ccf8aa315c3d735b222f4c674
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eda74b057aa6339fed6c6acc6d1e0b05c74f5c9eb3376abb6517efbfdfbc365a
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2a297c8dfea3a33d58ff583d0776a3c0e105b8fa49ec9f2faa3431471f362e
3
  size 4400216536