kmfoda commited on
Commit
d24963a
·
verified ·
1 Parent(s): 1e903d9

Run 10. Outer Step 103. Inner Step 0. Peers 13.

Browse files
Files changed (4) hide show
  1. config.json +118 -118
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -5,50 +5,50 @@
5
  "1": "NON_PARTICIPATING",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "SUCCESS",
9
- "102": "SUCCESS",
10
- "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "SUCCESS",
13
- "106": "SUCCESS",
14
- "107": "SUCCESS",
15
- "108": "NON_PARTICIPATING",
16
- "109": "SUCCESS",
17
- "11": "SUCCESS",
18
  "110": "NOT_ALIVE",
19
- "111": "SUCCESS",
20
- "112": "SUCCESS",
21
- "113": "SUCCESS",
22
- "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
- "118": "SUCCESS",
27
- "119": "SUCCESS",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
- "121": "SUCCESS",
31
- "122": "NON_PARTICIPATING",
32
- "123": "SUCCESS",
33
- "124": "SUCCESS",
34
- "125": "NON_PARTICIPATING",
35
- "126": "SUCCESS",
36
- "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
- "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
- "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
- "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
@@ -62,31 +62,31 @@
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "SUCCESS",
66
  "154": "NON_PARTICIPATING",
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NON_PARTICIPATING",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
- "163": "SUCCESS",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
- "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
- "168": "NON_PARTICIPATING",
82
- "169": "NOT_ALIVE",
83
- "17": "NON_PARTICIPATING",
84
  "170": "NOT_ALIVE",
85
- "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
- "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
@@ -96,62 +96,62 @@
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
- "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
- "186": "SUCCESS",
102
- "187": "NOT_ALIVE",
103
- "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
- "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
- "196": "NON_PARTICIPATING",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
- "20": "SUCCESS",
118
- "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "SUCCESS",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
- "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
- "211": "NON_PARTICIPATING",
131
- "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
- "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
- "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
- "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
- "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "SUCCESS",
147
- "227": "NON_PARTICIPATING",
148
- "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
- "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
- "231": "NON_PARTICIPATING",
153
- "232": "SUCCESS",
154
- "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
@@ -164,99 +164,99 @@
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "NON_PARTICIPATING",
168
- "246": "SUCCESS",
169
  "247": "NOT_ALIVE",
170
- "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
- "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
- "255": "SUCCESS",
179
- "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
- "28": "SUCCESS",
182
- "29": "NON_PARTICIPATING",
183
- "3": "NOT_ALIVE",
184
- "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "NON_PARTICIPATING",
190
- "36": "SUCCESS",
191
- "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
- "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
- "44": "SUCCESS",
200
- "45": "SUCCESS",
201
- "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
- "50": "NON_PARTICIPATING",
207
  "51": "NOT_ALIVE",
208
- "52": "SUCCESS",
209
- "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
- "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NON_PARTICIPATING",
217
- "60": "SUCCESS",
218
- "61": "SUCCESS",
219
- "62": "NON_PARTICIPATING",
220
- "63": "SUCCESS",
221
- "64": "SUCCESS",
222
- "65": "SUCCESS",
223
- "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
- "7": "NOT_ALIVE",
228
- "70": "NOT_ALIVE",
229
- "71": "SUCCESS",
230
- "72": "SUCCESS",
231
  "73": "NOT_ALIVE",
232
- "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
- "79": "NON_PARTICIPATING",
238
- "8": "SUCCESS",
239
- "80": "SUCCESS",
240
  "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
- "84": "SUCCESS",
244
- "85": "NOT_ALIVE",
245
- "86": "SUCCESS",
246
- "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
- "89": "SUCCESS",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
- "91": "SUCCESS",
252
- "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
- "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
- "96": "SUCCESS",
257
- "97": "NOT_ALIVE",
258
- "98": "SUCCESS",
259
- "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6522031,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
5
  "1": "NON_PARTICIPATING",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
+ "101": "FAIL",
9
+ "102": "FAIL",
10
+ "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
+ "106": "NOT_ALIVE",
14
+ "107": "NOT_ALIVE",
15
+ "108": "SUCCESS",
16
+ "109": "FAIL",
17
+ "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
+ "111": "FAIL",
20
+ "112": "NOT_ALIVE",
21
+ "113": "FAIL",
22
+ "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "SUCCESS",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "FAIL",
27
+ "119": "FAIL",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
+ "121": "NOT_ALIVE",
31
+ "122": "SUCCESS",
32
+ "123": "NOT_ALIVE",
33
+ "124": "FAIL",
34
+ "125": "NOT_ALIVE",
35
+ "126": "FAIL",
36
+ "127": "SUCCESS",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
+ "13": "FAIL",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
+ "136": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
+ "140": "FAIL",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
 
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
  "154": "NON_PARTICIPATING",
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NOT_ALIVE",
71
+ "159": "FAIL",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
+ "161": "FAIL",
75
  "162": "NOT_ALIVE",
76
+ "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "FAIL",
80
  "167": "NOT_ALIVE",
81
+ "168": "NOT_ALIVE",
82
+ "169": "NON_PARTICIPATING",
83
+ "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
+ "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
+ "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
 
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
+ "184": "NOT_ALIVE",
100
+ "185": "NOT_ALIVE",
101
+ "186": "NOT_ALIVE",
102
+ "187": "NON_PARTICIPATING",
103
+ "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
+ "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
+ "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
+ "20": "NOT_ALIVE",
118
+ "200": "FAIL",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
+ "205": "FAIL",
124
+ "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
+ "21": "FAIL",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "SUCCESS",
131
+ "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
+ "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
+ "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
+ "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "FAIL",
147
+ "227": "NOT_ALIVE",
148
+ "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
+ "23": "FAIL",
151
  "230": "NON_PARTICIPATING",
152
+ "231": "FAIL",
153
+ "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
 
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NOT_ALIVE",
168
+ "246": "FAIL",
169
  "247": "NOT_ALIVE",
170
+ "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
+ "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "NOT_ALIVE",
179
+ "26": "FAIL",
180
  "27": "NOT_ALIVE",
181
+ "28": "FAIL",
182
+ "29": "NOT_ALIVE",
183
+ "3": "FAIL",
184
+ "30": "NOT_ALIVE",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "FAIL",
190
+ "36": "FAIL",
191
+ "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
+ "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
+ "44": "NOT_ALIVE",
200
+ "45": "NOT_ALIVE",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
+ "50": "FAIL",
207
  "51": "NOT_ALIVE",
208
+ "52": "NOT_ALIVE",
209
+ "53": "FAIL",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "FAIL",
214
  "58": "NOT_ALIVE",
215
+ "59": "FAIL",
216
  "6": "NON_PARTICIPATING",
217
+ "60": "NOT_ALIVE",
218
+ "61": "FAIL",
219
+ "62": "FAIL",
220
+ "63": "NOT_ALIVE",
221
+ "64": "FAIL",
222
+ "65": "FAIL",
223
+ "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "FAIL",
226
  "69": "NON_PARTICIPATING",
227
+ "7": "NON_PARTICIPATING",
228
+ "70": "FAIL",
229
+ "71": "FAIL",
230
+ "72": "FAIL",
231
  "73": "NOT_ALIVE",
232
+ "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
+ "79": "FAIL",
238
+ "8": "FAIL",
239
+ "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
+ "82": "FAIL",
242
  "83": "NOT_ALIVE",
243
+ "84": "FAIL",
244
+ "85": "NON_PARTICIPATING",
245
+ "86": "FAIL",
246
+ "87": "FAIL",
247
  "88": "NOT_ALIVE",
248
+ "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
+ "91": "FAIL",
252
+ "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
+ "96": "NON_PARTICIPATING",
257
+ "97": "NON_PARTICIPATING",
258
+ "98": "NOT_ALIVE",
259
+ "99": "FAIL"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6522961,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9716e3ed7598658c8d78d03ef9c3c268a02441b3a2585f60467bbc1c52c3db48
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd5f742fc6877d827bc6e8cba1ec36037ba24902670bdf62d7d8f41e5045766
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8596b37adb515a96a413cb056d167fb48f9aadfcc86e31e32fcdaf4f0f75f34e
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec5960a796b6b29ceaadbf34ea48b2f2a4a4601b88cbecd854c621770af408b
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:728a3847fdcd32f86c441672a3976633f453f416d277faaccad043a0532c080a
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:014aac3c1a1b32bf3ef3c91acfcc37c718c4fb5b67a2e64ead9d4c7db6520478
3
  size 4400252568