kmfoda commited on
Commit
f1cd12e
·
verified ·
1 Parent(s): 789b7c5

Run 10. Outer Step 94. Inner Step 0. Peers 63.

Browse files
Files changed (4) hide show
  1. config.json +55 -55
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -5,18 +5,18 @@
5
  "1": "NON_PARTICIPATING",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
- "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
- "106": "SUCCESS",
14
- "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
- "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
- "111": "NOT_ALIVE",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
@@ -25,17 +25,17 @@
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "SUCCESS",
28
- "12": "NOT_ALIVE",
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": "SUCCESS",
38
- "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
@@ -48,14 +48,14 @@
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "SUCCESS",
52
- "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
- "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
- "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
@@ -67,7 +67,7 @@
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
@@ -76,11 +76,11 @@
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
- "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
- "169": "NON_PARTICIPATING",
83
- "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
@@ -89,7 +89,7 @@
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
- "178": "NON_PARTICIPATING",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
@@ -100,40 +100,40 @@
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
- "188": "SUCCESS",
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": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
- "211": "NOT_ALIVE",
131
- "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
@@ -142,22 +142,22 @@
142
  "222": "NOT_ALIVE",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
- "225": "NON_PARTICIPATING",
146
- "226": "NON_PARTICIPATING",
147
  "227": "SUCCESS",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
- "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
- "231": "NOT_ALIVE",
153
- "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
- "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
- "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NOT_ALIVE",
@@ -170,19 +170,19 @@
170
  "248": "SUCCESS",
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": "SUCCESS",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
- "29": "NON_PARTICIPATING",
183
- "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
- "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
@@ -194,11 +194,11 @@
194
  "4": "NON_PARTICIPATING",
195
  "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
- "42": "NON_PARTICIPATING",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
- "45": "NON_PARTICIPATING",
201
- "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
@@ -209,25 +209,25 @@
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
- "56": "NOT_ALIVE",
213
- "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
- "61": "NOT_ALIVE",
219
  "62": "NON_PARTICIPATING",
220
- "63": "NOT_ALIVE",
221
- "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "SUCCESS",
224
  "67": "NON_PARTICIPATING",
225
- "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
  "70": "SUCCESS",
229
  "71": "SUCCESS",
230
- "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
@@ -243,20 +243,20 @@
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
- "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
- "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
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": 6518328,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
5
  "1": "NON_PARTICIPATING",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
+ "101": "NON_PARTICIPATING",
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "SUCCESS",
13
+ "106": "NOT_ALIVE",
14
+ "107": "SUCCESS",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
+ "11": "NON_PARTICIPATING",
18
  "110": "NOT_ALIVE",
19
+ "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
 
25
  "117": "SUCCESS",
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": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "SUCCESS",
38
+ "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
 
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "NOT_ALIVE",
52
+ "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
+ "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
+ "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
 
67
  "155": "NOT_ALIVE",
68
  "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NOT_ALIVE",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
 
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
+ "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
+ "169": "NOT_ALIVE",
83
+ "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
 
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
+ "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
 
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
+ "188": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
+ "20": "NON_PARTICIPATING",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
+ "205": "NON_PARTICIPATING",
124
+ "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "NOT_ALIVE",
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "NON_PARTICIPATING",
131
+ "212": "NOT_ALIVE",
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",
 
142
  "222": "NOT_ALIVE",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
+ "225": "NOT_ALIVE",
146
+ "226": "NOT_ALIVE",
147
  "227": "SUCCESS",
148
  "228": "NON_PARTICIPATING",
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": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
+ "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NOT_ALIVE",
 
170
  "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
+ "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
+ "29": "NOT_ALIVE",
183
+ "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
185
+ "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
 
194
  "4": "NON_PARTICIPATING",
195
  "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
+ "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
+ "45": "NOT_ALIVE",
201
+ "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
 
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
+ "56": "NON_PARTICIPATING",
213
+ "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
+ "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "SUCCESS",
221
+ "64": "SUCCESS",
222
  "65": "NON_PARTICIPATING",
223
  "66": "SUCCESS",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
  "70": "SUCCESS",
229
  "71": "SUCCESS",
230
+ "72": "SUCCESS",
231
  "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
 
243
  "84": "SUCCESS",
244
  "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
+ "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
+ "9": "NON_PARTICIPATING",
250
  "90": "NON_PARTICIPATING",
251
  "91": "SUCCESS",
252
  "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
+ "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6518691,
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 sha256:7792fc91cf2c91bc70805d0bba0dc9d43fa0c28ec74deb23be270de1bb74a122
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e3f295625ab6591af1350dc156101794c9ff0f08af111861e1ddd883ee3554e
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:089d06de2d6403a0f26288969afcc83f3fa91a8d561d169c4aaf3af41626b7ee
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c6c37753d06d01de4db19d1fb9ff03c3cffbeb508e81e308a1c7b4ab5f5eca8
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab1ed89a1df2eabda8a4de9a806a6a3602db04e78f0e87a9ce34a7b3e4189f09
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8594df2c144b47800afc636dfb55f7f72bff1114566827cb72aebe5abd7d41a4
3
  size 4400252568