kmfoda commited on
Commit
7e7378f
·
verified ·
1 Parent(s): 05cc155

Run 10. Outer Step 37. Inner Step 0. Peers 62.

Browse files
Files changed (4) hide show
  1. config.json +54 -54
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -9,29 +9,29 @@
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
- "106": "NOT_ALIVE",
14
- "107": "NOT_ALIVE",
15
- "108": "NOT_ALIVE",
16
  "109": "SUCCESS",
17
  "11": "SUCCESS",
18
- "110": "NON_PARTICIPATING",
19
- "111": "SUCCESS",
20
- "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
  "117": "NOT_ALIVE",
26
- "118": "NON_PARTICIPATING",
27
- "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
- "125": "NON_PARTICIPATING",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "SUCCESS",
@@ -45,7 +45,7 @@
45
  "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
- "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
@@ -54,7 +54,7 @@
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
- "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
@@ -62,10 +62,10 @@
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
- "153": "NON_PARTICIPATING",
66
- "154": "SUCCESS",
67
  "155": "NON_PARTICIPATING",
68
- "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
@@ -82,21 +82,21 @@
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
- "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
- "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
- "184": "NON_PARTICIPATING",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
@@ -105,13 +105,13 @@
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
- "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
- "198": "SUCCESS",
115
  "199": "NOT_ALIVE",
116
  "2": "NON_PARTICIPATING",
117
  "20": "SUCCESS",
@@ -120,43 +120,43 @@
120
  "202": "NOT_ALIVE",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
- "205": "NOT_ALIVE",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
- "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
- "210": "NON_PARTICIPATING",
130
- "211": "SUCCESS",
131
  "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
- "214": "NOT_ALIVE",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
- "218": "NOT_ALIVE",
138
  "219": "SUCCESS",
139
  "22": "NON_PARTICIPATING",
140
- "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
  "222": "SUCCESS",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "NOT_ALIVE",
147
- "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
- "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
- "232": "SUCCESS",
154
- "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
@@ -165,12 +165,12 @@
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
- "246": "SUCCESS",
169
  "247": "NOT_ALIVE",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
@@ -180,13 +180,13 @@
180
  "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
- "3": "NON_PARTICIPATING",
184
  "30": "NOT_ALIVE",
185
- "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
- "35": "SUCCESS",
190
  "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
@@ -198,25 +198,25 @@
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
  "45": "SUCCESS",
201
- "46": "SUCCESS",
202
  "47": "SUCCESS",
203
- "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
- "5": "NON_PARTICIPATING",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
- "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
- "56": "SUCCESS",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
- "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
@@ -224,7 +224,7 @@
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
- "7": "SUCCESS",
228
  "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
@@ -236,7 +236,7 @@
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "SUCCESS",
239
- "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
@@ -249,11 +249,11 @@
249
  "9": "SUCCESS",
250
  "90": "NON_PARTICIPATING",
251
  "91": "SUCCESS",
252
- "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
- "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
- "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6487023,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
9
  "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "SUCCESS",
13
+ "106": "NON_PARTICIPATING",
14
+ "107": "SUCCESS",
15
+ "108": "NON_PARTICIPATING",
16
  "109": "SUCCESS",
17
  "11": "SUCCESS",
18
+ "110": "SUCCESS",
19
+ "111": "NON_PARTICIPATING",
20
+ "112": "NOT_ALIVE",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
+ "118": "SUCCESS",
27
+ "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
+ "125": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "SUCCESS",
 
45
  "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
+ "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
 
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
 
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
+ "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
+ "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
 
82
  "169": "SUCCESS",
83
  "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
+ "171": "SUCCESS",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "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": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
+ "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
 
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
+ "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
+ "198": "NOT_ALIVE",
115
  "199": "NOT_ALIVE",
116
  "2": "NON_PARTICIPATING",
117
  "20": "SUCCESS",
 
120
  "202": "NOT_ALIVE",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
+ "205": "NON_PARTICIPATING",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "SUCCESS",
128
  "21": "SUCCESS",
129
+ "210": "NOT_ALIVE",
130
+ "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
+ "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
+ "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
  "22": "NON_PARTICIPATING",
140
+ "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
  "222": "SUCCESS",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "NON_PARTICIPATING",
147
+ "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
+ "232": "NOT_ALIVE",
154
+ "233": "SUCCESS",
155
  "234": "SUCCESS",
156
  "235": "SUCCESS",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
 
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "NON_PARTICIPATING",
168
+ "246": "NOT_ALIVE",
169
  "247": "NOT_ALIVE",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
 
180
  "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
+ "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
+ "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "NON_PARTICIPATING",
190
  "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
 
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
  "45": "SUCCESS",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "SUCCESS",
203
+ "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "SUCCESS",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
+ "56": "NOT_ALIVE",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "SUCCESS",
218
  "61": "NOT_ALIVE",
219
+ "62": "NON_PARTICIPATING",
220
  "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
 
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
+ "7": "NON_PARTICIPATING",
228
  "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
 
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "SUCCESS",
239
+ "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
 
249
  "9": "SUCCESS",
250
  "90": "NON_PARTICIPATING",
251
  "91": "SUCCESS",
252
+ "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
+ "94": "SUCCESS",
255
  "95": "NOT_ALIVE",
256
+ "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6487477,
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 sha256:97bb46f4a5d633f42b3e21e87e035b04824dd2c6c7ddb000e6ad40ab380c2d1d
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50465e108ecc308c242ef923a9986c1b33b5c6a3930ca12fac24a63adcad26a5
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6775a5469106fff03335496bb4d1ad6d8a76c49a2a9a00063f3199e816f7e192
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4a5ff26da583c22247587409fe05c7e6f84e29b036ea12b0d51399200852eb
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c02adc48444476b4faee2583b7ca706d39e39a09a9af97c6820fc5a9014b6957
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6409bd75173604cd19b406f8e1d5cf920d4182a2e2208acfb827a041a0a3526
3
  size 4400252568