kmfoda commited on
Commit
caaafd3
·
verified ·
1 Parent(s): cc1a94f

Run 7. Outer Step 117. Inner Step 0. Peers 33.

Browse files
Files changed (4) hide show
  1. config.json +44 -44
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "strnan01/llama-1b-hot-6",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
@@ -16,20 +16,20 @@
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
- "111": "NOT_ALIVE",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
- "117": "NON_PARTICIPATING",
26
- "118": "FAIL",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
- "123": "SUCCESS",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
@@ -43,11 +43,11 @@
43
  "133": "NOT_ALIVE",
44
  "134": "SUCCESS",
45
  "135": "NOT_ALIVE",
46
- "136": "NOT_ALIVE",
47
- "137": "NON_PARTICIPATING",
48
- "138": "NOT_ALIVE",
49
  "139": "NOT_ALIVE",
50
- "14": "SUCCESS",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
@@ -64,16 +64,16 @@
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
  "154": "SUCCESS",
67
- "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "SUCCESS",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
- "163": "SUCCESS",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
@@ -81,7 +81,7 @@
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
- "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
@@ -92,28 +92,28 @@
92
  "178": "NOT_ALIVE",
93
  "179": "SUCCESS",
94
  "18": "SUCCESS",
95
- "180": "NOT_ALIVE",
96
- "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
- "186": "SUCCESS",
102
- "187": "SUCCESS",
103
  "188": "NON_PARTICIPATING",
104
- "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
- "191": "SUCCESS",
108
  "192": "SUCCESS",
109
  "193": "SUCCESS",
110
- "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
- "199": "SUCCESS",
116
- "2": "SUCCESS",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
@@ -126,13 +126,13 @@
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": "NON_PARTICIPATING",
133
- "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
- "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
@@ -153,14 +153,14 @@
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
- "235": "NOT_ALIVE",
157
- "236": "NOT_ALIVE",
158
- "237": "NOT_ALIVE",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "NOT_ALIVE",
164
  "242": "SUCCESS",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
@@ -170,15 +170,15 @@
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
- "26": "NOT_ALIVE",
180
  "27": "SUCCESS",
181
- "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
@@ -190,15 +190,15 @@
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
- "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
- "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
- "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
@@ -206,7 +206,7 @@
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
209
- "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
@@ -215,15 +215,15 @@
215
  "59": "SUCCESS",
216
  "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
- "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
- "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
@@ -249,9 +249,9 @@
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
- "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
- "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
@@ -271,7 +271,7 @@
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
- "last_allreduce_block": 6304533,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "AussieAck/D24_model",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
 
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
+ "111": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
+ "117": "NOT_ALIVE",
26
+ "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
+ "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
 
43
  "133": "NOT_ALIVE",
44
  "134": "SUCCESS",
45
  "135": "NOT_ALIVE",
46
+ "136": "NON_PARTICIPATING",
47
+ "137": "NOT_ALIVE",
48
+ "138": "NON_PARTICIPATING",
49
  "139": "NOT_ALIVE",
50
+ "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
 
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
  "154": "SUCCESS",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NOT_ALIVE",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
 
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
+ "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
 
92
  "178": "NOT_ALIVE",
93
  "179": "SUCCESS",
94
  "18": "SUCCESS",
95
+ "180": "NON_PARTICIPATING",
96
+ "181": "SUCCESS",
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
+ "186": "NOT_ALIVE",
102
+ "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
+ "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
+ "191": "NON_PARTICIPATING",
108
  "192": "SUCCESS",
109
  "193": "SUCCESS",
110
+ "194": "SUCCESS",
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "NOT_ALIVE",
116
+ "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
 
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
+ "210": "NOT_ALIVE",
130
+ "211": "SUCCESS",
131
+ "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
+ "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
 
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
+ "235": "NON_PARTICIPATING",
157
+ "236": "NON_PARTICIPATING",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NOT_ALIVE",
166
  "244": "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": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
+ "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
 
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
+ "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
 
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
209
+ "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
 
215
  "59": "SUCCESS",
216
  "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
+ "61": "SUCCESS",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
+ "64": "SUCCESS",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
+ "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
 
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
+ "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6305215,
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 sha256:72153bbb58ea8d6ce8227629a4a5e9d3a7eb647399d031d463146149e04b48dd
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c76ddbe412f6e53d380cf05fe0fef88c727e8291681dc848c66bc9e45fcb39
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f804402a50d376f3541666e8b9f3d86b1fd8905ffb7f58dd30907fd0b838c52e
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d504c36fa4141186a2870fbf3c80828afab146a94bc8a456255453520272cd4
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb7151343c97a5a923e7251a282f4e5cbc5846c050b8b0b6a63dc157ea388700
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7667a7e7ab38bcfe3873d3e59ebe5d54b042941dc3f1af1c682ae2527f3084
3
  size 4400252568