kmfoda commited on
Commit
a3ff651
·
verified ·
1 Parent(s): 11bb8fc

Run 7. Outer Step 107. Inner Step 0. Peers 31.

Browse files
Files changed (4) hide show
  1. config.json +42 -42
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
  4. outer_optimizer.pt +1 -1
config.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "_name_or_path": "AussieAck/D2_model",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
- "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
@@ -17,20 +17,20 @@
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
- "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "SUCCESS",
24
  "116": "NOT_ALIVE",
25
- "117": "SUCCESS",
26
- "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
- "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
@@ -42,16 +42,16 @@
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
- "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "SUCCESS",
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
- "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
@@ -59,18 +59,18 @@
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
- "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
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": "SUCCESS",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
- "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
@@ -83,29 +83,29 @@
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
- "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
- "178": "FAIL",
93
  "179": "NON_PARTICIPATING",
94
  "18": "SUCCESS",
95
  "180": "NON_PARTICIPATING",
96
- "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
- "187": "FAIL",
103
  "188": "NON_PARTICIPATING",
104
- "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
- "192": "SUCCESS",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
@@ -118,22 +118,22 @@
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
- "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
  "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
- "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
@@ -145,7 +145,7 @@
145
  "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
- "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
@@ -157,11 +157,11 @@
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
- "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "NON_PARTICIPATING",
164
- "242": "SUCCESS",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
@@ -171,13 +171,13 @@
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": "NON_PARTICIPATING",
180
- "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
@@ -192,11 +192,11 @@
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
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",
@@ -205,8 +205,8 @@
205
  "5": "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",
@@ -215,24 +215,24 @@
215
  "59": "SUCCESS",
216
  "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
- "61": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
- "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
- "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
@@ -249,14 +249,14 @@
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",
258
  "98": "NON_PARTICIPATING",
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": 6297733,
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": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
+ "100": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
  "103": "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": "SUCCESS",
24
  "116": "NOT_ALIVE",
25
+ "117": "NON_PARTICIPATING",
26
+ "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
+ "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
 
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
+ "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "NON_PARTICIPATING",
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
+ "140": "FAIL",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
+ "143": "SUCCESS",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
 
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
+ "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
  "154": "SUCCESS",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
+ "157": "NOT_ALIVE",
70
  "158": "SUCCESS",
71
+ "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
+ "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
 
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
+ "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
+ "178": "NOT_ALIVE",
93
  "179": "NON_PARTICIPATING",
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": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
+ "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
 
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "NOT_ALIVE",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
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": "SUCCESS",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
 
145
  "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
+ "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
 
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
+ "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
+ "241": "NOT_ALIVE",
164
+ "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
 
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
+ "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
+ "27": "NOT_ALIVE",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
 
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
 
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
+ "52": "NOT_ALIVE",
209
+ "53": "FAIL",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
 
215
  "59": "SUCCESS",
216
  "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
+ "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
+ "64": "NOT_ALIVE",
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": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
+ "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
+ "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
 
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
+ "92": "SUCCESS",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
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": 6298393,
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 sha256:24867c8545052e23bcff9a3a973ccd8c1fe77337b48fde545ff0b8b3a5def9d7
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7871faf6aa2b39931290cb530c4456231dd90690cfd2aeb206acf86ce40e617
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:659f9c20cdff610b2a4c0284ba9bc78bf3e3b27465815dbe1ddcc21c66b0a093
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08900553bc7cca84ffe7a057a3d8a6a38977d0c03602736f2f6bff4cf4ec5157
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd2946d0548d9b0699e2422ed2ac7e0f8fedf8c720dc2e3719996e28ee939e0e
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b05c7638cb0e981b0551543d1e8d3fbda45cd109a5b4aaba4b1fe8aa24ae56d
3
  size 4400252568