kmfoda commited on
Commit
f144328
·
verified ·
1 Parent(s): 66835f5

Run 7. Outer Step 83. Inner Step 0. Peers 30.

Browse files
Files changed (4) hide show
  1. config.json +53 -53
  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": "STR-NaN/llama-1b-hot-10",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
@@ -17,40 +17,40 @@
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
- "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
  "115": "SUCCESS",
24
  "116": "NOT_ALIVE",
25
- "117": "NON_PARTICIPATING",
26
  "118": "SUCCESS",
27
- "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
- "122": "NOT_ALIVE",
32
  "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
- "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
- "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
- "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
  "134": "NOT_ALIVE",
45
- "135": "NON_PARTICIPATING",
46
- "136": "NON_PARTICIPATING",
47
- "137": "NOT_ALIVE",
48
- "138": "SUCCESS",
49
- "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
- "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
@@ -68,12 +68,12 @@
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": "NON_PARTICIPATING",
76
- "163": "SUCCESS",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
@@ -84,7 +84,7 @@
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
@@ -100,12 +100,12 @@
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": "NON_PARTICIPATING",
107
- "191": "SUCCESS",
108
- "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
111
  "195": "NOT_ALIVE",
@@ -126,16 +126,16 @@
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
- "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
- "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
- "216": "NON_PARTICIPATING",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
- "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
@@ -148,24 +148,24 @@
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
- "234": "NOT_ALIVE",
156
  "235": "NOT_ALIVE",
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": "SUCCESS",
164
- "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
- "245": "NON_PARTICIPATING",
168
- "246": "NOT_ALIVE",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
@@ -173,20 +173,20 @@
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": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
- "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "SUCCESS",
190
  "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
@@ -196,25 +196,25 @@
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
- "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
- "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
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",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
- "6": "SUCCESS",
217
- "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
@@ -223,29 +223,29 @@
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NON_PARTICIPATING",
231
  "73": "SUCCESS",
232
  "74": "NOT_ALIVE",
233
  "75": "SUCCESS",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
- "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
- "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
- "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
@@ -256,7 +256,7 @@
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": 6278293,
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",
 
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
+ "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
  "115": "SUCCESS",
24
  "116": "NOT_ALIVE",
25
+ "117": "SUCCESS",
26
  "118": "SUCCESS",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
+ "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
+ "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
+ "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
+ "130": "FAIL",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
  "134": "NOT_ALIVE",
45
+ "135": "NOT_ALIVE",
46
+ "136": "NOT_ALIVE",
47
+ "137": "NON_PARTICIPATING",
48
+ "138": "NON_PARTICIPATING",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
+ "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
 
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "SUCCESS",
71
+ "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
 
84
  "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
+ "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
 
100
  "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
+ "188": "NOT_ALIVE",
104
+ "189": "FAIL",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "NON_PARTICIPATING",
108
+ "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
111
  "195": "NOT_ALIVE",
 
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
+ "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
+ "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
+ "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
+ "216": "NOT_ALIVE",
136
+ "217": "SUCCESS",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
 
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
+ "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
  "233": "NOT_ALIVE",
155
+ "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
+ "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "SUCCESS",
164
+ "242": "SUCCESS",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
+ "245": "NOT_ALIVE",
168
+ "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
 
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
+ "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
+ "27": "NON_PARTICIPATING",
181
+ "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
+ "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
+ "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "NON_PARTICIPATING",
190
  "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
 
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
+ "52": "NON_PARTICIPATING",
209
+ "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
+ "6": "NOT_ALIVE",
217
+ "60": "NOT_ALIVE",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
 
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
+ "69": "FAIL",
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": "SUCCESS",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
+ "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
+ "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
+ "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
 
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
271
  "initializer_range": 0.02,
272
  "inner_step": 0,
273
  "intermediate_size": 5632,
274
+ "last_allreduce_block": 6279125,
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:a33ca9169ee68eed1c217f836ccd44f49aba6aaf7cb7fda33aa7333ca85ab52a
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2505d70cc353b8955f992177445b1496154d150056b1c5b8821cbd694b55c747
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e819ce45cf3e0383a49235344e07fe05f156c3b8f77582d8797645a8101eab0c
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3f462cd0cb42c8a84ff56fdb4a904c4c95cee4b9223ad6b6f12784fecc47d90
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c975ae75dcb5f92d7cf5644a3ac99bd9309480b12a4cff5cc64649b14d71587
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd0ac85784d4d52d51a17f84e70806995b9dff86bbe50c6d08c47777db871c7d
3
  size 4400252568