kmfoda commited on
Commit
038a8e5
·
verified ·
1 Parent(s): fb8149a

Run 7. Outer Step 53. Inner Step 0. Peers 29.

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
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "fshami/fshami011",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "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": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
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": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
@@ -43,12 +43,12 @@
43
  "133": "SUCCESS",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
- "136": "NON_PARTICIPATING",
47
- "137": "NON_PARTICIPATING",
48
- "138": "FAIL",
49
  "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
- "140": "NOT_ALIVE",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "SUCCESS",
@@ -67,19 +67,19 @@
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NON_PARTICIPATING",
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": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
@@ -95,19 +95,19 @@
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "NOT_ALIVE",
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": "NON_PARTICIPATING",
109
- "193": "SUCCESS",
110
- "194": "SUCCESS",
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
@@ -127,25 +127,25 @@
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
- "211": "SUCCESS",
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
- "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
- "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
- "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
@@ -160,12 +160,12 @@
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "NOT_ALIVE",
164
- "242": "NOT_ALIVE",
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",
@@ -177,24 +177,24 @@
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": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
- "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
- "35": "SUCCESS",
190
  "36": "SUCCESS",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
- "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
- "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
  "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
@@ -206,33 +206,33 @@
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
- "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
- "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
- "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
- "73": "FAIL",
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",
@@ -240,12 +240,12 @@
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
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",
@@ -256,7 +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": 6254933,
275
  "max_position_embeddings": 2048,
276
  "mlp_bias": false,
277
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "asim22/sub38-178",
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": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
  "118": "NON_PARTICIPATING",
27
+ "119": "NOT_ALIVE",
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": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
 
43
  "133": "SUCCESS",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
+ "136": "FAIL",
47
+ "137": "NOT_ALIVE",
48
+ "138": "NON_PARTICIPATING",
49
  "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "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": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
 
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
+ "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
+ "185": "NOT_ALIVE",
101
+ "186": "SUCCESS",
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": "SUCCESS",
109
+ "193": "NON_PARTICIPATING",
110
+ "194": "FAIL",
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
 
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
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": "SUCCESS",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
+ "222": "SUCCESS",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
+ "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
 
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
+ "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
+ "246": "SUCCESS",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
 
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
+ "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
189
+ "35": "NOT_ALIVE",
190
  "36": "SUCCESS",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
+ "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
+ "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
  "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
 
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
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": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
+ "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
+ "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
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",
 
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
+ "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
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
  "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": 6255623,
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 sha256:5aaaa59a6a9ecf8ed994b5147650023ed8614be573fbca66e8c5f09c8038a290
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d37a909f9593309405ea4818c4f94c4cebf10085a3eca78d36a193225db6e2fe
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06398562ad013413de62cd2db68587ec77704212587b17c19b619dafc4e68fa2
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea8fb701050025df0408cb49493c0ed664422cf3a9dc5db51196280faf53ebe5
3
  size 4400216536
outer_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79d1d03f0714bd066c4d201885bac5529b1787e52ca5a5b21c0f3c842c7c2979
3
  size 4400252568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c87d95d282ef21c84b4d43186d3751acdf15e66f121104a379d6f6c3dea6b2d
3
  size 4400252568