zeras141a commited on
Commit
18ec47e
·
verified ·
1 Parent(s): 31bf621

Run 6. Outer Step 15. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +61 -61
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,11 +2,11 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
9
- "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
@@ -44,96 +44,96 @@
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
- "137": "NOT_ALIVE",
48
- "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "NOT_ALIVE",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
- "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
- "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
62
  "150": "NOT_ALIVE",
63
- "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
  "154": "NON_PARTICIPATING",
67
- "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
- "160": "NOT_ALIVE",
74
- "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
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": "NOT_ALIVE",
88
  "174": "NON_PARTICIPATING",
89
- "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
- "179": "NOT_ALIVE",
94
  "18": "SUCCESS",
95
- "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
- "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
- "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "NOT_ALIVE",
107
- "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
- "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "SUCCESS",
114
- "198": "NOT_ALIVE",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "NOT_ALIVE",
119
  "201": "SUCCESS",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
- "205": "NON_PARTICIPATING",
124
  "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
- "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
- "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
@@ -141,22 +141,22 @@
141
  "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
144
- "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
- "227": "NOT_ALIVE",
148
- "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "SUCCESS",
151
  "230": "SUCCESS",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
- "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
- "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
- "237": "NOT_ALIVE",
159
- "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
@@ -173,7 +173,7 @@
173
  "250": "NOT_ALIVE",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
- "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
@@ -182,8 +182,8 @@
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
- "31": "SUCCESS",
186
- "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
@@ -208,43 +208,43 @@
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
- "55": "NOT_ALIVE",
212
- "56": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
- "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
- "71": "SUCCESS",
230
- "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
- "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
- "80": "SUCCESS",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
- "83": "NOT_ALIVE",
243
- "84": "NOT_ALIVE",
244
  "85": "SUCCESS",
245
- "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
- "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
@@ -252,9 +252,9 @@
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
- "95": "NON_PARTICIPATING",
256
- "96": "NON_PARTICIPATING",
257
- "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "SUCCESS"
260
  },
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6132067,
268
- 6132083
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
- "inner_step": 221,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6130508,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
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": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
 
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
+ "137": "NON_PARTICIPATING",
48
+ "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
+ "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
62
  "150": "NOT_ALIVE",
63
+ "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
  "154": "NON_PARTICIPATING",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
+ "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
+ "168": "NOT_ALIVE",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
+ "170": "NOT_ALIVE",
85
+ "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
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": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
+ "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
+ "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
+ "190": "NON_PARTICIPATING",
107
+ "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
+ "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "SUCCESS",
114
+ "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "NON_PARTICIPATING",
119
  "201": "SUCCESS",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
+ "205": "NOT_ALIVE",
124
  "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
+ "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
+ "217": "SUCCESS",
137
  "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
 
141
  "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
144
+ "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
+ "227": "NON_PARTICIPATING",
148
+ "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
  "23": "SUCCESS",
151
  "230": "SUCCESS",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
+ "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
+ "237": "NON_PARTICIPATING",
159
+ "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
 
173
  "250": "NOT_ALIVE",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
+ "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
 
182
  "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
+ "31": "NOT_ALIVE",
186
+ "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
 
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
+ "55": "NON_PARTICIPATING",
212
+ "56": "NOT_ALIVE",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
+ "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
+ "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
+ "71": "NON_PARTICIPATING",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
+ "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
+ "80": "FAIL",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
+ "83": "NON_PARTICIPATING",
243
+ "84": "NON_PARTICIPATING",
244
  "85": "SUCCESS",
245
+ "86": "NON_PARTICIPATING",
246
  "87": "NOT_ALIVE",
247
+ "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
 
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "NOT_ALIVE",
256
+ "96": "NOT_ALIVE",
257
+ "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
  "99": "SUCCESS"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6132183,
268
+ 6132202
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
+ "inner_step": 5,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6131994,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:486571b9f86198c0a779b996725c5d162f034de67538b8174995e18111116f02
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04fd173b210590276b3b2c5bf05d3ab4ce187ad89695bdf8d0caedb3c361cd4f
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92b52379236c0d4a0d860e67645ae931c2652c88f3fdbebcfda7f363a2224009
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15a34549b840243413ca3e6c5488a5c57d001bbbb8a28cbbf18bf85407ae7fc
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c35a04f179ecd5b84716371d395c19cf8b19de8a72fde6c0142e828eb6b3eac6
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d051960532d4c9ebbd89e989c514e8a5ee4583a090e0c405f43bb26630673926
3
  size 4400216536