zeras141a commited on
Commit
2b573e3
·
verified ·
1 Parent(s): bea1283

Run 6. Outer Step 103. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +49 -49
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,14 +2,14 @@
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": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
@@ -17,7 +17,7 @@
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
- "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
@@ -28,7 +28,7 @@
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",
@@ -45,16 +45,16 @@
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "SUCCESS",
49
  "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
- "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
- "145": "SUCCESS",
57
- "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
@@ -63,30 +63,30 @@
63
  "151": "NON_PARTICIPATING",
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": "NOT_ALIVE",
71
- "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
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": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
- "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
- "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
@@ -100,15 +100,15 @@
100
  "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
111
- "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
@@ -121,7 +121,7 @@
121
  "203": "NOT_ALIVE",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
- "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
@@ -130,14 +130,14 @@
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
- "214": "SUCCESS",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
- "218": "NON_PARTICIPATING",
138
- "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
@@ -148,20 +148,20 @@
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
- "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
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": "NON_PARTICIPATING",
164
- "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
@@ -170,33 +170,33 @@
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
  "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
  "253": "NON_PARTICIPATING",
177
- "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
- "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
- "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
@@ -205,7 +205,7 @@
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
- "52": "SUCCESS",
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
@@ -214,23 +214,23 @@
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
- "61": "SUCCESS",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
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": "NOT_ALIVE",
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": "NON_PARTICIPATING",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6202908,
268
- 6202921
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": 186,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6201510,
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": "FAIL",
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": "NOT_ALIVE",
13
  "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
 
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",
 
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",
 
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
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": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
+ "145": "NOT_ALIVE",
57
+ "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
 
63
  "151": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
71
+ "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "FAIL",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
+ "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
+ "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
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": "NOT_ALIVE",
 
100
  "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
+ "188": "NOT_ALIVE",
104
+ "189": "FAIL",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
+ "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "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": "NOT_ALIVE",
 
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
+ "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
+ "218": "NOT_ALIVE",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
 
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
+ "230": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
+ "241": "SUCCESS",
164
+ "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
 
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
  "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
  "253": "NON_PARTICIPATING",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
+ "28": "NOT_ALIVE",
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": "NOT_ALIVE",
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
+ "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "FAIL",
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": "FAIL",
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
 
214
  "58": "NOT_ALIVE",
215
  "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
+ "60": "NOT_ALIVE",
218
+ "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
+ "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
+ "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
+ "75": "FAIL",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6203018,
268
+ 6203035
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": 4,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6202920,
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:c5fbfe5d228cc3669277e186dab94cdf7a04b7d2421b08e45400f947addee246
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0bef26d39805419b7f06ac6f9c3e2959cf5d2f1a2d76329d395778788a2a77
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dabd4611bc0a3ec2e0b097b1d6f63cd8770ce5e9bdb21fd49251d606a370df9
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bece5f51461ec6454fa2b077e747e85abc72cf6027ab770e0d5ac22fee62f39
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4679801b1696341fe260b78b0a593c9b1c1932cb8ab6d26513431397f2ab350f
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894e1205fd13af09bfa5c81688d807c5dd8bb18b88fa4f2750ccd28ff8a67843
3
  size 4400216536