zeras141a commited on
Commit
e09f14c
·
verified ·
1 Parent(s): 13fba2d

Run 6. Outer Step 20. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +53 -53
  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": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
- "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
- "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
@@ -15,7 +15,7 @@
15
  "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
- "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
@@ -45,7 +45,7 @@
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": "SUCCESS",
@@ -55,10 +55,10 @@
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
- "147": "SUCCESS",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
- "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
@@ -76,22 +76,22 @@
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
- "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
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": "NOT_ALIVE",
94
- "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
@@ -101,23 +101,23 @@
101
  "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
104
- "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "SUCCESS",
107
- "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
- "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
- "195": "NOT_ALIVE",
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": "NOT_ALIVE",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
@@ -125,34 +125,34 @@
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
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": "SUCCESS",
137
- "218": "NOT_ALIVE",
138
- "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
- "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
144
- "224": "NOT_ALIVE",
145
- "225": "NOT_ALIVE",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "SUCCESS",
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",
@@ -161,11 +161,11 @@
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": "NON_PARTICIPATING",
168
- "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
@@ -175,27 +175,27 @@
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
- "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
- "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
- "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
- "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
- "40": "NOT_ALIVE",
196
  "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
- "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
@@ -212,7 +212,7 @@
212
  "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
@@ -225,21 +225,21 @@
225
  "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
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": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
- "77": "NON_PARTICIPATING",
236
- "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "SUCCESS",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
- "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
@@ -252,11 +252,11 @@
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
- "95": "NON_PARTICIPATING",
256
- "96": "NOT_ALIVE",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
- "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6138797,
268
- 6138811
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": 56,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6138225,
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": "NOT_ALIVE",
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",
 
15
  "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
+ "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
 
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
 
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",
 
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
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": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
+ "172": "NOT_ALIVE",
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",
 
101
  "186": "NOT_ALIVE",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
104
+ "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
+ "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "FAIL",
110
  "194": "NOT_ALIVE",
111
+ "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
+ "197": "FAIL",
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": "NON_PARTICIPATING",
 
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
+ "21": "FAIL",
129
  "210": "NOT_ALIVE",
130
+ "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "NOT_ALIVE",
134
  "215": "NON_PARTICIPATING",
135
+ "216": "FAIL",
136
+ "217": "FAIL",
137
+ "218": "NON_PARTICIPATING",
138
+ "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
+ "221": "NOT_ALIVE",
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": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
+ "23": "FAIL",
151
+ "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "NOT_ALIVE",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
 
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "FAIL",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NON_PARTICIPATING",
168
+ "246": "NOT_ALIVE",
169
  "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
 
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
+ "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
+ "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
+ "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
+ "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
+ "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
 
212
  "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
 
225
  "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
+ "70": "NON_PARTICIPATING",
229
+ "71": "FAIL",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
+ "77": "SUCCESS",
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": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
 
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "NOT_ALIVE",
256
+ "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
+ "99": "FAIL"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6138900,
268
+ 6138917
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": 6138837,
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:d8cb3a30478ab44b258ae31d0310846a9ffb4f1abeac6094ba197cffb64797b8
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc42bed433c901d1245cb76d8247a5501cd5678b5ade956cb3b48f9cacf064d0
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1a877fcfce43498cc58011336703b1c6651455f75609b772956bdf1ceadb18e
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8439f976faff6153cc85d1ff88625cb9170ecb15d8a8ae0b87e12f3178773e68
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd1eef9c804a7af57c2e92669856cd3bad5f3016d1fd8688e902020f1bf72afe
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2da55e600a6eec70bcbeafb42b175db627e8c1bfe5e810bdee162b8892b66a63
3
  size 4400216536