aalv2 commited on
Commit
919b3dd
·
verified ·
1 Parent(s): 873016f

Run 8. Outer Step 2. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +182 -182
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +2 -2
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,262 +1,262 @@
1
  {
2
- "_name_or_path": "aalv2/c69-h6",
3
  "all_reduce_scores": {
4
- "0": "SUCCESS",
5
  "1": "SUCCESS",
6
- "10": "SUCCESS",
7
- "100": "SUCCESS",
8
- "101": "SUCCESS",
9
- "102": "SUCCESS",
10
- "103": "SUCCESS",
11
- "104": "SUCCESS",
12
- "105": "SUCCESS",
13
- "106": "SUCCESS",
14
- "107": "SUCCESS",
15
- "108": "SUCCESS",
16
- "109": "SUCCESS",
17
- "11": "SUCCESS",
18
- "110": "SUCCESS",
19
  "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
- "114": "SUCCESS",
23
- "115": "SUCCESS",
24
- "116": "SUCCESS",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
- "119": "SUCCESS",
28
- "12": "SUCCESS",
29
- "120": "SUCCESS",
30
  "121": "SUCCESS",
31
- "122": "SUCCESS",
32
- "123": "SUCCESS",
33
- "124": "SUCCESS",
34
- "125": "SUCCESS",
35
- "126": "SUCCESS",
36
- "127": "SUCCESS",
37
- "128": "SUCCESS",
38
  "129": "SUCCESS",
39
- "13": "SUCCESS",
40
  "130": "SUCCESS",
41
- "131": "SUCCESS",
42
- "132": "SUCCESS",
43
  "133": "SUCCESS",
44
- "134": "SUCCESS",
45
  "135": "SUCCESS",
46
- "136": "SUCCESS",
47
- "137": "SUCCESS",
48
  "138": "SUCCESS",
49
  "139": "SUCCESS",
50
- "14": "SUCCESS",
51
  "140": "SUCCESS",
52
- "141": "SUCCESS",
53
- "142": "SUCCESS",
54
- "143": "SUCCESS",
55
- "144": "SUCCESS",
56
- "145": "SUCCESS",
57
  "146": "SUCCESS",
58
  "147": "SUCCESS",
59
  "148": "SUCCESS",
60
- "149": "SUCCESS",
61
- "15": "SUCCESS",
62
- "150": "SUCCESS",
63
- "151": "SUCCESS",
64
- "152": "SUCCESS",
65
- "153": "SUCCESS",
66
- "154": "SUCCESS",
67
  "155": "SUCCESS",
68
- "156": "SUCCESS",
69
  "157": "SUCCESS",
70
  "158": "SUCCESS",
71
- "159": "SUCCESS",
72
- "16": "SUCCESS",
73
  "160": "SUCCESS",
74
- "161": "SUCCESS",
75
- "162": "SUCCESS",
76
  "163": "SUCCESS",
77
- "164": "SUCCESS",
78
- "165": "SUCCESS",
79
  "166": "SUCCESS",
80
- "167": "SUCCESS",
81
- "168": "SUCCESS",
82
- "169": "SUCCESS",
83
  "17": "SUCCESS",
84
- "170": "SUCCESS",
85
- "171": "SUCCESS",
86
- "172": "SUCCESS",
87
  "173": "SUCCESS",
88
- "174": "SUCCESS",
89
- "175": "SUCCESS",
90
- "176": "SUCCESS",
91
  "177": "SUCCESS",
92
- "178": "SUCCESS",
93
- "179": "SUCCESS",
94
- "18": "SUCCESS",
95
- "180": "SUCCESS",
96
- "181": "SUCCESS",
97
- "182": "SUCCESS",
98
- "183": "SUCCESS",
99
- "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
- "187": "SUCCESS",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
- "19": "SUCCESS",
106
- "190": "SUCCESS",
107
  "191": "SUCCESS",
108
  "192": "SUCCESS",
109
  "193": "SUCCESS",
110
  "194": "SUCCESS",
111
- "195": "SUCCESS",
112
- "196": "SUCCESS",
113
- "197": "SUCCESS",
114
- "198": "SUCCESS",
115
- "199": "SUCCESS",
116
  "2": "SUCCESS",
117
- "20": "SUCCESS",
118
- "200": "SUCCESS",
119
- "201": "SUCCESS",
120
- "202": "SUCCESS",
121
- "203": "SUCCESS",
122
  "204": "SUCCESS",
123
  "205": "SUCCESS",
124
  "206": "SUCCESS",
125
- "207": "SUCCESS",
126
- "208": "SUCCESS",
127
  "209": "SUCCESS",
128
- "21": "SUCCESS",
129
- "210": "SUCCESS",
130
  "211": "SUCCESS",
131
  "212": "SUCCESS",
132
- "213": "SUCCESS",
133
  "214": "SUCCESS",
134
- "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "SUCCESS",
138
  "219": "SUCCESS",
139
- "22": "SUCCESS",
140
- "220": "SUCCESS",
141
  "221": "SUCCESS",
142
- "222": "SUCCESS",
143
- "223": "SUCCESS",
144
- "224": "SUCCESS",
145
  "225": "SUCCESS",
146
- "226": "SUCCESS",
147
- "227": "SUCCESS",
148
  "228": "SUCCESS",
149
- "229": "SUCCESS",
150
- "23": "SUCCESS",
151
- "230": "SUCCESS",
152
- "231": "SUCCESS",
153
- "232": "SUCCESS",
154
- "233": "SUCCESS",
155
  "234": "SUCCESS",
156
- "235": "SUCCESS",
157
- "236": "SUCCESS",
158
- "237": "SUCCESS",
159
  "238": "SUCCESS",
160
- "239": "SUCCESS",
161
- "24": "SUCCESS",
162
- "240": "SUCCESS",
163
- "241": "SUCCESS",
164
- "242": "SUCCESS",
165
- "243": "SUCCESS",
166
- "244": "SUCCESS",
167
- "245": "SUCCESS",
168
  "246": "SUCCESS",
169
- "247": "SUCCESS",
170
- "248": "SUCCESS",
171
- "249": "SUCCESS",
172
  "25": "SUCCESS",
173
- "250": "SUCCESS",
174
  "251": "SUCCESS",
175
- "252": "SUCCESS",
176
  "253": "SUCCESS",
177
- "254": "SUCCESS",
178
- "255": "SUCCESS",
179
- "26": "SUCCESS",
180
  "27": "SUCCESS",
181
- "28": "SUCCESS",
182
- "29": "SUCCESS",
183
  "3": "SUCCESS",
184
  "30": "SUCCESS",
185
- "31": "SUCCESS",
186
- "32": "SUCCESS",
187
- "33": "SUCCESS",
188
- "34": "SUCCESS",
189
  "35": "SUCCESS",
190
  "36": "SUCCESS",
191
- "37": "SUCCESS",
192
- "38": "SUCCESS",
193
  "39": "SUCCESS",
194
- "4": "SUCCESS",
195
  "40": "SUCCESS",
196
- "41": "SUCCESS",
197
- "42": "SUCCESS",
198
- "43": "SUCCESS",
199
  "44": "SUCCESS",
200
- "45": "SUCCESS",
201
- "46": "SUCCESS",
202
  "47": "SUCCESS",
203
- "48": "SUCCESS",
204
- "49": "SUCCESS",
205
- "5": "SUCCESS",
206
- "50": "SUCCESS",
207
- "51": "SUCCESS",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
- "54": "SUCCESS",
211
- "55": "SUCCESS",
212
- "56": "SUCCESS",
213
  "57": "SUCCESS",
214
- "58": "SUCCESS",
215
  "59": "SUCCESS",
216
- "6": "SUCCESS",
217
- "60": "SUCCESS",
218
  "61": "SUCCESS",
219
- "62": "SUCCESS",
220
- "63": "SUCCESS",
221
- "64": "SUCCESS",
222
- "65": "SUCCESS",
223
- "66": "SUCCESS",
224
- "67": "SUCCESS",
225
- "68": "SUCCESS",
226
  "69": "SUCCESS",
227
- "7": "SUCCESS",
228
- "70": "SUCCESS",
229
- "71": "SUCCESS",
230
- "72": "SUCCESS",
231
  "73": "SUCCESS",
232
  "74": "SUCCESS",
233
- "75": "SUCCESS",
234
- "76": "SUCCESS",
235
- "77": "SUCCESS",
236
- "78": "SUCCESS",
237
- "79": "SUCCESS",
238
- "8": "SUCCESS",
239
  "80": "SUCCESS",
240
- "81": "SUCCESS",
241
- "82": "SUCCESS",
242
- "83": "SUCCESS",
243
- "84": "SUCCESS",
244
- "85": "SUCCESS",
245
  "86": "SUCCESS",
246
  "87": "SUCCESS",
247
- "88": "SUCCESS",
248
  "89": "SUCCESS",
249
- "9": "SUCCESS",
250
- "90": "SUCCESS",
251
- "91": "SUCCESS",
252
  "92": "SUCCESS",
253
  "93": "SUCCESS",
254
  "94": "SUCCESS",
255
- "95": "SUCCESS",
256
- "96": "SUCCESS",
257
  "97": "SUCCESS",
258
- "98": "SUCCESS",
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
- 6326825,
268
- 6326853
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": 153,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6317911,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
1
  {
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": "NOT_ALIVE",
16
+ "109": "NOT_ALIVE",
17
+ "11": "NOT_ALIVE",
18
+ "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
+ "114": "NON_PARTICIPATING",
23
+ "115": "NOT_ALIVE",
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": "NON_PARTICIPATING",
33
+ "124": "NOT_ALIVE",
34
+ "125": "FAIL",
35
+ "126": "NOT_ALIVE",
36
+ "127": "NOT_ALIVE",
37
+ "128": "NOT_ALIVE",
38
  "129": "SUCCESS",
39
+ "13": "NOT_ALIVE",
40
  "130": "SUCCESS",
41
+ "131": "NOT_ALIVE",
42
+ "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
+ "134": "FAIL",
45
  "135": "SUCCESS",
46
+ "136": "NON_PARTICIPATING",
47
+ "137": "NON_PARTICIPATING",
48
  "138": "SUCCESS",
49
  "139": "SUCCESS",
50
+ "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
+ "141": "NOT_ALIVE",
53
+ "142": "NON_PARTICIPATING",
54
+ "143": "FAIL",
55
+ "144": "FAIL",
56
+ "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
  "147": "SUCCESS",
59
  "148": "SUCCESS",
60
+ "149": "NOT_ALIVE",
61
+ "15": "FAIL",
62
+ "150": "NON_PARTICIPATING",
63
+ "151": "NOT_ALIVE",
64
+ "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
+ "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
68
+ "156": "NOT_ALIVE",
69
  "157": "SUCCESS",
70
  "158": "SUCCESS",
71
+ "159": "NON_PARTICIPATING",
72
+ "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
+ "161": "NOT_ALIVE",
75
+ "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
77
+ "164": "NON_PARTICIPATING",
78
+ "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
+ "167": "NOT_ALIVE",
81
+ "168": "NON_PARTICIPATING",
82
+ "169": "FAIL",
83
  "17": "SUCCESS",
84
+ "170": "NOT_ALIVE",
85
+ "171": "NON_PARTICIPATING",
86
+ "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
+ "174": "NOT_ALIVE",
89
+ "175": "NOT_ALIVE",
90
+ "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
+ "178": "NOT_ALIVE",
93
+ "179": "NOT_ALIVE",
94
+ "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
+ "181": "FAIL",
97
+ "182": "NON_PARTICIPATING",
98
+ "183": "NON_PARTICIPATING",
99
+ "184": "NOT_ALIVE",
100
  "185": "SUCCESS",
101
  "186": "SUCCESS",
102
+ "187": "FAIL",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
+ "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
  "191": "SUCCESS",
108
  "192": "SUCCESS",
109
  "193": "SUCCESS",
110
  "194": "SUCCESS",
111
+ "195": "FAIL",
112
+ "196": "NOT_ALIVE",
113
+ "197": "NOT_ALIVE",
114
+ "198": "NON_PARTICIPATING",
115
+ "199": "NOT_ALIVE",
116
  "2": "SUCCESS",
117
+ "20": "NOT_ALIVE",
118
+ "200": "NOT_ALIVE",
119
+ "201": "NOT_ALIVE",
120
+ "202": "NON_PARTICIPATING",
121
+ "203": "NOT_ALIVE",
122
  "204": "SUCCESS",
123
  "205": "SUCCESS",
124
  "206": "SUCCESS",
125
+ "207": "NOT_ALIVE",
126
+ "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
128
+ "21": "FAIL",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
  "212": "SUCCESS",
132
+ "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
+ "215": "NOT_ALIVE",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
+ "22": "NOT_ALIVE",
140
+ "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
+ "222": "FAIL",
143
+ "223": "NOT_ALIVE",
144
+ "224": "NOT_ALIVE",
145
  "225": "SUCCESS",
146
+ "226": "NOT_ALIVE",
147
+ "227": "NOT_ALIVE",
148
  "228": "SUCCESS",
149
+ "229": "NON_PARTICIPATING",
150
+ "23": "NOT_ALIVE",
151
+ "230": "NON_PARTICIPATING",
152
+ "231": "NON_PARTICIPATING",
153
+ "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
+ "235": "NOT_ALIVE",
157
+ "236": "NON_PARTICIPATING",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
+ "239": "NON_PARTICIPATING",
161
+ "24": "NOT_ALIVE",
162
+ "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
+ "242": "FAIL",
165
+ "243": "FAIL",
166
+ "244": "NON_PARTICIPATING",
167
+ "245": "NOT_ALIVE",
168
  "246": "SUCCESS",
169
+ "247": "NON_PARTICIPATING",
170
+ "248": "NOT_ALIVE",
171
+ "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "SUCCESS",
175
+ "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
+ "254": "NOT_ALIVE",
178
+ "255": "NOT_ALIVE",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
+ "28": "NON_PARTICIPATING",
182
+ "29": "NOT_ALIVE",
183
  "3": "SUCCESS",
184
  "30": "SUCCESS",
185
+ "31": "NOT_ALIVE",
186
+ "32": "NOT_ALIVE",
187
+ "33": "NOT_ALIVE",
188
+ "34": "NOT_ALIVE",
189
  "35": "SUCCESS",
190
  "36": "SUCCESS",
191
+ "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
  "39": "SUCCESS",
194
+ "4": "NOT_ALIVE",
195
  "40": "SUCCESS",
196
+ "41": "NON_PARTICIPATING",
197
+ "42": "NON_PARTICIPATING",
198
+ "43": "FAIL",
199
  "44": "SUCCESS",
200
+ "45": "NOT_ALIVE",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "SUCCESS",
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": "SUCCESS",
210
+ "54": "NOT_ALIVE",
211
+ "55": "NON_PARTICIPATING",
212
+ "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
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": "FAIL",
224
+ "67": "NOT_ALIVE",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "SUCCESS",
227
+ "7": "NOT_ALIVE",
228
+ "70": "NOT_ALIVE",
229
+ "71": "FAIL",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "SUCCESS",
232
  "74": "SUCCESS",
233
+ "75": "NOT_ALIVE",
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": "NOT_ALIVE",
241
+ "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
+ "84": "NON_PARTICIPATING",
244
+ "85": "NOT_ALIVE",
245
  "86": "SUCCESS",
246
  "87": "SUCCESS",
247
+ "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
+ "9": "NOT_ALIVE",
250
+ "90": "NOT_ALIVE",
251
+ "91": "NON_PARTICIPATING",
252
  "92": "SUCCESS",
253
  "93": "SUCCESS",
254
  "94": "SUCCESS",
255
+ "95": "NOT_ALIVE",
256
+ "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
+ "98": "NON_PARTICIPATING",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6326989,
268
+ 6327016
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": 9,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6326952,
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 sha256:3de8633f5c91079d8aaa2f1f8c211cb8c8a8750c707924c72ac6fe1e8cfd2e4e
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77252c50a9b8807c8696390f623e23f4301b4e3d048a17bbbe856ac96a9ee999
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fba58f77dff06ccf41807cf8a1300b11dd37df375ae01743cb68fb23ad13b8e
3
- size 4924926842
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33070887607f014b9eaf86d019c01386e4887ea9e39b0b757868e4099a8f89b9
3
+ size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f602db4d0beada5ec68c8fa84a4a15a84d6feea2788902ae4a103aa57e0e0cd7
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a42f92925a32a9097d20b65686a07e20072b108bb92c2e89c0e3d878d4c19e7b
3
  size 4400216536