aalv2 commited on
Commit
8aef9c0
·
verified ·
1 Parent(s): 98ec2e3

Run 10. Outer Step 12. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +63 -63
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "_name_or_path": "aalv2/c70-h11",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "FAIL",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
- "102": "NOT_ALIVE",
10
  "103": "FAIL",
11
  "104": "NOT_ALIVE",
12
  "105": "FAIL",
@@ -17,10 +17,10 @@
17
  "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
  "111": "FAIL",
20
- "112": "FAIL",
21
- "113": "FAIL",
22
- "114": "NON_PARTICIPATING",
23
- "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
@@ -29,9 +29,9 @@
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
- "123": "FAIL",
33
  "124": "NON_PARTICIPATING",
34
- "125": "FAIL",
35
  "126": "FAIL",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
@@ -41,7 +41,7 @@
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
- "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
@@ -52,10 +52,10 @@
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
  "143": "NON_PARTICIPATING",
55
- "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "FAIL",
58
- "147": "FAIL",
59
  "148": "NON_PARTICIPATING",
60
  "149": "FAIL",
61
  "15": "FAIL",
@@ -63,23 +63,23 @@
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "FAIL",
66
- "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "FAIL",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
- "16": "NON_PARTICIPATING",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
- "162": "NOT_ALIVE",
76
  "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
- "167": "NOT_ALIVE",
81
- "168": "NOT_ALIVE",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NON_PARTICIPATING",
84
  "170": "FAIL",
85
  "171": "NOT_ALIVE",
@@ -88,76 +88,76 @@
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
- "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
- "184": "FAIL",
100
  "185": "FAIL",
101
  "186": "FAIL",
102
  "187": "NOT_ALIVE",
103
  "188": "FAIL",
104
  "189": "NOT_ALIVE",
105
- "19": "NON_PARTICIPATING",
106
- "190": "FAIL",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "FAIL",
113
- "197": "NOT_ALIVE",
114
- "198": "FAIL",
115
- "199": "FAIL",
116
  "2": "NON_PARTICIPATING",
117
- "20": "NON_PARTICIPATING",
118
  "200": "FAIL",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "NOT_ALIVE",
124
  "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "FAIL",
128
  "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
- "211": "NON_PARTICIPATING",
131
  "212": "FAIL",
132
- "213": "NOT_ALIVE",
133
- "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
  "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
  "221": "FAIL",
142
  "222": "FAIL",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
- "226": "NOT_ALIVE",
147
- "227": "NOT_ALIVE",
148
  "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
- "23": "FAIL",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
- "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
- "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
  "237": "FAIL",
159
  "238": "FAIL",
160
- "239": "NON_PARTICIPATING",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
@@ -165,21 +165,21 @@
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "FAIL",
168
- "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
- "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "FAIL",
180
  "27": "NOT_ALIVE",
181
  "28": "FAIL",
182
- "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
@@ -189,9 +189,9 @@
189
  "35": "FAIL",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
- "38": "NOT_ALIVE",
193
- "39": "NON_PARTICIPATING",
194
- "4": "FAIL",
195
  "40": "FAIL",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
@@ -199,11 +199,11 @@
199
  "44": "FAIL",
200
  "45": "NON_PARTICIPATING",
201
  "46": "FAIL",
202
- "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
- "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
@@ -212,20 +212,20 @@
212
  "56": "FAIL",
213
  "57": "NOT_ALIVE",
214
  "58": "NON_PARTICIPATING",
215
- "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "FAIL",
218
  "61": "NOT_ALIVE",
219
- "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
- "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "FAIL",
227
- "7": "NON_PARTICIPATING",
228
- "70": "NON_PARTICIPATING",
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
@@ -233,17 +233,17 @@
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
- "78": "NON_PARTICIPATING",
237
  "79": "NON_PARTICIPATING",
238
- "8": "FAIL",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NON_PARTICIPATING",
243
  "84": "FAIL",
244
- "85": "FAIL",
245
- "86": "FAIL",
246
- "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "FAIL",
@@ -253,9 +253,9 @@
253
  "93": "NOT_ALIVE",
254
  "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
- "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
- "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6473445,
268
- 6473473
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": 85,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6472423,
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": "FAIL",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
+ "102": "NON_PARTICIPATING",
10
  "103": "FAIL",
11
  "104": "NOT_ALIVE",
12
  "105": "FAIL",
 
17
  "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
  "111": "FAIL",
20
+ "112": "NOT_ALIVE",
21
+ "113": "NOT_ALIVE",
22
+ "114": "FAIL",
23
+ "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
 
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
 
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
+ "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
 
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
  "143": "NON_PARTICIPATING",
55
+ "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "FAIL",
58
+ "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "FAIL",
61
  "15": "FAIL",
 
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "FAIL",
66
+ "154": "FAIL",
67
  "155": "NON_PARTICIPATING",
68
  "156": "FAIL",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
+ "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
+ "162": "NON_PARTICIPATING",
76
  "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NOT_ALIVE",
80
+ "167": "NON_PARTICIPATING",
81
+ "168": "FAIL",
82
+ "169": "FAIL",
83
  "17": "NON_PARTICIPATING",
84
  "170": "FAIL",
85
  "171": "NOT_ALIVE",
 
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
+ "177": "FAIL",
92
  "178": "NOT_ALIVE",
93
+ "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
+ "184": "NOT_ALIVE",
100
  "185": "FAIL",
101
  "186": "FAIL",
102
  "187": "NOT_ALIVE",
103
  "188": "FAIL",
104
  "189": "NOT_ALIVE",
105
+ "19": "NOT_ALIVE",
106
+ "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "FAIL",
113
+ "197": "NON_PARTICIPATING",
114
+ "198": "NOT_ALIVE",
115
+ "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
+ "20": "FAIL",
118
  "200": "FAIL",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
+ "205": "FAIL",
124
  "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "FAIL",
128
  "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "FAIL",
131
  "212": "FAIL",
132
+ "213": "NON_PARTICIPATING",
133
+ "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
  "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
  "221": "FAIL",
142
  "222": "FAIL",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "NON_PARTICIPATING",
147
+ "227": "FAIL",
148
  "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
+ "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
+ "232": "FAIL",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "FAIL",
159
  "238": "FAIL",
160
+ "239": "NOT_ALIVE",
161
  "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
 
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "FAIL",
168
+ "246": "NOT_ALIVE",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
+ "254": "FAIL",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "NOT_ALIVE",
180
  "27": "NOT_ALIVE",
181
  "28": "FAIL",
182
+ "29": "FAIL",
183
  "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
 
189
  "35": "FAIL",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
+ "39": "FAIL",
194
+ "4": "NOT_ALIVE",
195
  "40": "FAIL",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
 
199
  "44": "FAIL",
200
  "45": "NON_PARTICIPATING",
201
  "46": "FAIL",
202
+ "47": "FAIL",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
+ "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
 
212
  "56": "FAIL",
213
  "57": "NOT_ALIVE",
214
  "58": "NON_PARTICIPATING",
215
+ "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "FAIL",
218
  "61": "NOT_ALIVE",
219
+ "62": "NON_PARTICIPATING",
220
  "63": "NOT_ALIVE",
221
+ "64": "FAIL",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "FAIL",
227
+ "7": "NOT_ALIVE",
228
+ "70": "FAIL",
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
 
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
+ "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
+ "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NON_PARTICIPATING",
243
  "84": "FAIL",
244
+ "85": "NON_PARTICIPATING",
245
+ "86": "NOT_ALIVE",
246
+ "87": "NOT_ALIVE",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "FAIL",
 
253
  "93": "NOT_ALIVE",
254
  "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
+ "96": "NOT_ALIVE",
257
  "97": "NON_PARTICIPATING",
258
+ "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6473636,
268
+ 6473664
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": 6473589,
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 sha256:41e9851e155ac8d24f7d0c8985fec057f1ae9e2ed04644beab33d3dfaf31a30e
3
  size 88390091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f229d2a50d0548df518214d4c1d2919886cd92a5d6d789df376228469bc0cd22
3
  size 88390091
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:350c22b460048cc01f7eea2d982121bf2f96f3a970277baf4f35251fece950d3
3
  size 4924928111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:803d113e3f3159ff3774908a3a771a4fcd84f9111157bc0d64443f2c16f03d14
3
  size 4924928111
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5b266306e6ff56a093fe1afdb6a4c86de6b20b1e115d8854f967452ae1b8452
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccca3ed32d7db41aab33174696fb9d42561f171eaa15192b70bbd8122b71cbca
3
  size 4400216536