zeras141a commited on
Commit
ef1eb89
·
verified ·
1 Parent(s): ed892fa

Run 8. Outer Step 64. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +108 -111
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,173 +1,173 @@
1
  {
2
- "_name_or_path": "zeras141a/a2",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "NON_PARTICIPATING",
9
- "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
- "104": "FAIL",
12
  "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
- "107": "SUCCESS",
15
  "108": "SUCCESS",
16
- "109": "NOT_ALIVE",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
- "111": "NOT_ALIVE",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
- "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
- "117": "SUCCESS",
26
- "118": "NOT_ALIVE",
27
- "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
- "120": "NON_PARTICIPATING",
30
- "121": "NON_PARTICIPATING",
31
  "122": "SUCCESS",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
- "127": "FAIL",
37
- "128": "SUCCESS",
38
  "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
- "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
- "133": "NON_PARTICIPATING",
44
- "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
- "136": "SUCCESS",
47
- "137": "SUCCESS",
48
- "138": "NON_PARTICIPATING",
49
- "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
- "141": "NON_PARTICIPATING",
53
  "142": "FAIL",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
- "145": "NOT_ALIVE",
57
- "146": "NOT_ALIVE",
58
  "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
- "149": "FAIL",
61
- "15": "FAIL",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
65
- "153": "NON_PARTICIPATING",
66
- "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NOT_ALIVE",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
- "161": "SUCCESS",
75
- "162": "NON_PARTICIPATING",
76
- "163": "NOT_ALIVE",
77
- "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
- "166": "NOT_ALIVE",
80
- "167": "SUCCESS",
81
  "168": "SUCCESS",
82
  "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
- "171": "SUCCESS",
86
- "172": "FAIL",
87
  "173": "SUCCESS",
88
  "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
- "178": "FAIL",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
- "180": "SUCCESS",
96
  "181": "SUCCESS",
97
- "182": "SUCCESS",
98
  "183": "FAIL",
99
  "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
  "186": "SUCCESS",
102
- "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "NON_PARTICIPATING",
107
- "191": "SUCCESS",
108
  "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
- "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
- "199": "FAIL",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
- "202": "NON_PARTICIPATING",
121
- "203": "SUCCESS",
122
- "204": "SUCCESS",
123
- "205": "NON_PARTICIPATING",
124
- "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
- "208": "NON_PARTICIPATING",
127
- "209": "SUCCESS",
128
  "21": "SUCCESS",
129
- "210": "NOT_ALIVE",
130
  "211": "SUCCESS",
131
- "212": "FAIL",
132
  "213": "SUCCESS",
133
  "214": "SUCCESS",
134
- "215": "NOT_ALIVE",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "SUCCESS",
138
- "219": "FAIL",
139
- "22": "SUCCESS",
140
- "220": "SUCCESS",
141
- "221": "SUCCESS",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
- "226": "NOT_ALIVE",
147
- "227": "NOT_ALIVE",
148
- "228": "NON_PARTICIPATING",
149
- "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "FAIL",
152
- "231": "NON_PARTICIPATING",
153
- "232": "SUCCESS",
154
  "233": "SUCCESS",
155
- "234": "FAIL",
156
- "235": "SUCCESS",
157
  "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
- "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
- "243": "NON_PARTICIPATING",
166
  "244": "SUCCESS",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
- "247": "FAIL",
170
- "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
@@ -181,53 +181,53 @@
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
- "30": "FAIL",
185
- "31": "SUCCESS",
186
- "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
- "34": "NOT_ALIVE",
189
- "35": "NOT_ALIVE",
190
- "36": "SUCCESS",
191
  "37": "SUCCESS",
192
- "38": "NON_PARTICIPATING",
193
- "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
- "41": "SUCCESS",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
- "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
- "49": "NON_PARTICIPATING",
205
  "5": "FAIL",
206
  "50": "FAIL",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
- "54": "SUCCESS",
211
- "55": "NON_PARTICIPATING",
212
  "56": "SUCCESS",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
- "64": "SUCCESS",
222
- "65": "SUCCESS",
223
- "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "NOT_ALIVE",
226
- "69": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
  "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
@@ -240,22 +240,22 @@
240
  "81": "NON_PARTICIPATING",
241
  "82": "SUCCESS",
242
  "83": "SUCCESS",
243
- "84": "NOT_ALIVE",
244
- "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
- "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
- "90": "FAIL",
251
  "91": "NOT_ALIVE",
252
- "92": "NOT_ALIVE",
253
- "93": "NOT_ALIVE",
254
  "94": "NOT_ALIVE",
255
  "95": "NON_PARTICIPATING",
256
  "96": "SUCCESS",
257
  "97": "SUCCESS",
258
- "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,20 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6385609,
268
- 6385622,
269
- 6385634,
270
- 6385649,
271
- 6385664
272
  ],
273
  "bos_token_id": 1,
274
  "eos_token_id": 2,
275
  "hidden_act": "silu",
276
  "hidden_size": 2048,
277
  "initializer_range": 0.02,
278
- "inner_step": 132,
279
  "intermediate_size": 5632,
280
- "last_allreduce_block": 6382929,
281
  "max_position_embeddings": 2048,
282
  "mlp_bias": false,
283
  "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": "NOT_ALIVE",
8
+ "101": "FAIL",
9
+ "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
+ "104": "NON_PARTICIPATING",
12
  "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
+ "107": "NON_PARTICIPATING",
15
  "108": "SUCCESS",
16
+ "109": "SUCCESS",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
+ "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
+ "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "NOT_ALIVE",
26
+ "118": "NON_PARTICIPATING",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
+ "120": "NOT_ALIVE",
30
+ "121": "SUCCESS",
31
  "122": "SUCCESS",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
+ "127": "SUCCESS",
37
+ "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
+ "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
+ "133": "SUCCESS",
44
+ "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
+ "136": "FAIL",
47
+ "137": "NON_PARTICIPATING",
48
+ "138": "NOT_ALIVE",
49
+ "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
+ "140": "SUCCESS",
52
+ "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
+ "145": "SUCCESS",
57
+ "146": "NON_PARTICIPATING",
58
  "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "SUCCESS",
61
+ "15": "SUCCESS",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
65
+ "153": "NOT_ALIVE",
66
+ "154": "FAIL",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
+ "162": "FAIL",
76
+ "163": "SUCCESS",
77
+ "164": "SUCCESS",
78
  "165": "SUCCESS",
79
+ "166": "NON_PARTICIPATING",
80
+ "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
  "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
+ "171": "NON_PARTICIPATING",
86
+ "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
  "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
+ "178": "SUCCESS",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
  "181": "SUCCESS",
97
+ "182": "NOT_ALIVE",
98
  "183": "FAIL",
99
  "184": "SUCCESS",
100
+ "185": "FAIL",
101
  "186": "SUCCESS",
102
+ "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
+ "190": "FAIL",
107
+ "191": "NOT_ALIVE",
108
  "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
+ "196": "FAIL",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
+ "202": "FAIL",
121
+ "203": "NON_PARTICIPATING",
122
+ "204": "NON_PARTICIPATING",
123
+ "205": "SUCCESS",
124
+ "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
+ "208": "SUCCESS",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
+ "212": "SUCCESS",
132
  "213": "SUCCESS",
133
  "214": "SUCCESS",
134
+ "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "NOT_ALIVE",
138
+ "219": "NON_PARTICIPATING",
139
+ "22": "NOT_ALIVE",
140
+ "220": "FAIL",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
+ "226": "NON_PARTICIPATING",
147
+ "227": "NON_PARTICIPATING",
148
+ "228": "NOT_ALIVE",
149
+ "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "FAIL",
152
+ "231": "NOT_ALIVE",
153
+ "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
+ "234": "SUCCESS",
156
+ "235": "NOT_ALIVE",
157
  "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
+ "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
+ "243": "NOT_ALIVE",
166
  "244": "SUCCESS",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "NON_PARTICIPATING",
170
+ "248": "FAIL",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
 
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
+ "30": "SUCCESS",
185
+ "31": "NON_PARTICIPATING",
186
+ "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
+ "34": "SUCCESS",
189
+ "35": "FAIL",
190
+ "36": "FAIL",
191
  "37": "SUCCESS",
192
+ "38": "SUCCESS",
193
+ "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
+ "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
+ "49": "SUCCESS",
205
  "5": "FAIL",
206
  "50": "FAIL",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
+ "54": "FAIL",
211
+ "55": "SUCCESS",
212
  "56": "SUCCESS",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
+ "64": "NON_PARTICIPATING",
222
+ "65": "NON_PARTICIPATING",
223
+ "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "SUCCESS",
226
+ "69": "NOT_ALIVE",
227
  "7": "SUCCESS",
228
  "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
 
240
  "81": "NON_PARTICIPATING",
241
  "82": "SUCCESS",
242
  "83": "SUCCESS",
243
+ "84": "SUCCESS",
244
+ "85": "FAIL",
245
  "86": "NOT_ALIVE",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
+ "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "SUCCESS",
251
  "91": "NOT_ALIVE",
252
+ "92": "NON_PARTICIPATING",
253
+ "93": "NON_PARTICIPATING",
254
  "94": "NOT_ALIVE",
255
  "95": "NON_PARTICIPATING",
256
  "96": "SUCCESS",
257
  "97": "SUCCESS",
258
+ "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6385830,
268
+ 6385882
 
 
 
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": 3,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6385832,
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:eba02d9a763f8a67eb99610c21f34f8e7a3901e595f54800a7def9b2ebada115
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1b7619fc63a2bda5b35d516d2b558660624882ff695b2c88b6f19479a82d69e
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4eb6fe04f001b03a97ae2d2fe10b74d92339ff55a7d63017ad0a73fc9d56db07
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d16e3c1b64d1eee49cf7443830b54abde3f34c9a1d1d726ae3cd6c1fe025f5e3
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c1f4aa2fe65f8e8fb764ba86e7bbe1f429e9a84e6c13fb97c0a9411175ddbf5
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eaa8ec0365e50b5b2a38137acc1d8659a789598b1dcb0c56397e2689a2a6096
3
  size 4400216536