zeras141a commited on
Commit
f72584f
·
verified ·
1 Parent(s): c188d31

Run 8. Outer Step 71. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +109 -111
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,85 +1,85 @@
1
  {
2
- "_name_or_path": "zeras141a/a2",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
  "101": "SUCCESS",
9
- "102": "FAIL",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
  "107": "SUCCESS",
15
- "108": "NON_PARTICIPATING",
16
- "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "SUCCESS",
20
- "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
- "115": "SUCCESS",
24
- "116": "SUCCESS",
25
  "117": "SUCCESS",
26
  "118": "NON_PARTICIPATING",
27
- "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
- "120": "SUCCESS",
30
  "121": "SUCCESS",
31
  "122": "SUCCESS",
32
- "123": "NOT_ALIVE",
33
- "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
- "126": "FAIL",
36
  "127": "SUCCESS",
37
- "128": "SUCCESS",
38
  "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
- "134": "NOT_ALIVE",
45
- "135": "NON_PARTICIPATING",
46
- "136": "SUCCESS",
47
- "137": "NON_PARTICIPATING",
48
- "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
- "141": "NON_PARTICIPATING",
53
- "142": "FAIL",
54
  "143": "NON_PARTICIPATING",
55
- "144": "SUCCESS",
56
- "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
- "147": "SUCCESS",
59
- "148": "NOT_ALIVE",
60
- "149": "NON_PARTICIPATING",
61
  "15": "SUCCESS",
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": "FAIL",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "SUCCESS",
75
- "162": "NON_PARTICIPATING",
76
- "163": "NON_PARTICIPATING",
77
  "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
- "167": "NON_PARTICIPATING",
81
- "168": "NOT_ALIVE",
82
- "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "SUCCESS",
@@ -93,66 +93,66 @@
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
- "181": "SUCCESS",
97
- "182": "SUCCESS",
98
- "183": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
- "185": "FAIL",
101
- "186": "FAIL",
102
- "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
- "189": "FAIL",
105
  "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
- "191": "NOT_ALIVE",
108
  "192": "SUCCESS",
109
- "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
- "196": "NON_PARTICIPATING",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NOT_ALIVE",
115
- "199": "SUCCESS",
116
- "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
  "202": "SUCCESS",
121
- "203": "SUCCESS",
122
  "204": "NON_PARTICIPATING",
123
- "205": "NON_PARTICIPATING",
124
- "206": "SUCCESS",
125
- "207": "NON_PARTICIPATING",
126
- "208": "SUCCESS",
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
- "210": "SUCCESS",
130
- "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "SUCCESS",
133
  "214": "SUCCESS",
134
- "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "SUCCESS",
138
- "219": "NON_PARTICIPATING",
139
  "22": "FAIL",
140
  "220": "SUCCESS",
141
- "221": "NOT_ALIVE",
142
- "222": "NON_PARTICIPATING",
143
- "223": "SUCCESS",
144
- "224": "NON_PARTICIPATING",
145
- "225": "NOT_ALIVE",
146
- "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
- "228": "NON_PARTICIPATING",
149
- "229": "SUCCESS",
150
- "23": "NOT_ALIVE",
151
- "230": "FAIL",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
- "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
@@ -164,99 +164,99 @@
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "SUCCESS",
167
- "245": "NON_PARTICIPATING",
168
- "246": "NOT_ALIVE",
169
- "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
- "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "SUCCESS",
174
  "251": "NON_PARTICIPATING",
175
  "252": "SUCCESS",
176
- "253": "FAIL",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
- "26": "SUCCESS",
180
- "27": "FAIL",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
- "3": "FAIL",
184
  "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
- "35": "NOT_ALIVE",
190
  "36": "SUCCESS",
191
  "37": "SUCCESS",
192
  "38": "NON_PARTICIPATING",
193
- "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
  "41": "FAIL",
197
- "42": "NOT_ALIVE",
198
- "43": "FAIL",
199
- "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "SUCCESS",
204
  "49": "NON_PARTICIPATING",
205
- "5": "FAIL",
206
- "50": "FAIL",
207
- "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
- "54": "NON_PARTICIPATING",
211
- "55": "FAIL",
212
  "56": "SUCCESS",
213
  "57": "SUCCESS",
214
  "58": "SUCCESS",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
- "61": "FAIL",
219
  "62": "NON_PARTICIPATING",
220
  "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
- "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
- "68": "NON_PARTICIPATING",
226
- "69": "SUCCESS",
227
- "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
- "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
- "74": "FAIL",
233
  "75": "NON_PARTICIPATING",
234
  "76": "SUCCESS",
235
- "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
- "82": "NON_PARTICIPATING",
242
  "83": "SUCCESS",
243
- "84": "NON_PARTICIPATING",
244
  "85": "SUCCESS",
245
- "86": "NON_PARTICIPATING",
246
- "87": "NOT_ALIVE",
247
  "88": "NON_PARTICIPATING",
248
- "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
- "93": "NOT_ALIVE",
254
- "94": "NON_PARTICIPATING",
255
  "95": "SUCCESS",
256
  "96": "SUCCESS",
257
  "97": "SUCCESS",
258
- "98": "NOT_ALIVE",
259
- "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,19 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6393744,
268
- 6393759,
269
- 6393778,
270
- 6393793
271
  ],
272
  "bos_token_id": 1,
273
  "eos_token_id": 2,
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
- "inner_step": 51,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6393230,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
1
  {
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": "SUCCESS",
9
+ "102": "SUCCESS",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
  "107": "SUCCESS",
15
+ "108": "SUCCESS",
16
+ "109": "FAIL",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "SUCCESS",
20
+ "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NON_PARTICIPATING",
23
+ "115": "FAIL",
24
+ "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "NON_PARTICIPATING",
27
+ "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
+ "120": "NON_PARTICIPATING",
30
  "121": "SUCCESS",
31
  "122": "SUCCESS",
32
+ "123": "SUCCESS",
33
+ "124": "SUCCESS",
34
  "125": "NOT_ALIVE",
35
+ "126": "NON_PARTICIPATING",
36
  "127": "SUCCESS",
37
+ "128": "FAIL",
38
  "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
+ "134": "NON_PARTICIPATING",
45
+ "135": "SUCCESS",
46
+ "136": "FAIL",
47
+ "137": "FAIL",
48
+ "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "FAIL",
52
+ "141": "NOT_ALIVE",
53
+ "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
+ "144": "NON_PARTICIPATING",
56
+ "145": "FAIL",
57
  "146": "NON_PARTICIPATING",
58
+ "147": "NON_PARTICIPATING",
59
+ "148": "NON_PARTICIPATING",
60
+ "149": "SUCCESS",
61
  "15": "SUCCESS",
62
  "150": "SUCCESS",
63
+ "151": "NOT_ALIVE",
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": "SUCCESS",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "SUCCESS",
75
+ "162": "SUCCESS",
76
+ "163": "SUCCESS",
77
  "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
+ "167": "SUCCESS",
81
+ "168": "SUCCESS",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "SUCCESS",
 
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
+ "181": "NON_PARTICIPATING",
97
+ "182": "NON_PARTICIPATING",
98
+ "183": "SUCCESS",
99
  "184": "SUCCESS",
100
+ "185": "SUCCESS",
101
+ "186": "NON_PARTICIPATING",
102
+ "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
+ "189": "SUCCESS",
105
  "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "FAIL",
108
  "192": "SUCCESS",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
+ "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NOT_ALIVE",
115
+ "199": "NON_PARTICIPATING",
116
+ "2": "SUCCESS",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
  "202": "SUCCESS",
121
+ "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
+ "205": "SUCCESS",
124
+ "206": "NOT_ALIVE",
125
+ "207": "NOT_ALIVE",
126
+ "208": "NON_PARTICIPATING",
127
  "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
+ "210": "NON_PARTICIPATING",
130
+ "211": "NOT_ALIVE",
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": "FAIL",
140
  "220": "SUCCESS",
141
+ "221": "NON_PARTICIPATING",
142
+ "222": "NOT_ALIVE",
143
+ "223": "FAIL",
144
+ "224": "NOT_ALIVE",
145
+ "225": "NON_PARTICIPATING",
146
+ "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
+ "228": "NOT_ALIVE",
149
+ "229": "NON_PARTICIPATING",
150
+ "23": "SUCCESS",
151
+ "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
+ "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
 
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "SUCCESS",
167
+ "245": "SUCCESS",
168
+ "246": "NON_PARTICIPATING",
169
+ "247": "SUCCESS",
170
  "248": "NON_PARTICIPATING",
171
+ "249": "SUCCESS",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NON_PARTICIPATING",
175
  "252": "SUCCESS",
176
+ "253": "SUCCESS",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "NON_PARTICIPATING",
180
+ "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
+ "3": "SUCCESS",
184
  "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
+ "34": "SUCCESS",
189
+ "35": "FAIL",
190
  "36": "SUCCESS",
191
  "37": "SUCCESS",
192
  "38": "NON_PARTICIPATING",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
  "41": "FAIL",
197
+ "42": "NON_PARTICIPATING",
198
+ "43": "NON_PARTICIPATING",
199
+ "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "SUCCESS",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "NOT_ALIVE",
206
+ "50": "NOT_ALIVE",
207
+ "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
+ "54": "SUCCESS",
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": "NON_PARTICIPATING",
220
  "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
+ "65": "FAIL",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
+ "68": "SUCCESS",
226
+ "69": "NON_PARTICIPATING",
227
+ "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "SUCCESS",
235
+ "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
+ "82": "SUCCESS",
242
  "83": "SUCCESS",
243
+ "84": "FAIL",
244
  "85": "SUCCESS",
245
+ "86": "NOT_ALIVE",
246
+ "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
+ "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
+ "90": "SUCCESS",
251
  "91": "NOT_ALIVE",
252
  "92": "SUCCESS",
253
+ "93": "NON_PARTICIPATING",
254
+ "94": "NOT_ALIVE",
255
  "95": "SUCCESS",
256
  "96": "SUCCESS",
257
  "97": "SUCCESS",
258
+ "98": "NON_PARTICIPATING",
259
+ "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6393908,
268
+ 6393922
 
 
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": 6393866,
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 sha256:993a46c9f8c8611e4bdbf50ba83777d890c8ae8cb1a027eba68c983ebb0fc372
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74957b245a7271e0c9af6c6c26ed05fdcd0cfda174ce5803db98fa032b94a523
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd1cef2441be77dd2b16de295f92508c564b492a6f7e2e537bfe1c078a595a67
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138b05af45ccbfc13919485a204f227ecd4b22120e2cf7288222aa6cc5d20872
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8341cba6421e051b75a2de843c56fb8fb37291096fb6acaf5899b4e1678fcaef
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:352f6726c38a90a3f859d63119f62148030fb632a6b757a710853574a41665ac
3
  size 4400216536