zeras141a commited on
Commit
bda51f8
·
verified ·
1 Parent(s): 53a1a5a

Run 8. Outer Step 123. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +80 -80
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,55 +2,55 @@
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": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
- "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
- "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
- "111": "NOT_ALIVE",
20
  "112": "SUCCESS",
21
  "113": "NON_PARTICIPATING",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
- "117": "SUCCESS",
26
- "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
- "12": "SUCCESS",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
  "123": "NON_PARTICIPATING",
33
- "124": "NON_PARTICIPATING",
34
- "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
- "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NOT_ALIVE",
46
- "136": "NOT_ALIVE",
47
  "137": "NON_PARTICIPATING",
48
- "138": "NOT_ALIVE",
49
- "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
- "142": "NON_PARTICIPATING",
54
  "143": "SUCCESS",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
@@ -61,64 +61,64 @@
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
- "152": "SUCCESS",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
- "158": "FAIL",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
- "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
- "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
  "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
- "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
  "173": "FAIL",
88
  "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "NON_PARTICIPATING",
92
  "178": "NON_PARTICIPATING",
93
- "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NON_PARTICIPATING",
97
  "182": "SUCCESS",
98
  "183": "SUCCESS",
99
  "184": "SUCCESS",
100
- "185": "FAIL",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "NON_PARTICIPATING",
107
  "191": "NON_PARTICIPATING",
108
- "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
- "194": "SUCCESS",
111
- "195": "NON_PARTICIPATING",
112
- "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "NON_PARTICIPATING",
119
  "201": "SUCCESS",
120
- "202": "NON_PARTICIPATING",
121
- "203": "SUCCESS",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NOT_ALIVE",
@@ -127,7 +127,7 @@
127
  "209": "SUCCESS",
128
  "21": "SUCCESS",
129
  "210": "SUCCESS",
130
- "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "SUCCESS",
133
  "214": "SUCCESS",
@@ -135,28 +135,28 @@
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "SUCCESS",
138
- "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
- "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
- "225": "NON_PARTICIPATING",
146
- "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
- "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
- "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
- "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
@@ -164,14 +164,14 @@
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
- "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
- "247": "FAIL",
170
  "248": "SUCCESS",
171
- "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NOT_ALIVE",
174
- "251": "SUCCESS",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
@@ -182,10 +182,10 @@
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
- "31": "NON_PARTICIPATING",
186
- "32": "NON_PARTICIPATING",
187
  "33": "NON_PARTICIPATING",
188
- "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
  "36": "SUCCESS",
191
  "37": "NON_PARTICIPATING",
@@ -195,11 +195,11 @@
195
  "40": "SUCCESS",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
- "43": "NOT_ALIVE",
199
  "44": "NOT_ALIVE",
200
- "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
- "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
@@ -208,55 +208,55 @@
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
- "55": "NOT_ALIVE",
212
- "56": "NOT_ALIVE",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
- "6": "SUCCESS",
217
- "60": "NOT_ALIVE",
218
  "61": "SUCCESS",
219
  "62": "NOT_ALIVE",
220
- "63": "NON_PARTICIPATING",
221
- "64": "NOT_ALIVE",
222
- "65": "FAIL",
223
  "66": "NOT_ALIVE",
224
- "67": "NON_PARTICIPATING",
225
- "68": "SUCCESS",
226
  "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
- "70": "NOT_ALIVE",
229
  "71": "FAIL",
230
- "72": "NON_PARTICIPATING",
231
- "73": "NON_PARTICIPATING",
232
- "74": "SUCCESS",
233
- "75": "NOT_ALIVE",
234
- "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
- "81": "NOT_ALIVE",
241
- "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
- "86": "NON_PARTICIPATING",
246
- "87": "SUCCESS",
247
- "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "SUCCESS",
252
- "92": "NON_PARTICIPATING",
253
- "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
- "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NOT_ALIVE",
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
- 6441300,
268
- 6441308
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": 142,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6440668,
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": "NOT_ALIVE",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
+ "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
+ "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "NON_PARTICIPATING",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "NON_PARTICIPATING",
26
+ "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
+ "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NOT_ALIVE",
32
  "123": "NON_PARTICIPATING",
33
+ "124": "NOT_ALIVE",
34
+ "125": "FAIL",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
+ "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NOT_ALIVE",
46
+ "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "NON_PARTICIPATING",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
+ "142": "NOT_ALIVE",
54
  "143": "SUCCESS",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
 
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
+ "158": "SUCCESS",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
+ "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
+ "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
  "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
+ "171": "SUCCESS",
86
  "172": "NON_PARTICIPATING",
87
  "173": "FAIL",
88
  "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
+ "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
+ "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NON_PARTICIPATING",
97
  "182": "SUCCESS",
98
  "183": "SUCCESS",
99
  "184": "SUCCESS",
100
+ "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
+ "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
+ "194": "NON_PARTICIPATING",
111
+ "195": "SUCCESS",
112
+ "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "SUCCESS",
119
  "201": "SUCCESS",
120
+ "202": "NOT_ALIVE",
121
+ "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NOT_ALIVE",
 
127
  "209": "SUCCESS",
128
  "21": "SUCCESS",
129
  "210": "SUCCESS",
130
+ "211": "FAIL",
131
  "212": "NON_PARTICIPATING",
132
  "213": "SUCCESS",
133
  "214": "SUCCESS",
 
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "SUCCESS",
138
+ "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
+ "220": "SUCCESS",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "SUCCESS",
146
+ "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
+ "230": "NOT_ALIVE",
152
+ "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
+ "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
 
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
+ "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "SUCCESS",
170
  "248": "SUCCESS",
171
+ "249": "SUCCESS",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
+ "251": "FAIL",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
 
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
+ "31": "NOT_ALIVE",
186
+ "32": "NOT_ALIVE",
187
  "33": "NON_PARTICIPATING",
188
+ "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
  "36": "SUCCESS",
191
  "37": "NON_PARTICIPATING",
 
195
  "40": "SUCCESS",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
+ "43": "SUCCESS",
199
  "44": "NOT_ALIVE",
200
+ "45": "SUCCESS",
201
  "46": "NON_PARTICIPATING",
202
+ "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
 
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
+ "55": "NON_PARTICIPATING",
212
+ "56": "NON_PARTICIPATING",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
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": "SUCCESS",
223
  "66": "NOT_ALIVE",
224
+ "67": "NOT_ALIVE",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
+ "70": "NON_PARTICIPATING",
229
  "71": "FAIL",
230
+ "72": "SUCCESS",
231
+ "73": "NOT_ALIVE",
232
+ "74": "FAIL",
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": "NOT_ALIVE",
240
+ "81": "NON_PARTICIPATING",
241
+ "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
+ "86": "SUCCESS",
246
+ "87": "FAIL",
247
+ "88": "SUCCESS",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "SUCCESS",
252
+ "92": "NOT_ALIVE",
253
+ "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
+ "96": "FAIL",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NOT_ALIVE",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6441350,
268
+ 6441374
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": 5,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6441307,
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 sha256:94cd706b70a33e25ab54f5f0cf8b7f064516423a234a4fb9b523c0c905b555ab
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7351222525579503e9242e47154a3df427817d0bd762a6fcc4989de822e485
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54cbee551f5456830985e356d8dcf1c0856436eb30c1bb8596f2b124efff07b3
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72ede3074e3b383a3116d64c71fb60c53469608d33b348ae5d2208d3283e93f6
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bec86b320c391c87b6b4bf1a102045dacce871c9bab1f75ca11b11f15453c669
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087e470acac9921201dd48e9d26541c74c95af0c108cf0c575d117eafc9a499e
3
  size 4400216536