snoopsy commited on
Commit
ca8157b
·
verified ·
1 Parent(s): b81379b

Run 8. Outer Step 41. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +115 -115
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,115 +1,115 @@
1
  {
2
- "_name_or_path": "snoopsy/zza1",
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": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
- "105": "SUCCESS",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
- "110": "NON_PARTICIPATING",
19
- "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
- "115": "FAIL",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "FAIL",
31
- "122": "NON_PARTICIPATING",
32
- "123": "SUCCESS",
33
- "124": "FAIL",
34
  "125": "NOT_ALIVE",
35
- "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
- "128": "SUCCESS",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
- "132": "FAIL",
43
- "133": "SUCCESS",
44
- "134": "NOT_ALIVE",
45
- "135": "NOT_ALIVE",
46
- "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "FAIL",
49
- "139": "SUCCESS",
50
- "14": "SUCCESS",
51
- "140": "FAIL",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
- "143": "FAIL",
55
  "144": "SUCCESS",
56
  "145": "SUCCESS",
57
- "146": "SUCCESS",
58
- "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
- "149": "SUCCESS",
61
  "15": "SUCCESS",
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
- "152": "NOT_ALIVE",
65
- "153": "FAIL",
66
  "154": "NOT_ALIVE",
67
- "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "SUCCESS",
71
- "159": "NOT_ALIVE",
72
- "16": "SUCCESS",
73
- "160": "NOT_ALIVE",
74
  "161": "FAIL",
75
- "162": "NOT_ALIVE",
76
  "163": "FAIL",
77
- "164": "NON_PARTICIPATING",
78
- "165": "FAIL",
79
- "166": "SUCCESS",
80
  "167": "NON_PARTICIPATING",
81
- "168": "FAIL",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
- "173": "FAIL",
88
- "174": "NON_PARTICIPATING",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
- "177": "FAIL",
92
  "178": "NON_PARTICIPATING",
93
- "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
- "181": "FAIL",
97
  "182": "NOT_ALIVE",
98
- "183": "FAIL",
99
  "184": "NOT_ALIVE",
100
- "185": "SUCCESS",
101
- "186": "NON_PARTICIPATING",
102
- "187": "SUCCESS",
103
  "188": "FAIL",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
- "191": "SUCCESS",
108
- "192": "SUCCESS",
109
- "193": "SUCCESS",
110
- "194": "SUCCESS",
111
- "195": "FAIL",
112
- "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "SUCCESS",
@@ -117,89 +117,89 @@
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
- "202": "NON_PARTICIPATING",
121
  "203": "FAIL",
122
- "204": "FAIL",
123
- "205": "FAIL",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
- "208": "SUCCESS",
127
- "209": "FAIL",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
- "211": "FAIL",
131
- "212": "FAIL",
132
  "213": "NON_PARTICIPATING",
133
- "214": "SUCCESS",
134
- "215": "SUCCESS",
135
  "216": "SUCCESS",
136
- "217": "FAIL",
137
  "218": "FAIL",
138
- "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
- "220": "FAIL",
141
- "221": "FAIL",
142
- "222": "FAIL",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
- "225": "FAIL",
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": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
- "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "FAIL",
161
- "24": "SUCCESS",
162
- "240": "SUCCESS",
163
- "241": "FAIL",
164
- "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
- "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "FAIL",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
- "252": "FAIL",
176
- "253": "FAIL",
177
- "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
- "28": "FAIL",
182
  "29": "NOT_ALIVE",
183
- "3": "SUCCESS",
184
- "30": "NON_PARTICIPATING",
185
- "31": "NON_PARTICIPATING",
186
  "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "FAIL",
190
- "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "SUCCESS",
197
  "42": "NOT_ALIVE",
198
- "43": "FAIL",
199
  "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
- "46": "FAIL",
202
- "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
  "5": "FAIL",
@@ -208,53 +208,53 @@
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
- "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
- "58": "SUCCESS",
215
- "59": "SUCCESS",
216
- "6": "SUCCESS",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
- "63": "SUCCESS",
221
- "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
- "69": "SUCCESS",
227
- "7": "FAIL",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
- "74": "SUCCESS",
233
  "75": "NOT_ALIVE",
234
  "76": "FAIL",
235
- "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
- "79": "FAIL",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
- "84": "FAIL",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
- "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
- "91": "FAIL",
252
- "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
- "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
- "97": "FAIL",
258
  "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6368011,
268
- 6368022
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": 660,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6361535,
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": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
+ "100": "NON_PARTICIPATING",
8
+ "101": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NON_PARTICIPATING",
12
+ "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
+ "110": "SUCCESS",
19
+ "111": "NOT_ALIVE",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
23
+ "115": "SUCCESS",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "NOT_ALIVE",
31
+ "122": "FAIL",
32
+ "123": "NON_PARTICIPATING",
33
+ "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
+ "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
+ "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "NOT_ALIVE",
43
+ "133": "NOT_ALIVE",
44
+ "134": "NON_PARTICIPATING",
45
+ "135": "SUCCESS",
46
+ "136": "NOT_ALIVE",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "NON_PARTICIPATING",
65
+ "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
+ "155": "FAIL",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NON_PARTICIPATING",
71
+ "159": "NON_PARTICIPATING",
72
+ "16": "NOT_ALIVE",
73
+ "160": "NON_PARTICIPATING",
74
  "161": "FAIL",
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": "NOT_ALIVE",
82
+ "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "SUCCESS",
88
+ "174": "SUCCESS",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
+ "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
+ "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
+ "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
+ "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
+ "185": "NOT_ALIVE",
101
+ "186": "SUCCESS",
102
+ "187": "NOT_ALIVE",
103
  "188": "FAIL",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "FAIL",
108
+ "192": "FAIL",
109
+ "193": "NON_PARTICIPATING",
110
+ "194": "NON_PARTICIPATING",
111
+ "195": "NON_PARTICIPATING",
112
+ "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "SUCCESS",
 
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
+ "202": "FAIL",
121
  "203": "FAIL",
122
+ "204": "NOT_ALIVE",
123
+ "205": "SUCCESS",
124
+ "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
+ "208": "NOT_ALIVE",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "NON_PARTICIPATING",
131
+ "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "NON_PARTICIPATING",
134
+ "215": "FAIL",
135
  "216": "SUCCESS",
136
+ "217": "SUCCESS",
137
  "218": "FAIL",
138
+ "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
+ "221": "SUCCESS",
142
+ "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
+ "227": "NON_PARTICIPATING",
148
+ "228": "SUCCESS",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "FAIL",
152
+ "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
+ "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "FAIL",
161
+ "24": "NOT_ALIVE",
162
+ "240": "NON_PARTICIPATING",
163
+ "241": "SUCCESS",
164
+ "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "FAIL",
170
  "248": "NOT_ALIVE",
171
  "249": "FAIL",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
+ "252": "NOT_ALIVE",
176
+ "253": "SUCCESS",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "NOT_ALIVE",
180
  "27": "SUCCESS",
181
+ "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
+ "3": "FAIL",
184
+ "30": "SUCCESS",
185
+ "31": "NOT_ALIVE",
186
  "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "FAIL",
190
+ "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "FAIL",
197
  "42": "NOT_ALIVE",
198
+ "43": "NON_PARTICIPATING",
199
  "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
+ "46": "NON_PARTICIPATING",
202
+ "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
  "5": "FAIL",
 
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": "NOT_ALIVE",
216
+ "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
+ "63": "NON_PARTICIPATING",
221
+ "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
+ "69": "NON_PARTICIPATING",
227
+ "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
+ "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
  "76": "FAIL",
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": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
+ "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
+ "87": "NOT_ALIVE",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
+ "91": "NON_PARTICIPATING",
252
+ "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
+ "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6368222,
268
+ 6368237
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": 6368189,
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:cb3b18998eb2a0835a4fd7e6273f5ba55e6d4f5ebc7374c5928bae61017f2316
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8137d2baa89cb6db89f2bcd5e6f3de7370d92a5fb7033a468acba7574c885a1e
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b44ff8bd534046a317a1e2fb5ad88c7678c9fb325b2306239be38497de3aa455
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94bc86a782e66470b2ae90df6b5742eaf054d6d275b715a323d9b1787ddb769
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9333ec4ebefefbe28fc9a26605f291ff22f4def3c33fd7e0c5a09b3f4b355adb
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ae66b8dc1b6ff655dcf398a769ebad4b4dc4ce0d9be11505414cd03ba926ac7
3
  size 4400216536