snoopsy commited on
Commit
36235f4
·
verified ·
1 Parent(s): b01db96

Run 8. Outer Step 54. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +129 -129
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,32 +1,32 @@
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": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
- "103": "NOT_ALIVE",
11
- "104": "FAIL",
12
  "105": "NOT_ALIVE",
13
  "106": "FAIL",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
- "109": "NOT_ALIVE",
17
- "11": "NOT_ALIVE",
18
- "110": "NON_PARTICIPATING",
19
- "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "SUCCESS",
26
- "118": "SUCCESS",
27
- "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
- "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "SUCCESS",
32
  "123": "SUCCESS",
@@ -34,228 +34,228 @@
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
  "127": "SUCCESS",
37
- "128": "SUCCESS",
38
- "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
  "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
- "132": "FAIL",
43
  "133": "FAIL",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
47
- "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
- "139": "SUCCESS",
50
- "14": "SUCCESS",
51
- "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
- "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
- "145": "SUCCESS",
57
- "146": "SUCCESS",
58
  "147": "SUCCESS",
59
- "148": "SUCCESS",
60
  "149": "SUCCESS",
61
- "15": "NOT_ALIVE",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
- "152": "NON_PARTICIPATING",
65
- "153": "SUCCESS",
66
- "154": "NOT_ALIVE",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
71
- "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
- "162": "NOT_ALIVE",
76
- "163": "NOT_ALIVE",
77
- "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
- "168": "NOT_ALIVE",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
- "170": "SUCCESS",
85
  "171": "SUCCESS",
86
- "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
- "174": "FAIL",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "NOT_ALIVE",
92
- "178": "FAIL",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
  "182": "SUCCESS",
98
- "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
- "185": "NOT_ALIVE",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
- "189": "NOT_ALIVE",
105
- "19": "NOT_ALIVE",
106
- "190": "FAIL",
107
- "191": "SUCCESS",
108
- "192": "SUCCESS",
109
- "193": "NOT_ALIVE",
110
- "194": "NOT_ALIVE",
111
  "195": "SUCCESS",
112
  "196": "SUCCESS",
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": "NOT_ALIVE",
120
- "202": "FAIL",
121
- "203": "NON_PARTICIPATING",
122
- "204": "FAIL",
123
  "205": "SUCCESS",
124
- "206": "FAIL",
125
  "207": "NON_PARTICIPATING",
126
- "208": "SUCCESS",
127
  "209": "SUCCESS",
128
  "21": "SUCCESS",
129
- "210": "NOT_ALIVE",
130
  "211": "SUCCESS",
131
  "212": "SUCCESS",
132
- "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
- "216": "SUCCESS",
136
  "217": "FAIL",
137
- "218": "NOT_ALIVE",
138
  "219": "FAIL",
139
- "22": "FAIL",
140
- "220": "FAIL",
141
- "221": "SUCCESS",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
- "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "FAIL",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
- "230": "FAIL",
152
- "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
- "233": "NON_PARTICIPATING",
155
- "234": "SUCCESS",
156
- "235": "NOT_ALIVE",
157
- "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
- "238": "FAIL",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
- "241": "NON_PARTICIPATING",
164
- "242": "NON_PARTICIPATING",
165
- "243": "NOT_ALIVE",
166
  "244": "SUCCESS",
167
- "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
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": "SUCCESS",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
- "255": "NON_PARTICIPATING",
179
- "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
- "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
- "30": "NOT_ALIVE",
185
- "31": "SUCCESS",
186
- "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "NOT_ALIVE",
190
- "36": "NOT_ALIVE",
191
- "37": "NOT_ALIVE",
192
- "38": "SUCCESS",
193
- "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
- "40": "NOT_ALIVE",
196
- "41": "NOT_ALIVE",
197
- "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
- "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
- "5": "NOT_ALIVE",
206
- "50": "NOT_ALIVE",
207
- "51": "NOT_ALIVE",
208
- "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
- "55": "NOT_ALIVE",
212
- "56": "NON_PARTICIPATING",
213
- "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
- "6": "FAIL",
217
- "60": "NOT_ALIVE",
218
- "61": "NOT_ALIVE",
219
- "62": "NOT_ALIVE",
220
- "63": "NON_PARTICIPATING",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
- "66": "SUCCESS",
224
- "67": "NOT_ALIVE",
225
- "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
- "7": "NOT_ALIVE",
228
- "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
- "74": "FAIL",
233
- "75": "NOT_ALIVE",
234
- "76": "NOT_ALIVE",
235
- "77": "SUCCESS",
236
- "78": "NOT_ALIVE",
237
- "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
- "81": "NOT_ALIVE",
241
- "82": "SUCCESS",
242
  "83": "NON_PARTICIPATING",
243
- "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
- "87": "NOT_ALIVE",
247
- "88": "NOT_ALIVE",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
- "90": "FAIL",
251
- "91": "NON_PARTICIPATING",
252
  "92": "NOT_ALIVE",
253
- "93": "NOT_ALIVE",
254
  "94": "NOT_ALIVE",
255
- "95": "NOT_ALIVE",
256
  "96": "NOT_ALIVE",
257
  "97": "SUCCESS",
258
- "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6378107,
268
- 6378115
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": 266,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6376174,
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": "FAIL",
7
  "100": "NOT_ALIVE",
8
  "101": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
+ "103": "NON_PARTICIPATING",
11
+ "104": "NOT_ALIVE",
12
  "105": "NOT_ALIVE",
13
  "106": "FAIL",
14
  "107": "SUCCESS",
15
  "108": "SUCCESS",
16
+ "109": "NON_PARTICIPATING",
17
+ "11": "SUCCESS",
18
+ "110": "FAIL",
19
+ "111": "NOT_ALIVE",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NOT_ALIVE",
25
  "117": "SUCCESS",
26
+ "118": "NOT_ALIVE",
27
+ "119": "SUCCESS",
28
  "12": "NOT_ALIVE",
29
+ "120": "NON_PARTICIPATING",
30
  "121": "SUCCESS",
31
  "122": "SUCCESS",
32
  "123": "SUCCESS",
 
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
  "127": "SUCCESS",
37
+ "128": "NOT_ALIVE",
38
+ "129": "FAIL",
39
  "13": "NOT_ALIVE",
40
  "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "SUCCESS",
43
  "133": "FAIL",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
47
+ "137": "FAIL",
48
  "138": "NOT_ALIVE",
49
+ "139": "NOT_ALIVE",
50
+ "14": "NOT_ALIVE",
51
+ "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
+ "143": "SUCCESS",
55
  "144": "SUCCESS",
56
+ "145": "FAIL",
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": "SUCCESS",
65
+ "153": "NOT_ALIVE",
66
+ "154": "NON_PARTICIPATING",
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": "FAIL",
75
+ "162": "NON_PARTICIPATING",
76
+ "163": "SUCCESS",
77
+ "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
+ "168": "NON_PARTICIPATING",
82
+ "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
+ "170": "NON_PARTICIPATING",
85
  "171": "SUCCESS",
86
+ "172": "FAIL",
87
  "173": "SUCCESS",
88
+ "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
+ "177": "SUCCESS",
92
+ "178": "NOT_ALIVE",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
  "182": "SUCCESS",
98
+ "183": "FAIL",
99
  "184": "SUCCESS",
100
+ "185": "FAIL",
101
  "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
+ "189": "SUCCESS",
105
+ "19": "SUCCESS",
106
+ "190": "NON_PARTICIPATING",
107
+ "191": "NOT_ALIVE",
108
+ "192": "NOT_ALIVE",
109
+ "193": "FAIL",
110
+ "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
  "196": "SUCCESS",
113
+ "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "FAIL",
119
  "201": "NOT_ALIVE",
120
+ "202": "NON_PARTICIPATING",
121
+ "203": "SUCCESS",
122
+ "204": "SUCCESS",
123
  "205": "SUCCESS",
124
+ "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
+ "208": "NON_PARTICIPATING",
127
  "209": "SUCCESS",
128
  "21": "SUCCESS",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
  "212": "SUCCESS",
132
+ "213": "SUCCESS",
133
  "214": "SUCCESS",
134
  "215": "SUCCESS",
135
+ "216": "NOT_ALIVE",
136
  "217": "FAIL",
137
+ "218": "SUCCESS",
138
  "219": "FAIL",
139
+ "22": "SUCCESS",
140
+ "220": "SUCCESS",
141
+ "221": "FAIL",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "NON_PARTICIPATING",
146
  "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
148
  "228": "FAIL",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
+ "230": "NON_PARTICIPATING",
152
+ "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
+ "233": "SUCCESS",
155
+ "234": "NON_PARTICIPATING",
156
+ "235": "FAIL",
157
+ "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
+ "241": "NOT_ALIVE",
164
+ "242": "FAIL",
165
+ "243": "NON_PARTICIPATING",
166
  "244": "SUCCESS",
167
+ "245": "FAIL",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "SUCCESS",
170
+ "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
+ "255": "NOT_ALIVE",
179
+ "26": "SUCCESS",
180
  "27": "SUCCESS",
181
+ "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
+ "30": "SUCCESS",
185
+ "31": "NOT_ALIVE",
186
+ "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "FAIL",
190
+ "36": "SUCCESS",
191
+ "37": "SUCCESS",
192
+ "38": "NOT_ALIVE",
193
+ "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "NON_PARTICIPATING",
196
+ "41": "SUCCESS",
197
+ "42": "FAIL",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "SUCCESS",
206
+ "50": "FAIL",
207
+ "51": "FAIL",
208
+ "52": "SUCCESS",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
+ "55": "NON_PARTICIPATING",
212
+ "56": "SUCCESS",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "SUCCESS",
215
  "59": "NOT_ALIVE",
216
+ "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
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": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
+ "7": "SUCCESS",
228
+ "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
+ "74": "SUCCESS",
233
+ "75": "NON_PARTICIPATING",
234
+ "76": "NON_PARTICIPATING",
235
+ "77": "FAIL",
236
+ "78": "FAIL",
237
+ "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
+ "81": "NON_PARTICIPATING",
241
+ "82": "NOT_ALIVE",
242
  "83": "NON_PARTICIPATING",
243
+ "84": "SUCCESS",
244
  "85": "NOT_ALIVE",
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": "NOT_ALIVE",
253
+ "93": "NON_PARTICIPATING",
254
  "94": "NOT_ALIVE",
255
+ "95": "FAIL",
256
  "96": "NOT_ALIVE",
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
+ 6378260,
268
+ 6378269
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": 6378225,
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 sha256:29db7510d7dd2d954d457c05fafea5a1ab2bf990bd7c5926ddb189b79c32abb4
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bbc47dd3004b26902db4b0735c166fd696f514f72deb402be24cda9a5035493
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:038bc0b45032d80d02e88c89b30712137bf5f13da8461ec9aed3a3d484898b09
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c46854f2eb6df6f9d72036e1a96113dade26651173e648a927d11a7eb5b5d5b
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35e44e48d5a3fe6fb46da24e333bf855e771ced61d4efeaa4705272076b27005
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f82e8af1bc1b10b1b14082455c0a74175fc844cbe7bc27c8587da0e4b9b4dd7
3
  size 4400216536