snoopsy commited on
Commit
630a983
·
verified ·
1 Parent(s): bf9232a

Run 8. Outer Step 69. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +124 -126
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,259 +2,259 @@
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": "SUCCESS",
9
- "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "FAIL",
14
  "107": "SUCCESS",
15
- "108": "SUCCESS",
16
- "109": "SUCCESS",
17
- "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
- "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
- "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "NON_PARTICIPATING",
27
- "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
- "122": "FAIL",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
- "126": "NON_PARTICIPATING",
36
- "127": "NOT_ALIVE",
37
- "128": "SUCCESS",
38
- "129": "SUCCESS",
39
  "13": "SUCCESS",
40
- "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
- "132": "SUCCESS",
43
  "133": "SUCCESS",
44
- "134": "SUCCESS",
45
- "135": "SUCCESS",
46
  "136": "SUCCESS",
47
- "137": "SUCCESS",
48
  "138": "NOT_ALIVE",
49
- "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
- "143": "SUCCESS",
55
  "144": "SUCCESS",
56
- "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
- "147": "FAIL",
59
  "148": "NON_PARTICIPATING",
60
- "149": "SUCCESS",
61
- "15": "NOT_ALIVE",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
- "152": "NOT_ALIVE",
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": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "SUCCESS",
81
- "168": "FAIL",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
- "171": "NON_PARTICIPATING",
86
- "172": "NON_PARTICIPATING",
87
- "173": "NOT_ALIVE",
88
- "174": "SUCCESS",
89
- "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
- "178": "SUCCESS",
93
  "179": "SUCCESS",
94
  "18": "SUCCESS",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
  "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
- "184": "SUCCESS",
100
- "185": "SUCCESS",
101
  "186": "FAIL",
102
- "187": "NOT_ALIVE",
103
- "188": "FAIL",
104
- "189": "SUCCESS",
105
  "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
- "191": "SUCCESS",
108
- "192": "SUCCESS",
109
- "193": "SUCCESS",
110
- "194": "NOT_ALIVE",
111
  "195": "SUCCESS",
112
- "196": "NOT_ALIVE",
113
- "197": "NOT_ALIVE",
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": "FAIL",
121
- "203": "FAIL",
122
- "204": "FAIL",
123
- "205": "FAIL",
124
- "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
  "208": "SUCCESS",
127
  "209": "SUCCESS",
128
  "21": "SUCCESS",
129
- "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "SUCCESS",
133
- "214": "SUCCESS",
134
- "215": "FAIL",
135
- "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "SUCCESS",
138
- "219": "FAIL",
139
  "22": "SUCCESS",
140
- "220": "NON_PARTICIPATING",
141
- "221": "NOT_ALIVE",
142
- "222": "FAIL",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
- "225": "SUCCESS",
146
- "226": "NON_PARTICIPATING",
147
- "227": "NON_PARTICIPATING",
148
- "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
- "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
- "231": "NON_PARTICIPATING",
153
  "232": "SUCCESS",
154
- "233": "SUCCESS",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
- "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
- "239": "SUCCESS",
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
- "244": "FAIL",
167
- "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
- "247": "NON_PARTICIPATING",
170
  "248": "SUCCESS",
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": "NOT_ALIVE",
179
- "26": "SUCCESS",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
- "3": "FAIL",
184
- "30": "SUCCESS",
185
- "31": "NOT_ALIVE",
186
- "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
- "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
- "37": "FAIL",
192
- "38": "NON_PARTICIPATING",
193
- "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
- "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
- "43": "SUCCESS",
199
  "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
- "47": "NON_PARTICIPATING",
203
- "48": "NOT_ALIVE",
204
- "49": "NON_PARTICIPATING",
205
  "5": "SUCCESS",
206
- "50": "FAIL",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
- "55": "NON_PARTICIPATING",
212
- "56": "NON_PARTICIPATING",
213
  "57": "SUCCESS",
214
- "58": "SUCCESS",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
- "60": "SUCCESS",
218
- "61": "NOT_ALIVE",
219
  "62": "SUCCESS",
220
- "63": "FAIL",
221
- "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "SUCCESS",
226
- "69": "NON_PARTICIPATING",
227
- "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
- "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
- "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
  "76": "SUCCESS",
235
  "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
- "79": "FAIL",
238
  "8": "NOT_ALIVE",
239
- "80": "NOT_ALIVE",
240
- "81": "NOT_ALIVE",
241
  "82": "SUCCESS",
242
- "83": "NON_PARTICIPATING",
243
- "84": "SUCCESS",
244
- "85": "SUCCESS",
245
- "86": "NOT_ALIVE",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
- "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "FAIL",
251
  "91": "NOT_ALIVE",
252
- "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
- "94": "NOT_ALIVE",
255
- "95": "SUCCESS",
256
- "96": "SUCCESS",
257
- "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
@@ -264,19 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6392411,
268
- 6392429,
269
- 6392442,
270
- 6392458
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": 58,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6391958,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "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": "NON_PARTICIPATING",
8
  "101": "SUCCESS",
9
+ "102": "FAIL",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "FAIL",
14
  "107": "SUCCESS",
15
+ "108": "FAIL",
16
+ "109": "NON_PARTICIPATING",
17
+ "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
+ "115": "SUCCESS",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "NON_PARTICIPATING",
27
+ "119": "NOT_ALIVE",
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": "FAIL",
36
+ "127": "SUCCESS",
37
+ "128": "FAIL",
38
+ "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
+ "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "FAIL",
43
  "133": "SUCCESS",
44
+ "134": "NOT_ALIVE",
45
+ "135": "NOT_ALIVE",
46
  "136": "SUCCESS",
47
+ "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
+ "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
+ "145": "FAIL",
57
  "146": "NOT_ALIVE",
58
+ "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "NON_PARTICIPATING",
61
+ "15": "FAIL",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "SUCCESS",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "FAIL",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
+ "160": "NOT_ALIVE",
74
  "161": "SUCCESS",
75
+ "162": "FAIL",
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",
86
+ "172": "FAIL",
87
+ "173": "NON_PARTICIPATING",
88
+ "174": "FAIL",
89
+ "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
+ "178": "FAIL",
93
  "179": "SUCCESS",
94
  "18": "SUCCESS",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
  "182": "NON_PARTICIPATING",
98
  "183": "SUCCESS",
99
+ "184": "NON_PARTICIPATING",
100
+ "185": "FAIL",
101
  "186": "FAIL",
102
+ "187": "NON_PARTICIPATING",
103
+ "188": "SUCCESS",
104
+ "189": "NON_PARTICIPATING",
105
  "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "FAIL",
108
+ "192": "NON_PARTICIPATING",
109
+ "193": "FAIL",
110
+ "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
+ "196": "FAIL",
113
+ "197": "NON_PARTICIPATING",
114
  "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
+ "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
+ "202": "NOT_ALIVE",
121
+ "203": "NON_PARTICIPATING",
122
+ "204": "NON_PARTICIPATING",
123
+ "205": "NON_PARTICIPATING",
124
+ "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
  "208": "SUCCESS",
127
  "209": "SUCCESS",
128
  "21": "SUCCESS",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "SUCCESS",
133
+ "214": "FAIL",
134
+ "215": "SUCCESS",
135
+ "216": "FAIL",
136
  "217": "SUCCESS",
137
+ "218": "FAIL",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
+ "220": "SUCCESS",
141
+ "221": "NON_PARTICIPATING",
142
+ "222": "NOT_ALIVE",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "NON_PARTICIPATING",
146
+ "226": "NOT_ALIVE",
147
+ "227": "NOT_ALIVE",
148
+ "228": "NOT_ALIVE",
149
  "229": "NON_PARTICIPATING",
150
+ "23": "SUCCESS",
151
+ "230": "SUCCESS",
152
+ "231": "NOT_ALIVE",
153
  "232": "SUCCESS",
154
+ "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
+ "236": "FAIL",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
+ "239": "FAIL",
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
+ "244": "SUCCESS",
167
+ "245": "FAIL",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "FAIL",
170
  "248": "SUCCESS",
171
+ "249": "FAIL",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
+ "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
+ "255": "NON_PARTICIPATING",
179
+ "26": "FAIL",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
+ "3": "NOT_ALIVE",
184
+ "30": "FAIL",
185
+ "31": "NON_PARTICIPATING",
186
+ "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
+ "35": "FAIL",
190
  "36": "NON_PARTICIPATING",
191
+ "37": "NOT_ALIVE",
192
+ "38": "SUCCESS",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
+ "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
+ "43": "NON_PARTICIPATING",
199
  "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
+ "47": "FAIL",
203
+ "48": "NON_PARTICIPATING",
204
+ "49": "FAIL",
205
  "5": "SUCCESS",
206
+ "50": "SUCCESS",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
+ "55": "SUCCESS",
212
+ "56": "SUCCESS",
213
  "57": "SUCCESS",
214
+ "58": "FAIL",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "FAIL",
219
  "62": "SUCCESS",
220
+ "63": "SUCCESS",
221
+ "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "SUCCESS",
226
+ "69": "SUCCESS",
227
+ "7": "FAIL",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
+ "72": "FAIL",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "FAIL",
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": "NOT_ALIVE",
244
+ "85": "FAIL",
245
+ "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
+ "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "FAIL",
251
  "91": "NOT_ALIVE",
252
+ "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
254
+ "94": "NON_PARTICIPATING",
255
+ "95": "FAIL",
256
+ "96": "FAIL",
257
+ "97": "SUCCESS",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6392610,
268
+ 6392627
 
 
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": 6392575,
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:f71884e081a675a0a6f385b67db657fb67db783c71a84899fc4067df9d1f0818
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d57f4b1f94380c5916fcd41a38be4c73711f28b2e8b0977dded7492c7131318
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c8e3dfdf1ac64b6278fb8892e08362f7f1d263e9fd86a4efd946044c86295fd
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf96aa1d558b30ef4fa2b768e98ab102409ff9d64a1b9a7f252964421644654
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff0f1169fd6170217e52e2248b8c8515260a797bd4c7eeafcb503e578298455f
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29dfe49e032e240a65fdfb8f7183d08463308abf36e481a7c8428599b7ec349c
3
  size 4400216536