zeras141a commited on
Commit
21b3288
·
verified ·
1 Parent(s): a6d3976

Run 8. Outer Step 119. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +71 -71
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,13 +2,13 @@
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": "NON_PARTICIPATING",
11
- "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
@@ -22,10 +22,10 @@
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
- "117": "SUCCESS",
26
- "118": "NOT_ALIVE",
27
  "119": "NON_PARTICIPATING",
28
- "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
@@ -46,13 +46,13 @@
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
- "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
- "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
- "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
@@ -69,45 +69,45 @@
69
  "157": "NOT_ALIVE",
70
  "158": "SUCCESS",
71
  "159": "NOT_ALIVE",
72
- "16": "FAIL",
73
  "160": "SUCCESS",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NON_PARTICIPATING",
77
- "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
- "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
- "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
- "170": "NON_PARTICIPATING",
85
  "171": "SUCCESS",
86
- "172": "NOT_ALIVE",
87
  "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
- "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
- "178": "NOT_ALIVE",
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": "SUCCESS",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
- "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
- "190": "SUCCESS",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
- "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
@@ -123,135 +123,135 @@
123
  "205": "NON_PARTICIPATING",
124
  "206": "NOT_ALIVE",
125
  "207": "NON_PARTICIPATING",
126
- "208": "NON_PARTICIPATING",
127
- "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
- "210": "FAIL",
130
  "211": "SUCCESS",
131
- "212": "NOT_ALIVE",
132
- "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
  "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "NON_PARTICIPATING",
138
- "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
- "225": "NON_PARTICIPATING",
146
- "226": "NON_PARTICIPATING",
147
- "227": "NOT_ALIVE",
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
  "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
- "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
- "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
- "243": "NOT_ALIVE",
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": "NOT_ALIVE",
174
  "251": "SUCCESS",
175
- "252": "NOT_ALIVE",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
- "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NON_PARTICIPATING",
188
- "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
  "36": "SUCCESS",
191
- "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
- "39": "NON_PARTICIPATING",
194
  "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "NON_PARTICIPATING",
200
- "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
- "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
- "50": "SUCCESS",
207
- "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
- "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "SUCCESS",
218
- "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
- "63": "NOT_ALIVE",
221
- "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
  "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
- "70": "NOT_ALIVE",
229
- "71": "SUCCESS",
230
- "72": "FAIL",
231
  "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
233
- "75": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
241
  "82": "SUCCESS",
242
- "83": "NON_PARTICIPATING",
243
- "84": "NOT_ALIVE",
244
  "85": "NON_PARTICIPATING",
245
- "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
- "88": "NON_PARTICIPATING",
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": "SUCCESS",
255
  "95": "NON_PARTICIPATING",
256
  "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6438849,
268
- 6438858
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": 634,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6435370,
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": "NOT_ALIVE",
11
+ "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
 
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "FAIL",
26
+ "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
+ "12": "SUCCESS",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
 
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
+ "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
+ "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
 
69
  "157": "NOT_ALIVE",
70
  "158": "SUCCESS",
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": "NOT_ALIVE",
78
  "165": "SUCCESS",
79
+ "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
+ "170": "NOT_ALIVE",
85
  "171": "SUCCESS",
86
+ "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
+ "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
+ "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
+ "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
 
123
  "205": "NON_PARTICIPATING",
124
  "206": "NOT_ALIVE",
125
  "207": "NON_PARTICIPATING",
126
+ "208": "NOT_ALIVE",
127
+ "209": "FAIL",
128
  "21": "NOT_ALIVE",
129
+ "210": "SUCCESS",
130
  "211": "SUCCESS",
131
+ "212": "NON_PARTICIPATING",
132
+ "213": "SUCCESS",
133
  "214": "SUCCESS",
134
  "215": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "SUCCESS",
146
+ "226": "SUCCESS",
147
+ "227": "NON_PARTICIPATING",
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
  "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
+ "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
+ "236": "SUCCESS",
158
  "237": "SUCCESS",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
+ "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
+ "245": "FAIL",
168
  "246": "NON_PARTICIPATING",
169
  "247": "SUCCESS",
170
  "248": "SUCCESS",
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "SUCCESS",
175
+ "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "NOT_ALIVE",
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "NOT_ALIVE",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NON_PARTICIPATING",
188
+ "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
  "36": "SUCCESS",
191
+ "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
193
+ "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "NON_PARTICIPATING",
200
+ "45": "NON_PARTICIPATING",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
+ "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
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": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
+ "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
+ "61": "SUCCESS",
219
  "62": "NOT_ALIVE",
220
+ "63": "NON_PARTICIPATING",
221
+ "64": "NOT_ALIVE",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
  "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
+ "70": "NON_PARTICIPATING",
229
+ "71": "NON_PARTICIPATING",
230
+ "72": "SUCCESS",
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": "SUCCESS",
242
+ "83": "NOT_ALIVE",
243
+ "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "NON_PARTICIPATING",
246
  "87": "NON_PARTICIPATING",
247
+ "88": "SUCCESS",
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",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6438900,
268
+ 6438919
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": 6438846,
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 sha256:31a05ddded9626f8e58dab93541b648fde91535022defca8d727738d79173606
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c933a2fd234f04715843eca346ce939628dcf640503072cb702a33ec39db98c1
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8d70c6032d90e6ca6118b93674999a4d61a9bf16f5650d1292cb1a6bcf9a86a
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a69c81dc7d88c7cb8e6347d870f2193f7202abef6ca2443c438270a0e993274
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28d22e1717eff65edc45336ce69c8d28fef8c6a14d2b0b78ae97d593249d4c71
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05a3e93309781333693e16696b9c7fcd783693919fb9f345115bfc8e4d053e87
3
  size 4400216536