jkjjbk commited on
Commit
5ed3a2d
·
verified ·
1 Parent(s): 6239f55

Run 6. Outer Step 24. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +66 -66
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,17 +2,17 @@
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": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
- "108": "NOT_ALIVE",
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
@@ -44,18 +44,18 @@
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
- "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
- "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
- "147": "SUCCESS",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
@@ -71,15 +71,15 @@
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NOT_ALIVE",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
- "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
- "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
@@ -97,74 +97,74 @@
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
- "185": "SUCCESS",
101
  "186": "NON_PARTICIPATING",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
104
- "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
- "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "NON_PARTICIPATING",
119
  "201": "SUCCESS",
120
- "202": "NOT_ALIVE",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
- "205": "NON_PARTICIPATING",
124
  "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
- "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "NOT_ALIVE",
130
- "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
- "214": "NON_PARTICIPATING",
134
- "215": "NOT_ALIVE",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "NOT_ALIVE",
138
- "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
- "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
- "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
- "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
- "23": "SUCCESS",
151
  "230": "SUCCESS",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
- "234": "NOT_ALIVE",
156
- "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NON_PARTICIPATING",
160
- "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
- "242": "FAIL",
165
  "243": "NOT_ALIVE",
166
- "244": "SUCCESS",
167
- "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
@@ -172,25 +172,25 @@
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
  "251": "NON_PARTICIPATING",
175
- "252": "NOT_ALIVE",
176
- "253": "NON_PARTICIPATING",
177
- "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
- "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
- "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
- "31": "FAIL",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
- "35": "NON_PARTICIPATING",
190
- "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
- "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
@@ -198,9 +198,9 @@
198
  "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
- "46": "FAIL",
202
  "47": "NOT_ALIVE",
203
- "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "SUCCESS",
@@ -209,42 +209,42 @@
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
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": "NON_PARTICIPATING",
218
- "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
- "64": "NOT_ALIVE",
222
- "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
- "70": "NON_PARTICIPATING",
229
  "71": "SUCCESS",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
- "77": "FAIL",
236
- "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "SUCCESS",
240
- "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
- "83": "NON_PARTICIPATING",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
- "86": "NON_PARTICIPATING",
246
  "87": "NOT_ALIVE",
247
- "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
@@ -252,10 +252,10 @@
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
- "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
- "97": "NOT_ALIVE",
258
- "98": "NON_PARTICIPATING",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6142180,
268
- 6142195
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": 90,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6141514,
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": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
+ "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
+ "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
 
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
+ "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "FAIL",
52
  "141": "NON_PARTICIPATING",
53
+ "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
+ "147": "NOT_ALIVE",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
 
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
+ "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
 
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
+ "185": "NOT_ALIVE",
101
  "186": "NON_PARTICIPATING",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
104
+ "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
+ "190": "NON_PARTICIPATING",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
+ "197": "SUCCESS",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "NOT_ALIVE",
119
  "201": "SUCCESS",
120
+ "202": "NON_PARTICIPATING",
121
+ "203": "NOT_ALIVE",
122
  "204": "NON_PARTICIPATING",
123
+ "205": "NOT_ALIVE",
124
  "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "SUCCESS",
128
  "21": "SUCCESS",
129
  "210": "NOT_ALIVE",
130
+ "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "NOT_ALIVE",
134
+ "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "NON_PARTICIPATING",
138
+ "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
+ "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
144
+ "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
+ "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
+ "23": "NOT_ALIVE",
151
  "230": "SUCCESS",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
+ "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NOT_ALIVE",
160
+ "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "SUCCESS",
165
  "243": "NOT_ALIVE",
166
+ "244": "NON_PARTICIPATING",
167
+ "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
 
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
  "251": "NON_PARTICIPATING",
175
+ "252": "NON_PARTICIPATING",
176
+ "253": "NOT_ALIVE",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
+ "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
+ "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
+ "31": "NOT_ALIVE",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "NOT_ALIVE",
190
+ "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
+ "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
 
198
  "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
+ "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
+ "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "SUCCESS",
 
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
+ "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
+ "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
+ "64": "NON_PARTICIPATING",
222
+ "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
+ "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
+ "77": "NOT_ALIVE",
236
+ "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "SUCCESS",
240
+ "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
+ "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
+ "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
+ "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
 
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
+ "97": "NON_PARTICIPATING",
258
+ "98": "NOT_ALIVE",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6142258,
268
+ 6142273
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": 6142194,
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 sha256:6be37d8f8cee4d3873aa010694505d39fe23fa1893325711de81dc2a2cf74e45
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe8b7b8552950cb8a3ac2d8b2d202e714e48a89c73e8361752c25c013cfc589
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bab3f174f180159ab894451d01342692e87a0df3029d77ef7b3f10e60710c97
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ff530dbb8669f78f067edce8245d3a932f39700989a280162d070a8f1f1543
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:543ba2423198a769e9e48685ec245b962d9a6632b1229cb0417879ce7db03e4e
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da750b1dfa89d9fb6f17dc0513558ea2c7e585e679e274f1694d63b3f61a601e
3
  size 4400216536