jkjjbk commited on
Commit
6fa4e9d
·
verified ·
1 Parent(s): 2fbd11b

Run 6. Outer Step 13. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +40 -40
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,35 +2,35 @@
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": "NOT_ALIVE",
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": "NON_PARTICIPATING",
19
- "111": "NON_PARTICIPATING",
20
  "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
- "118": "NON_PARTICIPATING",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
33
- "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
@@ -46,10 +46,10 @@
46
  "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
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": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
@@ -58,13 +58,13 @@
58
  "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
- "15": "SUCCESS",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
  "154": "NON_PARTICIPATING",
67
- "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
@@ -82,7 +82,7 @@
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
- "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
@@ -96,15 +96,15 @@
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
- "184": "NOT_ALIVE",
100
- "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
- "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
- "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
@@ -117,7 +117,7 @@
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "SUCCESS",
120
- "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
@@ -148,12 +148,12 @@
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
- "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
- "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
  "238": "NON_PARTICIPATING",
@@ -174,25 +174,25 @@
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
- "254": "NON_PARTICIPATING",
178
- "255": "NOT_ALIVE",
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": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "NOT_ALIVE",
190
- "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
@@ -203,8 +203,8 @@
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
- "50": "NOT_ALIVE",
207
- "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
@@ -215,7 +215,7 @@
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
- "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
@@ -232,16 +232,16 @@
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
- "77": "NOT_ALIVE",
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": "SUCCESS",
243
  "84": "NOT_ALIVE",
244
- "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
  "88": "NON_PARTICIPATING",
@@ -250,13 +250,13 @@
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
- "93": "NOT_ALIVE",
254
- "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
- "98": "NON_PARTICIPATING",
259
- "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6129862,
268
- 6129875
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": 96,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6129192,
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": "NON_PARTICIPATING",
8
  "101": "NOT_ALIVE",
9
+ "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "NOT_ALIVE",
20
  "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
24
  "116": "NOT_ALIVE",
25
  "117": "NOT_ALIVE",
26
+ "118": "NOT_ALIVE",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "NOT_ALIVE",
33
+ "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NOT_ALIVE",
 
46
  "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "SUCCESS",
52
+ "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
 
58
  "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
+ "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
  "154": "NON_PARTICIPATING",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
 
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
+ "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
 
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
+ "184": "NON_PARTICIPATING",
100
+ "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
102
+ "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
+ "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
 
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "SUCCESS",
120
+ "202": "NOT_ALIVE",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
 
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
+ "230": "SUCCESS",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
+ "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
  "238": "NON_PARTICIPATING",
 
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
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": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "NON_PARTICIPATING",
190
+ "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
+ "40": "NOT_ALIVE",
196
  "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
 
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
+ "50": "SUCCESS",
207
+ "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
 
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
+ "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
 
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
+ "77": "NON_PARTICIPATING",
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": "NOT_ALIVE",
243
  "84": "NOT_ALIVE",
244
+ "85": "SUCCESS",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
  "88": "NON_PARTICIPATING",
 
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
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": "NOT_ALIVE",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6129934,
268
+ 6129946
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": 6129862,
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:d8d46f8a9d3b6debad97f3389b7e7bef53a636648b5fdaad377f28de083e6f67
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2426d2d42d0f7b176b5ca93ab5da5754409251e09b86c44fd0b175b869840b2
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1c602e39d9330e1ad95625d65b3ba93b3080bcec3c1a5d9d5d6e2e33a5de6bc
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf6c4857471765a6c60b32961f1223cdcf4f080bb6994d4bdc27d4c1cbc8050b
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b3d517a913e2c215d150f272c4d87c3a5711557433291268c8f111e83fa8d17
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac04318f909fa71d098be924daf61f30d34feb6da83bd878d9a9d584a3e2a83e
3
  size 4400216536