Mhair commited on
Commit
24fd546
·
verified ·
1 Parent(s): 02a4b5e

Run 5. Outer Step 60. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +43 -42
  2. inner_optimizer.pt +2 -2
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "Mhair/test",
3
  "all_reduce_scores": {
4
  "0": "NON_PARTICIPATING",
5
  "1": "SUCCESS",
@@ -13,11 +13,11 @@
13
  "106": "NON_PARTICIPATING",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
- "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
@@ -36,20 +36,20 @@
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
- "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "NON_PARTICIPATING",
43
  "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
- "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "SUCCESS",
51
  "140": "NON_PARTICIPATING",
52
- "141": "SUCCESS",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
@@ -70,11 +70,11 @@
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
- "160": "SUCCESS",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
- "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
@@ -84,12 +84,12 @@
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NON_PARTICIPATING",
91
  "177": "NON_PARTICIPATING",
92
- "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "SUCCESS",
95
  "180": "NON_PARTICIPATING",
@@ -102,9 +102,9 @@
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NON_PARTICIPATING",
105
- "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
- "191": "SUCCESS",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
@@ -114,13 +114,13 @@
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
  "2": "SUCCESS",
117
- "20": "SUCCESS",
118
- "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
- "205": "SUCCESS",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
@@ -137,7 +137,7 @@
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
- "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
@@ -154,11 +154,11 @@
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
@@ -176,12 +176,12 @@
176
  "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
- "30": "SUCCESS",
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NON_PARTICIPATING",
@@ -189,38 +189,38 @@
189
  "35": "SUCCESS",
190
  "36": "SUCCESS",
191
  "37": "SUCCESS",
192
- "38": "SUCCESS",
193
  "39": "SUCCESS",
194
  "4": "SUCCESS",
195
- "40": "NON_PARTICIPATING",
196
- "41": "SUCCESS",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
- "44": "SUCCESS",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
- "47": "SUCCESS",
203
  "48": "SUCCESS",
204
  "49": "SUCCESS",
205
  "5": "SUCCESS",
206
- "50": "SUCCESS",
207
- "51": "SUCCESS",
208
- "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "SUCCESS",
211
  "55": "SUCCESS",
212
  "56": "SUCCESS",
213
- "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "SUCCESS",
216
- "6": "SUCCESS",
217
  "60": "SUCCESS",
218
- "61": "SUCCESS",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
- "64": "SUCCESS",
222
  "65": "SUCCESS",
223
- "66": "SUCCESS",
224
  "67": "SUCCESS",
225
  "68": "SUCCESS",
226
  "69": "SUCCESS",
@@ -232,10 +232,10 @@
232
  "74": "SUCCESS",
233
  "75": "SUCCESS",
234
  "76": "SUCCESS",
235
- "77": "SUCCESS",
236
  "78": "SUCCESS",
237
  "79": "SUCCESS",
238
- "8": "SUCCESS",
239
  "80": "SUCCESS",
240
  "81": "SUCCESS",
241
  "82": "SUCCESS",
@@ -246,15 +246,15 @@
246
  "87": "SUCCESS",
247
  "88": "SUCCESS",
248
  "89": "SUCCESS",
249
- "9": "SUCCESS",
250
  "90": "SUCCESS",
251
  "91": "SUCCESS",
252
  "92": "SUCCESS",
253
  "93": "SUCCESS",
254
  "94": "SUCCESS",
255
  "95": "SUCCESS",
256
- "96": "NON_PARTICIPATING",
257
- "97": "SUCCESS",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
@@ -264,16 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5769324
 
268
  ],
269
  "bos_token_id": 1,
270
  "eos_token_id": 2,
271
  "hidden_act": "silu",
272
  "hidden_size": 2048,
273
  "initializer_range": 0.02,
274
- "inner_step": 0,
275
  "intermediate_size": 5632,
276
- "last_allreduce_block": 5758115,
277
  "max_position_embeddings": 2048,
278
  "mlp_bias": false,
279
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NON_PARTICIPATING",
5
  "1": "SUCCESS",
 
13
  "106": "NON_PARTICIPATING",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
+ "109": "SUCCESS",
17
  "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
+ "112": "FAIL",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
 
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
+ "13": "NON_PARTICIPATING",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "NON_PARTICIPATING",
43
  "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
+ "135": "FAIL",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "SUCCESS",
51
  "140": "NON_PARTICIPATING",
52
+ "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
 
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
+ "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
+ "164": "SUCCESS",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
 
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "SUCCESS",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NON_PARTICIPATING",
91
  "177": "NON_PARTICIPATING",
92
+ "178": "SUCCESS",
93
  "179": "NON_PARTICIPATING",
94
  "18": "SUCCESS",
95
  "180": "NON_PARTICIPATING",
 
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NON_PARTICIPATING",
105
+ "19": "FAIL",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
 
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
  "2": "SUCCESS",
117
+ "20": "NON_PARTICIPATING",
118
+ "200": "SUCCESS",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "SUCCESS",
122
  "204": "NON_PARTICIPATING",
123
+ "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
 
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
+ "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
 
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
+ "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
+ "24": "NON_PARTICIPATING",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
 
176
  "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "SUCCESS",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NON_PARTICIPATING",
 
189
  "35": "SUCCESS",
190
  "36": "SUCCESS",
191
  "37": "SUCCESS",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
194
  "4": "SUCCESS",
195
+ "40": "SUCCESS",
196
+ "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
+ "44": "NON_PARTICIPATING",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
+ "47": "NON_PARTICIPATING",
203
  "48": "SUCCESS",
204
  "49": "SUCCESS",
205
  "5": "SUCCESS",
206
+ "50": "NON_PARTICIPATING",
207
+ "51": "FAIL",
208
+ "52": "NON_PARTICIPATING",
209
  "53": "SUCCESS",
210
  "54": "SUCCESS",
211
  "55": "SUCCESS",
212
  "56": "SUCCESS",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "SUCCESS",
215
  "59": "SUCCESS",
216
+ "6": "NON_PARTICIPATING",
217
  "60": "SUCCESS",
218
+ "61": "NON_PARTICIPATING",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
+ "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
+ "66": "NON_PARTICIPATING",
224
  "67": "SUCCESS",
225
  "68": "SUCCESS",
226
  "69": "SUCCESS",
 
232
  "74": "SUCCESS",
233
  "75": "SUCCESS",
234
  "76": "SUCCESS",
235
+ "77": "NON_PARTICIPATING",
236
  "78": "SUCCESS",
237
  "79": "SUCCESS",
238
+ "8": "NON_PARTICIPATING",
239
  "80": "SUCCESS",
240
  "81": "SUCCESS",
241
  "82": "SUCCESS",
 
246
  "87": "SUCCESS",
247
  "88": "SUCCESS",
248
  "89": "SUCCESS",
249
+ "9": "NON_PARTICIPATING",
250
  "90": "SUCCESS",
251
  "91": "SUCCESS",
252
  "92": "SUCCESS",
253
  "93": "SUCCESS",
254
  "94": "SUCCESS",
255
  "95": "SUCCESS",
256
+ "96": "SUCCESS",
257
+ "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5784336,
268
+ 5784367
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": 2,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5784145,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7727167b1eb905de69733f435dd4f3bb9a62bd92b7f7ef16b4e2b7bcff054c3
3
- size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:021adbfe860799ef0e97f931f197a5b0ff6bc13116ba580393572654145102e6
3
+ size 8800564561
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd5e4b4203d721962008120e0d206a8930537567920ac4ad06e6f381a368d5f1
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:187f4802f86a3a78d380015ae2b8a811aead5790777a2dcc1f3e05c4481f5039
3
  size 4400216536