mizzaay commited on
Commit
064c04f
·
verified ·
1 Parent(s): 13d4a7b

Run 5. Outer Step 14. Inner Step 1.

Browse files
Files changed (3) hide show
  1. config.json +69 -69
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -2,27 +2,27 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NON_PARTICIPATING",
5
- "1": "NON_PARTICIPATING",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
- "104": "SUCCESS",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
- "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
- "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
- "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "SUCCESS",
@@ -47,18 +47,18 @@
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
- "14": "NON_PARTICIPATING",
51
  "140": "NON_PARTICIPATING",
52
- "141": "SUCCESS",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
- "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
- "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
@@ -71,7 +71,7 @@
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": "NON_PARTICIPATING",
@@ -80,7 +80,7 @@
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
- "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
@@ -93,7 +93,7 @@
93
  "179": "NON_PARTICIPATING",
94
  "18": "SUCCESS",
95
  "180": "NON_PARTICIPATING",
96
- "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
@@ -104,7 +104,7 @@
104
  "189": "NON_PARTICIPATING",
105
  "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
- "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
@@ -113,8 +113,8 @@
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
- "2": "NON_PARTICIPATING",
117
- "20": "NON_PARTICIPATING",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
@@ -135,8 +135,8 @@
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
- "219": "NON_PARTICIPATING",
139
- "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
@@ -147,12 +147,12 @@
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
- "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
- "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
@@ -168,7 +168,7 @@
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
- "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NON_PARTICIPATING",
@@ -177,86 +177,86 @@
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
- "27": "NON_PARTICIPATING",
181
- "28": "NON_PARTICIPATING",
182
- "29": "NON_PARTICIPATING",
183
  "3": "SUCCESS",
184
- "30": "NON_PARTICIPATING",
185
- "31": "NON_PARTICIPATING",
186
- "32": "NON_PARTICIPATING",
187
  "33": "NON_PARTICIPATING",
188
  "34": "SUCCESS",
189
- "35": "NON_PARTICIPATING",
190
- "36": "NON_PARTICIPATING",
191
  "37": "SUCCESS",
192
- "38": "NON_PARTICIPATING",
193
- "39": "NON_PARTICIPATING",
194
  "4": "SUCCESS",
195
- "40": "NON_PARTICIPATING",
196
- "41": "NON_PARTICIPATING",
197
- "42": "NON_PARTICIPATING",
198
- "43": "NON_PARTICIPATING",
199
- "44": "NON_PARTICIPATING",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
- "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
- "49": "NON_PARTICIPATING",
205
  "5": "SUCCESS",
206
  "50": "SUCCESS",
207
  "51": "SUCCESS",
208
  "52": "NON_PARTICIPATING",
209
- "53": "NON_PARTICIPATING",
210
- "54": "NON_PARTICIPATING",
211
  "55": "SUCCESS",
212
- "56": "NON_PARTICIPATING",
213
- "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
- "59": "NON_PARTICIPATING",
216
  "6": "SUCCESS",
217
  "60": "SUCCESS",
218
  "61": "SUCCESS",
219
- "62": "NON_PARTICIPATING",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "SUCCESS",
224
  "67": "SUCCESS",
225
- "68": "NON_PARTICIPATING",
226
- "69": "NON_PARTICIPATING",
227
- "7": "NON_PARTICIPATING",
228
  "70": "SUCCESS",
229
- "71": "NON_PARTICIPATING",
230
- "72": "NON_PARTICIPATING",
231
- "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
233
  "75": "SUCCESS",
234
- "76": "NON_PARTICIPATING",
235
- "77": "NON_PARTICIPATING",
236
  "78": "SUCCESS",
237
  "79": "SUCCESS",
238
  "8": "SUCCESS",
239
  "80": "SUCCESS",
240
- "81": "NON_PARTICIPATING",
241
- "82": "NON_PARTICIPATING",
242
- "83": "NON_PARTICIPATING",
243
  "84": "SUCCESS",
244
  "85": "SUCCESS",
245
  "86": "SUCCESS",
246
- "87": "NON_PARTICIPATING",
247
- "88": "NON_PARTICIPATING",
248
- "89": "NON_PARTICIPATING",
249
  "9": "NON_PARTICIPATING",
250
- "90": "NON_PARTICIPATING",
251
- "91": "NON_PARTICIPATING",
252
- "92": "NON_PARTICIPATING",
253
  "93": "SUCCESS",
254
- "94": "NON_PARTICIPATING",
255
- "95": "NON_PARTICIPATING",
256
- "96": "NON_PARTICIPATING",
257
- "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
- "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5718644,
268
- 5718661
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": 83,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5716303,
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": "NON_PARTICIPATING",
5
+ "1": "SUCCESS",
6
  "10": "NON_PARTICIPATING",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
+ "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
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": "SUCCESS",
20
  "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "SUCCESS",
 
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
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",
56
+ "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "SUCCESS",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
 
71
  "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "SUCCESS",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
 
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
+ "17": "SUCCESS",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
 
93
  "179": "NON_PARTICIPATING",
94
  "18": "SUCCESS",
95
  "180": "NON_PARTICIPATING",
96
+ "181": "SUCCESS",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "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",
 
113
  "197": "NON_PARTICIPATING",
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",
 
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "SUCCESS",
139
+ "22": "SUCCESS",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
 
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
+ "23": "SUCCESS",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
 
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
+ "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "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",
188
  "34": "SUCCESS",
189
+ "35": "SUCCESS",
190
+ "36": "SUCCESS",
191
  "37": "SUCCESS",
192
+ "38": "SUCCESS",
193
+ "39": "SUCCESS",
194
  "4": "SUCCESS",
195
+ "40": "SUCCESS",
196
+ "41": "SUCCESS",
197
+ "42": "SUCCESS",
198
+ "43": "SUCCESS",
199
+ "44": "SUCCESS",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
+ "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
204
+ "49": "SUCCESS",
205
  "5": "SUCCESS",
206
  "50": "SUCCESS",
207
  "51": "SUCCESS",
208
  "52": "NON_PARTICIPATING",
209
+ "53": "SUCCESS",
210
+ "54": "SUCCESS",
211
  "55": "SUCCESS",
212
+ "56": "SUCCESS",
213
+ "57": "SUCCESS",
214
  "58": "NON_PARTICIPATING",
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",
227
+ "7": "SUCCESS",
228
  "70": "SUCCESS",
229
+ "71": "SUCCESS",
230
+ "72": "SUCCESS",
231
+ "73": "SUCCESS",
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",
242
+ "83": "SUCCESS",
243
  "84": "SUCCESS",
244
  "85": "SUCCESS",
245
  "86": "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": "SUCCESS",
258
  "98": "SUCCESS",
259
+ "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5718732,
268
+ 5718747
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": 1,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5718662,
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 sha256:703e41665bca9548c52a11cfb70c4e180bb54f2f6c8bbeedd6d72adfc090242e
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4f2b562944576230b6b9d87731de9ac8153722de7b6135bc7ef8ad4b48b992d
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:409c1f7c6c85c67b96eebae3dfd48a0d342da51e78862d3d6016d5e8d7943c4e
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6543042d6403d85786370054a4316dd030e76d45bda4946ddb2c33e2451c4afd
3
  size 4400216536