tensor-tech commited on
Commit
029f822
·
verified ·
1 Parent(s): 85deacd

Run 5. Outer Step 57. Inner Step 1.

Browse files
Files changed (3) hide show
  1. config.json +31 -31
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -2,7 +2,7 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NON_PARTICIPATING",
5
- "1": "NON_PARTICIPATING",
6
  "10": "SUCCESS",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
@@ -32,7 +32,7 @@
32
  "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
- "126": "NON_PARTICIPATING",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
@@ -76,22 +76,22 @@
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
- "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "SUCCESS",
84
  "170": "NON_PARTICIPATING",
85
- "171": "SUCCESS",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NON_PARTICIPATING",
91
- "177": "SUCCESS",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
- "18": "SUCCESS",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
@@ -99,10 +99,10 @@
99
  "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
- "187": "SUCCESS",
103
- "188": "SUCCESS",
104
  "189": "NON_PARTICIPATING",
105
- "19": "NON_PARTICIPATING",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
@@ -117,8 +117,8 @@
117
  "20": "NON_PARTICIPATING",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
- "202": "SUCCESS",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
@@ -126,14 +126,14 @@
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
@@ -150,7 +150,7 @@
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",
@@ -168,9 +168,9 @@
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",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
@@ -199,11 +199,11 @@
199
  "44": "NON_PARTICIPATING",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
- "47": "SUCCESS",
203
- "48": "SUCCESS",
204
- "49": "NON_PARTICIPATING",
205
  "5": "SUCCESS",
206
- "50": "NON_PARTICIPATING",
207
  "51": "FAIL",
208
  "52": "NON_PARTICIPATING",
209
  "53": "SUCCESS",
@@ -212,7 +212,7 @@
212
  "56": "SUCCESS",
213
  "57": "NON_PARTICIPATING",
214
  "58": "SUCCESS",
215
- "59": "NON_PARTICIPATING",
216
  "6": "NON_PARTICIPATING",
217
  "60": "SUCCESS",
218
  "61": "NON_PARTICIPATING",
@@ -222,23 +222,23 @@
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "SUCCESS",
225
- "68": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
- "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
238
  "8": "NON_PARTICIPATING",
239
  "80": "SUCCESS",
240
  "81": "SUCCESS",
241
- "82": "NON_PARTICIPATING",
242
  "83": "SUCCESS",
243
  "84": "SUCCESS",
244
  "85": "SUCCESS",
@@ -253,10 +253,10 @@
253
  "93": "SUCCESS",
254
  "94": "SUCCESS",
255
  "95": "SUCCESS",
256
- "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
- "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,16 +264,16 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5781559
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": 5,
275
  "intermediate_size": 5632,
276
- "last_allreduce_block": 5780381,
277
  "max_position_embeddings": 2048,
278
  "mlp_bias": false,
279
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NON_PARTICIPATING",
5
+ "1": "SUCCESS",
6
  "10": "SUCCESS",
7
  "100": "NON_PARTICIPATING",
8
  "101": "NON_PARTICIPATING",
 
32
  "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
+ "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
 
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
+ "166": "SUCCESS",
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",
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": "NON_PARTICIPATING",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
 
99
  "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
  "186": "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",
 
117
  "20": "NON_PARTICIPATING",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
+ "202": "NON_PARTICIPATING",
121
+ "203": "SUCCESS",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
 
126
  "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
+ "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
+ "217": "SUCCESS",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
 
150
  "23": "SUCCESS",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
+ "232": "SUCCESS",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
 
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
+ "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
+ "250": "SUCCESS",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
 
199
  "44": "NON_PARTICIPATING",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
+ "47": "NON_PARTICIPATING",
203
+ "48": "NON_PARTICIPATING",
204
+ "49": "SUCCESS",
205
  "5": "SUCCESS",
206
+ "50": "SUCCESS",
207
  "51": "FAIL",
208
  "52": "NON_PARTICIPATING",
209
  "53": "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",
 
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "SUCCESS",
225
+ "68": "SUCCESS",
226
  "69": "SUCCESS",
227
+ "7": "NON_PARTICIPATING",
228
  "70": "SUCCESS",
229
  "71": "SUCCESS",
230
  "72": "SUCCESS",
231
  "73": "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",
242
  "83": "SUCCESS",
243
  "84": "SUCCESS",
244
  "85": "SUCCESS",
 
253
  "93": "SUCCESS",
254
  "94": "SUCCESS",
255
  "95": "SUCCESS",
256
+ "96": "SUCCESS",
257
  "97": "NON_PARTICIPATING",
258
  "98": "SUCCESS",
259
+ "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5781614
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": 1,
275
  "intermediate_size": 5632,
276
+ "last_allreduce_block": 5781479,
277
  "max_position_embeddings": 2048,
278
  "mlp_bias": false,
279
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55b58da65f327feaa87b9a3751ae391d20aedc232c45bb5ef991c190026fa515
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a39e113574a4b6f0990ecd8ebab1e36af39d64df7864b887a4018b9fce9713b
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c1d4361a76fc313364fbe1ec26e15b5a7303e168f21bd38619e2a70f10c7e09
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead010b60ac87783d4d56ddb026cede9d82e39de06b939cce4f26e648ac70848
3
  size 4400216536