zeras141a commited on
Commit
57e8911
·
verified ·
1 Parent(s): 66a814d

Run 6. Outer Step 73. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +44 -45
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -29,13 +29,13 @@
29
  "120": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
- "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
@@ -43,8 +43,8 @@
43
  "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
- "136": "SUCCESS",
47
- "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
@@ -64,7 +64,7 @@
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",
@@ -76,10 +76,10 @@
76
  "163": "NON_PARTICIPATING",
77
  "164": "SUCCESS",
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": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
@@ -92,16 +92,16 @@
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
- "180": "NOT_ALIVE",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
- "185": "NOT_ALIVE",
101
- "186": "NON_PARTICIPATING",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
- "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
@@ -117,14 +117,14 @@
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
- "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
- "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
@@ -140,33 +140,33 @@
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": "NOT_ALIVE",
148
- "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NOT_ALIVE",
159
  "238": "NON_PARTICIPATING",
160
- "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
- "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
- "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
@@ -176,16 +176,16 @@
176
  "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NOT_ALIVE",
180
  "27": "NON_PARTICIPATING",
181
- "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NON_PARTICIPATING",
188
- "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
@@ -196,11 +196,11 @@
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
- "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
- "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
@@ -218,31 +218,31 @@
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
- "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
- "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
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": "NOT_ALIVE",
234
- "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
- "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
- "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
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",
@@ -251,12 +251,12 @@
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
- "94": "NOT_ALIVE",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
- "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,18 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6179126,
268
- 6179134,
269
- 6179142
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
- "inner_step": 296,
277
  "intermediate_size": 5632,
278
- "last_allreduce_block": 6177675,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
 
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
+ "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
+ "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
 
43
  "133": "NON_PARTICIPATING",
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",
 
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",
 
76
  "163": "NON_PARTICIPATING",
77
  "164": "SUCCESS",
78
  "165": "NON_PARTICIPATING",
79
+ "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
 
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
+ "185": "NON_PARTICIPATING",
101
+ "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
+ "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
 
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
+ "202": "NOT_ALIVE",
121
+ "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
 
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
+ "223": "NON_PARTICIPATING",
144
+ "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NOT_ALIVE",
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": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
+ "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
+ "244": "NOT_ALIVE",
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
 
176
  "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
+ "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NON_PARTICIPATING",
188
+ "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
 
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
+ "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
 
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
+ "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
+ "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
+ "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
+ "74": "NON_PARTICIPATING",
233
+ "75": "NON_PARTICIPATING",
234
+ "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
+ "78": "SUCCESS",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
+ "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
+ "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
 
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6179224,
268
+ 6179232
 
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": 6179161,
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:a9a1998f1b760bc022b0ce90a2c3fd3403f8cca84036c91fe0611bc1035b893e
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe2931162ffab254bd6abe62997c3ba386c842f61f99658ae6eb4cf38abf18a
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2463b3619900a1c9a4b098aa91cd0deafdc464242db13b609af916864ee2681
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f126ae6d3030d292c8680a1f0aa40eaf7aaea85f735f70931cc97ec4268e24c
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfd22695ecb38caea217c755fa7b0a3ed1fdc64ecdd486195bd95fc15f3aba04
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4fb66bf2cd7ae84a36d9de7823c36734d963323e2cf3149e2a480012bdce420
3
  size 4400216536