ShinyUser commited on
Commit
f06de2c
·
verified ·
1 Parent(s): f7a72ae

Run 11. Outer Step 59. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +46 -46
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -8,9 +8,9 @@
8
  "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
10
  "103": "NOT_ALIVE",
11
- "104": "SUCCESS",
12
  "105": "SUCCESS",
13
- "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "SUCCESS",
@@ -26,38 +26,38 @@
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
- "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
  "123": "SUCCESS",
33
- "124": "SUCCESS",
34
- "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
- "13": "NON_PARTICIPATING",
40
  "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
- "135": "NON_PARTICIPATING",
46
  "136": "NOT_ALIVE",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
- "139": "SUCCESS",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
- "142": "NON_PARTICIPATING",
54
  "143": "SUCCESS",
55
  "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
  "148": "NOT_ALIVE",
60
- "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
@@ -68,12 +68,12 @@
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "SUCCESS",
71
- "159": "NOT_ALIVE",
72
- "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
@@ -91,18 +91,18 @@
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
- "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
  "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
- "186": "NOT_ALIVE",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
- "19": "SUCCESS",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
@@ -114,23 +114,23 @@
114
  "198": "NOT_ALIVE",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
- "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
- "205": "NON_PARTICIPATING",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
- "21": "NON_PARTICIPATING",
129
- "210": "NOT_ALIVE",
130
  "211": "NOT_ALIVE",
131
- "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
- "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "SUCCESS",
@@ -140,9 +140,9 @@
140
  "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
- "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
- "225": "NOT_ALIVE",
146
  "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
@@ -152,7 +152,7 @@
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
- "234": "NOT_ALIVE",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
@@ -164,24 +164,24 @@
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
- "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
  "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
- "252": "NON_PARTICIPATING",
176
- "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
- "3": "NOT_ALIVE",
184
- "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
@@ -189,7 +189,7 @@
189
  "35": "SUCCESS",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
- "38": "SUCCESS",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
@@ -201,24 +201,24 @@
201
  "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "SUCCESS",
204
- "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
- "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
- "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
- "61": "NOT_ALIVE",
219
  "62": "SUCCESS",
220
  "63": "NOT_ALIVE",
221
- "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
@@ -233,22 +233,22 @@
233
  "75": "SUCCESS",
234
  "76": "SUCCESS",
235
  "77": "NOT_ALIVE",
236
- "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
238
- "8": "SUCCESS",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
- "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
- "91": "NON_PARTICIPATING",
252
  "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6575311,
268
- 6575342
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
@@ -274,9 +274,9 @@
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
- "inner_step": 45,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6574967,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
8
  "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
10
  "103": "NOT_ALIVE",
11
+ "104": "NON_PARTICIPATING",
12
  "105": "SUCCESS",
13
+ "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "SUCCESS",
 
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
+ "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
  "123": "SUCCESS",
33
+ "124": "NOT_ALIVE",
34
+ "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
+ "13": "NOT_ALIVE",
40
  "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
+ "135": "SUCCESS",
46
  "136": "NOT_ALIVE",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
+ "139": "NOT_ALIVE",
50
  "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
+ "142": "SUCCESS",
54
  "143": "SUCCESS",
55
  "144": "NOT_ALIVE",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
  "148": "NOT_ALIVE",
60
+ "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
 
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "SUCCESS",
71
+ "159": "NON_PARTICIPATING",
72
+ "16": "NON_PARTICIPATING",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
 
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
+ "18": "NON_PARTICIPATING",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
  "183": "NOT_ALIVE",
99
  "184": "SUCCESS",
100
+ "185": "NOT_ALIVE",
101
+ "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
+ "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
 
114
  "198": "NOT_ALIVE",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
+ "20": "NON_PARTICIPATING",
118
  "200": "SUCCESS",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
+ "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
128
+ "21": "SUCCESS",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "NOT_ALIVE",
131
+ "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
+ "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "SUCCESS",
 
140
  "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
+ "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
+ "225": "NON_PARTICIPATING",
146
  "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
 
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
+ "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "SUCCESS",
 
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
  "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
  "251": "NOT_ALIVE",
175
+ "252": "SUCCESS",
176
+ "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
+ "3": "SUCCESS",
184
+ "30": "SUCCESS",
185
  "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
 
189
  "35": "SUCCESS",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
 
201
  "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "SUCCESS",
204
+ "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
+ "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
+ "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
213
  "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
+ "61": "SUCCESS",
219
  "62": "SUCCESS",
220
  "63": "NOT_ALIVE",
221
+ "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
 
233
  "75": "SUCCESS",
234
  "76": "SUCCESS",
235
  "77": "NOT_ALIVE",
236
+ "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
238
+ "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
+ "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
+ "91": "SUCCESS",
252
  "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6575450,
268
+ 6575491
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
 
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
+ "inner_step": 9,
278
  "intermediate_size": 5632,
279
+ "last_allreduce_block": 6575401,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:211d1e0fafaafbe4936742f55f17a3574e9010d643ad5dc9948fd7b195d75ca1
3
  size 88390091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed31ff741e10ce92b9ed08f1d978e09400d0fb8d0db26d7f304092826741f463
3
  size 88390091
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50b63eb7bb62536f64fa83549798351a5bc54bead13f1516c66dcb45233560cd
3
  size 4924928111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f641939df9599ba4e87925dc35a4beb72045a7ef35734ab04e18a7c4a02f64
3
  size 4924928111
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e281f855318d630b06b36a0a24dd45af63dc4c216b569703f37a3985a55a749d
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12fa6da8e9ad64901541be67db8b8842283fbb8bec03611de8bb7ed6eaa545c9
3
  size 4400216536