mizzaay commited on
Commit
e08aff5
·
verified ·
1 Parent(s): 9658597

Run 6. Outer Step 85. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +48 -48
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -27,14 +27,14 @@
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "NOT_ALIVE",
31
- "122": "NOT_ALIVE",
32
  "123": "NOT_ALIVE",
33
  "124": "NON_PARTICIPATING",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
@@ -43,10 +43,10 @@
43
  "133": "NON_PARTICIPATING",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
- "136": "SUCCESS",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
- "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
@@ -54,9 +54,9 @@
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
- "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
- "148": "NON_PARTICIPATING",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
@@ -67,22 +67,22 @@
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
- "158": "NOT_ALIVE",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
- "164": "NOT_ALIVE",
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",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
@@ -95,19 +95,19 @@
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
- "183": "NOT_ALIVE",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
- "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
- "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
- "193": "NON_PARTICIPATING",
110
- "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
@@ -119,8 +119,8 @@
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",
@@ -131,14 +131,14 @@
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
- "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
- "217": "NOT_ALIVE",
137
  "218": "NON_PARTICIPATING",
138
- "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
- "221": "SUCCESS",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
@@ -155,17 +155,17 @@
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NOT_ALIVE",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "SUCCESS",
164
- "242": "SUCCESS",
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",
@@ -174,7 +174,7 @@
174
  "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
  "253": "NON_PARTICIPATING",
177
- "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
  "26": "NOT_ALIVE",
180
  "27": "NON_PARTICIPATING",
@@ -187,18 +187,18 @@
187
  "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
  "35": "SUCCESS",
190
- "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
- "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NOT_ALIVE",
200
- "45": "NOT_ALIVE",
201
- "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
@@ -209,38 +209,38 @@
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
- "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
- "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
- "64": "NON_PARTICIPATING",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
- "71": "SUCCESS",
230
  "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
233
- "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
- "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
- "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
- "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
  "87": "NOT_ALIVE",
@@ -253,7 +253,7 @@
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"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6189232,
268
- 6189247
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": 81,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6188645,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "SUCCESS",
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": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
 
43
  "133": "NON_PARTICIPATING",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
+ "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
+ "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
 
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
+ "148": "NOT_ALIVE",
60
  "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
 
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
+ "158": "NON_PARTICIPATING",
71
+ "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
+ "164": "NON_PARTICIPATING",
78
+ "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
+ "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
 
95
  "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
+ "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
109
+ "193": "FAIL",
110
+ "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
 
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
+ "204": "NON_PARTICIPATING",
123
+ "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
 
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "NOT_ALIVE",
135
  "216": "NON_PARTICIPATING",
136
+ "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
 
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
+ "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
+ "246": "NOT_ALIVE",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
 
174
  "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
  "253": "NON_PARTICIPATING",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
  "26": "NOT_ALIVE",
180
  "27": "NON_PARTICIPATING",
 
187
  "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
  "35": "SUCCESS",
190
+ "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
+ "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NOT_ALIVE",
200
+ "45": "NON_PARTICIPATING",
201
+ "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
 
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
+ "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
+ "59": "SUCCESS",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
+ "64": "NOT_ALIVE",
222
  "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
+ "69": "FAIL",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
+ "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NOT_ALIVE",
233
+ "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "NON_PARTICIPATING",
236
+ "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
+ "82": "NOT_ALIVE",
242
  "83": "NON_PARTICIPATING",
243
+ "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
  "87": "NOT_ALIVE",
 
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
+ "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6189315,
268
+ 6189331
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": 6189257,
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:e3a9154cb77102ee22a3698c781bf74b34a5c21c1ab9bde5e329505b3158d858
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf6e3fe1a4f7989c4b706cd2b465abfa6413561ef35aa458c0cdb77f044bd1b
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cbde755b2449c4e99fc74a039ed846a53f3a6b2fe57824aca1ef894ba4a8a9a
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6a59ac6e84823939dd3a30b78d65be0d7525bd07b0bc88da4d07e7f44042ce
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:508fa2cdeaf171e7c0cf77101566d1872e7c4d699c854679508e776be8ae9d41
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd7764d67a47c56f46e4f1b7e2481a9e5d81198095f98669462375feaa5ec838
3
  size 4400216536