zeras141a commited on
Commit
502e2ea
·
verified ·
1 Parent(s): 45fd6b7

Run 6. Outer Step 76. 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
@@ -9,15 +9,15 @@
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
- "111": "NON_PARTICIPATING",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
@@ -29,12 +29,12 @@
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": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
@@ -43,12 +43,12 @@
43
  "133": "NON_PARTICIPATING",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
- "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "NOT_ALIVE",
49
- "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
@@ -56,18 +56,18 @@
56
  "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
- "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
- "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "SUCCESS",
69
  "157": "NOT_ALIVE",
70
- "158": "NOT_ALIVE",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
@@ -75,16 +75,16 @@
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
  "164": "SUCCESS",
78
- "165": "NON_PARTICIPATING",
79
- "166": "SUCCESS",
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": "NOT_ALIVE",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
@@ -97,41 +97,41 @@
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
- "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
- "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
  "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
- "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
- "197": "NON_PARTICIPATING",
114
- "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
- "2": "SUCCESS",
117
  "20": "NOT_ALIVE",
118
- "200": "NOT_ALIVE",
119
- "201": "SUCCESS",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
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",
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",
@@ -140,15 +140,15 @@
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
- "223": "NON_PARTICIPATING",
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": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
@@ -156,7 +156,7 @@
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
@@ -165,8 +165,8 @@
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",
172
  "25": "SUCCESS",
@@ -179,11 +179,11 @@
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
- "29": "NOT_ALIVE",
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",
@@ -197,7 +197,7 @@
197
  "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
- "45": "NOT_ALIVE",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
@@ -218,12 +218,12 @@
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": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
@@ -233,13 +233,13 @@
233
  "75": "NON_PARTICIPATING",
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",
@@ -250,9 +250,9 @@
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
- "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
- "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6182149,
268
- 6182166
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": 69,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6181469,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
+ "111": "NOT_ALIVE",
20
+ "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
 
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": "NON_PARTICIPATING",
37
+ "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
 
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": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
 
56
  "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
+ "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
+ "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "SUCCESS",
69
  "157": "NOT_ALIVE",
70
+ "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
 
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
  "164": "SUCCESS",
78
+ "165": "NOT_ALIVE",
79
+ "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
+ "170": "SUCCESS",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
+ "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
 
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
+ "185": "NOT_ALIVE",
101
  "186": "NON_PARTICIPATING",
102
+ "187": "NOT_ALIVE",
103
  "188": "NOT_ALIVE",
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": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
+ "197": "NOT_ALIVE",
114
+ "198": "NOT_ALIVE",
115
  "199": "NOT_ALIVE",
116
+ "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "NON_PARTICIPATING",
119
+ "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
+ "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
+ "214": "NOT_ALIVE",
134
+ "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
 
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": "NOT_ALIVE",
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",
 
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
 
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
+ "246": "NON_PARTICIPATING",
169
+ "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
 
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
+ "29": "NON_PARTICIPATING",
183
+ "3": "SUCCESS",
184
  "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
186
+ "32": "NOT_ALIVE",
187
  "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
  "35": "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": "NON_PARTICIPATING",
 
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "NON_PARTICIPATING",
221
+ "64": "NOT_ALIVE",
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",
 
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
+ "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
 
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
+ "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6182265,
268
+ 6182284
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": 6182090,
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 sha256:19593856a5278822534f9983337eba926c14c28822b2b6616f8a11acaf7fe6e3
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c860d411011d9ee2721804aef68d52ca2e18c8a3e322d243a817cd7636ac622b
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:628cea6bd462db5671b83fd696afde51d80b1d97bc31695a252fb6dd602f077f
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23fa84a45fda011ac8bbf4cd8154b60904633207cd0d06525d3493a1b0d30c88
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b41a421f59fce037319c9d29762926ffbd052521c4b8a63ad9f8b6687c6062f4
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3059cdd5feb7f87d8b6f3ef94b3ea5fbf0ea1d79afa43cfef7617720657937ac
3
  size 4400216536