ncaagcc commited on
Commit
8fd6486
·
verified ·
1 Parent(s): 4f06965

Run 5. Outer Step 135. Inner Step 1.

Browse files
Files changed (4) hide show
  1. config.json +62 -62
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -5,11 +5,11 @@
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
@@ -17,22 +17,22 @@
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
- "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
- "115": "NON_PARTICIPATING",
24
- "116": "NOT_ALIVE",
25
- "117": "NOT_ALIVE",
26
  "118": "NOT_ALIVE",
27
- "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
- "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
- "123": "NON_PARTICIPATING",
33
- "124": "NON_PARTICIPATING",
34
  "125": "NON_PARTICIPATING",
35
- "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
@@ -41,21 +41,21 @@
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
- "134": "NOT_ALIVE",
45
- "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
  "14": "SUCCESS",
51
- "140": "NON_PARTICIPATING",
52
- "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
- "145": "NON_PARTICIPATING",
57
  "146": "NOT_ALIVE",
58
- "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
@@ -74,18 +74,18 @@
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
- "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
- "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
- "174": "NON_PARTICIPATING",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
@@ -95,31 +95,31 @@
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
- "183": "SUCCESS",
99
  "184": "NON_PARTICIPATING",
100
  "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
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",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
113
- "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
- "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
- "204": "SUCCESS",
123
  "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
@@ -127,16 +127,16 @@
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
- "211": "NON_PARTICIPATING",
131
- "212": "NOT_ALIVE",
132
- "213": "NON_PARTICIPATING",
133
  "214": "NOT_ALIVE",
134
  "215": "SUCCESS",
135
  "216": "NOT_ALIVE",
136
- "217": "NOT_ALIVE",
137
- "218": "NOT_ALIVE",
138
  "219": "NOT_ALIVE",
139
- "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
@@ -148,7 +148,7 @@
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
@@ -159,12 +159,12 @@
159
  "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
- "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
- "243": "NON_PARTICIPATING",
166
  "244": "NOT_ALIVE",
167
- "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
@@ -174,14 +174,14 @@
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": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
- "3": "NOT_ALIVE",
184
- "30": "NOT_ALIVE",
185
  "31": "NON_PARTICIPATING",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
@@ -192,20 +192,20 @@
192
  "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
194
  "4": "NON_PARTICIPATING",
195
- "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
- "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
- "49": "NON_PARTICIPATING",
205
  "5": "SUCCESS",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
- "52": "NON_PARTICIPATING",
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
@@ -215,31 +215,31 @@
215
  "59": "NON_PARTICIPATING",
216
  "6": "NON_PARTICIPATING",
217
  "60": "NOT_ALIVE",
218
- "61": "NON_PARTICIPATING",
219
- "62": "NOT_ALIVE",
220
- "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
227
- "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
- "71": "NOT_ALIVE",
230
- "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
- "77": "SUCCESS",
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
  "8": "NOT_ALIVE",
239
- "80": "NON_PARTICIPATING",
240
- "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NOT_ALIVE",
243
  "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
@@ -253,7 +253,7 @@
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
- "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6005735,
268
- 6005771
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": 18,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6004524,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
+ "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
  "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
 
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
+ "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
  "114": "NON_PARTICIPATING",
23
+ "115": "NOT_ALIVE",
24
+ "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
  "118": "NOT_ALIVE",
27
+ "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
+ "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
+ "123": "NOT_ALIVE",
33
+ "124": "SUCCESS",
34
  "125": "NON_PARTICIPATING",
35
+ "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
 
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NON_PARTICIPATING",
44
+ "134": "NON_PARTICIPATING",
45
+ "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "SUCCESS",
49
  "139": "NON_PARTICIPATING",
50
  "14": "SUCCESS",
51
+ "140": "NOT_ALIVE",
52
+ "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
+ "145": "NOT_ALIVE",
57
  "146": "NOT_ALIVE",
58
+ "147": "NOT_ALIVE",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
 
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NOT_ALIVE",
77
+ "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
+ "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
+ "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
 
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
+ "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
  "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
102
  "187": "NOT_ALIVE",
103
+ "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
+ "19": "NON_PARTICIPATING",
106
+ "190": "NON_PARTICIPATING",
107
+ "191": "NON_PARTICIPATING",
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
113
+ "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
+ "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
+ "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
 
127
  "209": "NOT_ALIVE",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
+ "211": "NOT_ALIVE",
131
+ "212": "SUCCESS",
132
+ "213": "SUCCESS",
133
  "214": "NOT_ALIVE",
134
  "215": "SUCCESS",
135
  "216": "NOT_ALIVE",
136
+ "217": "NON_PARTICIPATING",
137
+ "218": "NON_PARTICIPATING",
138
  "219": "NOT_ALIVE",
139
+ "22": "NON_PARTICIPATING",
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
 
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NON_PARTICIPATING",
151
+ "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
 
159
  "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
+ "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
+ "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
+ "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
 
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NOT_ALIVE",
179
+ "26": "NOT_ALIVE",
180
  "27": "NOT_ALIVE",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
+ "3": "NON_PARTICIPATING",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
 
192
  "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
194
  "4": "NON_PARTICIPATING",
195
+ "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
+ "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
  "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
+ "49": "NOT_ALIVE",
205
  "5": "SUCCESS",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
+ "52": "SUCCESS",
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
 
215
  "59": "NON_PARTICIPATING",
216
  "6": "NON_PARTICIPATING",
217
  "60": "NOT_ALIVE",
218
+ "61": "NOT_ALIVE",
219
+ "62": "NON_PARTICIPATING",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
227
+ "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
+ "71": "NON_PARTICIPATING",
230
+ "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
+ "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
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",
 
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
+ "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NOT_ALIVE",
259
  "99": "NOT_ALIVE"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6005948,
268
+ 6005988
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": 1,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6005880,
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 sha256:39262482fd4a42f8106c2ff27616567bb139b4437344f582f75d011a1550e031
3
  size 44585978
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e4b931eff3191ce6793701be2ebb7c635dae319e34f3a9de306abbd39a4f137
3
  size 44585978
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5a393f24bdf2e2a8bf8ebddb71e711bc1ab2d576a6c11b2ea7cad3c87fd9937
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ff94fe4ded8e606f43887e9edc43cf14c7c83ebacc140886ab963d34366381
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:532ac190c9cbe7abf5964d35cdfb6fca7adca11b3e4b8c611e9994ae6f9f3a5c
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aed0632008e8d38b8aebaeb7743f5c0995f013eff595b88877d0d7e088496bb5
3
  size 4400216536