ncaagcc commited on
Commit
a2a9dc5
·
verified ·
1 Parent(s): d8ca276

Run 10. Outer Step 89. Inner Step 1.

Browse files
Files changed (4) hide show
  1. config.json +88 -88
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -7,67 +7,67 @@
7
  "100": "NOT_ALIVE",
8
  "101": "SUCCESS",
9
  "102": "SUCCESS",
10
- "103": "NON_PARTICIPATING",
11
  "104": "NOT_ALIVE",
12
- "105": "SUCCESS",
13
- "106": "NON_PARTICIPATING",
14
- "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
- "109": "SUCCESS",
17
- "11": "SUCCESS",
18
- "110": "NON_PARTICIPATING",
19
  "111": "SUCCESS",
20
- "112": "NON_PARTICIPATING",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
- "116": "SUCCESS",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
- "119": "NON_PARTICIPATING",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
- "121": "SUCCESS",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
- "124": "SUCCESS",
34
  "125": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NON_PARTICIPATING",
38
- "129": "SUCCESS",
39
- "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
- "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
- "142": "NOT_ALIVE",
54
  "143": "NOT_ALIVE",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
- "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
- "148": "NOT_ALIVE",
60
- "149": "NON_PARTICIPATING",
61
- "15": "NON_PARTICIPATING",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
- "154": "NOT_ALIVE",
67
- "155": "NON_PARTICIPATING",
68
- "156": "SUCCESS",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NOT_ALIVE",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
@@ -77,60 +77,60 @@
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
80
- "167": "SUCCESS",
81
  "168": "SUCCESS",
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": "NOT_ALIVE",
89
- "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "NON_PARTICIPATING",
92
- "178": "NON_PARTICIPATING",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
- "184": "SUCCESS",
100
  "185": "SUCCESS",
101
  "186": "NOT_ALIVE",
102
- "187": "SUCCESS",
103
  "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
- "19": "NON_PARTICIPATING",
106
- "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
- "192": "NON_PARTICIPATING",
109
- "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
- "196": "NOT_ALIVE",
113
- "197": "NON_PARTICIPATING",
114
  "198": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
- "202": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
- "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
- "21": "NON_PARTICIPATING",
129
- "210": "SUCCESS",
130
- "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
- "214": "SUCCESS",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
@@ -139,27 +139,27 @@
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
- "222": "NON_PARTICIPATING",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
- "227": "SUCCESS",
148
- "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
  "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
- "231": "NOT_ALIVE",
153
  "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
- "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
- "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
- "240": "NOT_ALIVE",
163
  "241": "NOT_ALIVE",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
@@ -169,36 +169,36 @@
169
  "247": "NOT_ALIVE",
170
  "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
- "25": "NOT_ALIVE",
173
  "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
- "255": "SUCCESS",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
- "28": "NON_PARTICIPATING",
182
  "29": "NON_PARTICIPATING",
183
- "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
- "35": "NOT_ALIVE",
190
  "36": "NON_PARTICIPATING",
191
- "37": "NON_PARTICIPATING",
192
- "38": "NON_PARTICIPATING",
193
- "39": "NOT_ALIVE",
194
  "4": "NON_PARTICIPATING",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
- "42": "NOT_ALIVE",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
- "45": "FAIL",
201
- "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
@@ -206,44 +206,44 @@
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
- "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
- "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NON_PARTICIPATING",
217
- "60": "FAIL",
218
  "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
- "63": "NOT_ALIVE",
221
  "64": "NOT_ALIVE",
222
- "65": "NOT_ALIVE",
223
  "66": "SUCCESS",
224
- "67": "NON_PARTICIPATING",
225
- "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
- "70": "NON_PARTICIPATING",
229
  "71": "SUCCESS",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
233
- "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
- "8": "NON_PARTICIPATING",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
- "82": "SUCCESS",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
- "85": "NON_PARTICIPATING",
245
- "86": "NOT_ALIVE",
246
- "87": "SUCCESS",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
  "9": "NON_PARTICIPATING",
@@ -256,7 +256,7 @@
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
  "98": "NOT_ALIVE",
259
- "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6512523,
268
- 6512531
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": 40,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6512341,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
7
  "100": "NOT_ALIVE",
8
  "101": "SUCCESS",
9
  "102": "SUCCESS",
10
+ "103": "SUCCESS",
11
  "104": "NOT_ALIVE",
12
+ "105": "NON_PARTICIPATING",
13
+ "106": "SUCCESS",
14
+ "107": "SUCCESS",
15
  "108": "NON_PARTICIPATING",
16
+ "109": "NON_PARTICIPATING",
17
+ "11": "NON_PARTICIPATING",
18
+ "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
+ "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "SUCCESS",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
+ "119": "SUCCESS",
28
  "12": "NON_PARTICIPATING",
29
  "120": "NOT_ALIVE",
30
+ "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
+ "124": "NOT_ALIVE",
34
  "125": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "SUCCESS",
38
+ "129": "NON_PARTICIPATING",
39
+ "13": "SUCCESS",
40
  "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
+ "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
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": "NOT_ALIVE",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
+ "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "NON_PARTICIPATING",
60
+ "149": "NOT_ALIVE",
61
+ "15": "NOT_ALIVE",
62
  "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "SUCCESS",
66
+ "154": "NON_PARTICIPATING",
67
+ "155": "NOT_ALIVE",
68
+ "156": "NON_PARTICIPATING",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
 
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
80
+ "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
  "169": "NON_PARTICIPATING",
83
+ "17": "NON_PARTICIPATING",
84
  "170": "SUCCESS",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
+ "173": "NOT_ALIVE",
88
  "174": "NOT_ALIVE",
89
+ "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
+ "177": "NOT_ALIVE",
92
+ "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
+ "184": "FAIL",
100
  "185": "SUCCESS",
101
  "186": "NOT_ALIVE",
102
+ "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
  "189": "NOT_ALIVE",
105
+ "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
+ "192": "NOT_ALIVE",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
+ "196": "SUCCESS",
113
+ "197": "NOT_ALIVE",
114
  "198": "SUCCESS",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
  "20": "SUCCESS",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
+ "202": "NOT_ALIVE",
121
+ "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "SUCCESS",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NON_PARTICIPATING",
128
+ "21": "NOT_ALIVE",
129
+ "210": "NON_PARTICIPATING",
130
+ "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
+ "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
 
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
+ "222": "NOT_ALIVE",
143
+ "223": "NOT_ALIVE",
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": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
+ "231": "SUCCESS",
153
  "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
163
  "241": "NOT_ALIVE",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
 
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": "NON_PARTICIPATING",
178
+ "255": "NOT_ALIVE",
179
  "26": "SUCCESS",
180
  "27": "NOT_ALIVE",
181
+ "28": "SUCCESS",
182
  "29": "NON_PARTICIPATING",
183
+ "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
+ "34": "NOT_ALIVE",
189
+ "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
+ "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NON_PARTICIPATING",
195
+ "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
+ "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
  "44": "SUCCESS",
200
+ "45": "NON_PARTICIPATING",
201
+ "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
 
206
  "50": "NON_PARTICIPATING",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
+ "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
+ "59": "SUCCESS",
216
  "6": "NON_PARTICIPATING",
217
+ "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
+ "65": "SUCCESS",
223
  "66": "SUCCESS",
224
+ "67": "NOT_ALIVE",
225
+ "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
+ "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
233
+ "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NON_PARTICIPATING",
238
+ "8": "SUCCESS",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
+ "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "SUCCESS",
244
+ "85": "NOT_ALIVE",
245
+ "86": "SUCCESS",
246
+ "87": "NON_PARTICIPATING",
247
  "88": "NOT_ALIVE",
248
  "89": "SUCCESS",
249
  "9": "NON_PARTICIPATING",
 
256
  "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
  "98": "NOT_ALIVE",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6516523,
268
+ 6516541
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": 6516415,
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:dcbbccf01b3293909adcb48a7e2e202ea08f05ae3897815d3a958e89686ab853
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73224340cc02ab834f305951009fba2b8d9c4e3028ed0c04346a14bf9e64a36
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb0884b8c043d82d826eb09b4c3bf1aa6516f2faf1c87ad3f4f8785024f47906
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf60e0d624235af08da12e92ca983759567a5b110c4080268ab50abae9c4ae09
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23f51df2720360de087e7c5fec6fb2f798d8f3a36f18ef0e6bd83a0b0385581f
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4053ea0d6096fd435d996da38dbb475834ca8c094e4780d3b7ed5a1e41748e40
3
  size 4400216536