MBA4215 commited on
Commit
0adda94
·
verified ·
1 Parent(s): 9b7943f

Run 9. Outer Step 18. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +110 -110
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -11,251 +11,251 @@
11
  "104": "NON_PARTICIPATING",
12
  "105": "FAIL",
13
  "106": "FAIL",
14
- "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NON_PARTICIPATING",
18
  "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
- "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
- "116": "FAIL",
25
- "117": "FAIL",
26
- "118": "NOT_ALIVE",
27
- "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
- "123": "NON_PARTICIPATING",
33
- "124": "FAIL",
34
- "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
- "127": "FAIL",
37
- "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "FAIL",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
- "133": "NOT_ALIVE",
44
- "134": "NON_PARTICIPATING",
45
- "135": "FAIL",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NOT_ALIVE",
50
- "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
- "142": "NOT_ALIVE",
54
  "143": "FAIL",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
- "146": "NOT_ALIVE",
58
- "147": "NOT_ALIVE",
59
- "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
- "150": "FAIL",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NON_PARTICIPATING",
67
- "155": "NON_PARTICIPATING",
68
  "156": "FAIL",
69
- "157": "NON_PARTICIPATING",
70
- "158": "FAIL",
71
- "159": "NOT_ALIVE",
72
- "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
- "169": "NOT_ALIVE",
83
- "17": "NOT_ALIVE",
84
- "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "FAIL",
88
  "174": "NOT_ALIVE",
89
- "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "FAIL",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NON_PARTICIPATING",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
- "182": "NOT_ALIVE",
98
- "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
- "185": "FAIL",
101
- "186": "NON_PARTICIPATING",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
- "189": "NOT_ALIVE",
105
  "19": "NON_PARTICIPATING",
106
- "190": "NOT_ALIVE",
107
- "191": "NON_PARTICIPATING",
108
- "192": "NOT_ALIVE",
109
- "193": "FAIL",
110
- "194": "NOT_ALIVE",
111
  "195": "FAIL",
112
  "196": "NON_PARTICIPATING",
113
  "197": "NON_PARTICIPATING",
114
- "198": "NOT_ALIVE",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
- "20": "FAIL",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
- "202": "FAIL",
121
- "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
- "205": "FAIL",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "FAIL",
128
  "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
- "211": "NON_PARTICIPATING",
131
- "212": "NON_PARTICIPATING",
132
  "213": "NOT_ALIVE",
133
- "214": "NON_PARTICIPATING",
134
- "215": "NOT_ALIVE",
135
- "216": "FAIL",
136
  "217": "NON_PARTICIPATING",
137
- "218": "FAIL",
138
- "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
- "220": "FAIL",
141
- "221": "FAIL",
142
  "222": "NON_PARTICIPATING",
143
  "223": "FAIL",
144
  "224": "NOT_ALIVE",
145
  "225": "FAIL",
146
- "226": "NON_PARTICIPATING",
147
  "227": "FAIL",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
- "23": "FAIL",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NON_PARTICIPATING",
154
- "233": "NOT_ALIVE",
155
- "234": "NON_PARTICIPATING",
156
- "235": "FAIL",
157
- "236": "FAIL",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
- "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
- "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "FAIL",
168
  "246": "FAIL",
169
- "247": "FAIL",
170
  "248": "NON_PARTICIPATING",
171
- "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
- "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
- "255": "FAIL",
179
  "26": "NON_PARTICIPATING",
180
- "27": "NOT_ALIVE",
181
- "28": "NOT_ALIVE",
182
- "29": "NON_PARTICIPATING",
183
  "3": "NON_PARTICIPATING",
184
- "30": "FAIL",
185
- "31": "NOT_ALIVE",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "NON_PARTICIPATING",
190
- "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "FAIL",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NON_PARTICIPATING",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
- "42": "NOT_ALIVE",
198
- "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
- "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
- "50": "NON_PARTICIPATING",
207
- "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
- "53": "FAIL",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "FAIL",
213
- "57": "FAIL",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NOT_ALIVE",
216
  "6": "NON_PARTICIPATING",
217
- "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
- "63": "FAIL",
221
- "64": "NOT_ALIVE",
222
- "65": "FAIL",
223
- "66": "FAIL",
224
  "67": "NON_PARTICIPATING",
225
- "68": "NOT_ALIVE",
226
- "69": "FAIL",
227
- "7": "NOT_ALIVE",
228
- "70": "FAIL",
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
- "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
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": "NOT_ALIVE",
242
- "83": "NON_PARTICIPATING",
243
- "84": "FAIL",
244
- "85": "FAIL",
245
- "86": "FAIL",
246
  "87": "NON_PARTICIPATING",
247
- "88": "FAIL",
248
  "89": "FAIL",
249
- "9": "FAIL",
250
  "90": "FAIL",
251
- "91": "NOT_ALIVE",
252
  "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
  "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
- "96": "FAIL",
257
- "97": "NON_PARTICIPATING",
258
- "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6460695,
268
- 6460725
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": 6459469,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
11
  "104": "NON_PARTICIPATING",
12
  "105": "FAIL",
13
  "106": "FAIL",
14
+ "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NON_PARTICIPATING",
18
  "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
+ "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
+ "117": "NON_PARTICIPATING",
26
+ "118": "FAIL",
27
+ "119": "FAIL",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
  "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "FAIL",
33
+ "124": "NON_PARTICIPATING",
34
+ "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
+ "127": "NOT_ALIVE",
37
+ "128": "FAIL",
38
  "129": "NOT_ALIVE",
39
  "13": "FAIL",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
+ "133": "NON_PARTICIPATING",
44
+ "134": "FAIL",
45
+ "135": "NOT_ALIVE",
46
  "136": "NOT_ALIVE",
47
  "137": "NOT_ALIVE",
48
  "138": "NOT_ALIVE",
49
  "139": "NOT_ALIVE",
50
+ "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
+ "142": "NON_PARTICIPATING",
54
  "143": "FAIL",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
+ "146": "FAIL",
58
+ "147": "NON_PARTICIPATING",
59
+ "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
+ "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NON_PARTICIPATING",
67
+ "155": "NOT_ALIVE",
68
  "156": "FAIL",
69
+ "157": "NOT_ALIVE",
70
+ "158": "NON_PARTICIPATING",
71
+ "159": "FAIL",
72
+ "16": "FAIL",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "FAIL",
77
  "164": "NOT_ALIVE",
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "FAIL",
83
+ "17": "NON_PARTICIPATING",
84
+ "170": "NON_PARTICIPATING",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
  "173": "FAIL",
88
  "174": "NOT_ALIVE",
89
+ "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
+ "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NON_PARTICIPATING",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
+ "182": "FAIL",
98
+ "183": "NON_PARTICIPATING",
99
  "184": "NON_PARTICIPATING",
100
+ "185": "NON_PARTICIPATING",
101
+ "186": "FAIL",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
+ "189": "NON_PARTICIPATING",
105
  "19": "NON_PARTICIPATING",
106
+ "190": "NON_PARTICIPATING",
107
+ "191": "FAIL",
108
+ "192": "NON_PARTICIPATING",
109
+ "193": "NOT_ALIVE",
110
+ "194": "NON_PARTICIPATING",
111
  "195": "FAIL",
112
  "196": "NON_PARTICIPATING",
113
  "197": "NON_PARTICIPATING",
114
+ "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
  "2": "NON_PARTICIPATING",
117
+ "20": "NON_PARTICIPATING",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
+ "202": "NON_PARTICIPATING",
121
+ "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
+ "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "FAIL",
128
  "21": "NON_PARTICIPATING",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "NOT_ALIVE",
131
+ "212": "FAIL",
132
  "213": "NOT_ALIVE",
133
+ "214": "NOT_ALIVE",
134
+ "215": "FAIL",
135
+ "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
+ "218": "NON_PARTICIPATING",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
+ "221": "NOT_ALIVE",
142
  "222": "NON_PARTICIPATING",
143
  "223": "FAIL",
144
  "224": "NOT_ALIVE",
145
  "225": "FAIL",
146
+ "226": "NOT_ALIVE",
147
  "227": "FAIL",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
+ "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NON_PARTICIPATING",
154
+ "233": "FAIL",
155
+ "234": "FAIL",
156
+ "235": "NOT_ALIVE",
157
+ "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NON_PARTICIPATING",
161
+ "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
+ "241": "NOT_ALIVE",
164
  "242": "NOT_ALIVE",
165
  "243": "NOT_ALIVE",
166
  "244": "NOT_ALIVE",
167
  "245": "FAIL",
168
  "246": "FAIL",
169
+ "247": "NON_PARTICIPATING",
170
  "248": "NON_PARTICIPATING",
171
+ "249": "FAIL",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
+ "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "NON_PARTICIPATING",
179
  "26": "NON_PARTICIPATING",
180
+ "27": "NON_PARTICIPATING",
181
+ "28": "FAIL",
182
+ "29": "NOT_ALIVE",
183
  "3": "NON_PARTICIPATING",
184
+ "30": "NON_PARTICIPATING",
185
+ "31": "FAIL",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "FAIL",
190
+ "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
  "38": "FAIL",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NON_PARTICIPATING",
195
+ "40": "FAIL",
196
  "41": "NOT_ALIVE",
197
+ "42": "FAIL",
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": "NOT_ALIVE",
205
  "5": "NON_PARTICIPATING",
206
+ "50": "NOT_ALIVE",
207
+ "51": "FAIL",
208
  "52": "NON_PARTICIPATING",
209
+ "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NOT_ALIVE",
212
  "56": "FAIL",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NOT_ALIVE",
216
  "6": "NON_PARTICIPATING",
217
+ "60": "FAIL",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "NOT_ALIVE",
221
+ "64": "FAIL",
222
+ "65": "NOT_ALIVE",
223
+ "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "NON_PARTICIPATING",
226
+ "69": "NON_PARTICIPATING",
227
+ "7": "FAIL",
228
+ "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "FAIL",
233
  "75": "NOT_ALIVE",
234
+ "76": "NON_PARTICIPATING",
235
  "77": "NOT_ALIVE",
236
+ "78": "FAIL",
237
  "79": "NON_PARTICIPATING",
238
+ "8": "FAIL",
239
+ "80": "FAIL",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
+ "83": "NOT_ALIVE",
243
+ "84": "NOT_ALIVE",
244
+ "85": "NON_PARTICIPATING",
245
+ "86": "NOT_ALIVE",
246
  "87": "NON_PARTICIPATING",
247
+ "88": "NOT_ALIVE",
248
  "89": "FAIL",
249
+ "9": "NOT_ALIVE",
250
  "90": "FAIL",
251
+ "91": "FAIL",
252
  "92": "FAIL",
253
  "93": "NOT_ALIVE",
254
  "94": "FAIL",
255
  "95": "NOT_ALIVE",
256
+ "96": "NOT_ALIVE",
257
+ "97": "NOT_ALIVE",
258
+ "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6460815,
268
+ 6460845
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": 9,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6460778,
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 sha256:66bfc140feb79bb5fdb2523a65757efc9d96ee63ea7f0c135496cfdc0a5e0b62
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:083db7e0ca5268080cdd3531455fbfd05f2a4def919017a336133f0d86790e89
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72e2ec6408795ee1685b36346d3aa7c75a0ed7fb39a3abdf706b75e0fb2916ce
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bca40e4c25dccc4dc02f1ac49709905594a94360501a9316a81cf3fcadd1672
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba7b5f3c3d27a8f1e03ec73d0d46decb40640cd2cfc36c58ae79c99520df58bc
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b002175b53894041d5f558727b38b0a2612c70c1953088f4f4e3073d908e69
3
  size 4400216536