thieu86 commited on
Commit
aba47fc
·
verified ·
1 Parent(s): 551b3e7

Run 5. Outer Step 70. Inner Step 2.

Browse files
Files changed (3) hide show
  1. config.json +146 -146
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -2,260 +2,260 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
- "1": "SUCCESS",
6
- "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "NOT_ALIVE",
9
- "102": "NOT_ALIVE",
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": "NON_PARTICIPATING",
17
- "11": "NOT_ALIVE",
18
- "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
- "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
- "117": "NOT_ALIVE",
26
- "118": "NON_PARTICIPATING",
27
  "119": "NOT_ALIVE",
28
- "12": "NON_PARTICIPATING",
29
- "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
- "122": "NON_PARTICIPATING",
32
- "123": "NOT_ALIVE",
33
- "124": "SUCCESS",
34
- "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
- "13": "NOT_ALIVE",
40
- "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
- "134": "SUCCESS",
45
  "135": "NON_PARTICIPATING",
46
- "136": "NON_PARTICIPATING",
47
  "137": "NOT_ALIVE",
48
- "138": "NOT_ALIVE",
49
- "139": "SUCCESS",
50
- "14": "NON_PARTICIPATING",
51
  "140": "NOT_ALIVE",
52
- "141": "SUCCESS",
53
  "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
- "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
- "148": "NOT_ALIVE",
60
- "149": "NON_PARTICIPATING",
61
  "15": "NON_PARTICIPATING",
62
- "150": "SUCCESS",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
- "153": "NON_PARTICIPATING",
66
- "154": "NOT_ALIVE",
67
- "155": "NOT_ALIVE",
68
- "156": "NON_PARTICIPATING",
69
- "157": "SUCCESS",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
- "160": "NOT_ALIVE",
74
- "161": "SUCCESS",
75
- "162": "NOT_ALIVE",
76
- "163": "SUCCESS",
77
  "164": "SUCCESS",
78
- "165": "NON_PARTICIPATING",
79
- "166": "NOT_ALIVE",
80
- "167": "SUCCESS",
81
- "168": "NON_PARTICIPATING",
82
- "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
- "171": "SUCCESS",
86
- "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
- "174": "SUCCESS",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "NON_PARTICIPATING",
92
  "178": "NOT_ALIVE",
93
- "179": "NOT_ALIVE",
94
- "18": "SUCCESS",
95
- "180": "NOT_ALIVE",
96
- "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
- "183": "SUCCESS",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
- "187": "SUCCESS",
103
- "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
- "190": "NON_PARTICIPATING",
107
- "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
- "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
- "198": "NOT_ALIVE",
115
  "199": "NON_PARTICIPATING",
116
- "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
- "203": "NOT_ALIVE",
122
- "204": "NON_PARTICIPATING",
123
- "205": "NOT_ALIVE",
124
- "206": "FAIL",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
- "209": "NOT_ALIVE",
128
- "21": "NON_PARTICIPATING",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
- "213": "NOT_ALIVE",
133
  "214": "NON_PARTICIPATING",
134
- "215": "NON_PARTICIPATING",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
- "219": "NOT_ALIVE",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
- "221": "NOT_ALIVE",
142
- "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
- "225": "NOT_ALIVE",
146
- "226": "NOT_ALIVE",
147
  "227": "NON_PARTICIPATING",
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",
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": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
- "241": "NOT_ALIVE",
164
- "242": "NOT_ALIVE",
165
  "243": "NON_PARTICIPATING",
166
- "244": "NOT_ALIVE",
167
- "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
- "247": "SUCCESS",
170
  "248": "NON_PARTICIPATING",
171
- "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
- "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "SUCCESS",
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
- "3": "SUCCESS",
184
- "30": "NOT_ALIVE",
185
- "31": "SUCCESS",
186
- "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
  "35": "NOT_ALIVE",
190
- "36": "NOT_ALIVE",
191
- "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
- "39": "NON_PARTICIPATING",
194
- "4": "NOT_ALIVE",
195
  "40": "SUCCESS",
196
  "41": "SUCCESS",
197
- "42": "NOT_ALIVE",
198
  "43": "SUCCESS",
199
- "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
- "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
- "48": "SUCCESS",
204
- "49": "NOT_ALIVE",
205
- "5": "NOT_ALIVE",
206
- "50": "NON_PARTICIPATING",
207
- "51": "NOT_ALIVE",
208
- "52": "NON_PARTICIPATING",
209
  "53": "NOT_ALIVE",
210
- "54": "SUCCESS",
211
- "55": "NOT_ALIVE",
212
  "56": "SUCCESS",
213
- "57": "SUCCESS",
214
- "58": "SUCCESS",
215
- "59": "NOT_ALIVE",
216
- "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
- "61": "NON_PARTICIPATING",
219
- "62": "NOT_ALIVE",
220
- "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
- "66": "SUCCESS",
224
  "67": "NOT_ALIVE",
225
- "68": "NOT_ALIVE",
226
- "69": "NOT_ALIVE",
227
- "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
- "71": "SUCCESS",
230
- "72": "NOT_ALIVE",
231
- "73": "SUCCESS",
232
  "74": "NON_PARTICIPATING",
233
  "75": "SUCCESS",
234
- "76": "SUCCESS",
235
- "77": "NON_PARTICIPATING",
236
  "78": "NOT_ALIVE",
237
- "79": "SUCCESS",
238
- "8": "NOT_ALIVE",
239
- "80": "NOT_ALIVE",
240
- "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
- "83": "NOT_ALIVE",
243
- "84": "SUCCESS",
244
- "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
- "87": "SUCCESS",
247
- "88": "NOT_ALIVE",
248
- "89": "NOT_ALIVE",
249
- "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
  "91": "NON_PARTICIPATING",
252
- "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
- "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
- "97": "NOT_ALIVE",
258
- "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5880221,
268
- 5880249
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": 46,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5878909,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "NON_PARTICIPATING",
6
+ "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
+ "101": "NON_PARTICIPATING",
9
+ "102": "NON_PARTICIPATING",
10
+ "103": "SUCCESS",
11
  "104": "NOT_ALIVE",
12
+ "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
+ "11": "NON_PARTICIPATING",
18
+ "110": "SUCCESS",
19
  "111": "NOT_ALIVE",
20
+ "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NON_PARTICIPATING",
23
  "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "NON_PARTICIPATING",
26
+ "118": "NOT_ALIVE",
27
  "119": "NOT_ALIVE",
28
+ "12": "NOT_ALIVE",
29
+ "120": "NON_PARTICIPATING",
30
  "121": "NON_PARTICIPATING",
31
+ "122": "SUCCESS",
32
+ "123": "NON_PARTICIPATING",
33
+ "124": "NON_PARTICIPATING",
34
+ "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NON_PARTICIPATING",
37
  "128": "NOT_ALIVE",
38
  "129": "NON_PARTICIPATING",
39
+ "13": "NON_PARTICIPATING",
40
+ "130": "NOT_ALIVE",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
+ "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
+ "136": "SUCCESS",
47
  "137": "NOT_ALIVE",
48
+ "138": "NON_PARTICIPATING",
49
+ "139": "NOT_ALIVE",
50
+ "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
+ "141": "NON_PARTICIPATING",
53
  "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
+ "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "SUCCESS",
60
+ "149": "NOT_ALIVE",
61
  "15": "NON_PARTICIPATING",
62
+ "150": "NOT_ALIVE",
63
  "151": "NOT_ALIVE",
64
  "152": "NON_PARTICIPATING",
65
+ "153": "SUCCESS",
66
+ "154": "NON_PARTICIPATING",
67
+ "155": "NON_PARTICIPATING",
68
+ "156": "SUCCESS",
69
+ "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
  "159": "NOT_ALIVE",
72
  "16": "NON_PARTICIPATING",
73
+ "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
+ "162": "NON_PARTICIPATING",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "SUCCESS",
78
+ "165": "SUCCESS",
79
+ "166": "NON_PARTICIPATING",
80
+ "167": "NON_PARTICIPATING",
81
+ "168": "SUCCESS",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
+ "171": "NON_PARTICIPATING",
86
+ "172": "NON_PARTICIPATING",
87
  "173": "NOT_ALIVE",
88
+ "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
+ "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
+ "179": "NON_PARTICIPATING",
94
+ "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
+ "181": "SUCCESS",
97
  "182": "NON_PARTICIPATING",
98
+ "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
+ "187": "NON_PARTICIPATING",
103
+ "188": "NOT_ALIVE",
104
  "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
+ "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
  "196": "NOT_ALIVE",
113
  "197": "NON_PARTICIPATING",
114
+ "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
+ "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "NON_PARTICIPATING",
122
+ "204": "NOT_ALIVE",
123
+ "205": "NON_PARTICIPATING",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "NON_PARTICIPATING",
128
+ "21": "SUCCESS",
129
+ "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
+ "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
+ "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
+ "221": "SUCCESS",
142
+ "222": "NOT_ALIVE",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NOT_ALIVE",
145
+ "225": "SUCCESS",
146
+ "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "NON_PARTICIPATING",
150
+ "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
+ "231": "NON_PARTICIPATING",
153
+ "232": "NON_PARTICIPATING",
154
+ "233": "NON_PARTICIPATING",
155
+ "234": "NOT_ALIVE",
156
+ "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "NON_PARTICIPATING",
159
+ "238": "SUCCESS",
160
+ "239": "NON_PARTICIPATING",
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
+ "241": "NON_PARTICIPATING",
164
+ "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
+ "244": "NON_PARTICIPATING",
167
+ "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
+ "3": "NON_PARTICIPATING",
184
+ "30": "SUCCESS",
185
+ "31": "NON_PARTICIPATING",
186
+ "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
+ "34": "NOT_ALIVE",
189
  "35": "NOT_ALIVE",
190
+ "36": "NON_PARTICIPATING",
191
+ "37": "NON_PARTICIPATING",
192
  "38": "SUCCESS",
193
+ "39": "SUCCESS",
194
+ "4": "NON_PARTICIPATING",
195
  "40": "SUCCESS",
196
  "41": "SUCCESS",
197
+ "42": "NON_PARTICIPATING",
198
  "43": "SUCCESS",
199
+ "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
+ "48": "NON_PARTICIPATING",
204
+ "49": "NON_PARTICIPATING",
205
+ "5": "NON_PARTICIPATING",
206
+ "50": "NOT_ALIVE",
207
+ "51": "NON_PARTICIPATING",
208
+ "52": "NOT_ALIVE",
209
  "53": "NOT_ALIVE",
210
+ "54": "NON_PARTICIPATING",
211
+ "55": "NON_PARTICIPATING",
212
  "56": "SUCCESS",
213
+ "57": "NOT_ALIVE",
214
+ "58": "NON_PARTICIPATING",
215
+ "59": "NON_PARTICIPATING",
216
+ "6": "NON_PARTICIPATING",
217
  "60": "NON_PARTICIPATING",
218
+ "61": "NOT_ALIVE",
219
+ "62": "SUCCESS",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
+ "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
+ "68": "NON_PARTICIPATING",
226
+ "69": "NON_PARTICIPATING",
227
+ "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
+ "71": "NON_PARTICIPATING",
230
+ "72": "NON_PARTICIPATING",
231
+ "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
  "75": "SUCCESS",
234
+ "76": "NON_PARTICIPATING",
235
+ "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
+ "79": "NON_PARTICIPATING",
238
+ "8": "NON_PARTICIPATING",
239
+ "80": "NON_PARTICIPATING",
240
+ "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
+ "83": "NON_PARTICIPATING",
243
+ "84": "NOT_ALIVE",
244
+ "85": "NOT_ALIVE",
245
  "86": "SUCCESS",
246
+ "87": "NON_PARTICIPATING",
247
+ "88": "NON_PARTICIPATING",
248
+ "89": "NON_PARTICIPATING",
249
+ "9": "NON_PARTICIPATING",
250
  "90": "SUCCESS",
251
  "91": "NON_PARTICIPATING",
252
+ "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
+ "97": "NON_PARTICIPATING",
258
+ "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5912875,
268
+ 5912904
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": 2,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5911865,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:005901d661c463235523be111af6b2c8ebaad02b80ea425575676711aaf13101
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1386d698de4b0570a2e1d3006871b9c22c9cb143cd3a0feb20c16964b335a244
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe4cdf1d416f1d827852d3a21dec929f7acd8bfc0bb4a63965ba4500eb0c3cd7
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:496c99f746b89b224c39a038691ee38ff3e14e77759f5b85f823455c927ee747
3
  size 4400216536