snoopsy commited on
Commit
f70220f
·
verified ·
1 Parent(s): b68bbcc

Run 8. Outer Step 50. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +69 -71
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -8,16 +8,16 @@
8
  "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
- "104": "NON_PARTICIPATING",
12
  "105": "NOT_ALIVE",
13
- "106": "NOT_ALIVE",
14
- "107": "NON_PARTICIPATING",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NOT_ALIVE",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
@@ -32,19 +32,19 @@
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
- "126": "NON_PARTICIPATING",
36
- "127": "SUCCESS",
37
  "128": "SUCCESS",
38
- "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
- "130": "NOT_ALIVE",
41
- "131": "NOT_ALIVE",
42
  "132": "SUCCESS",
43
- "133": "SUCCESS",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
47
- "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
@@ -62,9 +62,9 @@
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "FAIL",
65
- "153": "SUCCESS",
66
- "154": "NOT_ALIVE",
67
- "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
@@ -72,38 +72,38 @@
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
- "162": "NOT_ALIVE",
76
- "163": "FAIL",
77
  "164": "FAIL",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
- "168": "NOT_ALIVE",
82
  "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "NON_PARTICIPATING",
86
- "172": "NON_PARTICIPATING",
87
  "173": "NOT_ALIVE",
88
  "174": "SUCCESS",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
- "177": "SUCCESS",
92
- "178": "NON_PARTICIPATING",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
- "181": "FAIL",
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
- "185": "NOT_ALIVE",
101
- "186": "FAIL",
102
  "187": "NOT_ALIVE",
103
  "188": "FAIL",
104
- "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "SUCCESS",
107
  "191": "FAIL",
108
  "192": "FAIL",
109
  "193": "NOT_ALIVE",
@@ -111,50 +111,50 @@
111
  "195": "NON_PARTICIPATING",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
- "198": "NOT_ALIVE",
115
- "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
- "202": "FAIL",
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": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
- "211": "SUCCESS",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
- "214": "NON_PARTICIPATING",
134
- "215": "FAIL",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "FAIL",
138
  "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
- "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
- "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
- "224": "NOT_ALIVE",
145
- "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
- "227": "NON_PARTICIPATING",
148
  "228": "SUCCESS",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
- "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
- "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
@@ -164,29 +164,29 @@
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
- "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
- "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NON_PARTICIPATING",
174
- "251": "NON_PARTICIPATING",
175
- "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
- "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NOT_ALIVE",
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
  "3": "FAIL",
184
  "30": "SUCCESS",
185
- "31": "NOT_ALIVE",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "NOT_ALIVE",
190
  "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
@@ -196,15 +196,15 @@
196
  "41": "FAIL",
197
  "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
- "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
- "46": "SUCCESS",
202
- "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
- "5": "FAIL",
206
  "50": "NOT_ALIVE",
207
- "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
@@ -221,23 +221,23 @@
221
  "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
- "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
- "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
- "74": "NON_PARTICIPATING",
233
- "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
- "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
- "80": "NOT_ALIVE",
240
- "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "FAIL",
@@ -255,7 +255,7 @@
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "FAIL",
258
- "98": "FAIL",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,19 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6373957,
268
- 6373975,
269
- 6373991,
270
- 6374003
271
  ],
272
  "bos_token_id": 1,
273
  "eos_token_id": 2,
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
- "inner_step": 80,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6373432,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
8
  "101": "NOT_ALIVE",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
+ "104": "FAIL",
12
  "105": "NOT_ALIVE",
13
+ "106": "SUCCESS",
14
+ "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NOT_ALIVE",
20
+ "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
 
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
+ "126": "FAIL",
36
+ "127": "FAIL",
37
  "128": "SUCCESS",
38
+ "129": "NON_PARTICIPATING",
39
  "13": "NOT_ALIVE",
40
+ "130": "NON_PARTICIPATING",
41
+ "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
+ "133": "NOT_ALIVE",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
47
+ "137": "FAIL",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
 
62
  "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "FAIL",
65
+ "153": "NON_PARTICIPATING",
66
+ "154": "NON_PARTICIPATING",
67
+ "155": "FAIL",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
  "158": "NON_PARTICIPATING",
 
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
+ "162": "NON_PARTICIPATING",
76
+ "163": "SUCCESS",
77
  "164": "FAIL",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
+ "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "NON_PARTICIPATING",
86
+ "172": "NOT_ALIVE",
87
  "173": "NOT_ALIVE",
88
  "174": "SUCCESS",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
+ "177": "NON_PARTICIPATING",
92
+ "178": "NOT_ALIVE",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
+ "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
+ "185": "NON_PARTICIPATING",
101
+ "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "FAIL",
104
+ "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
+ "190": "FAIL",
107
  "191": "FAIL",
108
  "192": "FAIL",
109
  "193": "NOT_ALIVE",
 
111
  "195": "NON_PARTICIPATING",
112
  "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
+ "198": "NON_PARTICIPATING",
115
+ "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
+ "202": "NON_PARTICIPATING",
121
+ "203": "NON_PARTICIPATING",
122
  "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "NON_PARTICIPATING",
128
+ "21": "SUCCESS",
129
  "210": "NOT_ALIVE",
130
+ "211": "NON_PARTICIPATING",
131
  "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "FAIL",
134
+ "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "FAIL",
138
  "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
+ "220": "FAIL",
141
  "221": "SUCCESS",
142
+ "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
144
+ "224": "NON_PARTICIPATING",
145
+ "225": "NOT_ALIVE",
146
  "226": "NOT_ALIVE",
147
+ "227": "NOT_ALIVE",
148
  "228": "SUCCESS",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
+ "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
+ "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
  "239": "NON_PARTICIPATING",
 
164
  "242": "NON_PARTICIPATING",
165
  "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
+ "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
+ "248": "FAIL",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NOT_ALIVE",
174
+ "251": "NOT_ALIVE",
175
+ "252": "SUCCESS",
176
  "253": "SUCCESS",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "FAIL",
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
  "3": "FAIL",
184
  "30": "SUCCESS",
185
+ "31": "NON_PARTICIPATING",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "NON_PARTICIPATING",
190
  "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
 
196
  "41": "FAIL",
197
  "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
+ "46": "NON_PARTICIPATING",
202
+ "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
+ "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
 
221
  "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
+ "67": "NON_PARTICIPATING",
225
  "68": "NON_PARTICIPATING",
226
+ "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
+ "74": "SUCCESS",
233
+ "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
  "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
+ "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
+ "80": "NON_PARTICIPATING",
240
+ "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "FAIL",
 
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "FAIL",
258
+ "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6374167,
268
+ 6374181
 
 
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": 6374115,
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 sha256:72a3efe72b0e5abbcbc9b707bb1bd565c4b9d4cffa6d717609536875a62fbda3
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac9d3b8d22401da27527d125492bc5c93a4c78e0452304a611a98ec064a1a64
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4c64a2a416d2de57f3346bf74d8682886d3d14984e4f4530d053981edb93f72
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89ec75b8b3b605028193c8b54343cb718bd685e7c140c40d01dcd539f59d221
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f8e2bdf44709b589e2f447a2d8742d47bdb7cfa6de9bd68a6af166cac903043
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6b18726b7f016ddc344932e16a3429d5e0935ec4e054d521bfc25142df84cb8
3
  size 4400216536