snoopsy commited on
Commit
49ea6ef
·
verified ·
1 Parent(s): 891a5cc

Run 8. Outer Step 47. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +68 -69
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -11,7 +11,7 @@
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",
@@ -34,24 +34,24 @@
34
  "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
  "127": "SUCCESS",
37
- "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
- "131": "NOT_ALIVE",
42
  "132": "SUCCESS",
43
- "133": "NOT_ALIVE",
44
  "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
- "136": "NON_PARTICIPATING",
47
- "137": "FAIL",
48
  "138": "NOT_ALIVE",
49
  "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
- "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
- "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
@@ -61,30 +61,30 @@
61
  "15": "SUCCESS",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
- "152": "NON_PARTICIPATING",
65
  "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
- "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NOT_ALIVE",
71
- "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NOT_ALIVE",
77
- "164": "FAIL",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
- "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
- "173": "SUCCESS",
88
  "174": "SUCCESS",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
@@ -92,20 +92,20 @@
92
  "178": "NON_PARTICIPATING",
93
  "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
- "180": "NOT_ALIVE",
96
- "181": "SUCCESS",
97
  "182": "NOT_ALIVE",
98
- "183": "NOT_ALIVE",
99
- "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
- "186": "NOT_ALIVE",
102
  "187": "NOT_ALIVE",
103
- "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "FAIL",
108
- "192": "SUCCESS",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
@@ -120,26 +120,26 @@
120
  "202": "FAIL",
121
  "203": "FAIL",
122
  "204": "NON_PARTICIPATING",
123
- "205": "SUCCESS",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
- "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
- "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
- "214": "SUCCESS",
134
- "215": "NOT_ALIVE",
135
- "216": "SUCCESS",
136
- "217": "SUCCESS",
137
  "218": "FAIL",
138
- "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
- "220": "NOT_ALIVE",
141
  "221": "SUCCESS",
142
- "222": "SUCCESS",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
@@ -148,7 +148,7 @@
148
  "228": "SUCCESS",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
- "230": "FAIL",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
@@ -158,55 +158,55 @@
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
- "24": "NOT_ALIVE",
162
- "240": "NOT_ALIVE",
163
- "241": "NON_PARTICIPATING",
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": "NOT_ALIVE",
171
  "249": "FAIL",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
- "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "SUCCESS",
180
  "27": "SUCCESS",
181
  "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
- "3": "SUCCESS",
184
  "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
- "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
- "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
204
- "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
- "50": "SUCCESS",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
- "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
@@ -214,33 +214,33 @@
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
- "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
- "63": "SUCCESS",
221
  "64": "NOT_ALIVE",
222
  "65": "NOT_ALIVE",
223
- "66": "NOT_ALIVE",
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": "FAIL",
233
- "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
- "77": "SUCCESS",
236
- "78": "NOT_ALIVE",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
- "83": "NON_PARTICIPATING",
243
- "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "FAIL",
@@ -254,8 +254,8 @@
254
  "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
- "97": "SUCCESS",
258
- "98": "SUCCESS",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,18 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6371962,
268
- 6371978,
269
- 6371995
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
- "inner_step": 79,
277
  "intermediate_size": 5632,
278
- "last_allreduce_block": 6371430,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
 
11
  "104": "NON_PARTICIPATING",
12
  "105": "NOT_ALIVE",
13
  "106": "NOT_ALIVE",
14
+ "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
 
34
  "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
36
  "127": "SUCCESS",
37
+ "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
+ "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
+ "133": "FAIL",
44
  "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
+ "136": "SUCCESS",
47
+ "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
  "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
+ "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
+ "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
 
61
  "15": "SUCCESS",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "FAIL",
65
  "153": "SUCCESS",
66
  "154": "NOT_ALIVE",
67
+ "155": "FAIL",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "NON_PARTICIPATING",
71
+ "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "FAIL",
77
+ "164": "NON_PARTICIPATING",
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": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "NOT_ALIVE",
88
  "174": "SUCCESS",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
 
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": "FAIL",
100
  "185": "NON_PARTICIPATING",
101
+ "186": "FAIL",
102
  "187": "NOT_ALIVE",
103
+ "188": "FAIL",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "FAIL",
108
+ "192": "FAIL",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
 
120
  "202": "FAIL",
121
  "203": "FAIL",
122
  "204": "NON_PARTICIPATING",
123
+ "205": "FAIL",
124
  "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
+ "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "NON_PARTICIPATING",
134
+ "215": "FAIL",
135
+ "216": "NON_PARTICIPATING",
136
+ "217": "NON_PARTICIPATING",
137
  "218": "FAIL",
138
+ "219": "FAIL",
139
  "22": "NOT_ALIVE",
140
+ "220": "NON_PARTICIPATING",
141
  "221": "SUCCESS",
142
+ "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
 
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",
 
158
  "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
+ "24": "SUCCESS",
162
+ "240": "NON_PARTICIPATING",
163
+ "241": "NOT_ALIVE",
164
+ "242": "NOT_ALIVE",
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": "FAIL",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
+ "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
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": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
+ "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
  "38": "SUCCESS",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "FAIL",
197
  "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "NOT_ALIVE",
200
  "45": "NOT_ALIVE",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NOT_ALIVE",
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",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
 
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
+ "60": "NOT_ALIVE",
218
+ "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
+ "63": "FAIL",
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": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
+ "74": "NON_PARTICIPATING",
233
+ "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
+ "77": "NON_PARTICIPATING",
236
+ "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
+ "83": "NOT_ALIVE",
243
+ "84": "FAIL",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "FAIL",
 
254
  "94": "NOT_ALIVE",
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
+ "97": "FAIL",
258
+ "98": "FAIL",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6372324,
268
+ 6372340
 
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": 6372098,
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 sha256:1d803329e431d8e98fb60c48cfeaf00bcdb852cf8e885b9b89c79c32cf1747a9
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d75d4faed80bab2510fd8bb2ebdceb7533fa0091df1bd8fd02230782b760efd6
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd77deb78f286aa03738ed3fae09abf1cd85dcd384c5f7f1749e8e9241581813
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fca1581679b367a3fc9bc917b04fd4852a41c557a9b2a90785493c941cc76d6d
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bacf3b703788e06f0f518cafc0f2ac82be118c0d71bbdb9089522bfa1a0b7ce
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a471c069762e78006f065183e1fce9f2990b2cad1faae973a3f878a54e8362
3
  size 4400216536