ShinyUser commited on
Commit
9feaa8b
·
verified ·
1 Parent(s): 450bb9c

Run 11. Outer Step 64. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +46 -46
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -8,22 +8,22 @@
8
  "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
10
  "103": "NOT_ALIVE",
11
- "104": "SUCCESS",
12
- "105": "SUCCESS",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
- "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
- "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
- "115": "SUCCESS",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
- "118": "NOT_ALIVE",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
@@ -70,16 +70,16 @@
70
  "158": "SUCCESS",
71
  "159": "SUCCESS",
72
  "16": "NON_PARTICIPATING",
73
- "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
- "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
- "165": "NOT_ALIVE",
79
  "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
  "168": "SUCCESS",
82
- "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
@@ -97,25 +97,25 @@
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
- "185": "NOT_ALIVE",
101
- "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NON_PARTICIPATING",
105
- "19": "SUCCESS",
106
  "190": "SUCCESS",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
- "195": "NOT_ALIVE",
112
  "196": "NON_PARTICIPATING",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
- "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NON_PARTICIPATING",
118
- "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
@@ -130,23 +130,23 @@
130
  "211": "NOT_ALIVE",
131
  "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
- "214": "NOT_ALIVE",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
- "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
- "228": "NOT_ALIVE",
149
- "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
@@ -155,8 +155,8 @@
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NON_PARTICIPATING",
159
- "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
@@ -172,11 +172,11 @@
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
  "251": "NON_PARTICIPATING",
175
- "252": "NON_PARTICIPATING",
176
- "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
- "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
@@ -189,24 +189,24 @@
189
  "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
- "38": "NOT_ALIVE",
193
- "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
- "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
- "48": "NON_PARTICIPATING",
204
  "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
- "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
- "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
@@ -217,37 +217,37 @@
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
- "63": "NOT_ALIVE",
221
  "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
- "69": "NON_PARTICIPATING",
227
- "7": "NON_PARTICIPATING",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
- "74": "NON_PARTICIPATING",
233
  "75": "SUCCESS",
234
  "76": "SUCCESS",
235
- "77": "NON_PARTICIPATING",
236
  "78": "SUCCESS",
237
  "79": "NON_PARTICIPATING",
238
  "8": "SUCCESS",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
- "83": "SUCCESS",
243
- "84": "NON_PARTICIPATING",
244
- "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
- "90": "NON_PARTICIPATING",
251
  "91": "SUCCESS",
252
  "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
@@ -255,7 +255,7 @@
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
- "98": "NOT_ALIVE",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6577756,
268
- 6577793
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
@@ -274,9 +274,9 @@
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
- "inner_step": 63,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6577320,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
8
  "101": "NOT_ALIVE",
9
  "102": "SUCCESS",
10
  "103": "NOT_ALIVE",
11
+ "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NOT_ALIVE",
16
+ "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
+ "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
+ "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
+ "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
 
70
  "158": "SUCCESS",
71
  "159": "SUCCESS",
72
  "16": "NON_PARTICIPATING",
73
+ "160": "NOT_ALIVE",
74
  "161": "NON_PARTICIPATING",
75
+ "162": "NOT_ALIVE",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
+ "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
  "168": "SUCCESS",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
 
97
  "182": "NOT_ALIVE",
98
  "183": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
+ "185": "NON_PARTICIPATING",
101
+ "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NON_PARTICIPATING",
105
+ "19": "NOT_ALIVE",
106
  "190": "SUCCESS",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
+ "195": "NON_PARTICIPATING",
112
  "196": "NON_PARTICIPATING",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "NON_PARTICIPATING",
116
  "2": "NOT_ALIVE",
117
  "20": "NON_PARTICIPATING",
118
+ "200": "SUCCESS",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
 
130
  "211": "NOT_ALIVE",
131
  "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
+ "214": "NON_PARTICIPATING",
134
  "215": "NOT_ALIVE",
135
  "216": "NOT_ALIVE",
136
+ "217": "NOT_ALIVE",
137
  "218": "NOT_ALIVE",
138
  "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NOT_ALIVE",
143
+ "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NON_PARTICIPATING",
146
  "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
+ "228": "NON_PARTICIPATING",
149
+ "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
 
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "NOT_ALIVE",
159
+ "238": "SUCCESS",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
 
172
  "25": "SUCCESS",
173
  "250": "NOT_ALIVE",
174
  "251": "NON_PARTICIPATING",
175
+ "252": "SUCCESS",
176
+ "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
+ "26": "NOT_ALIVE",
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
 
189
  "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
+ "43": "NOT_ALIVE",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
+ "48": "NOT_ALIVE",
204
  "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
+ "51": "NOT_ALIVE",
208
  "52": "SUCCESS",
209
+ "53": "NOT_ALIVE",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NOT_ALIVE",
212
  "56": "NOT_ALIVE",
 
217
  "60": "NON_PARTICIPATING",
218
  "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
+ "69": "SUCCESS",
227
+ "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NOT_ALIVE",
230
  "72": "NOT_ALIVE",
231
  "73": "SUCCESS",
232
+ "74": "NOT_ALIVE",
233
  "75": "SUCCESS",
234
  "76": "SUCCESS",
235
+ "77": "NOT_ALIVE",
236
  "78": "SUCCESS",
237
  "79": "NON_PARTICIPATING",
238
  "8": "SUCCESS",
239
  "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
+ "83": "NOT_ALIVE",
243
+ "84": "NOT_ALIVE",
244
+ "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
+ "90": "SUCCESS",
251
  "91": "SUCCESS",
252
  "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
 
255
  "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
+ "98": "SUCCESS",
259
  "99": "SUCCESS"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6578048,
268
+ 6578076
269
  ],
270
  "bos_token_id": 1,
271
  "dtype": "float32",
 
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
+ "inner_step": 9,
278
  "intermediate_size": 5632,
279
+ "last_allreduce_block": 6577837,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:836a499ad37ed31c98f77fa7111c66e2db99a2f4d05fee08f9a9ac8e49bd872d
3
  size 88390091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16eb1e0a37356251399efff2f977abbeef3d7b22d9462c20c77ec76f4546a4e3
3
  size 88390091
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39fbc9bf365e6c33870b4291c1dbe79ad0da6e85bc2e93591e4f1bdd86450779
3
  size 4924928111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:945dade86eeae9a29dd8c0cfa584477549a64facd0b293de274f120673a9452a
3
  size 4924928111
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:040df2e05c8dbd8778609b92bd58f0041c2d34dcb8cf35ba2ffdedea050e8ab5
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2294a57630c7c2fb596382fbc4c9d40751768625413227423b46f00300f6e25
3
  size 4400216536