zeras141a commited on
Commit
8e5c94f
·
verified ·
1 Parent(s): c01a192

Run 6. Outer Step 75. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +44 -44
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -17,7 +17,7 @@
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
- "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
@@ -34,7 +34,7 @@
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
- "128": "NON_PARTICIPATING",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
@@ -45,15 +45,15 @@
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "NON_PARTICIPATING",
49
- "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
- "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
  "148": "NOT_ALIVE",
@@ -63,28 +63,28 @@
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
- "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "SUCCESS",
69
  "157": "NOT_ALIVE",
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": "NON_PARTICIPATING",
77
- "164": "NON_PARTICIPATING",
78
- "165": "NOT_ALIVE",
79
- "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
- "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
- "170": "SUCCESS",
85
- "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
@@ -96,17 +96,17 @@
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
- "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
@@ -115,12 +115,12 @@
115
  "199": "NOT_ALIVE",
116
  "2": "SUCCESS",
117
  "20": "NOT_ALIVE",
118
- "200": "NON_PARTICIPATING",
119
- "201": "NOT_ALIVE",
120
- "202": "NOT_ALIVE",
121
  "203": "NON_PARTICIPATING",
122
- "204": "NOT_ALIVE",
123
- "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
@@ -145,10 +145,10 @@
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NOT_ALIVE",
148
- "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
- "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
@@ -179,7 +179,7 @@
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
- "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
@@ -188,31 +188,31 @@
188
  "34": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
- "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
- "45": "NON_PARTICIPATING",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
- "49": "NON_PARTICIPATING",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
- "55": "NON_PARTICIPATING",
212
- "56": "NOT_ALIVE",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
@@ -223,9 +223,9 @@
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
- "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
- "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
@@ -233,7 +233,7 @@
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
- "78": "SUCCESS",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
@@ -249,10 +249,10 @@
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
- "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
- "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6181495,
268
- 6181515
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": 106,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6180591,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NON_PARTICIPATING",
20
+ "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
 
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "NON_PARTICIPATING",
37
+ "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
 
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
+ "138": "NOT_ALIVE",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
+ "140": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
+ "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NOT_ALIVE",
59
  "148": "NOT_ALIVE",
 
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
+ "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "SUCCESS",
69
  "157": "NOT_ALIVE",
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": "NON_PARTICIPATING",
77
+ "164": "SUCCESS",
78
+ "165": "NON_PARTICIPATING",
79
+ "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
+ "170": "NON_PARTICIPATING",
85
+ "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
+ "173": "NOT_ALIVE",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
 
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NON_PARTICIPATING",
99
+ "184": "NON_PARTICIPATING",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NON_PARTICIPATING",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
+ "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
+ "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
+ "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
 
115
  "199": "NOT_ALIVE",
116
  "2": "SUCCESS",
117
  "20": "NOT_ALIVE",
118
+ "200": "NOT_ALIVE",
119
+ "201": "SUCCESS",
120
+ "202": "NON_PARTICIPATING",
121
  "203": "NON_PARTICIPATING",
122
+ "204": "NON_PARTICIPATING",
123
+ "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
 
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NOT_ALIVE",
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",
 
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
+ "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
184
  "30": "NOT_ALIVE",
185
  "31": "NOT_ALIVE",
 
188
  "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
+ "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
+ "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
+ "45": "NOT_ALIVE",
201
  "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
+ "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
+ "55": "NOT_ALIVE",
212
+ "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
  "61": "NOT_ALIVE",
 
223
  "66": "NON_PARTICIPATING",
224
  "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
+ "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
+ "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
 
233
  "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
+ "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
 
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
+ "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6181621,
268
+ 6181641
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": 5,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6181469,
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:f9aa8e2bb14eb7b59603aff58a281446feafaac211c8dc6940719f0a048d93f3
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c03c2af35873af51ece3aff8a33d3035d1e374e8120aa07b1317a8ece641b943
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:689d35d27f577ac62ffd5d04b64f3be84e1f4a315b364e8832e6e38467487883
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d318d25c115b0a3239059fd91cb546cceda96fefce6fe44c5a8d15879d44bdf
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eea45326e0fc5fa1624052daadb2036d1fff0461864fbc400f31b10b7f1fd732
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc7b9c58fabd2691d71b36b35eab59a7c3a834ec1b03ef8080bc059f879fda26
3
  size 4400216536