Ham2363 commited on
Commit
41e14a6
·
verified ·
1 Parent(s): d2a13e0

Run 5. Outer Step 153. Inner Step 2.

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
@@ -3,7 +3,7 @@
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NON_PARTICIPATING",
6
- "10": "NON_PARTICIPATING",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
@@ -17,13 +17,13 @@
17
  "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NOT_ALIVE",
20
- "112": "NOT_ALIVE",
21
  "113": "NON_PARTICIPATING",
22
- "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
- "116": "NON_PARTICIPATING",
25
  "117": "NON_PARTICIPATING",
26
- "118": "NOT_ALIVE",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
@@ -31,7 +31,7 @@
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
- "125": "NON_PARTICIPATING",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
@@ -48,8 +48,8 @@
48
  "138": "SUCCESS",
49
  "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
- "141": "NOT_ALIVE",
53
  "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
@@ -57,7 +57,7 @@
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
- "149": "NOT_ALIVE",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
@@ -69,26 +69,26 @@
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
  "159": "NON_PARTICIPATING",
72
- "16": "NON_PARTICIPATING",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
- "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
- "167": "NON_PARTICIPATING",
81
  "168": "NOT_ALIVE",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
- "177": "NON_PARTICIPATING",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
@@ -101,19 +101,19 @@
101
  "186": "NON_PARTICIPATING",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
- "189": "NOT_ALIVE",
105
- "19": "NON_PARTICIPATING",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
112
- "196": "NON_PARTICIPATING",
113
  "197": "NOT_ALIVE",
114
  "198": "NOT_ALIVE",
115
  "199": "NON_PARTICIPATING",
116
- "2": "NON_PARTICIPATING",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NON_PARTICIPATING",
@@ -121,7 +121,7 @@
121
  "203": "NON_PARTICIPATING",
122
  "204": "SUCCESS",
123
  "205": "NOT_ALIVE",
124
- "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
@@ -129,8 +129,8 @@
129
  "210": "NOT_ALIVE",
130
  "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
- "213": "NOT_ALIVE",
133
- "214": "NOT_ALIVE",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NOT_ALIVE",
@@ -152,13 +152,13 @@
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
- "234": "NOT_ALIVE",
156
- "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
- "24": "NON_PARTICIPATING",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
@@ -168,9 +168,9 @@
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
- "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
@@ -183,14 +183,14 @@
183
  "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
- "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
- "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
- "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
@@ -199,25 +199,25 @@
199
  "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NOT_ALIVE",
202
- "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NOT_ALIVE",
208
- "52": "NOT_ALIVE",
209
- "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
- "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
- "57": "NOT_ALIVE",
214
- "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
- "60": "NOT_ALIVE",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
- "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
@@ -227,12 +227,12 @@
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NOT_ALIVE",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
- "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
- "77": "SUCCESS",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
@@ -240,7 +240,7 @@
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
- "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
  "87": "NOT_ALIVE",
@@ -250,7 +250,7 @@
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
- "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6089507,
268
- 6089534
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": 43,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6088400,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
  "1": "NON_PARTICIPATING",
6
+ "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
 
17
  "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NOT_ALIVE",
20
+ "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
+ "116": "NOT_ALIVE",
25
  "117": "NON_PARTICIPATING",
26
+ "118": "NON_PARTICIPATING",
27
  "119": "NOT_ALIVE",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
 
31
  "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
33
  "124": "NON_PARTICIPATING",
34
+ "125": "SUCCESS",
35
  "126": "NON_PARTICIPATING",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
 
48
  "138": "SUCCESS",
49
  "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
+ "140": "NOT_ALIVE",
52
+ "141": "NON_PARTICIPATING",
53
  "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
 
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
+ "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
 
69
  "157": "NON_PARTICIPATING",
70
  "158": "NOT_ALIVE",
71
  "159": "NON_PARTICIPATING",
72
+ "16": "NOT_ALIVE",
73
  "160": "NOT_ALIVE",
74
  "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
  "164": "NON_PARTICIPATING",
78
+ "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
+ "167": "NOT_ALIVE",
81
  "168": "NOT_ALIVE",
82
  "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
+ "173": "NOT_ALIVE",
88
  "174": "NON_PARTICIPATING",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
+ "177": "NOT_ALIVE",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
 
101
  "186": "NON_PARTICIPATING",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NOT_ALIVE",
104
+ "189": "NON_PARTICIPATING",
105
+ "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NOT_ALIVE",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NOT_ALIVE",
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": "NOT_ALIVE",
119
  "201": "NON_PARTICIPATING",
 
121
  "203": "NON_PARTICIPATING",
122
  "204": "SUCCESS",
123
  "205": "NOT_ALIVE",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
  "209": "NOT_ALIVE",
 
129
  "210": "NOT_ALIVE",
130
  "211": "NOT_ALIVE",
131
  "212": "NON_PARTICIPATING",
132
+ "213": "NON_PARTICIPATING",
133
+ "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "NON_PARTICIPATING",
136
  "217": "NOT_ALIVE",
 
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NOT_ALIVE",
155
+ "234": "NON_PARTICIPATING",
156
+ "235": "NOT_ALIVE",
157
  "236": "NOT_ALIVE",
158
  "237": "NOT_ALIVE",
159
  "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
+ "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NON_PARTICIPATING",
 
168
  "246": "NON_PARTICIPATING",
169
  "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
+ "249": "NON_PARTICIPATING",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
  "253": "NOT_ALIVE",
 
183
  "3": "NON_PARTICIPATING",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
+ "32": "NON_PARTICIPATING",
187
  "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
+ "35": "NOT_ALIVE",
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",
 
199
  "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
  "46": "NOT_ALIVE",
202
+ "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NON_PARTICIPATING",
207
  "51": "NOT_ALIVE",
208
+ "52": "SUCCESS",
209
+ "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
+ "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "NON_PARTICIPATING",
214
+ "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
 
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
  "74": "NON_PARTICIPATING",
233
+ "75": "SUCCESS",
234
  "76": "NOT_ALIVE",
235
+ "77": "NOT_ALIVE",
236
  "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
 
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": "NOT_ALIVE",
 
250
  "90": "NON_PARTICIPATING",
251
  "91": "NOT_ALIVE",
252
  "92": "NON_PARTICIPATING",
253
+ "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6089643,
268
+ 6089669
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": 6089554,
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 sha256:3aafbdd5e56be52c3b476b8222457e9f7626f8d24c3cd7400f8897770e55734d
3
  size 44585978
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:338902a28eaac658d5b0a6c893c3c0679cbdb2165461f939410fcaf95e81e6c7
3
  size 44585978
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bad34cbdb65a622713688d43149747edc20000f83c175d2024e5d152e0a8d35b
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d059a63250eabb3d6489856d2f659dd34b0b8ed4b98c023e58716894856eaad
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14df8688e256ba0d31af93aa464e2d54c9a6361bb082609a0cbcb293631e29e4
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1720878f5104877ab76d22450a1027afdbd3611ffce8fda21c3bdcf8861a46a
3
  size 4400216536