mujerry commited on
Commit
5c119fc
·
verified ·
1 Parent(s): 13a86e9

Run 11. Outer Step 48. Inner Step 9.

Browse files
Files changed (4) hide show
  1. config.json +51 -51
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -18,10 +18,10 @@
18
  "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
  "112": "NOT_ALIVE",
21
- "113": "NON_PARTICIPATING",
22
  "114": "NOT_ALIVE",
23
- "115": "NON_PARTICIPATING",
24
- "116": "NOT_ALIVE",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
@@ -29,14 +29,14 @@
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
- "123": "NOT_ALIVE",
33
  "124": "SUCCESS",
34
- "125": "SUCCESS",
35
  "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
- "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
@@ -50,14 +50,14 @@
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
- "142": "SUCCESS",
54
- "143": "NON_PARTICIPATING",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
  "148": "NOT_ALIVE",
60
- "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
@@ -66,9 +66,9 @@
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
- "157": "SUCCESS",
70
  "158": "SUCCESS",
71
- "159": "NOT_ALIVE",
72
  "16": "SUCCESS",
73
  "160": "NOT_ALIVE",
74
  "161": "NON_PARTICIPATING",
@@ -78,50 +78,50 @@
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
- "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
- "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NON_PARTICIPATING",
95
- "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
  "183": "NOT_ALIVE",
99
- "184": "SUCCESS",
100
- "185": "SUCCESS",
101
- "186": "NOT_ALIVE",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
- "19": "SUCCESS",
106
- "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
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": "SUCCESS",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
- "206": "SUCCESS",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
@@ -135,28 +135,28 @@
135
  "216": "NOT_ALIVE",
136
  "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
- "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
  "220": "SUCCESS",
141
- "221": "NON_PARTICIPATING",
142
- "222": "NON_PARTICIPATING",
143
- "223": "NOT_ALIVE",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
146
  "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
- "23": "NON_PARTICIPATING",
151
  "230": "NOT_ALIVE",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NON_PARTICIPATING",
154
  "233": "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",
@@ -167,12 +167,12 @@
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
- "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
- "252": "SUCCESS",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
@@ -180,7 +180,7 @@
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
- "3": "SUCCESS",
184
  "30": "NON_PARTICIPATING",
185
  "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
@@ -189,24 +189,24 @@
189
  "35": "NON_PARTICIPATING",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
- "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
- "41": "SUCCESS",
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": "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": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
@@ -218,7 +218,7 @@
218
  "61": "SUCCESS",
219
  "62": "SUCCESS",
220
  "63": "NON_PARTICIPATING",
221
- "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
@@ -241,19 +241,19 @@
241
  "82": "NOT_ALIVE",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
- "85": "SUCCESS",
245
- "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
- "88": "NOT_ALIVE",
248
- "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NON_PARTICIPATING",
252
- "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
- "96": "SUCCESS",
257
  "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
@@ -264,8 +264,8 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6569209,
268
- 6569234
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": 44,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6568913,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
18
  "110": "NOT_ALIVE",
19
  "111": "SUCCESS",
20
  "112": "NOT_ALIVE",
21
+ "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
+ "115": "SUCCESS",
24
+ "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NOT_ALIVE",
 
29
  "120": "NON_PARTICIPATING",
30
  "121": "NOT_ALIVE",
31
  "122": "NOT_ALIVE",
32
+ "123": "NON_PARTICIPATING",
33
  "124": "SUCCESS",
34
+ "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
  "127": "NOT_ALIVE",
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
+ "13": "NON_PARTICIPATING",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
 
50
  "14": "NOT_ALIVE",
51
  "140": "NOT_ALIVE",
52
  "141": "NOT_ALIVE",
53
+ "142": "FAIL",
54
+ "143": "SUCCESS",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NOT_ALIVE",
58
  "147": "NOT_ALIVE",
59
  "148": "NOT_ALIVE",
60
+ "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NOT_ALIVE",
 
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
+ "157": "FAIL",
70
  "158": "SUCCESS",
71
+ "159": "SUCCESS",
72
  "16": "SUCCESS",
73
  "160": "NOT_ALIVE",
74
  "161": "NON_PARTICIPATING",
 
78
  "165": "NOT_ALIVE",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "SUCCESS",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NOT_ALIVE",
86
  "172": "NOT_ALIVE",
87
+ "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
+ "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
  "179": "NOT_ALIVE",
94
  "18": "NON_PARTICIPATING",
95
+ "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NOT_ALIVE",
98
  "183": "NOT_ALIVE",
99
+ "184": "NOT_ALIVE",
100
+ "185": "NOT_ALIVE",
101
+ "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NOT_ALIVE",
105
+ "19": "NON_PARTICIPATING",
106
+ "190": "SUCCESS",
107
  "191": "NOT_ALIVE",
108
  "192": "NOT_ALIVE",
109
  "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
+ "196": "NOT_ALIVE",
113
+ "197": "SUCCESS",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NON_PARTICIPATING",
118
+ "200": "FAIL",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
+ "206": "NOT_ALIVE",
125
  "207": "NOT_ALIVE",
126
  "208": "NOT_ALIVE",
127
  "209": "NOT_ALIVE",
 
135
  "216": "NOT_ALIVE",
136
  "217": "SUCCESS",
137
  "218": "NOT_ALIVE",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "SUCCESS",
141
+ "221": "NOT_ALIVE",
142
+ "222": "NOT_ALIVE",
143
+ "223": "SUCCESS",
144
  "224": "NOT_ALIVE",
145
  "225": "NOT_ALIVE",
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": "NON_PARTICIPATING",
153
  "232": "NON_PARTICIPATING",
154
  "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
+ "236": "NOT_ALIVE",
158
+ "237": "SUCCESS",
159
+ "238": "NON_PARTICIPATING",
160
  "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
  "240": "NOT_ALIVE",
 
167
  "245": "NOT_ALIVE",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
170
+ "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
+ "252": "NON_PARTICIPATING",
176
  "253": "NOT_ALIVE",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
 
180
  "27": "SUCCESS",
181
  "28": "NOT_ALIVE",
182
  "29": "NOT_ALIVE",
183
+ "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
  "31": "SUCCESS",
186
  "32": "NOT_ALIVE",
 
189
  "35": "NON_PARTICIPATING",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
  "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
  "40": "NOT_ALIVE",
196
+ "41": "NOT_ALIVE",
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": "SUCCESS",
204
+ "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
+ "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
 
218
  "61": "SUCCESS",
219
  "62": "SUCCESS",
220
  "63": "NON_PARTICIPATING",
221
+ "64": "NON_PARTICIPATING",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
 
241
  "82": "NOT_ALIVE",
242
  "83": "SUCCESS",
243
  "84": "NON_PARTICIPATING",
244
+ "85": "NOT_ALIVE",
245
+ "86": "SUCCESS",
246
  "87": "SUCCESS",
247
+ "88": "NON_PARTICIPATING",
248
+ "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
  "91": "NON_PARTICIPATING",
252
+ "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
  "95": "NOT_ALIVE",
256
+ "96": "FAIL",
257
  "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
  "99": "SUCCESS"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6569362,
268
+ 6569389
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": 6569325,
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:ad311fe98a321ae42c80a529389e3dec710218047906fcf444df48dd8ae89431
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:889144e76d5598de15b6e955cc62d08e1282e6b6efb902529cb4b86e20f503a2
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddd2311ecffc7a63afff4252c96b271de1edf0d9c69dcd7e8b4b3ad2cc314406
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ac1b6db0f25a89e8ab075d53dc3dcba6833f3f09a70ce9c9b8ff21cb3e2444
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb925818c5637ccbc1cf35be2a60471c45c092adb48c090c7be8df5220361ebc
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5e2df30bc2f37ec71f7f4e3616cdb6b99bab2c79522937182f07b6c0b0b78f9
3
  size 4400216536