jkjjbk commited on
Commit
149fcb5
·
verified ·
1 Parent(s): 05dafc5

Run 6. Outer Step 18. Inner Step 6.

Browse files
Files changed (4) hide show
  1. config.json +62 -62
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -10,7 +10,7 @@
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
- "106": "SUCCESS",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
@@ -38,24 +38,24 @@
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
- "131": "NON_PARTICIPATING",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
  "134": "NOT_ALIVE",
45
- "135": "NOT_ALIVE",
46
- "136": "NOT_ALIVE",
47
- "137": "NOT_ALIVE",
48
  "138": "NON_PARTICIPATING",
49
- "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
53
- "142": "NOT_ALIVE",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
- "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
@@ -63,8 +63,8 @@
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
- "154": "NON_PARTICIPATING",
67
- "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
@@ -73,81 +73,81 @@
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
- "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
- "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
- "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
- "179": "NON_PARTICIPATING",
94
- "18": "SUCCESS",
95
- "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
- "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
- "187": "NON_PARTICIPATING",
103
- "188": "NON_PARTICIPATING",
104
- "189": "NON_PARTICIPATING",
105
  "19": "NOT_ALIVE",
106
- "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
- "192": "SUCCESS",
109
- "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "SUCCESS",
114
- "198": "NOT_ALIVE",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
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": "NOT_ALIVE",
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": "NON_PARTICIPATING",
132
- "213": "NOT_ALIVE",
133
- "214": "NOT_ALIVE",
134
- "215": "NOT_ALIVE",
135
  "216": "SUCCESS",
136
- "217": "NON_PARTICIPATING",
137
- "218": "NON_PARTICIPATING",
138
- "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
- "221": "NOT_ALIVE",
142
  "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
- "228": "NOT_ALIVE",
149
  "229": "NOT_ALIVE",
150
- "23": "SUCCESS",
151
  "230": "SUCCESS",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
@@ -163,7 +163,7 @@
163
  "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NOT_ALIVE",
166
- "244": "SUCCESS",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
@@ -173,7 +173,7 @@
173
  "250": "NOT_ALIVE",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
- "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NOT_ALIVE",
@@ -185,12 +185,12 @@
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
- "34": "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": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
@@ -198,12 +198,12 @@
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": "SUCCESS",
207
  "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
@@ -218,30 +218,30 @@
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
- "64": "NON_PARTICIPATING",
222
- "65": "NON_PARTICIPATING",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
- "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
- "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
- "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "SUCCESS",
240
- "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
  "83": "SUCCESS",
243
- "84": "NON_PARTICIPATING",
244
- "85": "SUCCESS",
245
  "86": "NON_PARTICIPATING",
246
  "87": "NOT_ALIVE",
247
  "88": "NON_PARTICIPATING",
@@ -252,8 +252,8 @@
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
- "95": "NOT_ALIVE",
256
- "96": "NON_PARTICIPATING",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
  "99": "SUCCESS"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6137674,
268
- 6137688
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": 656,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6133414,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
+ "106": "NOT_ALIVE",
14
  "107": "NOT_ALIVE",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NOT_ALIVE",
 
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
  "130": "NOT_ALIVE",
41
+ "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
  "133": "SUCCESS",
44
  "134": "NOT_ALIVE",
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": "SUCCESS",
52
  "141": "NON_PARTICIPATING",
53
+ "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
+ "147": "SUCCESS",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
 
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
+ "154": "NOT_ALIVE",
67
+ "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
 
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
80
  "167": "NOT_ALIVE",
81
+ "168": "NOT_ALIVE",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
+ "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
  "174": "NON_PARTICIPATING",
89
+ "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
92
  "178": "NOT_ALIVE",
93
+ "179": "NOT_ALIVE",
94
+ "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
  "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "NON_PARTICIPATING",
100
+ "185": "NOT_ALIVE",
101
  "186": "NOT_ALIVE",
102
+ "187": "SUCCESS",
103
+ "188": "SUCCESS",
104
+ "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
+ "190": "SUCCESS",
107
  "191": "NOT_ALIVE",
108
+ "192": "NON_PARTICIPATING",
109
+ "193": "NOT_ALIVE",
110
  "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "SUCCESS",
114
+ "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "NON_PARTICIPATING",
119
  "201": "SUCCESS",
120
  "202": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
  "212": "NON_PARTICIPATING",
132
+ "213": "NON_PARTICIPATING",
133
+ "214": "NON_PARTICIPATING",
134
+ "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
+ "217": "SUCCESS",
137
+ "218": "NOT_ALIVE",
138
+ "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
+ "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
+ "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
+ "23": "NOT_ALIVE",
151
  "230": "SUCCESS",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
 
163
  "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NOT_ALIVE",
166
+ "244": "NON_PARTICIPATING",
167
  "245": "NON_PARTICIPATING",
168
  "246": "NON_PARTICIPATING",
169
  "247": "NOT_ALIVE",
 
173
  "250": "NOT_ALIVE",
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
+ "253": "NON_PARTICIPATING",
177
  "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
  "26": "NOT_ALIVE",
 
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
+ "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
+ "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
+ "38": "NON_PARTICIPATING",
193
+ "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
 
198
  "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
+ "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
+ "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
+ "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
 
218
  "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
+ "64": "NOT_ALIVE",
222
+ "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
+ "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
+ "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
+ "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "SUCCESS",
240
+ "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "SUCCESS",
243
+ "84": "NOT_ALIVE",
244
+ "85": "NOT_ALIVE",
245
  "86": "NON_PARTICIPATING",
246
  "87": "NOT_ALIVE",
247
  "88": "NON_PARTICIPATING",
 
252
  "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "NON_PARTICIPATING",
256
+ "96": "NOT_ALIVE",
257
  "97": "NON_PARTICIPATING",
258
  "98": "NON_PARTICIPATING",
259
  "99": "SUCCESS"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6137773,
268
+ 6137788
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": 6137633,
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:da400c3e8b93115a65217ebf29990413b660d7e8a3395cfdbadc907b74642c9b
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43386c39310e8b1d351d03aacf96c768b1f607d566c1281041644151b43f8594
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66ae6f9847a5692d2c52d2ce813574b5a051fd24c3cb34306a941d3791be3d95
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a81d3e19602ba1bd1169c021fa0bd7b4a9fdfae798ca15178fa52d621068c50
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49b8413a846f504cb4f5e10e5d0f383ac2c64817d6fa7fcdf670b0ea5935c4b1
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c10180090c62d44ec9387c77ce86f8188b4abd21dd568517be7169cd8f913c
3
  size 4400216536