zeras141a commited on
Commit
8a40314
·
verified ·
1 Parent(s): 44100a1

Run 6. Outer Step 108. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +47 -47
  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": "NOT_ALIVE",
20
- "112": "NOT_ALIVE",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
@@ -37,21 +37,21 @@
37
  "128": "NOT_ALIVE",
38
  "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
- "130": "SUCCESS",
41
  "131": "NOT_ALIVE",
42
  "132": "NOT_ALIVE",
43
- "133": "NON_PARTICIPATING",
44
  "134": "NOT_ALIVE",
45
  "135": "NOT_ALIVE",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
- "138": "SUCCESS",
49
  "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
52
  "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
- "143": "NOT_ALIVE",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
@@ -63,7 +63,7 @@
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
- "154": "SUCCESS",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
@@ -73,18 +73,18 @@
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
- "163": "NON_PARTICIPATING",
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": "NOT_ALIVE",
85
- "171": "NON_PARTICIPATING",
86
  "172": "NOT_ALIVE",
87
- "173": "NON_PARTICIPATING",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
@@ -98,20 +98,20 @@
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
- "186": "NON_PARTICIPATING",
102
  "187": "NOT_ALIVE",
103
  "188": "NOT_ALIVE",
104
- "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
- "194": "NOT_ALIVE",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
- "198": "NOT_ALIVE",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
@@ -119,7 +119,7 @@
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
- "204": "NON_PARTICIPATING",
123
  "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
@@ -128,26 +128,26 @@
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
- "212": "NOT_ALIVE",
132
  "213": "NOT_ALIVE",
133
- "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
- "216": "NOT_ALIVE",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
- "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
- "225": "NOT_ALIVE",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
- "23": "SUCCESS",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
@@ -157,11 +157,11 @@
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
- "239": "NOT_ALIVE",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "SUCCESS",
164
- "242": "SUCCESS",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
@@ -170,14 +170,14 @@
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "NOT_ALIVE",
174
- "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
- "253": "NON_PARTICIPATING",
177
- "254": "NON_PARTICIPATING",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NON_PARTICIPATING",
180
- "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
@@ -186,21 +186,21 @@
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
- "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
- "40": "NON_PARTICIPATING",
196
  "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
  "44": "SUCCESS",
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",
@@ -209,19 +209,19 @@
209
  "53": "NOT_ALIVE",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
- "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
- "67": "NOT_ALIVE",
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
@@ -240,19 +240,19 @@
240
  "81": "NOT_ALIVE",
241
  "82": "NOT_ALIVE",
242
  "83": "NOT_ALIVE",
243
- "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
- "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
- "92": "NOT_ALIVE",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
- "95": "NOT_ALIVE",
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
- 6208602,
268
- 6208617
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": 398,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6205582,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
17
  "11": "NOT_ALIVE",
18
  "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
+ "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NOT_ALIVE",
 
37
  "128": "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": "NOT_ALIVE",
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": "SUCCESS",
55
  "144": "NOT_ALIVE",
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
 
63
  "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
+ "154": "NON_PARTICIPATING",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
 
73
  "160": "NON_PARTICIPATING",
74
  "161": "NON_PARTICIPATING",
75
  "162": "NOT_ALIVE",
76
+ "163": "NOT_ALIVE",
77
+ "164": "NON_PARTICIPATING",
78
+ "165": "NOT_ALIVE",
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": "NOT_ALIVE",
87
+ "173": "SUCCESS",
88
  "174": "NOT_ALIVE",
89
  "175": "NON_PARTICIPATING",
90
  "176": "NOT_ALIVE",
 
98
  "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
+ "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "NOT_ALIVE",
104
+ "189": "NOT_ALIVE",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
  "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
+ "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
  "196": "NOT_ALIVE",
113
  "197": "NOT_ALIVE",
114
+ "198": "NON_PARTICIPATING",
115
  "199": "NOT_ALIVE",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
 
119
  "201": "NOT_ALIVE",
120
  "202": "NOT_ALIVE",
121
  "203": "NOT_ALIVE",
122
+ "204": "NOT_ALIVE",
123
  "205": "NOT_ALIVE",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
 
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
+ "212": "SUCCESS",
132
  "213": "NOT_ALIVE",
133
+ "214": "SUCCESS",
134
  "215": "NON_PARTICIPATING",
135
+ "216": "NON_PARTICIPATING",
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NOT_ALIVE",
141
  "221": "NOT_ALIVE",
142
  "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
 
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
159
  "238": "NOT_ALIVE",
160
+ "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NOT_ALIVE",
163
  "241": "SUCCESS",
164
+ "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
 
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
+ "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
+ "253": "NOT_ALIVE",
177
+ "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "NOT_ALIVE",
180
+ "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
 
186
  "32": "NOT_ALIVE",
187
  "33": "NOT_ALIVE",
188
  "34": "NOT_ALIVE",
189
+ "35": "SUCCESS",
190
  "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NOT_ALIVE",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
  "41": "NOT_ALIVE",
197
  "42": "NOT_ALIVE",
198
  "43": "NON_PARTICIPATING",
199
  "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
+ "46": "NOT_ALIVE",
202
  "47": "NOT_ALIVE",
203
+ "48": "NOT_ALIVE",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
 
209
  "53": "NOT_ALIVE",
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": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "NOT_ALIVE",
221
  "64": "NON_PARTICIPATING",
222
+ "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
+ "67": "NON_PARTICIPATING",
225
  "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
 
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",
247
  "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
+ "92": "NON_PARTICIPATING",
253
  "93": "NOT_ALIVE",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "NON_PARTICIPATING",
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
+ 6208700,
268
+ 6208729
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": 6208650,
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 sha256:7f9ebeeb14b9a82f58001d15da249af0bfb1ed44052732fdb67376d698e2d744
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a060d5378823dab9ec94c88341c222399940bf3f85950329f590c77d2e3849
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c7a5d15c830321ca754d9310caf655d4a1a5b3fc1fe2318c72f5d8fbe69b9ad
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2046f721f70029b46226526f3b5f0c036c5f9147430664fbc76ae58c1b5f37d4
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d84fac5eea9078c89f6aa12d1b969109df0d4c85903cd3eeadc3cb4fdded28c2
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:983d636fddbac0acaae5108cf5b2e5e067b5ba040999a54bc5f7d7032bf6f1ad
3
  size 4400216536