zeras141a commited on
Commit
594632c
·
verified ·
1 Parent(s): 8187f21

Run 8. Outer Step 75. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +121 -123
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -4,11 +4,11 @@
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
- "100": "NON_PARTICIPATING",
8
- "101": "SUCCESS",
9
  "102": "NON_PARTICIPATING",
10
- "103": "NOT_ALIVE",
11
- "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
  "107": "SUCCESS",
@@ -23,240 +23,240 @@
23
  "115": "SUCCESS",
24
  "116": "SUCCESS",
25
  "117": "SUCCESS",
26
- "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "FAIL",
30
- "121": "NON_PARTICIPATING",
31
- "122": "SUCCESS",
32
  "123": "SUCCESS",
33
- "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
- "126": "SUCCESS",
36
  "127": "SUCCESS",
37
- "128": "NON_PARTICIPATING",
38
- "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
  "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
- "134": "NON_PARTICIPATING",
45
- "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "FAIL",
48
- "138": "NOT_ALIVE",
49
- "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "SUCCESS",
53
  "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
- "144": "SUCCESS",
56
  "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
- "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
  "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
- "150": "NOT_ALIVE",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
- "154": "SUCCESS",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "FAIL",
70
  "158": "NON_PARTICIPATING",
71
- "159": "SUCCESS",
72
  "16": "SUCCESS",
73
- "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
  "164": "SUCCESS",
78
- "165": "SUCCESS",
79
- "166": "SUCCESS",
80
- "167": "NON_PARTICIPATING",
81
- "168": "NON_PARTICIPATING",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
- "170": "SUCCESS",
85
  "171": "SUCCESS",
86
  "172": "NON_PARTICIPATING",
87
- "173": "SUCCESS",
88
  "174": "SUCCESS",
89
- "175": "FAIL",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
- "179": "NON_PARTICIPATING",
94
- "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
- "181": "NOT_ALIVE",
97
  "182": "NON_PARTICIPATING",
98
- "183": "NON_PARTICIPATING",
99
- "184": "NON_PARTICIPATING",
100
- "185": "SUCCESS",
101
- "186": "SUCCESS",
102
  "187": "NON_PARTICIPATING",
103
  "188": "FAIL",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "NON_PARTICIPATING",
107
- "191": "NON_PARTICIPATING",
108
- "192": "SUCCESS",
109
- "193": "NOT_ALIVE",
110
- "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
112
- "196": "FAIL",
113
- "197": "NOT_ALIVE",
114
- "198": "NON_PARTICIPATING",
115
- "199": "FAIL",
116
- "2": "SUCCESS",
117
- "20": "NOT_ALIVE",
118
- "200": "FAIL",
119
  "201": "NOT_ALIVE",
120
- "202": "FAIL",
121
- "203": "FAIL",
122
- "204": "NON_PARTICIPATING",
123
- "205": "NON_PARTICIPATING",
124
- "206": "NON_PARTICIPATING",
125
- "207": "NON_PARTICIPATING",
126
- "208": "SUCCESS",
127
- "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
- "210": "NON_PARTICIPATING",
130
  "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "FAIL",
134
- "215": "NON_PARTICIPATING",
135
- "216": "NOT_ALIVE",
136
  "217": "SUCCESS",
137
- "218": "SUCCESS",
138
- "219": "NON_PARTICIPATING",
139
- "22": "FAIL",
140
  "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
- "222": "SUCCESS",
143
- "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
- "225": "NON_PARTICIPATING",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
- "229": "NON_PARTICIPATING",
150
  "23": "SUCCESS",
151
- "230": "FAIL",
152
- "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
- "233": "SUCCESS",
155
  "234": "SUCCESS",
156
- "235": "SUCCESS",
157
- "236": "SUCCESS",
158
  "237": "NON_PARTICIPATING",
159
- "238": "SUCCESS",
160
- "239": "SUCCESS",
161
- "24": "SUCCESS",
162
- "240": "NOT_ALIVE",
163
- "241": "NOT_ALIVE",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
- "244": "SUCCESS",
167
  "245": "SUCCESS",
168
  "246": "SUCCESS",
169
  "247": "NON_PARTICIPATING",
170
- "248": "NOT_ALIVE",
171
- "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
- "252": "SUCCESS",
176
- "253": "NOT_ALIVE",
177
  "254": "NON_PARTICIPATING",
178
- "255": "NON_PARTICIPATING",
179
  "26": "SUCCESS",
180
- "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "NOT_ALIVE",
184
- "30": "FAIL",
185
  "31": "SUCCESS",
186
- "32": "NOT_ALIVE",
187
- "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
- "35": "FAIL",
190
- "36": "SUCCESS",
191
  "37": "SUCCESS",
192
  "38": "FAIL",
193
- "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
- "40": "NOT_ALIVE",
196
  "41": "SUCCESS",
197
  "42": "SUCCESS",
198
- "43": "NOT_ALIVE",
199
- "44": "NOT_ALIVE",
200
- "45": "NOT_ALIVE",
201
- "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "SUCCESS",
204
- "49": "FAIL",
205
- "5": "SUCCESS",
206
- "50": "SUCCESS",
207
  "51": "NON_PARTICIPATING",
208
- "52": "SUCCESS",
209
  "53": "SUCCESS",
210
- "54": "SUCCESS",
211
  "55": "SUCCESS",
212
  "56": "NON_PARTICIPATING",
213
  "57": "SUCCESS",
214
- "58": "SUCCESS",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
- "61": "FAIL",
219
  "62": "SUCCESS",
220
- "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "SUCCESS",
226
  "69": "SUCCESS",
227
- "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
  "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
- "74": "NON_PARTICIPATING",
233
- "75": "NON_PARTICIPATING",
234
  "76": "SUCCESS",
235
  "77": "SUCCESS",
236
- "78": "NON_PARTICIPATING",
237
- "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
  "80": "SUCCESS",
240
- "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
- "83": "NON_PARTICIPATING",
243
- "84": "NON_PARTICIPATING",
244
  "85": "SUCCESS",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
- "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "FAIL",
251
  "91": "NON_PARTICIPATING",
252
- "92": "SUCCESS",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
- "95": "FAIL",
256
  "96": "NON_PARTICIPATING",
257
- "97": "SUCCESS",
258
  "98": "NON_PARTICIPATING",
259
- "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,19 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6395753,
268
- 6395769,
269
- 6395783,
270
- 6395800
271
  ],
272
  "bos_token_id": 1,
273
  "eos_token_id": 2,
274
  "hidden_act": "silu",
275
  "hidden_size": 2048,
276
  "initializer_range": 0.02,
277
- "inner_step": 90,
278
  "intermediate_size": 5632,
279
- "last_allreduce_block": 6395177,
280
  "max_position_embeddings": 2048,
281
  "mlp_bias": false,
282
  "model_type": "llama",
 
4
  "0": "NOT_ALIVE",
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
+ "100": "NOT_ALIVE",
8
+ "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
+ "103": "SUCCESS",
11
+ "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "SUCCESS",
14
  "107": "SUCCESS",
 
23
  "115": "SUCCESS",
24
  "116": "SUCCESS",
25
  "117": "SUCCESS",
26
+ "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "FAIL",
30
+ "121": "NOT_ALIVE",
31
+ "122": "NON_PARTICIPATING",
32
  "123": "SUCCESS",
33
+ "124": "SUCCESS",
34
  "125": "NOT_ALIVE",
35
+ "126": "FAIL",
36
  "127": "SUCCESS",
37
+ "128": "SUCCESS",
38
+ "129": "SUCCESS",
39
  "13": "SUCCESS",
40
  "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
+ "134": "SUCCESS",
45
+ "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "FAIL",
48
+ "138": "FAIL",
49
+ "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "SUCCESS",
53
  "142": "SUCCESS",
54
  "143": "NON_PARTICIPATING",
55
+ "144": "NON_PARTICIPATING",
56
  "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
+ "147": "FAIL",
59
  "148": "NON_PARTICIPATING",
60
  "149": "SUCCESS",
61
  "15": "NOT_ALIVE",
62
+ "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
+ "154": "NON_PARTICIPATING",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "FAIL",
70
  "158": "NON_PARTICIPATING",
71
+ "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
+ "160": "SUCCESS",
74
+ "161": "SUCCESS",
75
  "162": "NON_PARTICIPATING",
76
  "163": "NON_PARTICIPATING",
77
  "164": "SUCCESS",
78
+ "165": "NON_PARTICIPATING",
79
+ "166": "NON_PARTICIPATING",
80
+ "167": "SUCCESS",
81
+ "168": "SUCCESS",
82
+ "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
+ "170": "FAIL",
85
  "171": "SUCCESS",
86
  "172": "NON_PARTICIPATING",
87
+ "173": "NOT_ALIVE",
88
  "174": "SUCCESS",
89
+ "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
+ "179": "NOT_ALIVE",
94
+ "18": "FAIL",
95
  "180": "SUCCESS",
96
+ "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
98
+ "183": "SUCCESS",
99
+ "184": "FAIL",
100
+ "185": "FAIL",
101
+ "186": "FAIL",
102
  "187": "NON_PARTICIPATING",
103
  "188": "FAIL",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
+ "191": "SUCCESS",
108
+ "192": "NON_PARTICIPATING",
109
+ "193": "NON_PARTICIPATING",
110
+ "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
+ "196": "SUCCESS",
113
+ "197": "NON_PARTICIPATING",
114
+ "198": "SUCCESS",
115
+ "199": "SUCCESS",
116
+ "2": "FAIL",
117
+ "20": "SUCCESS",
118
+ "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
+ "202": "SUCCESS",
121
+ "203": "SUCCESS",
122
+ "204": "SUCCESS",
123
+ "205": "SUCCESS",
124
+ "206": "NOT_ALIVE",
125
+ "207": "NOT_ALIVE",
126
+ "208": "NON_PARTICIPATING",
127
+ "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
+ "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "FAIL",
134
+ "215": "FAIL",
135
+ "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "FAIL",
138
+ "219": "SUCCESS",
139
+ "22": "SUCCESS",
140
  "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
+ "222": "NON_PARTICIPATING",
143
+ "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "FAIL",
146
  "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
+ "229": "SUCCESS",
150
  "23": "SUCCESS",
151
+ "230": "NON_PARTICIPATING",
152
+ "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
+ "233": "FAIL",
155
  "234": "SUCCESS",
156
+ "235": "NON_PARTICIPATING",
157
+ "236": "NOT_ALIVE",
158
  "237": "NON_PARTICIPATING",
159
+ "238": "NOT_ALIVE",
160
+ "239": "NON_PARTICIPATING",
161
+ "24": "FAIL",
162
+ "240": "SUCCESS",
163
+ "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
+ "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "SUCCESS",
169
  "247": "NON_PARTICIPATING",
170
+ "248": "NON_PARTICIPATING",
171
+ "249": "FAIL",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
  "251": "NOT_ALIVE",
175
+ "252": "NON_PARTICIPATING",
176
+ "253": "SUCCESS",
177
  "254": "NON_PARTICIPATING",
178
+ "255": "NOT_ALIVE",
179
  "26": "SUCCESS",
180
+ "27": "NON_PARTICIPATING",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "NOT_ALIVE",
184
+ "30": "SUCCESS",
185
  "31": "SUCCESS",
186
+ "32": "SUCCESS",
187
+ "33": "NON_PARTICIPATING",
188
  "34": "SUCCESS",
189
+ "35": "NOT_ALIVE",
190
+ "36": "NON_PARTICIPATING",
191
  "37": "SUCCESS",
192
  "38": "FAIL",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
  "41": "SUCCESS",
197
  "42": "SUCCESS",
198
+ "43": "NON_PARTICIPATING",
199
+ "44": "NON_PARTICIPATING",
200
+ "45": "NON_PARTICIPATING",
201
+ "46": "NOT_ALIVE",
202
  "47": "NON_PARTICIPATING",
203
  "48": "SUCCESS",
204
+ "49": "NON_PARTICIPATING",
205
+ "5": "NOT_ALIVE",
206
+ "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
+ "52": "FAIL",
209
  "53": "SUCCESS",
210
+ "54": "NON_PARTICIPATING",
211
  "55": "SUCCESS",
212
  "56": "NON_PARTICIPATING",
213
  "57": "SUCCESS",
214
+ "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "SUCCESS",
218
+ "61": "NOT_ALIVE",
219
  "62": "SUCCESS",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "NON_PARTICIPATING",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
  "68": "SUCCESS",
226
  "69": "SUCCESS",
227
+ "7": "SUCCESS",
228
  "70": "NOT_ALIVE",
229
  "71": "SUCCESS",
230
  "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "SUCCESS",
233
+ "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
  "77": "SUCCESS",
236
+ "78": "FAIL",
237
+ "79": "NON_PARTICIPATING",
238
  "8": "NOT_ALIVE",
239
  "80": "SUCCESS",
240
+ "81": "NON_PARTICIPATING",
241
  "82": "NON_PARTICIPATING",
242
+ "83": "NOT_ALIVE",
243
+ "84": "SUCCESS",
244
  "85": "SUCCESS",
245
  "86": "NON_PARTICIPATING",
246
  "87": "SUCCESS",
247
+ "88": "NOT_ALIVE",
248
  "89": "NOT_ALIVE",
249
  "9": "NOT_ALIVE",
250
  "90": "FAIL",
251
  "91": "NON_PARTICIPATING",
252
+ "92": "FAIL",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "SUCCESS",
256
  "96": "NON_PARTICIPATING",
257
+ "97": "FAIL",
258
  "98": "NON_PARTICIPATING",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6396889,
268
+ 6396905
 
 
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": 4,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6396547,
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 sha256:7d64c1f74abca09d9d3e7d28599ccd41fbf01b3b0d6404b68121420de4aff0e7
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c3598035d5e07e8c4ed0b25ab5a56fc7ff4ace8a9deecec25ad0762ca79386
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e9dbb69b0afd6bfe47ea2940c57014887c093b0f3ef0a6ed52daccc6f18a3b2
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:745d27e6a5e454258f6794d667161196b82e3e61ce04abf06956f15ef29ba2fb
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b14247940a070bfb8537bc6afca935160160324d53b71eb38077204bee76bf1
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feff846c1048f291b0abc452fd78ddfafe373935b7757282823c09f5a7fa8f5f
3
  size 4400216536