zeras141a commited on
Commit
f2a88f1
·
verified ·
1 Parent(s): 3c6fd1a

Run 8. Outer Step 128. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +70 -70
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -5,45 +5,45 @@
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
- "101": "NON_PARTICIPATING",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
- "104": "NON_PARTICIPATING",
12
- "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
- "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
- "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "NON_PARTICIPATING",
22
  "114": "SUCCESS",
23
- "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
- "117": "FAIL",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
- "121": "NOT_ALIVE",
31
  "122": "NON_PARTICIPATING",
32
- "123": "NON_PARTICIPATING",
33
- "124": "NOT_ALIVE",
34
- "125": "SUCCESS",
35
  "126": "NOT_ALIVE",
36
- "127": "NON_PARTICIPATING",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
- "13": "NOT_ALIVE",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "NON_PARTICIPATING",
43
  "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NOT_ALIVE",
46
- "136": "NOT_ALIVE",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
@@ -51,17 +51,17 @@
51
  "140": "NON_PARTICIPATING",
52
  "141": "SUCCESS",
53
  "142": "SUCCESS",
54
- "143": "SUCCESS",
55
- "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
- "150": "NON_PARTICIPATING",
63
- "151": "NOT_ALIVE",
64
- "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
@@ -76,28 +76,28 @@
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
- "166": "SUCCESS",
80
  "167": "SUCCESS",
81
- "168": "SUCCESS",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
86
- "172": "NOT_ALIVE",
87
- "173": "NOT_ALIVE",
88
- "174": "NON_PARTICIPATING",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
- "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NON_PARTICIPATING",
97
  "182": "SUCCESS",
98
  "183": "SUCCESS",
99
- "184": "NOT_ALIVE",
100
- "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
@@ -105,26 +105,26 @@
105
  "19": "NOT_ALIVE",
106
  "190": "SUCCESS",
107
  "191": "NON_PARTICIPATING",
108
- "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
- "196": "NON_PARTICIPATING",
113
  "197": "NOT_ALIVE",
114
  "198": "SUCCESS",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
- "200": "SUCCESS",
119
  "201": "SUCCESS",
120
- "202": "FAIL",
121
  "203": "SUCCESS",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
- "206": "NOT_ALIVE",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
- "209": "NON_PARTICIPATING",
128
  "21": "NOT_ALIVE",
129
  "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
@@ -133,13 +133,13 @@
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
- "217": "NON_PARTICIPATING",
137
- "218": "NOT_ALIVE",
138
- "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
- "222": "NOT_ALIVE",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
@@ -149,10 +149,10 @@
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
- "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
- "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
@@ -162,37 +162,37 @@
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
- "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
  "247": "SUCCESS",
170
- "248": "SUCCESS",
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
- "252": "NON_PARTICIPATING",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
- "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
- "29": "NOT_ALIVE",
183
  "3": "NOT_ALIVE",
184
- "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NON_PARTICIPATING",
187
- "33": "NON_PARTICIPATING",
188
  "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
- "36": "SUCCESS",
191
  "37": "NON_PARTICIPATING",
192
- "38": "SUCCESS",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
- "40": "NOT_ALIVE",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "SUCCESS",
@@ -201,7 +201,7 @@
201
  "46": "NON_PARTICIPATING",
202
  "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
204
- "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "SUCCESS",
@@ -209,7 +209,7 @@
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
- "56": "NOT_ALIVE",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
@@ -218,20 +218,20 @@
218
  "61": "SUCCESS",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
- "64": "NOT_ALIVE",
222
- "65": "NON_PARTICIPATING",
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
- "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
- "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
- "73": "NOT_ALIVE",
232
  "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
- "76": "SUCCESS",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
@@ -242,21 +242,21 @@
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
- "86": "SUCCESS",
246
- "87": "SUCCESS",
247
- "88": "SUCCESS",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
- "91": "SUCCESS",
252
  "92": "NON_PARTICIPATING",
253
- "93": "SUCCESS",
254
  "94": "SUCCESS",
255
  "95": "NON_PARTICIPATING",
256
- "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
- "98": "SUCCESS",
259
- "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6444400,
268
- 6444416
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": 72,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6443839,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
5
  "1": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
+ "101": "NOT_ALIVE",
9
  "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
+ "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
  "106": "NOT_ALIVE",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
+ "109": "SUCCESS",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "NON_PARTICIPATING",
22
  "114": "SUCCESS",
23
+ "115": "NOT_ALIVE",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "NON_PARTICIPATING",
26
  "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NOT_ALIVE",
30
+ "121": "NON_PARTICIPATING",
31
  "122": "NON_PARTICIPATING",
32
+ "123": "SUCCESS",
33
+ "124": "NON_PARTICIPATING",
34
+ "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
+ "127": "SUCCESS",
37
  "128": "NON_PARTICIPATING",
38
  "129": "NON_PARTICIPATING",
39
+ "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "NON_PARTICIPATING",
43
  "133": "SUCCESS",
44
  "134": "NON_PARTICIPATING",
45
  "135": "NOT_ALIVE",
46
+ "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
 
51
  "140": "NON_PARTICIPATING",
52
  "141": "SUCCESS",
53
  "142": "SUCCESS",
54
+ "143": "NON_PARTICIPATING",
55
+ "144": "NON_PARTICIPATING",
56
  "145": "NOT_ALIVE",
57
  "146": "SUCCESS",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
+ "150": "NOT_ALIVE",
63
+ "151": "NON_PARTICIPATING",
64
+ "152": "SUCCESS",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
  "155": "NOT_ALIVE",
 
76
  "163": "NOT_ALIVE",
77
  "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
+ "166": "NON_PARTICIPATING",
80
  "167": "SUCCESS",
81
+ "168": "NON_PARTICIPATING",
82
+ "169": "NOT_ALIVE",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "NON_PARTICIPATING",
86
+ "172": "NON_PARTICIPATING",
87
+ "173": "SUCCESS",
88
+ "174": "NOT_ALIVE",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "NON_PARTICIPATING",
92
+ "178": "SUCCESS",
93
  "179": "NON_PARTICIPATING",
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NON_PARTICIPATING",
97
  "182": "SUCCESS",
98
  "183": "SUCCESS",
99
+ "184": "NON_PARTICIPATING",
100
+ "185": "SUCCESS",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
 
105
  "19": "NOT_ALIVE",
106
  "190": "SUCCESS",
107
  "191": "NON_PARTICIPATING",
108
+ "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
+ "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "SUCCESS",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "NON_PARTICIPATING",
119
  "201": "SUCCESS",
120
+ "202": "SUCCESS",
121
  "203": "SUCCESS",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
+ "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "SUCCESS",
128
  "21": "NOT_ALIVE",
129
  "210": "SUCCESS",
130
  "211": "NON_PARTICIPATING",
 
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
+ "217": "NOT_ALIVE",
137
+ "218": "SUCCESS",
138
+ "219": "NOT_ALIVE",
139
  "22": "NOT_ALIVE",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
+ "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
 
149
  "229": "NOT_ALIVE",
150
  "23": "NOT_ALIVE",
151
  "230": "NON_PARTICIPATING",
152
+ "231": "NON_PARTICIPATING",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
  "237": "SUCCESS",
 
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "NOT_ALIVE",
165
+ "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
  "247": "SUCCESS",
170
+ "248": "NON_PARTICIPATING",
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
+ "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NOT_ALIVE",
179
+ "26": "NOT_ALIVE",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
+ "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NON_PARTICIPATING",
187
+ "33": "NOT_ALIVE",
188
  "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
+ "36": "NON_PARTICIPATING",
191
  "37": "NON_PARTICIPATING",
192
+ "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
  "4": "NOT_ALIVE",
195
+ "40": "SUCCESS",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NON_PARTICIPATING",
198
  "43": "SUCCESS",
 
201
  "46": "NON_PARTICIPATING",
202
  "47": "SUCCESS",
203
  "48": "NON_PARTICIPATING",
204
+ "49": "SUCCESS",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "SUCCESS",
 
209
  "53": "NON_PARTICIPATING",
210
  "54": "NON_PARTICIPATING",
211
  "55": "NON_PARTICIPATING",
212
+ "56": "NON_PARTICIPATING",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
 
218
  "61": "SUCCESS",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
+ "64": "NON_PARTICIPATING",
222
+ "65": "SUCCESS",
223
  "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
+ "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
+ "73": "NON_PARTICIPATING",
232
  "74": "SUCCESS",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "NON_PARTICIPATING",
235
  "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
 
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
  "85": "NON_PARTICIPATING",
245
+ "86": "NON_PARTICIPATING",
246
+ "87": "NON_PARTICIPATING",
247
+ "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "NON_PARTICIPATING",
251
+ "91": "NON_PARTICIPATING",
252
  "92": "NON_PARTICIPATING",
253
+ "93": "NON_PARTICIPATING",
254
  "94": "SUCCESS",
255
  "95": "NON_PARTICIPATING",
256
+ "96": "SUCCESS",
257
  "97": "SUCCESS",
258
+ "98": "FAIL",
259
+ "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6444548,
268
+ 6444561
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": 6444495,
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:ca65868f6343f1bbfb5b6c20c43ff4098b57b0a260ea45cb8ccb7843caf0f33b
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75ed45e53c298ea6f253b0c02b34db8c8af4bb90a2ef90db7665ab5f8d36ccbb
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a516a3ba355fca6c974e2f1999516d9e35d405a6a9038f941cc46ee9a14649a
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f216229c662502a95567207a27a33eee6aea38b9d20626c286d6d35bb411ca96
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:863a75ccdb70090ef2d8b5edbf4dd3bcf1a81018d403ba129ffdaefc672dd471
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9fefbe027661b8d735b15c0264209d3760c88e9dbc77a8665d1c2e3e3c5b2de
3
  size 4400216536