zeras141a commited on
Commit
1f9d8e6
·
verified ·
1 Parent(s): ed37e39

Run 8. Outer Step 121. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +79 -79
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -11,41 +11,41 @@
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
- "107": "NOT_ALIVE",
15
- "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "SUCCESS",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NON_PARTICIPATING",
22
- "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
- "117": "NON_PARTICIPATING",
26
  "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "SUCCESS",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
- "122": "NON_PARTICIPATING",
32
  "123": "NON_PARTICIPATING",
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": "FAIL",
41
- "131": "NOT_ALIVE",
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": "NOT_ALIVE",
49
  "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
@@ -56,18 +56,18 @@
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
- "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
- "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
- "158": "SUCCESS",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
@@ -79,90 +79,90 @@
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": "SUCCESS",
86
  "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
- "174": "NON_PARTICIPATING",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "NOT_ALIVE",
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": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
- "191": "NON_PARTICIPATING",
108
- "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
- "194": "SUCCESS",
111
  "195": "NON_PARTICIPATING",
112
- "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
- "199": "FAIL",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
- "202": "NOT_ALIVE",
121
- "203": "FAIL",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NOT_ALIVE",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NOT_ALIVE",
127
- "209": "FAIL",
128
- "21": "NOT_ALIVE",
129
  "210": "SUCCESS",
130
  "211": "SUCCESS",
131
  "212": "NON_PARTICIPATING",
132
  "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
134
- "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
- "217": "SUCCESS",
137
- "218": "SUCCESS",
138
- "219": "NON_PARTICIPATING",
139
  "22": "NOT_ALIVE",
140
- "220": "SUCCESS",
141
  "221": "NON_PARTICIPATING",
142
- "222": "NON_PARTICIPATING",
143
- "223": "FAIL",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
  "226": "SUCCESS",
147
- "227": "SUCCESS",
148
- "228": "NON_PARTICIPATING",
149
  "229": "NOT_ALIVE",
150
- "23": "SUCCESS",
151
- "230": "NOT_ALIVE",
152
  "231": "SUCCESS",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
  "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
- "237": "FAIL",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
- "242": "NON_PARTICIPATING",
165
- "243": "NON_PARTICIPATING",
166
  "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
@@ -171,77 +171,77 @@
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
- "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
- "253": "NON_PARTICIPATING",
177
  "254": "NOT_ALIVE",
178
- "255": "NON_PARTICIPATING",
179
- "26": "NOT_ALIVE",
180
  "27": "SUCCESS",
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": "NON_PARTICIPATING",
188
- "34": "NON_PARTICIPATING",
189
  "35": "NON_PARTICIPATING",
190
- "36": "FAIL",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
- "40": "FAIL",
196
  "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
- "44": "NON_PARTICIPATING",
200
  "45": "NON_PARTICIPATING",
201
- "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NON_PARTICIPATING",
208
- "52": "NON_PARTICIPATING",
209
- "53": "NOT_ALIVE",
210
- "54": "NON_PARTICIPATING",
211
- "55": "NON_PARTICIPATING",
212
- "56": "NON_PARTICIPATING",
213
  "57": "NOT_ALIVE",
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": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
- "65": "FAIL",
223
- "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "NOT_ALIVE",
226
- "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
- "71": "FAIL",
230
- "72": "SUCCESS",
231
- "73": "NOT_ALIVE",
232
- "74": "NON_PARTICIPATING",
233
- "75": "NOT_ALIVE",
234
  "76": "NON_PARTICIPATING",
235
- "77": "NOT_ALIVE",
236
  "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
- "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
- "85": "NON_PARTICIPATING",
245
  "86": "SUCCESS",
246
  "87": "SUCCESS",
247
  "88": "SUCCESS",
@@ -251,12 +251,12 @@
251
  "91": "SUCCESS",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
- "94": "NON_PARTICIPATING",
255
  "95": "NON_PARTICIPATING",
256
  "96": "SUCCESS",
257
- "97": "NON_PARTICIPATING",
258
  "98": "NOT_ALIVE",
259
- "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6439992,
268
- 6439999
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": 105,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6439452,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NOT_ALIVE",
14
+ "107": "NON_PARTICIPATING",
15
+ "108": "NOT_ALIVE",
16
  "109": "NON_PARTICIPATING",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
  "111": "SUCCESS",
20
+ "112": "SUCCESS",
21
  "113": "NON_PARTICIPATING",
22
+ "114": "NON_PARTICIPATING",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
+ "117": "SUCCESS",
26
  "118": "SUCCESS",
27
  "119": "NON_PARTICIPATING",
28
  "12": "SUCCESS",
29
  "120": "NOT_ALIVE",
30
  "121": "NON_PARTICIPATING",
31
+ "122": "NOT_ALIVE",
32
  "123": "NON_PARTICIPATING",
33
+ "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NOT_ALIVE",
36
  "127": "SUCCESS",
37
  "128": "NON_PARTICIPATING",
38
+ "129": "NOT_ALIVE",
39
  "13": "SUCCESS",
40
+ "130": "NON_PARTICIPATING",
41
+ "131": "NON_PARTICIPATING",
42
  "132": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "NON_PARTICIPATING",
 
56
  "145": "NOT_ALIVE",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
+ "148": "NOT_ALIVE",
60
  "149": "NON_PARTICIPATING",
61
  "15": "NOT_ALIVE",
62
  "150": "SUCCESS",
63
  "151": "NON_PARTICIPATING",
64
+ "152": "FAIL",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NOT_ALIVE",
67
  "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
+ "158": "FAIL",
71
  "159": "NOT_ALIVE",
72
  "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
 
79
  "166": "NON_PARTICIPATING",
80
  "167": "NON_PARTICIPATING",
81
  "168": "SUCCESS",
82
+ "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "NOT_ALIVE",
85
  "171": "SUCCESS",
86
  "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
+ "174": "NOT_ALIVE",
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": "NOT_ALIVE",
97
  "182": "SUCCESS",
98
  "183": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
+ "185": "SUCCESS",
101
  "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "NOT_ALIVE",
108
+ "192": "NOT_ALIVE",
109
  "193": "NON_PARTICIPATING",
110
+ "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
112
+ "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
+ "202": "NON_PARTICIPATING",
121
+ "203": "NON_PARTICIPATING",
122
  "204": "NOT_ALIVE",
123
  "205": "NON_PARTICIPATING",
124
  "206": "NOT_ALIVE",
125
  "207": "NON_PARTICIPATING",
126
  "208": "NOT_ALIVE",
127
+ "209": "SUCCESS",
128
+ "21": "SUCCESS",
129
  "210": "SUCCESS",
130
  "211": "SUCCESS",
131
  "212": "NON_PARTICIPATING",
132
  "213": "SUCCESS",
133
  "214": "NON_PARTICIPATING",
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": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
+ "222": "NOT_ALIVE",
143
+ "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
  "226": "SUCCESS",
147
+ "227": "NON_PARTICIPATING",
148
+ "228": "SUCCESS",
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": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
  "239": "NON_PARTICIPATING",
161
  "24": "NOT_ALIVE",
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",
 
171
  "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
+ "251": "SUCCESS",
175
  "252": "NON_PARTICIPATING",
176
+ "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
+ "255": "NOT_ALIVE",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
+ "28": "NOT_ALIVE",
182
  "29": "NON_PARTICIPATING",
183
  "3": "NOT_ALIVE",
184
  "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NON_PARTICIPATING",
188
+ "34": "NOT_ALIVE",
189
  "35": "NON_PARTICIPATING",
190
+ "36": "NOT_ALIVE",
191
  "37": "NON_PARTICIPATING",
192
  "38": "NON_PARTICIPATING",
193
  "39": "NOT_ALIVE",
194
  "4": "SUCCESS",
195
+ "40": "SUCCESS",
196
  "41": "NON_PARTICIPATING",
197
  "42": "SUCCESS",
198
  "43": "NOT_ALIVE",
199
+ "44": "NOT_ALIVE",
200
  "45": "NON_PARTICIPATING",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
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": "NOT_ALIVE",
212
+ "56": "SUCCESS",
213
  "57": "NOT_ALIVE",
214
  "58": "NOT_ALIVE",
215
  "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
  "60": "NON_PARTICIPATING",
218
+ "61": "SUCCESS",
219
+ "62": "FAIL",
220
  "63": "NON_PARTICIPATING",
221
  "64": "NOT_ALIVE",
222
+ "65": "SUCCESS",
223
+ "66": "NOT_ALIVE",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "NON_PARTICIPATING",
226
+ "69": "NON_PARTICIPATING",
227
  "7": "NOT_ALIVE",
228
  "70": "NON_PARTICIPATING",
229
+ "71": "SUCCESS",
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",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NON_PARTICIPATING",
241
+ "82": "SUCCESS",
242
  "83": "NOT_ALIVE",
243
  "84": "NON_PARTICIPATING",
244
+ "85": "NOT_ALIVE",
245
  "86": "SUCCESS",
246
  "87": "SUCCESS",
247
  "88": "SUCCESS",
 
251
  "91": "SUCCESS",
252
  "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
+ "94": "NOT_ALIVE",
255
  "95": "NON_PARTICIPATING",
256
  "96": "SUCCESS",
257
+ "97": "NOT_ALIVE",
258
  "98": "NOT_ALIVE",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6440058,
268
+ 6440067
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": 6440039,
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:e6af482373cef277a86953f60b0ae04e7d5c0e760e096506219bb6488dc3f111
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caa9a7db6b0fb8cf5f855ee6e306cdd6f7c16b87e5734589fb88fed8fe256a49
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c87a370622593467c4431393ae00461be37cb974e9d7eede7e3155abed6741f
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a09ee6aaeccaa0cd1981d7ad21b9c2d9ef3a706392e1e1e3d2bce210f10302cc
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8ab1bebad1ac6d482346648d617d81359015eb851ac76f79ee57a2d7eb00afa
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bea3827c94f61ed86b92abaa8c8072d09b4f20d6484f1c31e19d69183d3e2e0
3
  size 4400216536