zeras141a commited on
Commit
78a0309
·
verified ·
1 Parent(s): cbce009

Run 8. Outer Step 94. Inner Step 240.

Browse files
Files changed (4) hide show
  1. config.json +199 -199
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +2 -2
  4. model.safetensors +1 -1
config.json CHANGED
@@ -1,262 +1,262 @@
1
  {
2
- "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
- "0": "SUCCESS",
5
- "1": "SUCCESS",
6
- "10": "SUCCESS",
7
- "100": "SUCCESS",
8
- "101": "SUCCESS",
9
- "102": "SUCCESS",
10
- "103": "SUCCESS",
11
- "104": "SUCCESS",
12
- "105": "SUCCESS",
13
  "106": "SUCCESS",
14
- "107": "SUCCESS",
15
- "108": "SUCCESS",
16
  "109": "SUCCESS",
17
- "11": "SUCCESS",
18
  "110": "SUCCESS",
19
- "111": "SUCCESS",
20
- "112": "SUCCESS",
21
- "113": "SUCCESS",
22
- "114": "SUCCESS",
23
- "115": "SUCCESS",
24
- "116": "SUCCESS",
25
- "117": "SUCCESS",
26
- "118": "SUCCESS",
27
- "119": "SUCCESS",
28
- "12": "SUCCESS",
29
- "120": "SUCCESS",
30
- "121": "SUCCESS",
31
- "122": "SUCCESS",
32
- "123": "SUCCESS",
33
  "124": "SUCCESS",
34
- "125": "SUCCESS",
35
  "126": "SUCCESS",
36
- "127": "SUCCESS",
37
- "128": "SUCCESS",
38
  "129": "SUCCESS",
39
- "13": "SUCCESS",
40
- "130": "SUCCESS",
41
- "131": "SUCCESS",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
- "134": "SUCCESS",
45
  "135": "SUCCESS",
46
- "136": "SUCCESS",
47
- "137": "SUCCESS",
48
- "138": "SUCCESS",
49
  "139": "SUCCESS",
50
- "14": "SUCCESS",
51
  "140": "SUCCESS",
52
- "141": "SUCCESS",
53
- "142": "SUCCESS",
54
- "143": "SUCCESS",
55
- "144": "SUCCESS",
56
  "145": "SUCCESS",
57
- "146": "SUCCESS",
58
- "147": "SUCCESS",
59
- "148": "SUCCESS",
60
  "149": "SUCCESS",
61
- "15": "SUCCESS",
62
- "150": "SUCCESS",
63
- "151": "SUCCESS",
64
- "152": "SUCCESS",
65
- "153": "SUCCESS",
66
  "154": "SUCCESS",
67
  "155": "SUCCESS",
68
  "156": "SUCCESS",
69
- "157": "SUCCESS",
70
- "158": "SUCCESS",
71
  "159": "SUCCESS",
72
- "16": "SUCCESS",
73
  "160": "SUCCESS",
74
  "161": "SUCCESS",
75
- "162": "SUCCESS",
76
- "163": "SUCCESS",
77
- "164": "SUCCESS",
78
- "165": "SUCCESS",
79
- "166": "SUCCESS",
80
- "167": "SUCCESS",
81
  "168": "SUCCESS",
82
- "169": "SUCCESS",
83
- "17": "SUCCESS",
84
  "170": "SUCCESS",
85
- "171": "SUCCESS",
86
- "172": "SUCCESS",
87
  "173": "SUCCESS",
88
- "174": "SUCCESS",
89
  "175": "SUCCESS",
90
- "176": "SUCCESS",
91
  "177": "SUCCESS",
92
- "178": "SUCCESS",
93
- "179": "SUCCESS",
94
- "18": "SUCCESS",
95
- "180": "SUCCESS",
96
- "181": "SUCCESS",
97
- "182": "SUCCESS",
98
  "183": "SUCCESS",
99
- "184": "SUCCESS",
100
  "185": "SUCCESS",
101
- "186": "SUCCESS",
102
- "187": "SUCCESS",
103
  "188": "SUCCESS",
104
- "189": "SUCCESS",
105
- "19": "SUCCESS",
106
- "190": "SUCCESS",
107
  "191": "SUCCESS",
108
- "192": "SUCCESS",
109
- "193": "SUCCESS",
110
  "194": "SUCCESS",
111
- "195": "SUCCESS",
112
- "196": "SUCCESS",
113
- "197": "SUCCESS",
114
- "198": "SUCCESS",
115
  "199": "SUCCESS",
116
- "2": "SUCCESS",
117
- "20": "SUCCESS",
118
  "200": "SUCCESS",
119
- "201": "SUCCESS",
120
- "202": "SUCCESS",
121
- "203": "SUCCESS",
122
  "204": "SUCCESS",
123
- "205": "SUCCESS",
124
- "206": "SUCCESS",
125
- "207": "SUCCESS",
126
- "208": "SUCCESS",
127
- "209": "SUCCESS",
128
- "21": "SUCCESS",
129
- "210": "SUCCESS",
130
  "211": "SUCCESS",
131
- "212": "SUCCESS",
132
  "213": "SUCCESS",
133
- "214": "SUCCESS",
134
- "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "SUCCESS",
138
- "219": "SUCCESS",
139
  "22": "SUCCESS",
140
- "220": "SUCCESS",
141
- "221": "SUCCESS",
142
- "222": "SUCCESS",
143
- "223": "SUCCESS",
144
- "224": "SUCCESS",
145
  "225": "SUCCESS",
146
- "226": "SUCCESS",
147
  "227": "SUCCESS",
148
- "228": "SUCCESS",
149
- "229": "SUCCESS",
150
- "23": "SUCCESS",
151
- "230": "SUCCESS",
152
- "231": "SUCCESS",
153
- "232": "SUCCESS",
154
- "233": "SUCCESS",
155
  "234": "SUCCESS",
156
- "235": "SUCCESS",
157
- "236": "SUCCESS",
158
- "237": "SUCCESS",
159
  "238": "SUCCESS",
160
- "239": "SUCCESS",
161
  "24": "SUCCESS",
162
- "240": "SUCCESS",
163
- "241": "SUCCESS",
164
- "242": "SUCCESS",
165
- "243": "SUCCESS",
166
- "244": "SUCCESS",
167
  "245": "SUCCESS",
168
- "246": "SUCCESS",
169
  "247": "SUCCESS",
170
  "248": "SUCCESS",
171
- "249": "SUCCESS",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
  "251": "SUCCESS",
175
- "252": "SUCCESS",
176
  "253": "SUCCESS",
177
- "254": "SUCCESS",
178
  "255": "SUCCESS",
179
- "26": "SUCCESS",
180
  "27": "SUCCESS",
181
- "28": "SUCCESS",
182
- "29": "SUCCESS",
183
- "3": "SUCCESS",
184
- "30": "SUCCESS",
185
  "31": "SUCCESS",
186
- "32": "SUCCESS",
187
- "33": "SUCCESS",
188
- "34": "SUCCESS",
189
- "35": "SUCCESS",
190
- "36": "SUCCESS",
191
- "37": "SUCCESS",
192
- "38": "SUCCESS",
193
- "39": "SUCCESS",
194
- "4": "SUCCESS",
195
- "40": "SUCCESS",
196
- "41": "SUCCESS",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "SUCCESS",
200
- "45": "SUCCESS",
201
- "46": "SUCCESS",
202
- "47": "SUCCESS",
203
  "48": "SUCCESS",
204
- "49": "SUCCESS",
205
- "5": "SUCCESS",
206
- "50": "SUCCESS",
207
- "51": "SUCCESS",
208
- "52": "SUCCESS",
209
- "53": "SUCCESS",
210
- "54": "SUCCESS",
211
- "55": "SUCCESS",
212
  "56": "SUCCESS",
213
- "57": "SUCCESS",
214
- "58": "SUCCESS",
215
- "59": "SUCCESS",
216
- "6": "SUCCESS",
217
- "60": "SUCCESS",
218
  "61": "SUCCESS",
219
  "62": "SUCCESS",
220
- "63": "SUCCESS",
221
- "64": "SUCCESS",
222
- "65": "SUCCESS",
223
- "66": "SUCCESS",
224
- "67": "SUCCESS",
225
- "68": "SUCCESS",
226
- "69": "SUCCESS",
227
- "7": "SUCCESS",
228
- "70": "SUCCESS",
229
- "71": "SUCCESS",
230
- "72": "SUCCESS",
231
- "73": "SUCCESS",
232
- "74": "SUCCESS",
233
- "75": "SUCCESS",
234
  "76": "SUCCESS",
235
- "77": "SUCCESS",
236
- "78": "SUCCESS",
237
- "79": "SUCCESS",
238
- "8": "SUCCESS",
239
- "80": "SUCCESS",
240
- "81": "SUCCESS",
241
- "82": "SUCCESS",
242
- "83": "SUCCESS",
243
- "84": "SUCCESS",
244
- "85": "SUCCESS",
245
- "86": "SUCCESS",
246
- "87": "SUCCESS",
247
- "88": "SUCCESS",
248
- "89": "SUCCESS",
249
- "9": "SUCCESS",
250
- "90": "SUCCESS",
251
- "91": "SUCCESS",
252
- "92": "SUCCESS",
253
- "93": "SUCCESS",
254
- "94": "SUCCESS",
255
  "95": "SUCCESS",
256
- "96": "SUCCESS",
257
- "97": "SUCCESS",
258
- "98": "SUCCESS",
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
- 6413950,
268
- 6413967
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": 6317911,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "zeras141a/tata",
3
  "all_reduce_scores": {
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": "NOT_ALIVE",
11
+ "104": "NOT_ALIVE",
12
+ "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
+ "107": "NOT_ALIVE",
15
+ "108": "NOT_ALIVE",
16
  "109": "SUCCESS",
17
+ "11": "NOT_ALIVE",
18
  "110": "SUCCESS",
19
+ "111": "NOT_ALIVE",
20
+ "112": "NON_PARTICIPATING",
21
+ "113": "NON_PARTICIPATING",
22
+ "114": "NON_PARTICIPATING",
23
+ "115": "NOT_ALIVE",
24
+ "116": "NOT_ALIVE",
25
+ "117": "NOT_ALIVE",
26
+ "118": "NOT_ALIVE",
27
+ "119": "NON_PARTICIPATING",
28
+ "12": "NOT_ALIVE",
29
+ "120": "NON_PARTICIPATING",
30
+ "121": "NON_PARTICIPATING",
31
+ "122": "NON_PARTICIPATING",
32
+ "123": "NOT_ALIVE",
33
  "124": "SUCCESS",
34
+ "125": "NOT_ALIVE",
35
  "126": "SUCCESS",
36
+ "127": "NOT_ALIVE",
37
+ "128": "NON_PARTICIPATING",
38
  "129": "SUCCESS",
39
+ "13": "NOT_ALIVE",
40
+ "130": "NON_PARTICIPATING",
41
+ "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
+ "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
+ "136": "NON_PARTICIPATING",
47
+ "137": "NOT_ALIVE",
48
+ "138": "NOT_ALIVE",
49
  "139": "SUCCESS",
50
+ "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
+ "141": "NON_PARTICIPATING",
53
+ "142": "NOT_ALIVE",
54
+ "143": "NOT_ALIVE",
55
+ "144": "NOT_ALIVE",
56
  "145": "SUCCESS",
57
+ "146": "NOT_ALIVE",
58
+ "147": "NON_PARTICIPATING",
59
+ "148": "NOT_ALIVE",
60
  "149": "SUCCESS",
61
+ "15": "NOT_ALIVE",
62
+ "150": "NOT_ALIVE",
63
+ "151": "NON_PARTICIPATING",
64
+ "152": "NOT_ALIVE",
65
+ "153": "NOT_ALIVE",
66
  "154": "SUCCESS",
67
  "155": "SUCCESS",
68
  "156": "SUCCESS",
69
+ "157": "NON_PARTICIPATING",
70
+ "158": "NON_PARTICIPATING",
71
  "159": "SUCCESS",
72
+ "16": "NOT_ALIVE",
73
  "160": "SUCCESS",
74
  "161": "SUCCESS",
75
+ "162": "NON_PARTICIPATING",
76
+ "163": "NOT_ALIVE",
77
+ "164": "NON_PARTICIPATING",
78
+ "165": "NON_PARTICIPATING",
79
+ "166": "NOT_ALIVE",
80
+ "167": "NOT_ALIVE",
81
  "168": "SUCCESS",
82
+ "169": "NOT_ALIVE",
83
+ "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
+ "171": "NOT_ALIVE",
86
+ "172": "NOT_ALIVE",
87
  "173": "SUCCESS",
88
+ "174": "NON_PARTICIPATING",
89
  "175": "SUCCESS",
90
+ "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
+ "178": "NON_PARTICIPATING",
93
+ "179": "NON_PARTICIPATING",
94
+ "18": "NOT_ALIVE",
95
+ "180": "NON_PARTICIPATING",
96
+ "181": "NON_PARTICIPATING",
97
+ "182": "NOT_ALIVE",
98
  "183": "SUCCESS",
99
+ "184": "NON_PARTICIPATING",
100
  "185": "SUCCESS",
101
+ "186": "NON_PARTICIPATING",
102
+ "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
+ "189": "NOT_ALIVE",
105
+ "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
  "191": "SUCCESS",
108
+ "192": "NON_PARTICIPATING",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "SUCCESS",
111
+ "195": "NON_PARTICIPATING",
112
+ "196": "NOT_ALIVE",
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": "NOT_ALIVE",
122
  "204": "SUCCESS",
123
+ "205": "NOT_ALIVE",
124
+ "206": "NON_PARTICIPATING",
125
+ "207": "NOT_ALIVE",
126
+ "208": "NON_PARTICIPATING",
127
+ "209": "NOT_ALIVE",
128
+ "21": "NOT_ALIVE",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
+ "212": "NOT_ALIVE",
132
  "213": "SUCCESS",
133
+ "214": "NOT_ALIVE",
134
+ "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "SUCCESS",
138
+ "219": "NON_PARTICIPATING",
139
  "22": "SUCCESS",
140
+ "220": "FAIL",
141
+ "221": "NOT_ALIVE",
142
+ "222": "NOT_ALIVE",
143
+ "223": "NOT_ALIVE",
144
+ "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
+ "226": "NOT_ALIVE",
147
  "227": "SUCCESS",
148
+ "228": "NOT_ALIVE",
149
+ "229": "NON_PARTICIPATING",
150
+ "23": "NOT_ALIVE",
151
+ "230": "NOT_ALIVE",
152
+ "231": "NON_PARTICIPATING",
153
+ "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
  "234": "SUCCESS",
156
+ "235": "NON_PARTICIPATING",
157
+ "236": "NON_PARTICIPATING",
158
+ "237": "NOT_ALIVE",
159
  "238": "SUCCESS",
160
+ "239": "NOT_ALIVE",
161
  "24": "SUCCESS",
162
+ "240": "NOT_ALIVE",
163
+ "241": "NON_PARTICIPATING",
164
+ "242": "NON_PARTICIPATING",
165
+ "243": "NON_PARTICIPATING",
166
+ "244": "NOT_ALIVE",
167
  "245": "SUCCESS",
168
+ "246": "NOT_ALIVE",
169
  "247": "SUCCESS",
170
  "248": "SUCCESS",
171
+ "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "SUCCESS",
174
  "251": "SUCCESS",
175
+ "252": "NON_PARTICIPATING",
176
  "253": "SUCCESS",
177
+ "254": "NON_PARTICIPATING",
178
  "255": "SUCCESS",
179
+ "26": "NOT_ALIVE",
180
  "27": "SUCCESS",
181
+ "28": "NON_PARTICIPATING",
182
+ "29": "NOT_ALIVE",
183
+ "3": "NOT_ALIVE",
184
+ "30": "NOT_ALIVE",
185
  "31": "SUCCESS",
186
+ "32": "NOT_ALIVE",
187
+ "33": "NON_PARTICIPATING",
188
+ "34": "NON_PARTICIPATING",
189
+ "35": "NOT_ALIVE",
190
+ "36": "NOT_ALIVE",
191
+ "37": "NOT_ALIVE",
192
+ "38": "NOT_ALIVE",
193
+ "39": "NOT_ALIVE",
194
+ "4": "NOT_ALIVE",
195
+ "40": "NON_PARTICIPATING",
196
+ "41": "NOT_ALIVE",
197
  "42": "SUCCESS",
198
  "43": "SUCCESS",
199
  "44": "SUCCESS",
200
+ "45": "NOT_ALIVE",
201
+ "46": "NON_PARTICIPATING",
202
+ "47": "NON_PARTICIPATING",
203
  "48": "SUCCESS",
204
+ "49": "NON_PARTICIPATING",
205
+ "5": "NOT_ALIVE",
206
+ "50": "NOT_ALIVE",
207
+ "51": "FAIL",
208
+ "52": "NON_PARTICIPATING",
209
+ "53": "NOT_ALIVE",
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": "NOT_ALIVE",
218
  "61": "SUCCESS",
219
  "62": "SUCCESS",
220
+ "63": "NON_PARTICIPATING",
221
+ "64": "NOT_ALIVE",
222
+ "65": "NOT_ALIVE",
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": "NOT_ALIVE",
230
+ "72": "NOT_ALIVE",
231
+ "73": "NON_PARTICIPATING",
232
+ "74": "NON_PARTICIPATING",
233
+ "75": "NOT_ALIVE",
234
  "76": "SUCCESS",
235
+ "77": "NOT_ALIVE",
236
+ "78": "NOT_ALIVE",
237
+ "79": "NON_PARTICIPATING",
238
+ "8": "NOT_ALIVE",
239
+ "80": "NOT_ALIVE",
240
+ "81": "NON_PARTICIPATING",
241
+ "82": "NOT_ALIVE",
242
+ "83": "NOT_ALIVE",
243
+ "84": "NOT_ALIVE",
244
+ "85": "NON_PARTICIPATING",
245
+ "86": "NON_PARTICIPATING",
246
+ "87": "NON_PARTICIPATING",
247
+ "88": "NOT_ALIVE",
248
+ "89": "NOT_ALIVE",
249
+ "9": "NOT_ALIVE",
250
+ "90": "NON_PARTICIPATING",
251
+ "91": "NOT_ALIVE",
252
+ "92": "NOT_ALIVE",
253
+ "93": "NOT_ALIVE",
254
+ "94": "NON_PARTICIPATING",
255
  "95": "SUCCESS",
256
+ "96": "NON_PARTICIPATING",
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
+ 6414028,
268
+ 6414037
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": 240,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 6412880,
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:abdc80648ad6b3922fcac929992af8819c271c9b5c4b42f6a51d7123de2334fa
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3061d12b6e641f587c7fa388295e8c6d517e9aca36467ef6ffa547dfa8b2e067
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eca601001cd3f35811c61a881088a6398c01c7c1842b3744a844b7646c6bc70b
3
- size 4924926842
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad108f62530d7423ec96ace42bfafd07ad48a4579fa3819bef52de985f1d6dd
3
+ size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55e639aac61b61588ca5599a12cd5bd2a7502cc5c0dadcbd88008ceb5e5f3a4a
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca53a42dcf6da3ac981499e5df7128e3b2da3b4cf90ccc8f215db13dd12f88b3
3
  size 4400216536