mizzaay commited on
Commit
cb98486
·
verified ·
1 Parent(s): e95c47f

Run 8. Outer Step 67. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +104 -104
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,28 +2,28 @@
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
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": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
- "105": "FAIL",
13
- "106": "FAIL",
14
- "107": "NON_PARTICIPATING",
15
- "108": "NON_PARTICIPATING",
16
- "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
- "110": "FAIL",
19
- "111": "FAIL",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
- "118": "FAIL",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
@@ -33,25 +33,25 @@
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
- "127": "NON_PARTICIPATING",
37
  "128": "SUCCESS",
38
- "129": "NON_PARTICIPATING",
39
  "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
- "132": "FAIL",
43
  "133": "SUCCESS",
44
- "134": "FAIL",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
47
- "137": "FAIL",
48
  "138": "NOT_ALIVE",
49
- "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
- "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
@@ -59,165 +59,165 @@
59
  "148": "NON_PARTICIPATING",
60
  "149": "SUCCESS",
61
  "15": "FAIL",
62
- "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
- "154": "NOT_ALIVE",
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
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": "SUCCESS",
77
  "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "SUCCESS",
81
  "168": "SUCCESS",
82
- "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "SUCCESS",
86
- "172": "NON_PARTICIPATING",
87
- "173": "FAIL",
88
- "174": "FAIL",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
- "177": "SUCCESS",
92
- "178": "NOT_ALIVE",
93
- "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
- "182": "NON_PARTICIPATING",
98
- "183": "NON_PARTICIPATING",
99
  "184": "SUCCESS",
100
- "185": "FAIL",
101
- "186": "FAIL",
102
  "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
- "189": "FAIL",
105
- "19": "NOT_ALIVE",
106
  "190": "NON_PARTICIPATING",
107
- "191": "FAIL",
108
  "192": "SUCCESS",
109
- "193": "FAIL",
110
  "194": "NON_PARTICIPATING",
111
- "195": "NON_PARTICIPATING",
112
- "196": "FAIL",
113
  "197": "NON_PARTICIPATING",
114
- "198": "NON_PARTICIPATING",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
- "202": "FAIL",
121
- "203": "FAIL",
122
- "204": "FAIL",
123
- "205": "SUCCESS",
124
- "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
- "208": "NOT_ALIVE",
127
  "209": "SUCCESS",
128
  "21": "SUCCESS",
129
  "210": "SUCCESS",
130
- "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "SUCCESS",
133
  "214": "FAIL",
134
  "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
- "218": "SUCCESS",
138
  "219": "SUCCESS",
139
- "22": "FAIL",
140
- "220": "NOT_ALIVE",
141
- "221": "NON_PARTICIPATING",
142
- "222": "NON_PARTICIPATING",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
  "226": "NON_PARTICIPATING",
147
- "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
- "230": "SUCCESS",
152
- "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "SUCCESS",
155
  "234": "SUCCESS",
156
- "235": "NON_PARTICIPATING",
157
  "236": "SUCCESS",
158
- "237": "NON_PARTICIPATING",
159
- "238": "NON_PARTICIPATING",
160
- "239": "FAIL",
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
- "242": "FAIL",
165
  "243": "NON_PARTICIPATING",
166
- "244": "SUCCESS",
167
  "245": "SUCCESS",
168
- "246": "SUCCESS",
169
- "247": "FAIL",
170
- "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
- "250": "FAIL",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
- "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NOT_ALIVE",
180
- "27": "FAIL",
181
- "28": "SUCCESS",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
- "30": "SUCCESS",
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
- "35": "FAIL",
190
  "36": "NON_PARTICIPATING",
191
  "37": "SUCCESS",
192
- "38": "SUCCESS",
193
- "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
- "43": "FAIL",
199
- "44": "FAIL",
200
  "45": "NON_PARTICIPATING",
201
  "46": "SUCCESS",
202
- "47": "FAIL",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
  "5": "FAIL",
206
- "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
- "52": "SUCCESS",
209
  "53": "FAIL",
210
  "54": "NON_PARTICIPATING",
211
- "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
- "57": "SUCCESS",
214
  "58": "SUCCESS",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
- "61": "FAIL",
219
  "62": "SUCCESS",
220
- "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
@@ -229,33 +229,33 @@
229
  "71": "NON_PARTICIPATING",
230
  "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
- "74": "FAIL",
233
- "75": "NOT_ALIVE",
234
- "76": "NON_PARTICIPATING",
235
- "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
- "80": "FAIL",
240
  "81": "NOT_ALIVE",
241
  "82": "SUCCESS",
242
- "83": "NON_PARTICIPATING",
243
- "84": "NON_PARTICIPATING",
244
- "85": "FAIL",
245
  "86": "NON_PARTICIPATING",
246
- "87": "NON_PARTICIPATING",
247
- "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
- "90": "FAIL",
251
  "91": "NOT_ALIVE",
252
- "92": "NON_PARTICIPATING",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
- "95": "NON_PARTICIPATING",
256
  "96": "SUCCESS",
257
  "97": "SUCCESS",
258
- "98": "NON_PARTICIPATING",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6391261,
268
- 6391272
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": 87,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6390689,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
2
  "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NOT_ALIVE",
5
+ "1": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
  "100": "NON_PARTICIPATING",
8
  "101": "SUCCESS",
9
+ "102": "NOT_ALIVE",
10
  "103": "NON_PARTICIPATING",
11
  "104": "NON_PARTICIPATING",
12
+ "105": "NON_PARTICIPATING",
13
+ "106": "SUCCESS",
14
+ "107": "SUCCESS",
15
+ "108": "SUCCESS",
16
+ "109": "SUCCESS",
17
  "11": "SUCCESS",
18
+ "110": "NON_PARTICIPATING",
19
+ "111": "NON_PARTICIPATING",
20
  "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
  "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
26
+ "118": "NON_PARTICIPATING",
27
  "119": "NON_PARTICIPATING",
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
 
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "FAIL",
36
+ "127": "SUCCESS",
37
  "128": "SUCCESS",
38
+ "129": "SUCCESS",
39
  "13": "SUCCESS",
40
  "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
+ "132": "NON_PARTICIPATING",
43
  "133": "SUCCESS",
44
+ "134": "NON_PARTICIPATING",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
47
+ "137": "NON_PARTICIPATING",
48
  "138": "NOT_ALIVE",
49
+ "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
+ "143": "SUCCESS",
55
  "144": "SUCCESS",
56
  "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
 
59
  "148": "NON_PARTICIPATING",
60
  "149": "SUCCESS",
61
  "15": "FAIL",
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": "NOT_ALIVE",
70
+ "158": "FAIL",
71
  "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
+ "160": "NON_PARTICIPATING",
74
+ "161": "NON_PARTICIPATING",
75
+ "162": "SUCCESS",
76
+ "163": "NON_PARTICIPATING",
77
  "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NON_PARTICIPATING",
80
  "167": "SUCCESS",
81
  "168": "SUCCESS",
82
+ "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
85
  "171": "SUCCESS",
86
+ "172": "SUCCESS",
87
+ "173": "NOT_ALIVE",
88
+ "174": "SUCCESS",
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
+ "177": "FAIL",
92
+ "178": "SUCCESS",
93
+ "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
  "181": "SUCCESS",
97
+ "182": "SUCCESS",
98
+ "183": "SUCCESS",
99
  "184": "SUCCESS",
100
+ "185": "NOT_ALIVE",
101
+ "186": "NOT_ALIVE",
102
  "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
+ "189": "SUCCESS",
105
+ "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "NOT_ALIVE",
108
  "192": "SUCCESS",
109
+ "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
+ "195": "SUCCESS",
112
+ "196": "NON_PARTICIPATING",
113
  "197": "NON_PARTICIPATING",
114
+ "198": "NOT_ALIVE",
115
  "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NOT_ALIVE",
120
+ "202": "NON_PARTICIPATING",
121
+ "203": "SUCCESS",
122
+ "204": "NON_PARTICIPATING",
123
+ "205": "NON_PARTICIPATING",
124
+ "206": "SUCCESS",
125
  "207": "NON_PARTICIPATING",
126
+ "208": "NON_PARTICIPATING",
127
  "209": "SUCCESS",
128
  "21": "SUCCESS",
129
  "210": "SUCCESS",
130
+ "211": "NOT_ALIVE",
131
  "212": "SUCCESS",
132
  "213": "SUCCESS",
133
  "214": "FAIL",
134
  "215": "SUCCESS",
135
  "216": "SUCCESS",
136
  "217": "SUCCESS",
137
+ "218": "FAIL",
138
  "219": "SUCCESS",
139
+ "22": "SUCCESS",
140
+ "220": "NON_PARTICIPATING",
141
+ "221": "NOT_ALIVE",
142
+ "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
  "226": "NON_PARTICIPATING",
147
+ "227": "NOT_ALIVE",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
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": "FAIL",
159
+ "238": "SUCCESS",
160
+ "239": "SUCCESS",
161
  "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
+ "242": "SUCCESS",
165
  "243": "NON_PARTICIPATING",
166
+ "244": "NON_PARTICIPATING",
167
  "245": "SUCCESS",
168
+ "246": "FAIL",
169
+ "247": "NON_PARTICIPATING",
170
+ "248": "NON_PARTICIPATING",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
+ "250": "NON_PARTICIPATING",
174
  "251": "NOT_ALIVE",
175
  "252": "SUCCESS",
176
+ "253": "FAIL",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "NON_PARTICIPATING",
180
+ "27": "SUCCESS",
181
+ "28": "NON_PARTICIPATING",
182
  "29": "SUCCESS",
183
  "3": "SUCCESS",
184
+ "30": "FAIL",
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
  "34": "SUCCESS",
189
+ "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
  "37": "SUCCESS",
192
+ "38": "NON_PARTICIPATING",
193
+ "39": "SUCCESS",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "SUCCESS",
197
  "42": "NOT_ALIVE",
198
+ "43": "SUCCESS",
199
+ "44": "SUCCESS",
200
  "45": "NON_PARTICIPATING",
201
  "46": "SUCCESS",
202
+ "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
  "5": "FAIL",
206
+ "50": "FAIL",
207
  "51": "NOT_ALIVE",
208
+ "52": "FAIL",
209
  "53": "FAIL",
210
  "54": "NON_PARTICIPATING",
211
+ "55": "SUCCESS",
212
  "56": "NON_PARTICIPATING",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "SUCCESS",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "SUCCESS",
218
+ "61": "SUCCESS",
219
  "62": "SUCCESS",
220
+ "63": "NON_PARTICIPATING",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
 
229
  "71": "NON_PARTICIPATING",
230
  "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "SUCCESS",
233
+ "75": "NON_PARTICIPATING",
234
+ "76": "SUCCESS",
235
+ "77": "NON_PARTICIPATING",
236
  "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
238
  "8": "NOT_ALIVE",
239
+ "80": "NON_PARTICIPATING",
240
  "81": "NOT_ALIVE",
241
  "82": "SUCCESS",
242
+ "83": "SUCCESS",
243
+ "84": "SUCCESS",
244
+ "85": "NON_PARTICIPATING",
245
  "86": "NON_PARTICIPATING",
246
+ "87": "SUCCESS",
247
+ "88": "NOT_ALIVE",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
+ "90": "SUCCESS",
251
  "91": "NOT_ALIVE",
252
+ "92": "NOT_ALIVE",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "FAIL",
256
  "96": "SUCCESS",
257
  "97": "SUCCESS",
258
+ "98": "NOT_ALIVE",
259
  "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6391350,
268
+ 6391374
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": 6391321,
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 sha256:71eac21a5cab094b98a1961bcdd9645f536ffc958000501ac8608c1c787e6998
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ded100f269b18817972cdf190c8707d6d62ba2ba33d6dd186ee71be9d7446a5c
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0f444a6633cf9efd78999919af34ca7f02b6ec943d72cba190e0dfd5eac243a
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec3183e8717f7212fdd01342ed0a445c9122c7ba9c73a618cb9605a7822e531
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f81692f9f7502dd726a358c86434361bb5029abfe5653ce06d3b2004c411fb62
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f572b54b2ba842b3205c44d856052a343bf228a4b85d53619accaccf413e0e5c
3
  size 4400216536