snoopsy commited on
Commit
ec8df74
·
verified ·
1 Parent(s): 1f0a3f8

Run 8. Outer Step 58. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +105 -105
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,7 +2,7 @@
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": "NOT_ALIVE",
8
  "101": "SUCCESS",
@@ -11,15 +11,15 @@
11
  "104": "NON_PARTICIPATING",
12
  "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
- "107": "SUCCESS",
15
  "108": "SUCCESS",
16
- "109": "NON_PARTICIPATING",
17
  "11": "SUCCESS",
18
- "110": "NOT_ALIVE",
19
  "111": "NOT_ALIVE",
20
- "112": "NON_PARTICIPATING",
21
  "113": "NOT_ALIVE",
22
- "114": "NOT_ALIVE",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
@@ -28,57 +28,57 @@
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "SUCCESS",
31
- "122": "FAIL",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
- "126": "FAIL",
36
  "127": "SUCCESS",
37
- "128": "SUCCESS",
38
- "129": "NOT_ALIVE",
39
  "13": "NOT_ALIVE",
40
- "130": "FAIL",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
- "133": "SUCCESS",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
47
- "137": "NOT_ALIVE",
48
- "138": "NOT_ALIVE",
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
- "143": "SUCCESS",
55
- "144": "NON_PARTICIPATING",
56
  "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
  "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
  "149": "SUCCESS",
61
  "15": "SUCCESS",
62
- "150": "SUCCESS",
63
- "151": "NON_PARTICIPATING",
64
- "152": "SUCCESS",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NON_PARTICIPATING",
67
- "155": "FAIL",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NON_PARTICIPATING",
71
- "159": "SUCCESS",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "FAIL",
75
  "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
77
- "164": "SUCCESS",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
- "168": "NON_PARTICIPATING",
82
  "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
@@ -89,85 +89,85 @@
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
- "178": "NOT_ALIVE",
93
- "179": "SUCCESS",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
- "181": "NOT_ALIVE",
97
- "182": "SUCCESS",
98
- "183": "SUCCESS",
99
- "184": "SUCCESS",
100
- "185": "NON_PARTICIPATING",
101
- "186": "SUCCESS",
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
- "189": "SUCCESS",
105
- "19": "FAIL",
106
  "190": "NON_PARTICIPATING",
107
- "191": "FAIL",
108
- "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
110
- "194": "NON_PARTICIPATING",
111
  "195": "SUCCESS",
112
  "196": "SUCCESS",
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": "NON_PARTICIPATING",
121
- "203": "NON_PARTICIPATING",
122
  "204": "SUCCESS",
123
  "205": "SUCCESS",
124
- "206": "SUCCESS",
125
- "207": "NON_PARTICIPATING",
126
  "208": "NON_PARTICIPATING",
127
- "209": "SUCCESS",
128
- "21": "NOT_ALIVE",
129
- "210": "NOT_ALIVE",
130
  "211": "SUCCESS",
131
  "212": "SUCCESS",
132
- "213": "SUCCESS",
133
  "214": "SUCCESS",
134
- "215": "SUCCESS",
135
- "216": "FAIL",
136
- "217": "SUCCESS",
137
- "218": "SUCCESS",
138
  "219": "FAIL",
139
- "22": "FAIL",
140
- "220": "NON_PARTICIPATING",
141
- "221": "NON_PARTICIPATING",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
- "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
- "228": "SUCCESS",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "SUCCESS",
152
- "231": "NON_PARTICIPATING",
153
- "232": "SUCCESS",
154
- "233": "NOT_ALIVE",
155
- "234": "FAIL",
156
  "235": "SUCCESS",
157
  "236": "SUCCESS",
158
- "237": "NON_PARTICIPATING",
159
- "238": "SUCCESS",
160
- "239": "NON_PARTICIPATING",
161
- "24": "FAIL",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
- "243": "NON_PARTICIPATING",
166
  "244": "SUCCESS",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
- "247": "SUCCESS",
170
- "248": "FAIL",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
@@ -176,62 +176,62 @@
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "FAIL",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
- "3": "SUCCESS",
184
- "30": "FAIL",
185
- "31": "NON_PARTICIPATING",
186
- "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
- "34": "NOT_ALIVE",
189
- "35": "FAIL",
190
- "36": "FAIL",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
- "41": "SUCCESS",
197
  "42": "SUCCESS",
198
- "43": "NOT_ALIVE",
199
- "44": "FAIL",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
- "47": "NON_PARTICIPATING",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
- "5": "FAIL",
206
  "50": "FAIL",
207
- "51": "SUCCESS",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
- "55": "FAIL",
212
  "56": "FAIL",
213
- "57": "FAIL",
214
- "58": "SUCCESS",
215
- "59": "NOT_ALIVE",
216
  "6": "NOT_ALIVE",
217
- "60": "NON_PARTICIPATING",
218
  "61": "NON_PARTICIPATING",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
- "65": "SUCCESS",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
- "68": "NOT_ALIVE",
226
  "69": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
- "70": "SUCCESS",
229
  "71": "NON_PARTICIPATING",
230
- "72": "NOT_ALIVE",
231
- "73": "NOT_ALIVE",
232
- "74": "FAIL",
233
  "75": "NON_PARTICIPATING",
234
- "76": "NON_PARTICIPATING",
235
  "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
@@ -240,23 +240,23 @@
240
  "81": "NON_PARTICIPATING",
241
  "82": "SUCCESS",
242
  "83": "SUCCESS",
243
- "84": "SUCCESS",
244
- "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
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": "NOT_ALIVE",
255
- "95": "SUCCESS",
256
- "96": "NON_PARTICIPATING",
257
  "97": "SUCCESS",
258
- "98": "NOT_ALIVE",
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
- 6380825,
268
- 6380835
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": 137,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6378907,
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": "NOT_ALIVE",
8
  "101": "SUCCESS",
 
11
  "104": "NON_PARTICIPATING",
12
  "105": "NOT_ALIVE",
13
  "106": "SUCCESS",
14
+ "107": "NON_PARTICIPATING",
15
  "108": "SUCCESS",
16
+ "109": "NOT_ALIVE",
17
  "11": "SUCCESS",
18
+ "110": "NON_PARTICIPATING",
19
  "111": "NOT_ALIVE",
20
+ "112": "SUCCESS",
21
  "113": "NOT_ALIVE",
22
+ "114": "FAIL",
23
  "115": "NON_PARTICIPATING",
24
  "116": "NON_PARTICIPATING",
25
  "117": "SUCCESS",
 
28
  "12": "NOT_ALIVE",
29
  "120": "NON_PARTICIPATING",
30
  "121": "SUCCESS",
31
+ "122": "SUCCESS",
32
  "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
+ "126": "NON_PARTICIPATING",
36
  "127": "SUCCESS",
37
+ "128": "FAIL",
38
+ "129": "FAIL",
39
  "13": "NOT_ALIVE",
40
+ "130": "NOT_ALIVE",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
+ "133": "NON_PARTICIPATING",
44
  "134": "NOT_ALIVE",
45
  "135": "SUCCESS",
46
  "136": "SUCCESS",
47
+ "137": "NON_PARTICIPATING",
48
+ "138": "NON_PARTICIPATING",
49
  "139": "SUCCESS",
50
  "14": "NOT_ALIVE",
51
+ "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "FAIL",
54
+ "143": "FAIL",
55
+ "144": "FAIL",
56
  "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
  "147": "SUCCESS",
59
  "148": "NON_PARTICIPATING",
60
  "149": "SUCCESS",
61
  "15": "SUCCESS",
62
+ "150": "FAIL",
63
+ "151": "NOT_ALIVE",
64
+ "152": "NON_PARTICIPATING",
65
  "153": "NON_PARTICIPATING",
66
  "154": "NON_PARTICIPATING",
67
+ "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "FAIL",
71
+ "159": "FAIL",
72
  "16": "NOT_ALIVE",
73
  "160": "NON_PARTICIPATING",
74
  "161": "FAIL",
75
  "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
77
+ "164": "NON_PARTICIPATING",
78
  "165": "SUCCESS",
79
  "166": "NOT_ALIVE",
80
  "167": "NON_PARTICIPATING",
81
+ "168": "SUCCESS",
82
  "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "SUCCESS",
 
89
  "175": "SUCCESS",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
+ "178": "NON_PARTICIPATING",
93
+ "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "SUCCESS",
96
+ "181": "FAIL",
97
+ "182": "NOT_ALIVE",
98
+ "183": "FAIL",
99
+ "184": "FAIL",
100
+ "185": "SUCCESS",
101
+ "186": "FAIL",
102
  "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
+ "189": "NOT_ALIVE",
105
+ "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
+ "191": "NOT_ALIVE",
108
+ "192": "SUCCESS",
109
  "193": "SUCCESS",
110
+ "194": "FAIL",
111
  "195": "SUCCESS",
112
  "196": "SUCCESS",
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "FAIL",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
+ "200": "SUCCESS",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
+ "203": "SUCCESS",
122
  "204": "SUCCESS",
123
  "205": "SUCCESS",
124
+ "206": "NON_PARTICIPATING",
125
+ "207": "NOT_ALIVE",
126
  "208": "NON_PARTICIPATING",
127
+ "209": "NON_PARTICIPATING",
128
+ "21": "SUCCESS",
129
+ "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
  "212": "SUCCESS",
132
+ "213": "NON_PARTICIPATING",
133
  "214": "SUCCESS",
134
+ "215": "FAIL",
135
+ "216": "SUCCESS",
136
+ "217": "FAIL",
137
+ "218": "NON_PARTICIPATING",
138
  "219": "FAIL",
139
+ "22": "SUCCESS",
140
+ "220": "SUCCESS",
141
+ "221": "FAIL",
142
  "222": "SUCCESS",
143
  "223": "SUCCESS",
144
  "224": "NON_PARTICIPATING",
145
+ "225": "FAIL",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
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": "SUCCESS",
157
  "236": "SUCCESS",
158
+ "237": "FAIL",
159
+ "238": "NOT_ALIVE",
160
+ "239": "FAIL",
161
+ "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
  "241": "NON_PARTICIPATING",
164
  "242": "SUCCESS",
165
+ "243": "NOT_ALIVE",
166
  "244": "SUCCESS",
167
  "245": "SUCCESS",
168
  "246": "NON_PARTICIPATING",
169
+ "247": "FAIL",
170
+ "248": "SUCCESS",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "FAIL",
 
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "SUCCESS",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "SUCCESS",
183
+ "3": "NOT_ALIVE",
184
+ "30": "NON_PARTICIPATING",
185
+ "31": "SUCCESS",
186
+ "32": "FAIL",
187
  "33": "NOT_ALIVE",
188
+ "34": "SUCCESS",
189
+ "35": "NON_PARTICIPATING",
190
+ "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
  "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
+ "41": "FAIL",
197
  "42": "SUCCESS",
198
+ "43": "NON_PARTICIPATING",
199
+ "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
  "46": "SUCCESS",
202
+ "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
  "49": "NON_PARTICIPATING",
205
+ "5": "SUCCESS",
206
  "50": "FAIL",
207
+ "51": "NON_PARTICIPATING",
208
  "52": "SUCCESS",
209
  "53": "SUCCESS",
210
  "54": "NON_PARTICIPATING",
211
+ "55": "SUCCESS",
212
  "56": "FAIL",
213
+ "57": "SUCCESS",
214
+ "58": "NOT_ALIVE",
215
+ "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
+ "60": "FAIL",
218
  "61": "NON_PARTICIPATING",
219
  "62": "SUCCESS",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
+ "65": "NOT_ALIVE",
223
  "66": "NON_PARTICIPATING",
224
  "67": "NON_PARTICIPATING",
225
+ "68": "FAIL",
226
  "69": "NON_PARTICIPATING",
227
  "7": "SUCCESS",
228
+ "70": "NON_PARTICIPATING",
229
  "71": "NON_PARTICIPATING",
230
+ "72": "NON_PARTICIPATING",
231
+ "73": "NON_PARTICIPATING",
232
+ "74": "NON_PARTICIPATING",
233
  "75": "NON_PARTICIPATING",
234
+ "76": "FAIL",
235
  "77": "SUCCESS",
236
  "78": "NON_PARTICIPATING",
237
  "79": "SUCCESS",
 
240
  "81": "NON_PARTICIPATING",
241
  "82": "SUCCESS",
242
  "83": "SUCCESS",
243
+ "84": "NOT_ALIVE",
244
+ "85": "NON_PARTICIPATING",
245
  "86": "NOT_ALIVE",
246
  "87": "FAIL",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NOT_ALIVE",
250
  "90": "SUCCESS",
251
+ "91": "FAIL",
252
+ "92": "FAIL",
253
  "93": "NON_PARTICIPATING",
254
  "94": "NOT_ALIVE",
255
+ "95": "NON_PARTICIPATING",
256
+ "96": "SUCCESS",
257
  "97": "SUCCESS",
258
+ "98": "NON_PARTICIPATING",
259
+ "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6380908,
268
+ 6380918
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": 6380868,
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 sha256:6100afc4768a1db996ed18f21e287d4aebf3be217fea0a7a0c83d20ac6f05284
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37774878191f6883606deabce438eb85f0272a99a418bcc78864a2923712ba99
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:045aa52c067df6d963ab4d2d68898387bf5a7866a72ecf461b2e144def723884
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b3a33944fefc5d7e56504f6268e59f0758093db30dc97e2deb2e5dfa7b5f1c
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5af41cf6eaeabbddbb0fce07909dac93e83e9e2501fe502b15f952a1c312f551
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de20706c21cfd624fca92d6310cf199ab18e6fbcc3c8862c894c3c337c329cb0
3
  size 4400216536