snoopsy commited on
Commit
eca7b61
·
verified ·
1 Parent(s): 8254971

Run 8. Outer Step 34. Inner Step 4.

Browse files
Files changed (4) hide show
  1. config.json +64 -63
  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": "SUCCESS",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "SUCCESS",
@@ -16,7 +16,7 @@
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
- "111": "SUCCESS",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
@@ -29,7 +29,7 @@
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "NOT_ALIVE",
32
- "123": "SUCCESS",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
@@ -37,25 +37,25 @@
37
  "128": "NOT_ALIVE",
38
  "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
- "130": "SUCCESS",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
- "134": "SUCCESS",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "SUCCESS",
49
- "139": "NOT_ALIVE",
50
  "14": "SUCCESS",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "SUCCESS",
55
  "144": "SUCCESS",
56
- "145": "SUCCESS",
57
  "146": "SUCCESS",
58
- "147": "NOT_ALIVE",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
@@ -67,59 +67,59 @@
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
- "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
  "160": "NON_PARTICIPATING",
74
- "161": "NOT_ALIVE",
75
- "162": "NOT_ALIVE",
76
  "163": "SUCCESS",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
- "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
- "172": "NOT_ALIVE",
87
  "173": "SUCCESS",
88
- "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
- "179": "FAIL",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "SUCCESS",
97
  "182": "NOT_ALIVE",
98
- "183": "NOT_ALIVE",
99
  "184": "NOT_ALIVE",
100
  "185": "SUCCESS",
101
- "186": "SUCCESS",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
- "192": "NOT_ALIVE",
109
  "193": "SUCCESS",
110
- "194": "SUCCESS",
111
- "195": "SUCCESS",
112
- "196": "SUCCESS",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
- "199": "SUCCESS",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NOT_ALIVE",
122
- "204": "SUCCESS",
123
  "205": "SUCCESS",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
@@ -128,55 +128,55 @@
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
- "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
- "214": "SUCCESS",
134
- "215": "NOT_ALIVE",
135
- "216": "SUCCESS",
136
  "217": "SUCCESS",
137
  "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
- "220": "NON_PARTICIPATING",
141
- "221": "NON_PARTICIPATING",
142
- "222": "SUCCESS",
143
  "223": "NOT_ALIVE",
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": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
- "234": "SUCCESS",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
- "237": "NOT_ALIVE",
159
  "238": "SUCCESS",
160
- "239": "NON_PARTICIPATING",
161
- "24": "SUCCESS",
162
  "240": "NON_PARTICIPATING",
163
- "241": "NON_PARTICIPATING",
164
- "242": "NON_PARTICIPATING",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
- "246": "SUCCESS",
169
- "247": "NON_PARTICIPATING",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
- "251": "SUCCESS",
175
  "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
- "26": "NON_PARTICIPATING",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
@@ -189,64 +189,64 @@
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
192
- "38": "NOT_ALIVE",
193
  "39": "NON_PARTICIPATING",
194
  "4": "NOT_ALIVE",
195
  "40": "NON_PARTICIPATING",
196
  "41": "NON_PARTICIPATING",
197
  "42": "NOT_ALIVE",
198
- "43": "SUCCESS",
199
  "44": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
- "46": "SUCCESS",
202
  "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
- "49": "NON_PARTICIPATING",
205
- "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
- "52": "SUCCESS",
209
- "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
213
- "57": "SUCCESS",
214
  "58": "NOT_ALIVE",
215
- "59": "NOT_ALIVE",
216
  "6": "SUCCESS",
217
  "60": "NOT_ALIVE",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
- "63": "NOT_ALIVE",
221
  "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
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": "SUCCESS",
232
- "74": "NOT_ALIVE",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "SUCCESS",
236
- "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
- "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
- "88": "SUCCESS",
248
  "89": "NON_PARTICIPATING",
249
- "9": "NOT_ALIVE",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
@@ -256,7 +256,7 @@
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
- "99": "NOT_ALIVE"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,18 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 6357037,
268
- 6357054
 
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": 146,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6354618,
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": "NOT_ALIVE",
6
  "10": "NOT_ALIVE",
7
  "100": "NOT_ALIVE",
8
  "101": "SUCCESS",
 
16
  "109": "NOT_ALIVE",
17
  "11": "NOT_ALIVE",
18
  "110": "NON_PARTICIPATING",
19
+ "111": "FAIL",
20
  "112": "SUCCESS",
21
  "113": "SUCCESS",
22
  "114": "NOT_ALIVE",
 
29
  "120": "NOT_ALIVE",
30
  "121": "SUCCESS",
31
  "122": "NOT_ALIVE",
32
+ "123": "FAIL",
33
  "124": "NOT_ALIVE",
34
  "125": "NOT_ALIVE",
35
  "126": "NON_PARTICIPATING",
 
37
  "128": "NOT_ALIVE",
38
  "129": "SUCCESS",
39
  "13": "NOT_ALIVE",
40
+ "130": "NON_PARTICIPATING",
41
  "131": "NON_PARTICIPATING",
42
  "132": "SUCCESS",
43
  "133": "SUCCESS",
44
+ "134": "FAIL",
45
  "135": "SUCCESS",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "SUCCESS",
49
+ "139": "SUCCESS",
50
  "14": "SUCCESS",
51
  "140": "SUCCESS",
52
  "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "SUCCESS",
55
  "144": "SUCCESS",
56
+ "145": "FAIL",
57
  "146": "SUCCESS",
58
+ "147": "SUCCESS",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
 
67
  "155": "SUCCESS",
68
  "156": "NOT_ALIVE",
69
  "157": "NON_PARTICIPATING",
70
+ "158": "SUCCESS",
71
  "159": "NON_PARTICIPATING",
72
  "16": "SUCCESS",
73
  "160": "NON_PARTICIPATING",
74
+ "161": "FAIL",
75
+ "162": "FAIL",
76
  "163": "SUCCESS",
77
  "164": "NON_PARTICIPATING",
78
  "165": "NON_PARTICIPATING",
79
  "166": "SUCCESS",
80
  "167": "NOT_ALIVE",
81
  "168": "NON_PARTICIPATING",
82
+ "169": "SUCCESS",
83
  "17": "NOT_ALIVE",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
+ "172": "NON_PARTICIPATING",
87
  "173": "SUCCESS",
88
+ "174": "FAIL",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "SUCCESS",
92
  "178": "NOT_ALIVE",
93
+ "179": "NOT_ALIVE",
94
  "18": "NOT_ALIVE",
95
  "180": "NON_PARTICIPATING",
96
  "181": "SUCCESS",
97
  "182": "NOT_ALIVE",
98
+ "183": "NON_PARTICIPATING",
99
  "184": "NOT_ALIVE",
100
  "185": "SUCCESS",
101
+ "186": "NON_PARTICIPATING",
102
  "187": "SUCCESS",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
  "190": "NOT_ALIVE",
107
  "191": "NON_PARTICIPATING",
108
+ "192": "SUCCESS",
109
  "193": "SUCCESS",
110
+ "194": "NON_PARTICIPATING",
111
+ "195": "NOT_ALIVE",
112
+ "196": "FAIL",
113
  "197": "NOT_ALIVE",
114
  "198": "NON_PARTICIPATING",
115
+ "199": "FAIL",
116
  "2": "NOT_ALIVE",
117
  "20": "NOT_ALIVE",
118
  "200": "NOT_ALIVE",
119
  "201": "NOT_ALIVE",
120
  "202": "NON_PARTICIPATING",
121
  "203": "NOT_ALIVE",
122
+ "204": "FAIL",
123
  "205": "SUCCESS",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NOT_ALIVE",
 
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
  "211": "SUCCESS",
131
+ "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
+ "214": "NON_PARTICIPATING",
134
+ "215": "SUCCESS",
135
+ "216": "NOT_ALIVE",
136
  "217": "SUCCESS",
137
  "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
140
+ "220": "NOT_ALIVE",
141
+ "221": "SUCCESS",
142
+ "222": "NOT_ALIVE",
143
  "223": "NOT_ALIVE",
144
  "224": "NON_PARTICIPATING",
145
  "225": "SUCCESS",
146
  "226": "NOT_ALIVE",
147
  "227": "NOT_ALIVE",
148
+ "228": "FAIL",
149
  "229": "NON_PARTICIPATING",
150
  "23": "NOT_ALIVE",
151
  "230": "SUCCESS",
152
+ "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "NON_PARTICIPATING",
156
  "235": "NOT_ALIVE",
157
  "236": "NON_PARTICIPATING",
158
+ "237": "NON_PARTICIPATING",
159
  "238": "SUCCESS",
160
+ "239": "NOT_ALIVE",
161
+ "24": "NOT_ALIVE",
162
  "240": "NON_PARTICIPATING",
163
+ "241": "SUCCESS",
164
+ "242": "FAIL",
165
  "243": "NOT_ALIVE",
166
  "244": "NON_PARTICIPATING",
167
  "245": "NOT_ALIVE",
168
+ "246": "NON_PARTICIPATING",
169
+ "247": "NOT_ALIVE",
170
  "248": "NOT_ALIVE",
171
  "249": "NOT_ALIVE",
172
  "25": "SUCCESS",
173
  "250": "NON_PARTICIPATING",
174
+ "251": "NOT_ALIVE",
175
  "252": "NOT_ALIVE",
176
  "253": "SUCCESS",
177
  "254": "NOT_ALIVE",
178
  "255": "NON_PARTICIPATING",
179
+ "26": "NOT_ALIVE",
180
  "27": "SUCCESS",
181
  "28": "SUCCESS",
182
  "29": "NOT_ALIVE",
 
189
  "35": "NOT_ALIVE",
190
  "36": "NOT_ALIVE",
191
  "37": "NOT_ALIVE",
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": "SUCCESS",
200
  "45": "NOT_ALIVE",
201
+ "46": "FAIL",
202
  "47": "SUCCESS",
203
  "48": "NOT_ALIVE",
204
+ "49": "NOT_ALIVE",
205
+ "5": "SUCCESS",
206
  "50": "NOT_ALIVE",
207
  "51": "NOT_ALIVE",
208
+ "52": "NON_PARTICIPATING",
209
+ "53": "SUCCESS",
210
  "54": "NOT_ALIVE",
211
  "55": "NON_PARTICIPATING",
212
  "56": "NOT_ALIVE",
213
+ "57": "FAIL",
214
  "58": "NOT_ALIVE",
215
+ "59": "FAIL",
216
  "6": "SUCCESS",
217
  "60": "NOT_ALIVE",
218
  "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
+ "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "NOT_ALIVE",
223
  "66": "NOT_ALIVE",
224
  "67": "NOT_ALIVE",
225
  "68": "NON_PARTICIPATING",
226
+ "69": "SUCCESS",
227
  "7": "NOT_ALIVE",
228
  "70": "NOT_ALIVE",
229
  "71": "NON_PARTICIPATING",
230
  "72": "NON_PARTICIPATING",
231
  "73": "SUCCESS",
232
+ "74": "FAIL",
233
  "75": "NOT_ALIVE",
234
  "76": "NOT_ALIVE",
235
  "77": "SUCCESS",
236
+ "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
  "80": "NOT_ALIVE",
240
  "81": "NOT_ALIVE",
241
  "82": "NON_PARTICIPATING",
242
  "83": "NOT_ALIVE",
243
+ "84": "NON_PARTICIPATING",
244
  "85": "NOT_ALIVE",
245
  "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
+ "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
+ "9": "SUCCESS",
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
 
256
  "96": "NOT_ALIVE",
257
  "97": "NOT_ALIVE",
258
  "98": "SUCCESS",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6357787,
268
+ 6357790,
269
+ 6357802
270
  ],
271
  "bos_token_id": 1,
272
  "eos_token_id": 2,
273
  "hidden_act": "silu",
274
  "hidden_size": 2048,
275
  "initializer_range": 0.02,
276
+ "inner_step": 4,
277
  "intermediate_size": 5632,
278
+ "last_allreduce_block": 6357647,
279
  "max_position_embeddings": 2048,
280
  "mlp_bias": false,
281
  "model_type": "llama",
gradients.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a55fc353aab38c9bc81d85f2abe992724b8adb989120a14319415b9ef6bd921b
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:615a8f50ed8e49987240ce436e8af5acd07e6449fec1c3fba05f5ced84c37c97
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60d8b0aa19c56a3b6068ffc9b4a6409210f73bc3da49484341614e8b6db41619
3
  size 4924926906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d7c52e5d3188345323f65f5ba4c2697007a29265c322b231a8f87a3c3480aab
3
  size 4924926906
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e22939949cbbb22b364b3ee9ade9674410e26c2a46fc1042c4de80dbe0523caa
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e53a54755c990f0e0636a6ded1d6d60e1e843ea315381911043c307bdf18498
3
  size 4400216536