zeras141a commited on
Commit
2f274a5
·
verified ·
1 Parent(s): 2655333

Run 6. Outer Step 12. Inner Step 5.

Browse files
Files changed (4) hide show
  1. config.json +52 -52
  2. gradients.pt +1 -1
  3. inner_optimizer.pt +1 -1
  4. model.safetensors +1 -1
config.json CHANGED
@@ -2,11 +2,11 @@
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": "NOT_ALIVE",
9
- "102": "NON_PARTICIPATING",
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
@@ -40,40 +40,40 @@
40
  "130": "NOT_ALIVE",
41
  "131": "NON_PARTICIPATING",
42
  "132": "NOT_ALIVE",
43
- "133": "NON_PARTICIPATING",
44
- "134": "NOT_ALIVE",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
- "137": "NON_PARTICIPATING",
48
- "138": "NON_PARTICIPATING",
49
- "139": "NON_PARTICIPATING",
50
  "14": "NOT_ALIVE",
51
- "140": "NON_PARTICIPATING",
52
- "141": "NON_PARTICIPATING",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
- "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
62
  "150": "NOT_ALIVE",
63
- "151": "NON_PARTICIPATING",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
  "154": "NON_PARTICIPATING",
67
- "155": "NON_PARTICIPATING",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
- "160": "NON_PARTICIPATING",
74
- "161": "NON_PARTICIPATING",
75
  "162": "NON_PARTICIPATING",
76
- "163": "NON_PARTICIPATING",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
@@ -81,11 +81,11 @@
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
- "170": "NOT_ALIVE",
85
- "171": "NOT_ALIVE",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
- "174": "NOT_ALIVE",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
@@ -94,22 +94,22 @@
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
- "182": "NOT_ALIVE",
98
  "183": "NOT_ALIVE",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
- "187": "NON_PARTICIPATING",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
- "190": "NON_PARTICIPATING",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
- "196": "SUCCESS",
113
  "197": "SUCCESS",
114
  "198": "NOT_ALIVE",
115
  "199": "NOT_ALIVE",
@@ -128,12 +128,12 @@
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
- "212": "NOT_ALIVE",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
- "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
@@ -147,11 +147,11 @@
147
  "227": "NOT_ALIVE",
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
- "23": "SUCCESS",
151
- "230": "SUCCESS",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
- "233": "NON_PARTICIPATING",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
@@ -174,9 +174,9 @@
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": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
@@ -185,9 +185,9 @@
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
- "34": "NON_PARTICIPATING",
189
- "35": "NON_PARTICIPATING",
190
- "36": "SUCCESS",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
@@ -198,24 +198,24 @@
198
  "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
- "46": "SUCCESS",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
- "51": "NON_PARTICIPATING",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
- "55": "NON_PARTICIPATING",
212
  "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
- "61": "NON_PARTICIPATING",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
@@ -225,24 +225,24 @@
225
  "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
- "70": "SUCCESS",
229
- "71": "NON_PARTICIPATING",
230
- "72": "NON_PARTICIPATING",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
- "77": "NON_PARTICIPATING",
236
- "78": "NON_PARTICIPATING",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
- "80": "NON_PARTICIPATING",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
  "83": "SUCCESS",
243
  "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
- "86": "NON_PARTICIPATING",
246
  "87": "NOT_ALIVE",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
@@ -250,13 +250,13 @@
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
- "93": "NON_PARTICIPATING",
254
- "94": "NON_PARTICIPATING",
255
- "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
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
- 6129194,
268
- 6129212
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": 81,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 6128530,
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": "NOT_ALIVE",
9
+ "102": "NOT_ALIVE",
10
  "103": "NOT_ALIVE",
11
  "104": "NOT_ALIVE",
12
  "105": "NON_PARTICIPATING",
 
40
  "130": "NOT_ALIVE",
41
  "131": "NON_PARTICIPATING",
42
  "132": "NOT_ALIVE",
43
+ "133": "NOT_ALIVE",
44
+ "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
+ "137": "NOT_ALIVE",
48
+ "138": "NOT_ALIVE",
49
+ "139": "NOT_ALIVE",
50
  "14": "NOT_ALIVE",
51
+ "140": "NOT_ALIVE",
52
+ "141": "NOT_ALIVE",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "SUCCESS",
56
  "145": "NOT_ALIVE",
57
+ "146": "NOT_ALIVE",
58
  "147": "NON_PARTICIPATING",
59
  "148": "SUCCESS",
60
  "149": "NOT_ALIVE",
61
  "15": "SUCCESS",
62
  "150": "NOT_ALIVE",
63
+ "151": "NOT_ALIVE",
64
  "152": "NOT_ALIVE",
65
  "153": "NOT_ALIVE",
66
  "154": "NON_PARTICIPATING",
67
+ "155": "NOT_ALIVE",
68
  "156": "NOT_ALIVE",
69
  "157": "NOT_ALIVE",
70
  "158": "NON_PARTICIPATING",
71
  "159": "NON_PARTICIPATING",
72
  "16": "NOT_ALIVE",
73
+ "160": "NOT_ALIVE",
74
+ "161": "NOT_ALIVE",
75
  "162": "NON_PARTICIPATING",
76
+ "163": "NOT_ALIVE",
77
  "164": "NOT_ALIVE",
78
  "165": "NON_PARTICIPATING",
79
  "166": "NON_PARTICIPATING",
 
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
  "17": "NOT_ALIVE",
84
+ "170": "NON_PARTICIPATING",
85
+ "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
87
  "173": "NON_PARTICIPATING",
88
+ "174": "NON_PARTICIPATING",
89
  "175": "NOT_ALIVE",
90
  "176": "NOT_ALIVE",
91
  "177": "NOT_ALIVE",
 
94
  "18": "NOT_ALIVE",
95
  "180": "NOT_ALIVE",
96
  "181": "NOT_ALIVE",
97
+ "182": "NON_PARTICIPATING",
98
  "183": "NOT_ALIVE",
99
  "184": "NOT_ALIVE",
100
  "185": "NON_PARTICIPATING",
101
  "186": "NOT_ALIVE",
102
+ "187": "NOT_ALIVE",
103
  "188": "SUCCESS",
104
  "189": "SUCCESS",
105
  "19": "NOT_ALIVE",
106
+ "190": "NOT_ALIVE",
107
  "191": "NOT_ALIVE",
108
  "192": "NON_PARTICIPATING",
109
  "193": "SUCCESS",
110
  "194": "NOT_ALIVE",
111
  "195": "NOT_ALIVE",
112
+ "196": "NOT_ALIVE",
113
  "197": "SUCCESS",
114
  "198": "NOT_ALIVE",
115
  "199": "NOT_ALIVE",
 
128
  "21": "NOT_ALIVE",
129
  "210": "NOT_ALIVE",
130
  "211": "NON_PARTICIPATING",
131
+ "212": "NON_PARTICIPATING",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
134
  "215": "NON_PARTICIPATING",
135
  "216": "SUCCESS",
136
+ "217": "SUCCESS",
137
  "218": "NON_PARTICIPATING",
138
  "219": "SUCCESS",
139
  "22": "NOT_ALIVE",
 
147
  "227": "NOT_ALIVE",
148
  "228": "SUCCESS",
149
  "229": "NOT_ALIVE",
150
+ "23": "NOT_ALIVE",
151
+ "230": "NOT_ALIVE",
152
  "231": "NOT_ALIVE",
153
  "232": "NOT_ALIVE",
154
+ "233": "NOT_ALIVE",
155
  "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NOT_ALIVE",
 
174
  "251": "NON_PARTICIPATING",
175
  "252": "NON_PARTICIPATING",
176
  "253": "NON_PARTICIPATING",
177
+ "254": "NON_PARTICIPATING",
178
+ "255": "NOT_ALIVE",
179
+ "26": "NON_PARTICIPATING",
180
  "27": "NOT_ALIVE",
181
  "28": "NON_PARTICIPATING",
182
  "29": "NOT_ALIVE",
 
185
  "31": "SUCCESS",
186
  "32": "SUCCESS",
187
  "33": "NOT_ALIVE",
188
+ "34": "NOT_ALIVE",
189
+ "35": "NOT_ALIVE",
190
+ "36": "NON_PARTICIPATING",
191
  "37": "NOT_ALIVE",
192
  "38": "NON_PARTICIPATING",
193
  "39": "SUCCESS",
 
198
  "43": "NON_PARTICIPATING",
199
  "44": "NON_PARTICIPATING",
200
  "45": "NOT_ALIVE",
201
+ "46": "NON_PARTICIPATING",
202
  "47": "NOT_ALIVE",
203
  "48": "NON_PARTICIPATING",
204
  "49": "NOT_ALIVE",
205
  "5": "NOT_ALIVE",
206
  "50": "NOT_ALIVE",
207
+ "51": "NOT_ALIVE",
208
  "52": "NOT_ALIVE",
209
  "53": "NON_PARTICIPATING",
210
  "54": "NOT_ALIVE",
211
+ "55": "NOT_ALIVE",
212
  "56": "NON_PARTICIPATING",
213
  "57": "NON_PARTICIPATING",
214
  "58": "NOT_ALIVE",
215
  "59": "NON_PARTICIPATING",
216
  "6": "NOT_ALIVE",
217
  "60": "NOT_ALIVE",
218
+ "61": "NOT_ALIVE",
219
  "62": "NOT_ALIVE",
220
  "63": "SUCCESS",
221
  "64": "NON_PARTICIPATING",
 
225
  "68": "NOT_ALIVE",
226
  "69": "NOT_ALIVE",
227
  "7": "NOT_ALIVE",
228
+ "70": "NON_PARTICIPATING",
229
+ "71": "SUCCESS",
230
+ "72": "NOT_ALIVE",
231
  "73": "NOT_ALIVE",
232
  "74": "NOT_ALIVE",
233
  "75": "NON_PARTICIPATING",
234
  "76": "NOT_ALIVE",
235
+ "77": "NOT_ALIVE",
236
+ "78": "NOT_ALIVE",
237
  "79": "NOT_ALIVE",
238
  "8": "NOT_ALIVE",
239
+ "80": "SUCCESS",
240
  "81": "NON_PARTICIPATING",
241
  "82": "NOT_ALIVE",
242
  "83": "SUCCESS",
243
  "84": "NOT_ALIVE",
244
  "85": "NOT_ALIVE",
245
+ "86": "NOT_ALIVE",
246
  "87": "NOT_ALIVE",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NOT_ALIVE",
 
250
  "90": "NOT_ALIVE",
251
  "91": "NOT_ALIVE",
252
  "92": "NOT_ALIVE",
253
+ "93": "NOT_ALIVE",
254
+ "94": "NOT_ALIVE",
255
+ "95": "NOT_ALIVE",
256
  "96": "NON_PARTICIPATING",
257
  "97": "NOT_ALIVE",
258
  "98": "NON_PARTICIPATING",
259
+ "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 6129298,
268
+ 6129314
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": 6129192,
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 sha256:2c792c6a86a275dcbb71d54f1cf1b0ef5ce33fa9b89cf65bddc853b202fe042a
3
  size 88389626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98b1e1dcafcbc61b9faa4c7608f084e16becae374332316c93cdf13210f6020d
3
  size 88389626
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ceef918dd8a1ae84430d3d935678ace3d106ef981c863123860ec8e478b1b9c7
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d69742aa065fc13ca4d771b935f5c9eb96527c174a85752d828bc0a765cddac
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed387212d65685a7ad49bce72edae2a994d5a9e3b0f74f593099e49e3477a532
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3c6f18ceea83ddb93ffe7fd8d563d4da2851c630c760e009a548f1e76262bfe
3
  size 4400216536