appvoid commited on
Commit
534cfcf
·
verified ·
1 Parent(s): 11d8d66

Qwen90M step 895000; complete resumable checkpoint

Browse files
Files changed (6) hide show
  1. complete.json +5 -5
  2. coverage.json +50 -50
  3. latest.json +1 -1
  4. model.safetensors +1 -1
  5. shard_scheduler.json +269 -59
  6. trainer.pt +2 -2
complete.json CHANGED
@@ -1,18 +1,18 @@
1
  {
2
- "step": 890000,
3
  "files": {
4
  "config.json": "cbc72137da3dae65085a2a8c39ad7634d16bf92d785ca00d283ee82fe32b37e7",
5
  "generation_config.json": "54ed0d19f6226888c91157964ede8a892bd5ae175bfad85336152b3d9b6cd7c4",
6
- "model.safetensors": "4004a418f0a4d22cc89ba6b698b860d4e1d48da439b2ae725b34fbbff792b3a6",
7
  "tokenization_byte.py": "279b9990f77b1eaedc7c1184fe13d60273a713ead856200f1fb9ae323c7b1e03",
8
  "tokenizer_config.json": "0ecbd4fd39e35125800d806af981ba0cacd8a7ba5f02c9e729c4ecc54af6d300",
9
  "special_tokens_map.json": "20d4b94d0e657c3f44d9123522c106e7315b6c1a1b6d259478f17bd2918b1263",
10
  "byte_vocab.json": "57a1cd2e70dd5b7cc6fd2eaa12ebfcd173c1620fa5d45c2c6282511c29b6a5f6",
11
- "trainer.pt": "2190176915a9e996d9ff3392761fa977ba84ff82f831e2f53700f0a741af6d71",
12
  "training_config.json": "4e8f8b2fc7193aabdbca12082e7c7cc3a0ed080bd5ff16e060cc02e10ffc53dd",
13
  "performance.json": "49b9042fb538cca213af1e6f33ceb5a89185fc6d2bab488be3f60e812871f343",
14
- "shard_scheduler.json": "ad91bf9e2d654997f21660598ea391f402bf51bd0d59590f213adfe6c8ea1693",
15
- "coverage.json": "3d2c825d6c142490cc70e6674777e6cb288e5f0fc3593033a53369bfcf8e718d",
16
  "README.md": "9ce0f9efacbc46177a7e818b6aed274d84e7145ff944b5c7d6ecd5d33b9d4419"
17
  },
18
  "signature": "052aedaef69b550457da29474e17df28fa635c99594a7b9c0881f3ac3827000e"
 
1
  {
2
+ "step": 895000,
3
  "files": {
4
  "config.json": "cbc72137da3dae65085a2a8c39ad7634d16bf92d785ca00d283ee82fe32b37e7",
5
  "generation_config.json": "54ed0d19f6226888c91157964ede8a892bd5ae175bfad85336152b3d9b6cd7c4",
6
+ "model.safetensors": "eb78dafba7ed6edbbc1920e8d24942367894be7585480ad296217c19df2e72bd",
7
  "tokenization_byte.py": "279b9990f77b1eaedc7c1184fe13d60273a713ead856200f1fb9ae323c7b1e03",
8
  "tokenizer_config.json": "0ecbd4fd39e35125800d806af981ba0cacd8a7ba5f02c9e729c4ecc54af6d300",
9
  "special_tokens_map.json": "20d4b94d0e657c3f44d9123522c106e7315b6c1a1b6d259478f17bd2918b1263",
10
  "byte_vocab.json": "57a1cd2e70dd5b7cc6fd2eaa12ebfcd173c1620fa5d45c2c6282511c29b6a5f6",
11
+ "trainer.pt": "3cc6aff6ad2f08dece94cc67d7a302ec23b409b0da9ac246329b68a9b3231985",
12
  "training_config.json": "4e8f8b2fc7193aabdbca12082e7c7cc3a0ed080bd5ff16e060cc02e10ffc53dd",
13
  "performance.json": "49b9042fb538cca213af1e6f33ceb5a89185fc6d2bab488be3f60e812871f343",
14
+ "shard_scheduler.json": "2d68de6c3624467095a90ec9bdeef51e2fc5ab4e71e38707f6c6cc942ef1b8c8",
15
+ "coverage.json": "da94cd20bec68c816560b61fce43b1062241b6873d42a2e73f505b9d916b5a6b",
16
  "README.md": "9ce0f9efacbc46177a7e818b6aed274d84e7145ff944b5c7d6ecd5d33b9d4419"
17
  },
18
  "signature": "052aedaef69b550457da29474e17df28fa635c99594a7b9c0881f3ac3827000e"
coverage.json CHANGED
@@ -1,107 +1,107 @@
1
  {
2
- "step": 890000,
3
  "stats": {
4
- "climbmix/blocks": 32040000,
5
- "climbmix/targets": 53560197117,
6
- "climbmix/input_tokens": 53563591350,
7
- "ultra_qa/blocks": 12015000,
8
- "ultra_qa/targets": 19601686615,
9
- "ultra_qa/input_tokens": 19601724275,
10
- "cortex/blocks": 12015000,
11
- "cortex/targets": 456854037,
12
- "cortex/input_tokens": 19098644075,
13
- "ultra_style/blocks": 12015000,
14
- "ultra_style/targets": 19004406950,
15
- "ultra_style/input_tokens": 19005403363,
16
- "openmath/blocks": 8010000,
17
- "openmath/targets": 12376992365,
18
- "openmath/input_tokens": 12381116654,
19
- "rewrite6/blocks": 4005000,
20
- "rewrite6/targets": 6565715309,
21
- "rewrite6/input_tokens": 6572913655
22
  },
23
  "sources": {
24
  "climbmix": {
25
- "page": 4388,
26
- "row": 384,
27
  "start": {
28
- "file": 212,
29
  "reader": {
30
  "format": "parquet-row-v1",
31
- "row_group": 34,
32
  "row": 1024
33
  }
34
  },
35
  "epoch": 0,
36
- "offset": 0,
37
- "documents": 17973632
38
  },
39
  "rewrite6": {
40
- "page": 46,
41
- "row": 1874,
42
  "start": {
43
  "file": 0,
44
  "reader": {
45
  "format": "jsonl-row-v1",
46
- "row": 188416
47
  }
48
  },
49
- "epoch": 49,
50
- "offset": 2048,
51
- "documents": 10255086
52
  },
53
  "openmath": {
54
- "page": 2742,
55
- "row": 2292,
56
  "start": {
57
  "file": 25,
58
  "reader": {
59
  "format": "parquet-row-v1",
60
- "row_group": 314,
61
- "row": 984
62
  }
63
  },
64
  "epoch": 0,
65
  "offset": 0,
66
- "documents": 11233524
67
  },
68
  "ultra_qa": {
69
- "page": 1185,
70
- "row": 2980,
71
  "start": {
72
  "file": 9,
73
  "reader": {
74
  "format": "parquet-row-v1",
75
- "row_group": 2,
76
- "row": 48005
77
  }
78
  },
79
  "epoch": 0,
80
- "offset": 2048,
81
- "documents": 4856740
82
  },
83
  "ultra_style": {
84
- "page": 1809,
85
- "row": 2888,
86
  "start": {
87
  "file": 10,
88
  "reader": {
89
  "format": "parquet-row-v1",
90
- "row_group": 6,
91
- "row": 50376
92
  }
93
  },
94
  "epoch": 0,
95
  "offset": 2048,
96
- "documents": 7412552
97
  },
98
  "cortex": {
99
- "page": 233012,
100
- "row": 113,
101
  "start": null,
102
  "epoch": 0,
103
  "offset": 0,
104
- "documents": 29825649
105
  }
106
  }
107
  }
 
1
  {
2
+ "step": 895000,
3
  "stats": {
4
+ "climbmix/blocks": 32220000,
5
+ "climbmix/targets": 53861724331,
6
+ "climbmix/input_tokens": 53865137686,
7
+ "ultra_qa/blocks": 12082500,
8
+ "ultra_qa/targets": 19711743279,
9
+ "ultra_qa/input_tokens": 19711781154,
10
+ "cortex/blocks": 12082500,
11
+ "cortex/targets": 459427225,
12
+ "cortex/input_tokens": 19205987571,
13
+ "ultra_style/blocks": 12082500,
14
+ "ultra_style/targets": 19110329995,
15
+ "ultra_style/input_tokens": 19111332267,
16
+ "openmath/blocks": 8055000,
17
+ "openmath/targets": 12446359341,
18
+ "openmath/input_tokens": 12450506245,
19
+ "rewrite6/blocks": 4027500,
20
+ "rewrite6/targets": 6602556148,
21
+ "rewrite6/input_tokens": 6609794679
22
  },
23
  "sources": {
24
  "climbmix": {
25
+ "page": 4412,
26
+ "row": 2552,
27
  "start": {
28
+ "file": 213,
29
  "reader": {
30
  "format": "parquet-row-v1",
31
+ "row_group": 47,
32
  "row": 1024
33
  }
34
  },
35
  "epoch": 0,
36
+ "offset": 4096,
37
+ "documents": 18074104
38
  },
39
  "rewrite6": {
40
+ "page": 10,
41
+ "row": 1253,
42
  "start": {
43
  "file": 0,
44
  "reader": {
45
  "format": "jsonl-row-v1",
46
+ "row": 40960
47
  }
48
  },
49
+ "epoch": 50,
50
+ "offset": 4096,
51
+ "documents": 10312413
52
  },
53
  "openmath": {
54
+ "page": 2757,
55
+ "row": 3359,
56
  "start": {
57
  "file": 25,
58
  "reader": {
59
  "format": "parquet-row-v1",
60
+ "row_group": 376,
61
+ "row": 424
62
  }
63
  },
64
  "epoch": 0,
65
  "offset": 0,
66
+ "documents": 11296031
67
  },
68
  "ultra_qa": {
69
+ "page": 1192,
70
+ "row": 1692,
71
  "start": {
72
  "file": 9,
73
  "reader": {
74
  "format": "parquet-row-v1",
75
+ "row_group": 3,
76
+ "row": 12028
77
  }
78
  },
79
  "epoch": 0,
80
+ "offset": 4096,
81
+ "documents": 4884124
82
  },
83
  "ultra_style": {
84
+ "page": 1820,
85
+ "row": 334,
86
  "start": {
87
  "file": 10,
88
  "reader": {
89
  "format": "parquet-row-v1",
90
+ "row_group": 7,
91
+ "row": 9554
92
  }
93
  },
94
  "epoch": 0,
95
  "offset": 2048,
96
+ "documents": 7455054
97
  },
98
  "cortex": {
99
+ "page": 234323,
100
+ "row": 46,
101
  "start": null,
102
  "epoch": 0,
103
  "offset": 0,
104
+ "documents": 29993390
105
  }
106
  }
107
  }
latest.json CHANGED
@@ -1 +1 @@
1
- {"step": 890000, "files": {"config.json": "cbc72137da3dae65085a2a8c39ad7634d16bf92d785ca00d283ee82fe32b37e7", "generation_config.json": "54ed0d19f6226888c91157964ede8a892bd5ae175bfad85336152b3d9b6cd7c4", "model.safetensors": "4004a418f0a4d22cc89ba6b698b860d4e1d48da439b2ae725b34fbbff792b3a6", "tokenization_byte.py": "279b9990f77b1eaedc7c1184fe13d60273a713ead856200f1fb9ae323c7b1e03", "tokenizer_config.json": "0ecbd4fd39e35125800d806af981ba0cacd8a7ba5f02c9e729c4ecc54af6d300", "special_tokens_map.json": "20d4b94d0e657c3f44d9123522c106e7315b6c1a1b6d259478f17bd2918b1263", "byte_vocab.json": "57a1cd2e70dd5b7cc6fd2eaa12ebfcd173c1620fa5d45c2c6282511c29b6a5f6", "trainer.pt": "2190176915a9e996d9ff3392761fa977ba84ff82f831e2f53700f0a741af6d71", "training_config.json": "4e8f8b2fc7193aabdbca12082e7c7cc3a0ed080bd5ff16e060cc02e10ffc53dd", "performance.json": "49b9042fb538cca213af1e6f33ceb5a89185fc6d2bab488be3f60e812871f343", "shard_scheduler.json": "ad91bf9e2d654997f21660598ea391f402bf51bd0d59590f213adfe6c8ea1693", "coverage.json": "3d2c825d6c142490cc70e6674777e6cb288e5f0fc3593033a53369bfcf8e718d", "README.md": "9ce0f9efacbc46177a7e818b6aed274d84e7145ff944b5c7d6ecd5d33b9d4419"}, "signature": "052aedaef69b550457da29474e17df28fa635c99594a7b9c0881f3ac3827000e", "folder": "step-000000890000"}
 
1
+ {"step": 895000, "files": {"config.json": "cbc72137da3dae65085a2a8c39ad7634d16bf92d785ca00d283ee82fe32b37e7", "generation_config.json": "54ed0d19f6226888c91157964ede8a892bd5ae175bfad85336152b3d9b6cd7c4", "model.safetensors": "eb78dafba7ed6edbbc1920e8d24942367894be7585480ad296217c19df2e72bd", "tokenization_byte.py": "279b9990f77b1eaedc7c1184fe13d60273a713ead856200f1fb9ae323c7b1e03", "tokenizer_config.json": "0ecbd4fd39e35125800d806af981ba0cacd8a7ba5f02c9e729c4ecc54af6d300", "special_tokens_map.json": "20d4b94d0e657c3f44d9123522c106e7315b6c1a1b6d259478f17bd2918b1263", "byte_vocab.json": "57a1cd2e70dd5b7cc6fd2eaa12ebfcd173c1620fa5d45c2c6282511c29b6a5f6", "trainer.pt": "3cc6aff6ad2f08dece94cc67d7a302ec23b409b0da9ac246329b68a9b3231985", "training_config.json": "4e8f8b2fc7193aabdbca12082e7c7cc3a0ed080bd5ff16e060cc02e10ffc53dd", "performance.json": "49b9042fb538cca213af1e6f33ceb5a89185fc6d2bab488be3f60e812871f343", "shard_scheduler.json": "2d68de6c3624467095a90ec9bdeef51e2fc5ab4e71e38707f6c6cc942ef1b8c8", "coverage.json": "da94cd20bec68c816560b61fce43b1062241b6873d42a2e73f505b9d916b5a6b", "README.md": "9ce0f9efacbc46177a7e818b6aed274d84e7145ff944b5c7d6ecd5d33b9d4419"}, "signature": "052aedaef69b550457da29474e17df28fa635c99594a7b9c0881f3ac3827000e", "folder": "step-000000895000"}
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4004a418f0a4d22cc89ba6b698b860d4e1d48da439b2ae725b34fbbff792b3a6
3
  size 360622744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb78dafba7ed6edbbc1920e8d24942367894be7585480ad296217c19df2e72bd
3
  size 360622744
shard_scheduler.json CHANGED
@@ -22,8 +22,8 @@
22
  "tokens_per_second": 598315.063954628,
23
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
24
  "estimated_pages_for_buffer": 1,
25
- "required_token_positions_per_second": 76502.40131697868,
26
- "required_pages_per_second_upper_estimate": 0.005292613633135749
27
  },
28
  {
29
  "source": "rewrite6",
@@ -36,8 +36,8 @@
36
  "tokens_per_second": 8533.957213384612,
37
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
38
  "estimated_pages_for_buffer": 1,
39
- "required_token_positions_per_second": 9562.800164622335,
40
- "required_pages_per_second_upper_estimate": 0.004003744734951975
41
  },
42
  {
43
  "source": "openmath",
@@ -50,8 +50,8 @@
50
  "tokens_per_second": 380144.35761751566,
51
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
52
  "estimated_pages_for_buffer": 1,
53
- "required_token_positions_per_second": 19125.60032924467,
54
- "required_pages_per_second_upper_estimate": 0.003983358172583166
55
  },
56
  {
57
  "source": "ultra_qa",
@@ -64,8 +64,8 @@
64
  "tokens_per_second": 43742.16556775435,
65
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
66
  "estimated_pages_for_buffer": 1,
67
- "required_token_positions_per_second": 28688.400493867004,
68
- "required_pages_per_second_upper_estimate": 0.0017198258049561444
69
  },
70
  {
71
  "source": "ultra_style",
@@ -78,8 +78,8 @@
78
  "tokens_per_second": 22018.86276523721,
79
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
80
  "estimated_pages_for_buffer": 1,
81
- "required_token_positions_per_second": 28688.400493867004,
82
- "required_pages_per_second_upper_estimate": 0.002230396951460234
83
  },
84
  {
85
  "source": "cortex",
@@ -92,8 +92,8 @@
92
  "tokens_per_second": 910315.184299418,
93
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
94
  "estimated_pages_for_buffer": 23,
95
- "required_token_positions_per_second": 28688.400493867004,
96
- "required_pages_per_second_upper_estimate": 0.36798399833079365
97
  }
98
  ],
99
  "gpu_measurement": "Selected forward/backward estimate; replaced by live successful update timings.",
@@ -158,63 +158,27 @@
158
  "prefetch_batches": 63,
159
  "prefetch_capacity_limit": 512,
160
  "batch_memory_estimate_bytes": 720750,
161
- "producer_batch_seconds": 0.04824891578905266,
162
- "producer_p95_seconds": 0.16322065300028044,
163
- "gpu_update_seconds": 0.9637344544848563,
164
- "producer_batches_per_second": 20.725854325350312,
165
- "gpu_batches_per_second": 1.037630226196,
166
- "producer_headroom": 19.97421991197408,
167
  "sustainable": true,
168
- "buffer_seconds": 60.715270632545945,
169
  "buffer_drain_seconds": null,
170
  "shard_target_mib": 16,
171
- "upload_pages_per_commit": 84,
172
  "max_pending_pages": 4096,
173
- "generation_bytes_per_second": 347300.0185245126,
174
- "upload_bytes_per_second": 5171426.317954449,
175
  "upload_sustainable": true,
176
  "logical_page_rows": 4096,
177
  "logical_cortex_page_rows": 128,
178
- "estimated_full_shards_per_hour": 74.52249924470456,
179
  "selection_policy": "Smallest shard within 90% of measured local peak, enlarged to amortize 30 seconds of measured page production; bounded to 256 MiB."
180
  },
181
  "upload_measurements": [
182
- {
183
- "seconds": 1.357899806999967,
184
- "bytes": 22393,
185
- "pages": 1,
186
- "shards": 1
187
- },
188
- {
189
- "seconds": 1.3004982690001725,
190
- "bytes": 5957332,
191
- "pages": 32,
192
- "shards": 2
193
- },
194
- {
195
- "seconds": 1.5475466269999743,
196
- "bytes": 6964239,
197
- "pages": 34,
198
- "shards": 2
199
- },
200
- {
201
- "seconds": 1.287959292999858,
202
- "bytes": 7677212,
203
- "pages": 36,
204
- "shards": 3
205
- },
206
- {
207
- "seconds": 1.560628134000126,
208
- "bytes": 10720223,
209
- "pages": 36,
210
- "shards": 3
211
- },
212
- {
213
- "seconds": 1.479639369999859,
214
- "bytes": 2607690,
215
- "pages": 36,
216
- "shards": 2
217
- },
218
  {
219
  "seconds": 1.0580149020001954,
220
  "bytes": 6239919,
@@ -352,6 +316,252 @@
352
  "bytes": 7144629,
353
  "pages": 30,
354
  "shards": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
355
  }
356
  ],
357
  "cache_key": {
 
22
  "tokens_per_second": 598315.063954628,
23
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
24
  "estimated_pages_for_buffer": 1,
25
+ "required_token_positions_per_second": 76601.26916859495,
26
+ "required_pages_per_second_upper_estimate": 0.005299453540515585
27
  },
28
  {
29
  "source": "rewrite6",
 
36
  "tokens_per_second": 8533.957213384612,
37
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
38
  "estimated_pages_for_buffer": 1,
39
+ "required_token_positions_per_second": 9575.15864607437,
40
+ "required_pages_per_second_upper_estimate": 0.004008918973061503
41
  },
42
  {
43
  "source": "openmath",
 
50
  "tokens_per_second": 380144.35761751566,
51
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
52
  "estimated_pages_for_buffer": 1,
53
+ "required_token_positions_per_second": 19150.31729214874,
54
+ "required_pages_per_second_upper_estimate": 0.003988506064125937
55
  },
56
  {
57
  "source": "ultra_qa",
 
64
  "tokens_per_second": 43742.16556775435,
65
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
66
  "estimated_pages_for_buffer": 1,
67
+ "required_token_positions_per_second": 28725.47593822311,
68
+ "required_pages_per_second_upper_estimate": 0.0017220484212343672
69
  },
70
  {
71
  "source": "ultra_style",
 
78
  "tokens_per_second": 22018.86276523721,
79
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
80
  "estimated_pages_for_buffer": 1,
81
+ "required_token_positions_per_second": 28725.47593822311,
82
+ "required_pages_per_second_upper_estimate": 0.0022332794041812756
83
  },
84
  {
85
  "source": "cortex",
 
92
  "tokens_per_second": 910315.184299418,
93
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
94
  "estimated_pages_for_buffer": 23,
95
+ "required_token_positions_per_second": 28725.47593822311,
96
+ "required_pages_per_second_upper_estimate": 0.36845956232248317
97
  }
98
  ],
99
  "gpu_measurement": "Selected forward/backward estimate; replaced by live successful update timings.",
 
158
  "prefetch_batches": 63,
159
  "prefetch_capacity_limit": 512,
160
  "batch_memory_estimate_bytes": 720750,
161
+ "producer_batch_seconds": 0.09046511610937102,
162
+ "producer_p95_seconds": 0.19785067599877948,
163
+ "gpu_update_seconds": 0.9624905801198795,
164
+ "producer_batches_per_second": 11.053984596571063,
165
+ "gpu_batches_per_second": 1.0389712072563335,
166
+ "producer_headroom": 10.639356046989894,
167
  "sustainable": true,
168
+ "buffer_seconds": 60.636906547552414,
169
  "buffer_drain_seconds": null,
170
  "shard_target_mib": 16,
171
+ "upload_pages_per_commit": 80,
172
  "max_pending_pages": 4096,
173
+ "generation_bytes_per_second": 539194.1073240534,
174
+ "upload_bytes_per_second": 5396381.570381515,
175
  "upload_sustainable": true,
176
  "logical_page_rows": 4096,
177
  "logical_cortex_page_rows": 128,
178
+ "estimated_full_shards_per_hour": 115.6985036353226,
179
  "selection_policy": "Smallest shard within 90% of measured local peak, enlarged to amortize 30 seconds of measured page production; bounded to 256 MiB."
180
  },
181
  "upload_measurements": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
182
  {
183
  "seconds": 1.0580149020001954,
184
  "bytes": 6239919,
 
316
  "bytes": 7144629,
317
  "pages": 30,
318
  "shards": 3
319
+ },
320
+ {
321
+ "seconds": 1.0513503590000255,
322
+ "bytes": 1139099,
323
+ "pages": 34,
324
+ "shards": 2
325
+ },
326
+ {
327
+ "seconds": 0.996597190999637,
328
+ "bytes": 6046442,
329
+ "pages": 28,
330
+ "shards": 2
331
+ },
332
+ {
333
+ "seconds": 1.1579751299996133,
334
+ "bytes": 6933490,
335
+ "pages": 30,
336
+ "shards": 3
337
+ },
338
+ {
339
+ "seconds": 1.4397287989995675,
340
+ "bytes": 11874214,
341
+ "pages": 32,
342
+ "shards": 3
343
+ },
344
+ {
345
+ "seconds": 1.0771185140001762,
346
+ "bytes": 6044727,
347
+ "pages": 37,
348
+ "shards": 2
349
+ },
350
+ {
351
+ "seconds": 1.0941710249999232,
352
+ "bytes": 2736868,
353
+ "pages": 37,
354
+ "shards": 2
355
+ },
356
+ {
357
+ "seconds": 1.062443419000374,
358
+ "bytes": 5796244,
359
+ "pages": 20,
360
+ "shards": 2
361
+ },
362
+ {
363
+ "seconds": 1.0528361209999275,
364
+ "bytes": 5176693,
365
+ "pages": 44,
366
+ "shards": 2
367
+ },
368
+ {
369
+ "seconds": 1.123353902999952,
370
+ "bytes": 7475982,
371
+ "pages": 39,
372
+ "shards": 3
373
+ },
374
+ {
375
+ "seconds": 1.3653379679999489,
376
+ "bytes": 11617938,
377
+ "pages": 31,
378
+ "shards": 3
379
+ },
380
+ {
381
+ "seconds": 1.2881032879995473,
382
+ "bytes": 6772198,
383
+ "pages": 31,
384
+ "shards": 3
385
+ },
386
+ {
387
+ "seconds": 1.1199771049996343,
388
+ "bytes": 6074153,
389
+ "pages": 36,
390
+ "shards": 2
391
+ },
392
+ {
393
+ "seconds": 1.1042831229997319,
394
+ "bytes": 6145766,
395
+ "pages": 36,
396
+ "shards": 2
397
+ },
398
+ {
399
+ "seconds": 1.2581367550001232,
400
+ "bytes": 2542671,
401
+ "pages": 33,
402
+ "shards": 2
403
+ },
404
+ {
405
+ "seconds": 1.7602326240003094,
406
+ "bytes": 10170709,
407
+ "pages": 35,
408
+ "shards": 3
409
+ },
410
+ {
411
+ "seconds": 1.23988030000055,
412
+ "bytes": 8293432,
413
+ "pages": 33,
414
+ "shards": 3
415
+ },
416
+ {
417
+ "seconds": 1.1932894399997167,
418
+ "bytes": 6531618,
419
+ "pages": 36,
420
+ "shards": 2
421
+ },
422
+ {
423
+ "seconds": 1.1864704220006388,
424
+ "bytes": 6136727,
425
+ "pages": 35,
426
+ "shards": 2
427
+ },
428
+ {
429
+ "seconds": 1.2697396670000671,
430
+ "bytes": 6182466,
431
+ "pages": 33,
432
+ "shards": 3
433
+ },
434
+ {
435
+ "seconds": 1.2363136280000617,
436
+ "bytes": 6022734,
437
+ "pages": 37,
438
+ "shards": 2
439
+ },
440
+ {
441
+ "seconds": 1.2937560119999034,
442
+ "bytes": 947666,
443
+ "pages": 30,
444
+ "shards": 1
445
+ },
446
+ {
447
+ "seconds": 1.5761228700002903,
448
+ "bytes": 18281686,
449
+ "pages": 39,
450
+ "shards": 5
451
+ },
452
+ {
453
+ "seconds": 1.1403170100002171,
454
+ "bytes": 5965661,
455
+ "pages": 36,
456
+ "shards": 2
457
+ },
458
+ {
459
+ "seconds": 1.088612870000361,
460
+ "bytes": 2479743,
461
+ "pages": 29,
462
+ "shards": 2
463
+ },
464
+ {
465
+ "seconds": 1.3296366939994186,
466
+ "bytes": 6147791,
467
+ "pages": 36,
468
+ "shards": 2
469
+ },
470
+ {
471
+ "seconds": 1.1267749469989212,
472
+ "bytes": 894977,
473
+ "pages": 27,
474
+ "shards": 1
475
+ },
476
+ {
477
+ "seconds": 1.4399002789996302,
478
+ "bytes": 10842331,
479
+ "pages": 40,
480
+ "shards": 4
481
+ },
482
+ {
483
+ "seconds": 1.632049243999063,
484
+ "bytes": 11967346,
485
+ "pages": 40,
486
+ "shards": 3
487
+ },
488
+ {
489
+ "seconds": 0.9512228559997311,
490
+ "bytes": 901267,
491
+ "pages": 26,
492
+ "shards": 1
493
+ },
494
+ {
495
+ "seconds": 1.6983987419989717,
496
+ "bytes": 12559131,
497
+ "pages": 36,
498
+ "shards": 4
499
+ },
500
+ {
501
+ "seconds": 1.1707839329992566,
502
+ "bytes": 6060902,
503
+ "pages": 32,
504
+ "shards": 2
505
+ },
506
+ {
507
+ "seconds": 1.1801391750013863,
508
+ "bytes": 2749619,
509
+ "pages": 37,
510
+ "shards": 3
511
+ },
512
+ {
513
+ "seconds": 1.1686728980002954,
514
+ "bytes": 6121581,
515
+ "pages": 36,
516
+ "shards": 2
517
+ },
518
+ {
519
+ "seconds": 1.3895534080002108,
520
+ "bytes": 15955272,
521
+ "pages": 35,
522
+ "shards": 4
523
+ },
524
+ {
525
+ "seconds": 0.9986490080009389,
526
+ "bytes": 2653371,
527
+ "pages": 37,
528
+ "shards": 2
529
+ },
530
+ {
531
+ "seconds": 1.1648389490001136,
532
+ "bytes": 5951393,
533
+ "pages": 27,
534
+ "shards": 2
535
+ },
536
+ {
537
+ "seconds": 1.1927761070000997,
538
+ "bytes": 2669572,
539
+ "pages": 36,
540
+ "shards": 2
541
+ },
542
+ {
543
+ "seconds": 1.1629383399995277,
544
+ "bytes": 10339749,
545
+ "pages": 40,
546
+ "shards": 3
547
+ },
548
+ {
549
+ "seconds": 1.6129309269999794,
550
+ "bytes": 5876330,
551
+ "pages": 28,
552
+ "shards": 2
553
+ },
554
+ {
555
+ "seconds": 1.7068213439997635,
556
+ "bytes": 8291481,
557
+ "pages": 35,
558
+ "shards": 3
559
+ },
560
+ {
561
+ "seconds": 1.2685745549988496,
562
+ "bytes": 6220542,
563
+ "pages": 34,
564
+ "shards": 2
565
  }
566
  ],
567
  "cache_key": {
trainer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2190176915a9e996d9ff3392761fa977ba84ff82f831e2f53700f0a741af6d71
3
- size 721773055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc6aff6ad2f08dece94cc67d7a302ec23b409b0da9ac246329b68a9b3231985
3
+ size 721774207