appvoid commited on
Commit
4d45095
·
verified ·
1 Parent(s): c7ee32e

Qwen90M step 165000; complete resumable checkpoint

Browse files
Files changed (6) hide show
  1. complete.json +5 -5
  2. coverage.json +51 -51
  3. latest.json +1 -1
  4. model.safetensors +1 -1
  5. shard_scheduler.json +269 -23
  6. trainer.pt +2 -2
complete.json CHANGED
@@ -1,18 +1,18 @@
1
  {
2
- "step": 160000,
3
  "files": {
4
  "config.json": "cbc72137da3dae65085a2a8c39ad7634d16bf92d785ca00d283ee82fe32b37e7",
5
  "generation_config.json": "54ed0d19f6226888c91157964ede8a892bd5ae175bfad85336152b3d9b6cd7c4",
6
- "model.safetensors": "204af5881a577fef1ed88738397873be9f9b5acc4b3f00f0f4a334c0cc5e8b87",
7
  "tokenization_byte.py": "279b9990f77b1eaedc7c1184fe13d60273a713ead856200f1fb9ae323c7b1e03",
8
  "tokenizer_config.json": "0ecbd4fd39e35125800d806af981ba0cacd8a7ba5f02c9e729c4ecc54af6d300",
9
  "special_tokens_map.json": "20d4b94d0e657c3f44d9123522c106e7315b6c1a1b6d259478f17bd2918b1263",
10
  "byte_vocab.json": "57a1cd2e70dd5b7cc6fd2eaa12ebfcd173c1620fa5d45c2c6282511c29b6a5f6",
11
- "trainer.pt": "58b1a9a87c98368688872d521c56ed9c3b9c63110540b20f692c5f45af15e7f4",
12
  "training_config.json": "95ba9e002790d11959d1191b36ed994bfa10a6da51c22c772e143bec517a9783",
13
  "performance.json": "d8fc0ab4ba9b75a14bc27c39b9cdaf8c3a3b38cccaa4c038b8370fdf2cd49c08",
14
- "shard_scheduler.json": "b3d4d07ae7a6200c6ddee288c163b45048e3d78bd520197a93226391eb377b08",
15
- "coverage.json": "a820d638cc498caf3588ee86be26b0f7f1fac193033602fe4336d6fc6fd2fc93",
16
  "README.md": "9ce0f9efacbc46177a7e818b6aed274d84e7145ff944b5c7d6ecd5d33b9d4419"
17
  },
18
  "signature": "9fee47918905b0750bee87876aa424f021ccc4507ee8db22a11d01fbc6109063"
 
1
  {
2
+ "step": 165000,
3
  "files": {
4
  "config.json": "cbc72137da3dae65085a2a8c39ad7634d16bf92d785ca00d283ee82fe32b37e7",
5
  "generation_config.json": "54ed0d19f6226888c91157964ede8a892bd5ae175bfad85336152b3d9b6cd7c4",
6
+ "model.safetensors": "2055e13f7b5b304d0c2206d7fb9fd41c1dbf127325878ef730f5b741d6555462",
7
  "tokenization_byte.py": "279b9990f77b1eaedc7c1184fe13d60273a713ead856200f1fb9ae323c7b1e03",
8
  "tokenizer_config.json": "0ecbd4fd39e35125800d806af981ba0cacd8a7ba5f02c9e729c4ecc54af6d300",
9
  "special_tokens_map.json": "20d4b94d0e657c3f44d9123522c106e7315b6c1a1b6d259478f17bd2918b1263",
10
  "byte_vocab.json": "57a1cd2e70dd5b7cc6fd2eaa12ebfcd173c1620fa5d45c2c6282511c29b6a5f6",
11
+ "trainer.pt": "4aadd2411e27d45ea0852b13570a9cc811de9a400c6b05705bce64c357639250",
12
  "training_config.json": "95ba9e002790d11959d1191b36ed994bfa10a6da51c22c772e143bec517a9783",
13
  "performance.json": "d8fc0ab4ba9b75a14bc27c39b9cdaf8c3a3b38cccaa4c038b8370fdf2cd49c08",
14
+ "shard_scheduler.json": "37c2d3b415e95706fcd09442dbfed95fbe0847366375512b565a88834bde0eeb",
15
+ "coverage.json": "6b16c159bcce254a2303d601ede22d8e32b19a35679351555cb18cba36d7f12d",
16
  "README.md": "9ce0f9efacbc46177a7e818b6aed274d84e7145ff944b5c7d6ecd5d33b9d4419"
17
  },
18
  "signature": "9fee47918905b0750bee87876aa424f021ccc4507ee8db22a11d01fbc6109063"
coverage.json CHANGED
@@ -1,107 +1,107 @@
1
  {
2
- "step": 160000,
3
  "stats": {
4
- "climbmix/blocks": 5760000,
5
- "climbmix/targets": 9627080225,
6
- "climbmix/input_tokens": 9627690635,
7
- "ultra_qa/blocks": 2160000,
8
- "ultra_qa/targets": 3523611388,
9
- "ultra_qa/input_tokens": 3523618170,
10
- "cortex/blocks": 2160000,
11
- "cortex/targets": 82159978,
12
- "cortex/input_tokens": 3433330864,
13
- "ultra_style/blocks": 2160000,
14
- "ultra_style/targets": 3416345189,
15
- "ultra_style/input_tokens": 3416524370,
16
- "openmath/blocks": 1440000,
17
- "openmath/targets": 2224889648,
18
- "openmath/input_tokens": 2225631152,
19
- "rewrite6/blocks": 720000,
20
- "rewrite6/targets": 1180373319,
21
- "rewrite6/input_tokens": 1181667487
22
  },
23
  "sources": {
24
  "climbmix": {
25
- "page": 789,
26
- "row": 1412,
27
  "start": {
28
- "file": 38,
29
  "reader": {
30
  "format": "parquet-row-v1",
31
- "row_group": 10,
32
  "row": 1024
33
  }
34
  },
35
  "epoch": 0,
36
- "offset": 0,
37
- "documents": 3233156
38
  },
39
  "rewrite6": {
40
- "page": 48,
41
- "row": 3853,
42
  "start": {
43
  "file": 0,
44
  "reader": {
45
  "format": "jsonl-row-v1",
46
- "row": 196608
47
  }
48
  },
49
- "epoch": 8,
50
- "offset": 2048,
51
- "documents": 1843693
52
  },
53
  "openmath": {
54
- "page": 493,
55
- "row": 341,
56
  "start": {
57
  "file": 4,
58
  "reader": {
59
  "format": "parquet-row-v1",
60
- "row_group": 272,
61
- "row": 728
62
  }
63
  },
64
  "epoch": 0,
65
- "offset": 2048,
66
- "documents": 2019669
67
  },
68
  "ultra_qa": {
69
- "page": 213,
70
- "row": 777,
71
  "start": {
72
  "file": 1,
73
  "reader": {
74
  "format": "parquet-row-v1",
75
  "row_group": 5,
76
- "row": 29914
77
  }
78
  },
79
  "epoch": 0,
80
  "offset": 2048,
81
- "documents": 873225
82
  },
83
  "ultra_style": {
84
- "page": 325,
85
- "row": 1744,
86
  "start": {
87
- "file": 1,
88
  "reader": {
89
  "format": "parquet-row-v1",
90
- "row_group": 7,
91
- "row": 50737
92
  }
93
  },
94
  "epoch": 0,
95
- "offset": 0,
96
- "documents": 1332944
97
  },
98
  "cortex": {
99
- "page": 41888,
100
- "row": 1,
101
  "start": null,
102
  "epoch": 0,
103
  "offset": 0,
104
- "documents": 5361665
105
  }
106
  }
107
  }
 
1
  {
2
+ "step": 165000,
3
  "stats": {
4
+ "climbmix/blocks": 5940000,
5
+ "climbmix/targets": 9927628187,
6
+ "climbmix/input_tokens": 9928257678,
7
+ "ultra_qa/blocks": 2227500,
8
+ "ultra_qa/targets": 3633811973,
9
+ "ultra_qa/input_tokens": 3633818963,
10
+ "cortex/blocks": 2227500,
11
+ "cortex/targets": 84725586,
12
+ "cortex/input_tokens": 3540651120,
13
+ "ultra_style/blocks": 2227500,
14
+ "ultra_style/targets": 3523134670,
15
+ "ultra_style/input_tokens": 3523319504,
16
+ "openmath/blocks": 1485000,
17
+ "openmath/targets": 2294270266,
18
+ "openmath/input_tokens": 2295034673,
19
+ "rewrite6/blocks": 742500,
20
+ "rewrite6/targets": 1217215870,
21
+ "rewrite6/input_tokens": 1218550219
22
  },
23
  "sources": {
24
  "climbmix": {
25
+ "page": 814,
26
+ "row": 242,
27
  "start": {
28
+ "file": 39,
29
  "reader": {
30
  "format": "parquet-row-v1",
31
+ "row_group": 27,
32
  "row": 1024
33
  }
34
  },
35
  "epoch": 0,
36
+ "offset": 2048,
37
+ "documents": 3334386
38
  },
39
  "rewrite6": {
40
+ "page": 12,
41
+ "row": 3197,
42
  "start": {
43
  "file": 0,
44
  "reader": {
45
  "format": "jsonl-row-v1",
46
+ "row": 49152
47
  }
48
  },
49
+ "epoch": 9,
50
+ "offset": 0,
51
+ "documents": 1900985
52
  },
53
  "openmath": {
54
+ "page": 508,
55
+ "row": 1788,
56
  "start": {
57
  "file": 4,
58
  "reader": {
59
  "format": "parquet-row-v1",
60
+ "row_group": 334,
61
+ "row": 168
62
  }
63
  },
64
  "epoch": 0,
65
+ "offset": 0,
66
+ "documents": 2082556
67
  },
68
  "ultra_qa": {
69
+ "page": 219,
70
+ "row": 3510,
71
  "start": {
72
  "file": 1,
73
  "reader": {
74
  "format": "parquet-row-v1",
75
  "row_group": 5,
76
+ "row": 54490
77
  }
78
  },
79
  "epoch": 0,
80
  "offset": 2048,
81
+ "documents": 900534
82
  },
83
  "ultra_style": {
84
+ "page": 335,
85
+ "row": 2292,
86
  "start": {
87
+ "file": 2,
88
  "reader": {
89
  "format": "parquet-row-v1",
90
+ "row_group": 0,
91
+ "row": 2278
92
  }
93
  },
94
  "epoch": 0,
95
+ "offset": 2048,
96
+ "documents": 1374452
97
  },
98
  "cortex": {
99
+ "page": 43197,
100
+ "row": 83,
101
  "start": null,
102
  "epoch": 0,
103
  "offset": 0,
104
+ "documents": 5529299
105
  }
106
  }
107
  }
latest.json CHANGED
@@ -1 +1 @@
1
- {"step": 160000, "files": {"config.json": "cbc72137da3dae65085a2a8c39ad7634d16bf92d785ca00d283ee82fe32b37e7", "generation_config.json": "54ed0d19f6226888c91157964ede8a892bd5ae175bfad85336152b3d9b6cd7c4", "model.safetensors": "204af5881a577fef1ed88738397873be9f9b5acc4b3f00f0f4a334c0cc5e8b87", "tokenization_byte.py": "279b9990f77b1eaedc7c1184fe13d60273a713ead856200f1fb9ae323c7b1e03", "tokenizer_config.json": "0ecbd4fd39e35125800d806af981ba0cacd8a7ba5f02c9e729c4ecc54af6d300", "special_tokens_map.json": "20d4b94d0e657c3f44d9123522c106e7315b6c1a1b6d259478f17bd2918b1263", "byte_vocab.json": "57a1cd2e70dd5b7cc6fd2eaa12ebfcd173c1620fa5d45c2c6282511c29b6a5f6", "trainer.pt": "58b1a9a87c98368688872d521c56ed9c3b9c63110540b20f692c5f45af15e7f4", "training_config.json": "95ba9e002790d11959d1191b36ed994bfa10a6da51c22c772e143bec517a9783", "performance.json": "d8fc0ab4ba9b75a14bc27c39b9cdaf8c3a3b38cccaa4c038b8370fdf2cd49c08", "shard_scheduler.json": "b3d4d07ae7a6200c6ddee288c163b45048e3d78bd520197a93226391eb377b08", "coverage.json": "a820d638cc498caf3588ee86be26b0f7f1fac193033602fe4336d6fc6fd2fc93", "README.md": "9ce0f9efacbc46177a7e818b6aed274d84e7145ff944b5c7d6ecd5d33b9d4419"}, "signature": "9fee47918905b0750bee87876aa424f021ccc4507ee8db22a11d01fbc6109063", "folder": "step-000000160000"}
 
1
+ {"step": 165000, "files": {"config.json": "cbc72137da3dae65085a2a8c39ad7634d16bf92d785ca00d283ee82fe32b37e7", "generation_config.json": "54ed0d19f6226888c91157964ede8a892bd5ae175bfad85336152b3d9b6cd7c4", "model.safetensors": "2055e13f7b5b304d0c2206d7fb9fd41c1dbf127325878ef730f5b741d6555462", "tokenization_byte.py": "279b9990f77b1eaedc7c1184fe13d60273a713ead856200f1fb9ae323c7b1e03", "tokenizer_config.json": "0ecbd4fd39e35125800d806af981ba0cacd8a7ba5f02c9e729c4ecc54af6d300", "special_tokens_map.json": "20d4b94d0e657c3f44d9123522c106e7315b6c1a1b6d259478f17bd2918b1263", "byte_vocab.json": "57a1cd2e70dd5b7cc6fd2eaa12ebfcd173c1620fa5d45c2c6282511c29b6a5f6", "trainer.pt": "4aadd2411e27d45ea0852b13570a9cc811de9a400c6b05705bce64c357639250", "training_config.json": "95ba9e002790d11959d1191b36ed994bfa10a6da51c22c772e143bec517a9783", "performance.json": "d8fc0ab4ba9b75a14bc27c39b9cdaf8c3a3b38cccaa4c038b8370fdf2cd49c08", "shard_scheduler.json": "37c2d3b415e95706fcd09442dbfed95fbe0847366375512b565a88834bde0eeb", "coverage.json": "6b16c159bcce254a2303d601ede22d8e32b19a35679351555cb18cba36d7f12d", "README.md": "9ce0f9efacbc46177a7e818b6aed274d84e7145ff944b5c7d6ecd5d33b9d4419"}, "signature": "9fee47918905b0750bee87876aa424f021ccc4507ee8db22a11d01fbc6109063", "folder": "step-000000165000"}
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:204af5881a577fef1ed88738397873be9f9b5acc4b3f00f0f4a334c0cc5e8b87
3
  size 360622744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2055e13f7b5b304d0c2206d7fb9fd41c1dbf127325878ef730f5b741d6555462
3
  size 360622744
shard_scheduler.json CHANGED
@@ -22,8 +22,8 @@
22
  "tokens_per_second": 1062967.6168812835,
23
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
24
  "estimated_pages_for_buffer": 1,
25
- "required_token_positions_per_second": 75895.57656905257,
26
- "required_pages_per_second_upper_estimate": 0.006578436221425263
27
  },
28
  {
29
  "source": "rewrite6",
@@ -36,8 +36,8 @@
36
  "tokens_per_second": 1206672.263377472,
37
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
38
  "estimated_pages_for_buffer": 1,
39
- "required_token_positions_per_second": 9486.947071131572,
40
- "required_pages_per_second_upper_estimate": 0.0037844850291732773
41
  },
42
  {
43
  "source": "openmath",
@@ -50,8 +50,8 @@
50
  "tokens_per_second": 410042.7581134458,
51
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
52
  "estimated_pages_for_buffer": 1,
53
- "required_token_positions_per_second": 18973.894142263143,
54
- "required_pages_per_second_upper_estimate": 0.0043892764806807705
55
  },
56
  {
57
  "source": "ultra_qa",
@@ -64,8 +64,8 @@
64
  "tokens_per_second": 2163486.5624068812,
65
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
66
  "estimated_pages_for_buffer": 1,
67
- "required_token_positions_per_second": 28460.841213394717,
68
- "required_pages_per_second_upper_estimate": 0.0017331159074021418
69
  },
70
  {
71
  "source": "ultra_style",
@@ -78,8 +78,8 @@
78
  "tokens_per_second": 1546694.2737633225,
79
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
80
  "estimated_pages_for_buffer": 1,
81
- "required_token_positions_per_second": 28460.841213394717,
82
- "required_pages_per_second_upper_estimate": 0.002190994341258046
83
  },
84
  {
85
  "source": "cortex",
@@ -92,8 +92,8 @@
92
  "tokens_per_second": 1015177.8395898147,
93
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
94
  "estimated_pages_for_buffer": 22,
95
- "required_token_positions_per_second": 28460.841213394717,
96
- "required_pages_per_second_upper_estimate": 0.35338839556222257
97
  }
98
  ],
99
  "gpu_measurement": "Selected forward/backward estimate; replaced by live successful update timings.",
@@ -158,24 +158,24 @@
158
  "prefetch_batches": 62,
159
  "prefetch_capacity_limit": 512,
160
  "batch_memory_estimate_bytes": 688946,
161
- "producer_batch_seconds": 0.5166383134453412,
162
- "producer_p95_seconds": 0.1841241980000632,
163
- "gpu_update_seconds": 0.9714400144640783,
164
- "producer_batches_per_second": 1.935590090737235,
165
- "gpu_batches_per_second": 1.0293996387946585,
166
- "producer_headroom": 1.8803096657423064,
167
  "sustainable": true,
168
- "buffer_seconds": 60.229280896772856,
169
  "buffer_drain_seconds": null,
170
  "shard_target_mib": 16,
171
- "upload_pages_per_commit": 76,
172
  "max_pending_pages": 4096,
173
- "generation_bytes_per_second": 394137.7785946498,
174
- "upload_bytes_per_second": 4508842.591861955,
175
  "upload_sustainable": true,
176
  "logical_page_rows": 4096,
177
  "logical_cortex_page_rows": 128,
178
- "estimated_full_shards_per_hour": 84.57279222850438,
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": [
@@ -274,6 +274,252 @@
274
  "bytes": 5755818,
275
  "pages": 29,
276
  "shards": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
277
  }
278
  ],
279
  "cache_key": {
 
22
  "tokens_per_second": 1062967.6168812835,
23
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
24
  "estimated_pages_for_buffer": 1,
25
+ "required_token_positions_per_second": 76024.17600051314,
26
+ "required_pages_per_second_upper_estimate": 0.006589582894211986
27
  },
28
  {
29
  "source": "rewrite6",
 
36
  "tokens_per_second": 1206672.263377472,
37
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
38
  "estimated_pages_for_buffer": 1,
39
+ "required_token_positions_per_second": 9503.022000064142,
40
+ "required_pages_per_second_upper_estimate": 0.0037908975586660853
41
  },
42
  {
43
  "source": "openmath",
 
50
  "tokens_per_second": 410042.7581134458,
51
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
52
  "estimated_pages_for_buffer": 1,
53
+ "required_token_positions_per_second": 19006.044000128284,
54
+ "required_pages_per_second_upper_estimate": 0.004396713784479697
55
  },
56
  {
57
  "source": "ultra_qa",
 
64
  "tokens_per_second": 2163486.5624068812,
65
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
66
  "estimated_pages_for_buffer": 1,
67
+ "required_token_positions_per_second": 28509.06600019243,
68
+ "required_pages_per_second_upper_estimate": 0.0017360525439022204
69
  },
70
  {
71
  "source": "ultra_style",
 
78
  "tokens_per_second": 1546694.2737633225,
79
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
80
  "estimated_pages_for_buffer": 1,
81
+ "required_token_positions_per_second": 28509.06600019243,
82
+ "required_pages_per_second_upper_estimate": 0.002194706818840488
83
  },
84
  {
85
  "source": "cortex",
 
92
  "tokens_per_second": 1015177.8395898147,
93
  "note": "Bounded fresh sample; full-page latency is an extrapolation.",
94
  "estimated_pages_for_buffer": 22,
95
+ "required_token_positions_per_second": 28509.06600019243,
96
+ "required_pages_per_second_upper_estimate": 0.35398718601627116
97
  }
98
  ],
99
  "gpu_measurement": "Selected forward/backward estimate; replaced by live successful update timings.",
 
158
  "prefetch_batches": 62,
159
  "prefetch_capacity_limit": 512,
160
  "batch_memory_estimate_bytes": 688946,
161
+ "producer_batch_seconds": 0.09048123760162241,
162
+ "producer_p95_seconds": 0.1997182420000172,
163
+ "gpu_update_seconds": 0.9697967656959854,
164
+ "producer_batches_per_second": 11.05201505314146,
165
+ "gpu_batches_per_second": 1.0311438802152932,
166
+ "producer_headroom": 10.718208452959932,
167
  "sustainable": true,
168
+ "buffer_seconds": 60.127399473151094,
169
  "buffer_drain_seconds": null,
170
  "shard_target_mib": 16,
171
+ "upload_pages_per_commit": 83,
172
  "max_pending_pages": 4096,
173
+ "generation_bytes_per_second": 314248.84728296526,
174
+ "upload_bytes_per_second": 5212065.682698314,
175
  "upload_sustainable": true,
176
  "logical_page_rows": 4096,
177
  "logical_cortex_page_rows": 128,
178
+ "estimated_full_shards_per_hour": 67.43048728815764,
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": [
 
274
  "bytes": 5755818,
275
  "pages": 29,
276
  "shards": 2
277
+ },
278
+ {
279
+ "seconds": 1.4588776000000507,
280
+ "bytes": 16176314,
281
+ "pages": 44,
282
+ "shards": 4
283
+ },
284
+ {
285
+ "seconds": 0.8323371429996769,
286
+ "bytes": 2088001,
287
+ "pages": 18,
288
+ "shards": 2
289
+ },
290
+ {
291
+ "seconds": 1.2336509919996388,
292
+ "bytes": 6127983,
293
+ "pages": 36,
294
+ "shards": 2
295
+ },
296
+ {
297
+ "seconds": 1.0918112409999594,
298
+ "bytes": 968274,
299
+ "pages": 28,
300
+ "shards": 1
301
+ },
302
+ {
303
+ "seconds": 1.2902597590000369,
304
+ "bytes": 12650540,
305
+ "pages": 36,
306
+ "shards": 4
307
+ },
308
+ {
309
+ "seconds": 1.0202606470002138,
310
+ "bytes": 1124000,
311
+ "pages": 34,
312
+ "shards": 2
313
+ },
314
+ {
315
+ "seconds": 1.3055697850004435,
316
+ "bytes": 13351938,
317
+ "pages": 38,
318
+ "shards": 4
319
+ },
320
+ {
321
+ "seconds": 1.0015427250000357,
322
+ "bytes": 6023702,
323
+ "pages": 35,
324
+ "shards": 2
325
+ },
326
+ {
327
+ "seconds": 1.052357557000505,
328
+ "bytes": 4323709,
329
+ "pages": 27,
330
+ "shards": 2
331
+ },
332
+ {
333
+ "seconds": 1.0870202730002347,
334
+ "bytes": 7523830,
335
+ "pages": 37,
336
+ "shards": 3
337
+ },
338
+ {
339
+ "seconds": 0.8949287559998993,
340
+ "bytes": 6264749,
341
+ "pages": 35,
342
+ "shards": 2
343
+ },
344
+ {
345
+ "seconds": 1.0034355950001554,
346
+ "bytes": 860910,
347
+ "pages": 25,
348
+ "shards": 1
349
+ },
350
+ {
351
+ "seconds": 1.6520775649996722,
352
+ "bytes": 17392082,
353
+ "pages": 43,
354
+ "shards": 5
355
+ },
356
+ {
357
+ "seconds": 1.2575243370001772,
358
+ "bytes": 1055853,
359
+ "pages": 33,
360
+ "shards": 1
361
+ },
362
+ {
363
+ "seconds": 2.737182930999552,
364
+ "bytes": 7527517,
365
+ "pages": 37,
366
+ "shards": 3
367
+ },
368
+ {
369
+ "seconds": 0.9472420219999549,
370
+ "bytes": 626425,
371
+ "pages": 19,
372
+ "shards": 1
373
+ },
374
+ {
375
+ "seconds": 1.3963090409997676,
376
+ "bytes": 10793699,
377
+ "pages": 45,
378
+ "shards": 3
379
+ },
380
+ {
381
+ "seconds": 1.3661847930006843,
382
+ "bytes": 7242166,
383
+ "pages": 29,
384
+ "shards": 3
385
+ },
386
+ {
387
+ "seconds": 1.0256425439993109,
388
+ "bytes": 848800,
389
+ "pages": 26,
390
+ "shards": 1
391
+ },
392
+ {
393
+ "seconds": 1.479707024000163,
394
+ "bytes": 13318632,
395
+ "pages": 43,
396
+ "shards": 4
397
+ },
398
+ {
399
+ "seconds": 1.157918292999966,
400
+ "bytes": 10292312,
401
+ "pages": 36,
402
+ "shards": 3
403
+ },
404
+ {
405
+ "seconds": 2.16527700000006,
406
+ "bytes": 1181305,
407
+ "pages": 34,
408
+ "shards": 1
409
+ },
410
+ {
411
+ "seconds": 1.226145381000606,
412
+ "bytes": 7407097,
413
+ "pages": 30,
414
+ "shards": 3
415
+ },
416
+ {
417
+ "seconds": 0.7928119780008274,
418
+ "bytes": 1141631,
419
+ "pages": 33,
420
+ "shards": 1
421
+ },
422
+ {
423
+ "seconds": 1.3008312719994137,
424
+ "bytes": 10073702,
425
+ "pages": 31,
426
+ "shards": 3
427
+ },
428
+ {
429
+ "seconds": 1.3391879739992874,
430
+ "bytes": 13717263,
431
+ "pages": 44,
432
+ "shards": 4
433
+ },
434
+ {
435
+ "seconds": 0.882563871999082,
436
+ "bytes": 1071171,
437
+ "pages": 33,
438
+ "shards": 1
439
+ },
440
+ {
441
+ "seconds": 1.5854626939999434,
442
+ "bytes": 7158059,
443
+ "pages": 27,
444
+ "shards": 3
445
+ },
446
+ {
447
+ "seconds": 1.1073119590000715,
448
+ "bytes": 10577372,
449
+ "pages": 37,
450
+ "shards": 3
451
+ },
452
+ {
453
+ "seconds": 0.7750392130001273,
454
+ "bytes": 1199165,
455
+ "pages": 34,
456
+ "shards": 1
457
+ },
458
+ {
459
+ "seconds": 1.0709359819993551,
460
+ "bytes": 7553738,
461
+ "pages": 32,
462
+ "shards": 3
463
+ },
464
+ {
465
+ "seconds": 0.9643511739996029,
466
+ "bytes": 6918272,
467
+ "pages": 35,
468
+ "shards": 2
469
+ },
470
+ {
471
+ "seconds": 1.0286668139997346,
472
+ "bytes": 9530498,
473
+ "pages": 29,
474
+ "shards": 3
475
+ },
476
+ {
477
+ "seconds": 0.9772154700003739,
478
+ "bytes": 2553165,
479
+ "pages": 32,
480
+ "shards": 2
481
+ },
482
+ {
483
+ "seconds": 1.3266675979994034,
484
+ "bytes": 5992849,
485
+ "pages": 30,
486
+ "shards": 2
487
+ },
488
+ {
489
+ "seconds": 1.2236139670003467,
490
+ "bytes": 7766768,
491
+ "pages": 37,
492
+ "shards": 3
493
+ },
494
+ {
495
+ "seconds": 1.4731977419996838,
496
+ "bytes": 6241189,
497
+ "pages": 37,
498
+ "shards": 3
499
+ },
500
+ {
501
+ "seconds": 1.5922990050003136,
502
+ "bytes": 11693360,
503
+ "pages": 32,
504
+ "shards": 3
505
+ },
506
+ {
507
+ "seconds": 0.8287107050000486,
508
+ "bytes": 2337614,
509
+ "pages": 28,
510
+ "shards": 2
511
+ },
512
+ {
513
+ "seconds": 0.9556833940005163,
514
+ "bytes": 6215473,
515
+ "pages": 35,
516
+ "shards": 2
517
+ },
518
+ {
519
+ "seconds": 1.3753932430008717,
520
+ "bytes": 9934254,
521
+ "pages": 39,
522
+ "shards": 3
523
  }
524
  ],
525
  "cache_key": {
trainer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58b1a9a87c98368688872d521c56ed9c3b9c63110540b20f692c5f45af15e7f4
3
- size 721773183
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aadd2411e27d45ea0852b13570a9cc811de9a400c6b05705bce64c357639250
3
+ size 721766463