appvoid commited on
Commit
bea9f36
·
verified ·
1 Parent(s): fb54c71

Qwen90M step 535000; complete resumable checkpoint

Browse files
Files changed (6) hide show
  1. complete.json +5 -5
  2. coverage.json +49 -55
  3. latest.json +1 -1
  4. model.safetensors +1 -1
  5. shard_scheduler.json +269 -41
  6. trainer.pt +2 -2
complete.json CHANGED
@@ -1,18 +1,18 @@
1
  {
2
- "step": 530000,
3
  "files": {
4
  "config.json": "cbc72137da3dae65085a2a8c39ad7634d16bf92d785ca00d283ee82fe32b37e7",
5
  "generation_config.json": "54ed0d19f6226888c91157964ede8a892bd5ae175bfad85336152b3d9b6cd7c4",
6
- "model.safetensors": "3345a1d3d37a56145174811805daadbe6545c69564f12badd37ca9980383c189",
7
  "tokenization_byte.py": "279b9990f77b1eaedc7c1184fe13d60273a713ead856200f1fb9ae323c7b1e03",
8
  "tokenizer_config.json": "0ecbd4fd39e35125800d806af981ba0cacd8a7ba5f02c9e729c4ecc54af6d300",
9
  "special_tokens_map.json": "20d4b94d0e657c3f44d9123522c106e7315b6c1a1b6d259478f17bd2918b1263",
10
  "byte_vocab.json": "57a1cd2e70dd5b7cc6fd2eaa12ebfcd173c1620fa5d45c2c6282511c29b6a5f6",
11
- "trainer.pt": "4273939d74c5226bc57df9a209306193dff7da001a42417dfdf439575063da35",
12
  "training_config.json": "c8bdf052510c2d9092e5a6824b119dd6584dc7697f8c4a8e9b7ecf3057c5bbb6",
13
  "performance.json": "3070ebbdf9b2b0fd6a0a237819043aa2c2a35c74a97edfa223e5c324471af4af",
14
- "shard_scheduler.json": "3e8b88313d070ffdb6572b9af938d708afe66786c34590df9f577e00e5a7ad71",
15
- "coverage.json": "1f166ed6ce6875dfc663aa1359c72063b2c84099952c88e471aa37b08f50927f",
16
  "README.md": "9ce0f9efacbc46177a7e818b6aed274d84e7145ff944b5c7d6ecd5d33b9d4419"
17
  },
18
  "signature": "9fee47918905b0750bee87876aa424f021ccc4507ee8db22a11d01fbc6109063"
 
1
  {
2
+ "step": 535000,
3
  "files": {
4
  "config.json": "cbc72137da3dae65085a2a8c39ad7634d16bf92d785ca00d283ee82fe32b37e7",
5
  "generation_config.json": "54ed0d19f6226888c91157964ede8a892bd5ae175bfad85336152b3d9b6cd7c4",
6
+ "model.safetensors": "746a63165b4986046476ae84c2713e36ed3fa23737687659143ada4b831f1654",
7
  "tokenization_byte.py": "279b9990f77b1eaedc7c1184fe13d60273a713ead856200f1fb9ae323c7b1e03",
8
  "tokenizer_config.json": "0ecbd4fd39e35125800d806af981ba0cacd8a7ba5f02c9e729c4ecc54af6d300",
9
  "special_tokens_map.json": "20d4b94d0e657c3f44d9123522c106e7315b6c1a1b6d259478f17bd2918b1263",
10
  "byte_vocab.json": "57a1cd2e70dd5b7cc6fd2eaa12ebfcd173c1620fa5d45c2c6282511c29b6a5f6",
11
+ "trainer.pt": "2b45969c25feb44bef2bbc28e1a234c7ba36a717f6375ea0dba3053855528f94",
12
  "training_config.json": "c8bdf052510c2d9092e5a6824b119dd6584dc7697f8c4a8e9b7ecf3057c5bbb6",
13
  "performance.json": "3070ebbdf9b2b0fd6a0a237819043aa2c2a35c74a97edfa223e5c324471af4af",
14
+ "shard_scheduler.json": "dc3b4c9c9c5634b43786ba061a7ead1b9ed759c5b1eacff95382e91a9ef4f364",
15
+ "coverage.json": "7998ce90c7aacd5ffa1b3b45381b7a23cce87145599cd5217ab5d192996cc5db",
16
  "README.md": "9ce0f9efacbc46177a7e818b6aed274d84e7145ff944b5c7d6ecd5d33b9d4419"
17
  },
18
  "signature": "9fee47918905b0750bee87876aa424f021ccc4507ee8db22a11d01fbc6109063"
coverage.json CHANGED
@@ -1,107 +1,101 @@
1
  {
2
- "step": 530000,
3
  "stats": {
4
- "climbmix/blocks": 19080000,
5
- "climbmix/targets": 31893841018,
6
- "climbmix/input_tokens": 31895861954,
7
- "ultra_qa/blocks": 7155000,
8
- "ultra_qa/targets": 11672418639,
9
- "ultra_qa/input_tokens": 11672441161,
10
- "cortex/blocks": 7155000,
11
- "cortex/targets": 272094364,
12
- "cortex/input_tokens": 11373535505,
13
- "ultra_style/blocks": 7155000,
14
- "ultra_style/targets": 11316260253,
15
- "ultra_style/input_tokens": 11316853356,
16
- "openmath/blocks": 4770000,
17
- "openmath/targets": 7370634197,
18
- "openmath/input_tokens": 7373089745,
19
- "rewrite6/blocks": 2385000,
20
- "rewrite6/targets": 3909838802,
21
- "rewrite6/input_tokens": 3914125422
22
  },
23
  "sources": {
24
  "climbmix": {
25
- "page": 2613,
26
- "row": 1722,
27
  "start": {
28
- "file": 126,
29
  "reader": {
30
  "format": "parquet-row-v1",
31
- "row_group": 37,
32
  "row": 1024
33
  }
34
  },
35
  "epoch": 0,
36
  "offset": 0,
37
- "documents": 10704570
38
  },
39
  "rewrite6": {
40
- "page": 36,
41
- "row": 2819,
42
- "start": {
43
- "file": 0,
44
- "reader": {
45
- "format": "jsonl-row-v1",
46
- "row": 147456
47
- }
48
- },
49
- "epoch": 29,
50
- "offset": 0,
51
- "documents": 6106991
52
  },
53
  "openmath": {
54
- "page": 1633,
55
- "row": 76,
56
  "start": {
57
  "file": 15,
58
  "reader": {
59
  "format": "parquet-row-v1",
60
- "row_group": 139,
61
- "row": 18
62
  }
63
  },
64
  "epoch": 0,
65
  "offset": 0,
66
- "documents": 6688844
67
  },
68
  "ultra_qa": {
69
- "page": 706,
70
- "row": 539,
71
  "start": {
72
  "file": 5,
73
  "reader": {
74
  "format": "parquet-row-v1",
75
  "row_group": 4,
76
- "row": 35556
77
  }
78
  },
79
  "epoch": 0,
80
- "offset": 2048,
81
- "documents": 2892315
82
  },
83
  "ultra_style": {
84
- "page": 1077,
85
- "row": 2689,
86
  "start": {
87
  "file": 6,
88
  "reader": {
89
  "format": "parquet-row-v1",
90
- "row_group": 3,
91
- "row": 45678
92
  }
93
  },
94
  "epoch": 0,
95
- "offset": 2048,
96
- "documents": 4414081
97
  },
98
  "cortex": {
99
- "page": 138765,
100
- "row": 110,
101
  "start": null,
102
  "epoch": 0,
103
  "offset": 0,
104
- "documents": 17762030
105
  }
106
  }
107
  }
 
1
  {
2
+ "step": 535000,
3
  "stats": {
4
+ "climbmix/blocks": 19260000,
5
+ "climbmix/targets": 32195111082,
6
+ "climbmix/input_tokens": 32197151068,
7
+ "ultra_qa/blocks": 7222500,
8
+ "ultra_qa/targets": 11782590681,
9
+ "ultra_qa/input_tokens": 11782613431,
10
+ "cortex/blocks": 7222500,
11
+ "cortex/targets": 274657059,
12
+ "cortex/input_tokens": 11480802169,
13
+ "ultra_style/blocks": 7222500,
14
+ "ultra_style/targets": 11423290047,
15
+ "ultra_style/input_tokens": 11423888845,
16
+ "openmath/blocks": 4815000,
17
+ "openmath/targets": 7439991699,
18
+ "openmath/input_tokens": 7442470149,
19
+ "rewrite6/blocks": 2407500,
20
+ "rewrite6/targets": 3946780306,
21
+ "rewrite6/input_tokens": 3951107292
22
  },
23
  "sources": {
24
  "climbmix": {
25
+ "page": 2637,
26
+ "row": 4073,
27
  "start": {
28
+ "file": 127,
29
  "reader": {
30
  "format": "parquet-row-v1",
31
+ "row_group": 51,
32
  "row": 1024
33
  }
34
  },
35
  "epoch": 0,
36
  "offset": 0,
37
+ "documents": 10805225
38
  },
39
  "rewrite6": {
40
+ "page": 0,
41
+ "row": 2348,
42
+ "start": null,
43
+ "epoch": 30,
44
+ "offset": 2048,
45
+ "documents": 6164468
 
 
 
 
 
 
46
  },
47
  "openmath": {
48
+ "page": 1648,
49
+ "row": 1424,
50
  "start": {
51
  "file": 15,
52
  "reader": {
53
  "format": "parquet-row-v1",
54
+ "row_group": 200,
55
+ "row": 458
56
  }
57
  },
58
  "epoch": 0,
59
  "offset": 0,
60
+ "documents": 6751632
61
  },
62
  "ultra_qa": {
63
+ "page": 712,
64
+ "row": 3263,
65
  "start": {
66
  "file": 5,
67
  "reader": {
68
  "format": "parquet-row-v1",
69
  "row_group": 4,
70
+ "row": 60132
71
  }
72
  },
73
  "epoch": 0,
74
+ "offset": 6144,
75
+ "documents": 2919615
76
  },
77
  "ultra_style": {
78
+ "page": 1087,
79
+ "row": 3342,
80
  "start": {
81
  "file": 6,
82
  "reader": {
83
  "format": "parquet-row-v1",
84
+ "row_group": 4,
85
+ "row": 2030
86
  }
87
  },
88
  "epoch": 0,
89
+ "offset": 4096,
90
+ "documents": 4455694
91
  },
92
  "cortex": {
93
+ "page": 140074,
94
+ "row": 15,
95
  "start": null,
96
  "epoch": 0,
97
  "offset": 0,
98
+ "documents": 17929487
99
  }
100
  }
101
  }
latest.json CHANGED
@@ -1 +1 @@
1
- {"step": 530000, "files": {"config.json": "cbc72137da3dae65085a2a8c39ad7634d16bf92d785ca00d283ee82fe32b37e7", "generation_config.json": "54ed0d19f6226888c91157964ede8a892bd5ae175bfad85336152b3d9b6cd7c4", "model.safetensors": "3345a1d3d37a56145174811805daadbe6545c69564f12badd37ca9980383c189", "tokenization_byte.py": "279b9990f77b1eaedc7c1184fe13d60273a713ead856200f1fb9ae323c7b1e03", "tokenizer_config.json": "0ecbd4fd39e35125800d806af981ba0cacd8a7ba5f02c9e729c4ecc54af6d300", "special_tokens_map.json": "20d4b94d0e657c3f44d9123522c106e7315b6c1a1b6d259478f17bd2918b1263", "byte_vocab.json": "57a1cd2e70dd5b7cc6fd2eaa12ebfcd173c1620fa5d45c2c6282511c29b6a5f6", "trainer.pt": "4273939d74c5226bc57df9a209306193dff7da001a42417dfdf439575063da35", "training_config.json": "c8bdf052510c2d9092e5a6824b119dd6584dc7697f8c4a8e9b7ecf3057c5bbb6", "performance.json": "3070ebbdf9b2b0fd6a0a237819043aa2c2a35c74a97edfa223e5c324471af4af", "shard_scheduler.json": "3e8b88313d070ffdb6572b9af938d708afe66786c34590df9f577e00e5a7ad71", "coverage.json": "1f166ed6ce6875dfc663aa1359c72063b2c84099952c88e471aa37b08f50927f", "README.md": "9ce0f9efacbc46177a7e818b6aed274d84e7145ff944b5c7d6ecd5d33b9d4419"}, "signature": "9fee47918905b0750bee87876aa424f021ccc4507ee8db22a11d01fbc6109063", "folder": "step-000000530000"}
 
1
+ {"step": 535000, "files": {"config.json": "cbc72137da3dae65085a2a8c39ad7634d16bf92d785ca00d283ee82fe32b37e7", "generation_config.json": "54ed0d19f6226888c91157964ede8a892bd5ae175bfad85336152b3d9b6cd7c4", "model.safetensors": "746a63165b4986046476ae84c2713e36ed3fa23737687659143ada4b831f1654", "tokenization_byte.py": "279b9990f77b1eaedc7c1184fe13d60273a713ead856200f1fb9ae323c7b1e03", "tokenizer_config.json": "0ecbd4fd39e35125800d806af981ba0cacd8a7ba5f02c9e729c4ecc54af6d300", "special_tokens_map.json": "20d4b94d0e657c3f44d9123522c106e7315b6c1a1b6d259478f17bd2918b1263", "byte_vocab.json": "57a1cd2e70dd5b7cc6fd2eaa12ebfcd173c1620fa5d45c2c6282511c29b6a5f6", "trainer.pt": "2b45969c25feb44bef2bbc28e1a234c7ba36a717f6375ea0dba3053855528f94", "training_config.json": "c8bdf052510c2d9092e5a6824b119dd6584dc7697f8c4a8e9b7ecf3057c5bbb6", "performance.json": "3070ebbdf9b2b0fd6a0a237819043aa2c2a35c74a97edfa223e5c324471af4af", "shard_scheduler.json": "dc3b4c9c9c5634b43786ba061a7ead1b9ed759c5b1eacff95382e91a9ef4f364", "coverage.json": "7998ce90c7aacd5ffa1b3b45381b7a23cce87145599cd5217ab5d192996cc5db", "README.md": "9ce0f9efacbc46177a7e818b6aed274d84e7145ff944b5c7d6ecd5d33b9d4419"}, "signature": "9fee47918905b0750bee87876aa424f021ccc4507ee8db22a11d01fbc6109063", "folder": "step-000000535000"}
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3345a1d3d37a56145174811805daadbe6545c69564f12badd37ca9980383c189
3
  size 360622744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:746a63165b4986046476ae84c2713e36ed3fa23737687659143ada4b831f1654
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": 77015.98464267456,
26
- "required_pages_per_second_upper_estimate": 0.005328144519284888
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": 9626.99808033432,
40
- "required_pages_per_second_upper_estimate": 0.0040306230616556585
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": 19253.99616066864,
54
- "required_pages_per_second_upper_estimate": 0.004010099638243004
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": 28880.99424100296,
68
- "required_pages_per_second_upper_estimate": 0.0017313715060233205
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": 28880.99424100296,
82
- "required_pages_per_second_upper_estimate": 0.0022453702681696883
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": 28880.99424100296,
96
- "required_pages_per_second_upper_estimate": 0.3704543841279994
97
  }
98
  ],
99
  "gpu_measurement": "Selected forward/backward estimate; replaced by live successful update timings.",
@@ -158,45 +158,27 @@
158
  "prefetch_batches": 63,
159
  "prefetch_capacity_limit": 512,
160
  "batch_memory_estimate_bytes": 704566,
161
- "producer_batch_seconds": 0.320096299234379,
162
- "producer_p95_seconds": 0.15855196899974544,
163
- "gpu_update_seconds": 0.95730776334381,
164
- "producer_batches_per_second": 3.1240598607101857,
165
- "gpu_batches_per_second": 1.0445961458696094,
166
- "producer_headroom": 2.9906867578086427,
167
  "sustainable": true,
168
- "buffer_seconds": 60.310389090660024,
169
  "buffer_drain_seconds": null,
170
  "shard_target_mib": 16,
171
- "upload_pages_per_commit": 79,
172
  "max_pending_pages": 4096,
173
- "generation_bytes_per_second": 386229.8712076355,
174
- "upload_bytes_per_second": 3476176.657096584,
175
  "upload_sustainable": true,
176
  "logical_page_rows": 4096,
177
  "logical_cortex_page_rows": 128,
178
- "estimated_full_shards_per_hour": 82.87593938991354,
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": 1.0629590909998115,
184
- "bytes": 25106,
185
- "pages": 1,
186
- "shards": 1
187
- },
188
- {
189
- "seconds": 1.218460234000304,
190
- "bytes": 6273746,
191
- "pages": 34,
192
- "shards": 3
193
- },
194
- {
195
- "seconds": 1.1453777450001326,
196
- "bytes": 12048299,
197
- "pages": 34,
198
- "shards": 3
199
- },
200
  {
201
  "seconds": 1.011093388000063,
202
  "bytes": 1199201,
@@ -334,6 +316,252 @@
334
  "bytes": 6117097,
335
  "pages": 37,
336
  "shards": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
337
  }
338
  ],
339
  "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": 76499.76095720792,
26
+ "required_pages_per_second_upper_estimate": 0.00529243096692033
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": 9562.47011965099,
40
+ "required_pages_per_second_upper_estimate": 0.004003606552014596
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": 19124.94023930198,
54
+ "required_pages_per_second_upper_estimate": 0.003983220693255846
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": 28687.41035895297,
68
+ "required_pages_per_second_upper_estimate": 0.0017197664478798965
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": 28687.41035895297,
82
+ "required_pages_per_second_upper_estimate": 0.002230319972825811
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": 28687.41035895297,
96
+ "required_pages_per_second_upper_estimate": 0.36797129794324046
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": 704566,
161
+ "producer_batch_seconds": 0.08245735881254745,
162
+ "producer_p95_seconds": 0.19908109500102,
163
+ "gpu_update_seconds": 0.9637677174081841,
164
+ "producer_batches_per_second": 12.127480365619363,
165
+ "gpu_batches_per_second": 1.03759441402463,
166
+ "producer_headroom": 11.688074069885543,
167
  "sustainable": true,
168
+ "buffer_seconds": 60.7173661967156,
169
  "buffer_drain_seconds": null,
170
  "shard_target_mib": 16,
171
+ "upload_pages_per_commit": 87,
172
  "max_pending_pages": 4096,
173
+ "generation_bytes_per_second": 322888.0851025507,
174
+ "upload_bytes_per_second": 4628498.063736584,
175
  "upload_sustainable": true,
176
  "logical_page_rows": 4096,
177
  "logical_cortex_page_rows": 128,
178
+ "estimated_full_shards_per_hour": 69.28426661307708,
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": 1.011093388000063,
184
  "bytes": 1199201,
 
316
  "bytes": 6117097,
317
  "pages": 37,
318
  "shards": 2
319
+ },
320
+ {
321
+ "seconds": 1.1878640209997684,
322
+ "bytes": 11776096,
323
+ "pages": 38,
324
+ "shards": 3
325
+ },
326
+ {
327
+ "seconds": 1.224845865000134,
328
+ "bytes": 2065038,
329
+ "pages": 19,
330
+ "shards": 2
331
+ },
332
+ {
333
+ "seconds": 0.9610936170001878,
334
+ "bytes": 5798019,
335
+ "pages": 27,
336
+ "shards": 2
337
+ },
338
+ {
339
+ "seconds": 1.1097549460000664,
340
+ "bytes": 5080154,
341
+ "pages": 36,
342
+ "shards": 2
343
+ },
344
+ {
345
+ "seconds": 1.1122178149998945,
346
+ "bytes": 7607293,
347
+ "pages": 38,
348
+ "shards": 3
349
+ },
350
+ {
351
+ "seconds": 1.0907007900004828,
352
+ "bytes": 6092133,
353
+ "pages": 36,
354
+ "shards": 2
355
+ },
356
+ {
357
+ "seconds": 0.8937167260000933,
358
+ "bytes": 2214439,
359
+ "pages": 24,
360
+ "shards": 2
361
+ },
362
+ {
363
+ "seconds": 1.3153861170003438,
364
+ "bytes": 17177113,
365
+ "pages": 40,
366
+ "shards": 4
367
+ },
368
+ {
369
+ "seconds": 0.9797320220004622,
370
+ "bytes": 1103154,
371
+ "pages": 35,
372
+ "shards": 2
373
+ },
374
+ {
375
+ "seconds": 1.195222697000645,
376
+ "bytes": 7323521,
377
+ "pages": 29,
378
+ "shards": 3
379
+ },
380
+ {
381
+ "seconds": 1.158046825999918,
382
+ "bytes": 6457008,
383
+ "pages": 36,
384
+ "shards": 2
385
+ },
386
+ {
387
+ "seconds": 1.1688710530006574,
388
+ "bytes": 6589194,
389
+ "pages": 40,
390
+ "shards": 3
391
+ },
392
+ {
393
+ "seconds": 1.0017207049995704,
394
+ "bytes": 5856566,
395
+ "pages": 27,
396
+ "shards": 2
397
+ },
398
+ {
399
+ "seconds": 1.1244407199992565,
400
+ "bytes": 12346633,
401
+ "pages": 40,
402
+ "shards": 3
403
+ },
404
+ {
405
+ "seconds": 0.9011206420000235,
406
+ "bytes": 2301339,
407
+ "pages": 25,
408
+ "shards": 2
409
+ },
410
+ {
411
+ "seconds": 1.4037659219993657,
412
+ "bytes": 10492690,
413
+ "pages": 42,
414
+ "shards": 3
415
+ },
416
+ {
417
+ "seconds": 0.9956328799999028,
418
+ "bytes": 1276481,
419
+ "pages": 36,
420
+ "shards": 1
421
+ },
422
+ {
423
+ "seconds": 1.4530193070004316,
424
+ "bytes": 7690650,
425
+ "pages": 38,
426
+ "shards": 3
427
+ },
428
+ {
429
+ "seconds": 1.0416680760008603,
430
+ "bytes": 5628205,
431
+ "pages": 24,
432
+ "shards": 2
433
+ },
434
+ {
435
+ "seconds": 1.0915457699993567,
436
+ "bytes": 13214903,
437
+ "pages": 39,
438
+ "shards": 4
439
+ },
440
+ {
441
+ "seconds": 1.4333472569996957,
442
+ "bytes": 6210705,
443
+ "pages": 36,
444
+ "shards": 2
445
+ },
446
+ {
447
+ "seconds": 1.232096203000765,
448
+ "bytes": 1201273,
449
+ "pages": 35,
450
+ "shards": 1
451
+ },
452
+ {
453
+ "seconds": 1.2199994860002334,
454
+ "bytes": 7355179,
455
+ "pages": 26,
456
+ "shards": 3
457
+ },
458
+ {
459
+ "seconds": 1.1187948159986263,
460
+ "bytes": 10435269,
461
+ "pages": 45,
462
+ "shards": 3
463
+ },
464
+ {
465
+ "seconds": 0.8605066399995849,
466
+ "bytes": 757336,
467
+ "pages": 24,
468
+ "shards": 1
469
+ },
470
+ {
471
+ "seconds": 1.4440002779992938,
472
+ "bytes": 13477323,
473
+ "pages": 45,
474
+ "shards": 4
475
+ },
476
+ {
477
+ "seconds": 1.0930595740010176,
478
+ "bytes": 6005049,
479
+ "pages": 30,
480
+ "shards": 2
481
+ },
482
+ {
483
+ "seconds": 1.1409170160004578,
484
+ "bytes": 7751245,
485
+ "pages": 38,
486
+ "shards": 3
487
+ },
488
+ {
489
+ "seconds": 1.385997141000189,
490
+ "bytes": 5854774,
491
+ "pages": 28,
492
+ "shards": 2
493
+ },
494
+ {
495
+ "seconds": 0.8962630369987892,
496
+ "bytes": 1124581,
497
+ "pages": 35,
498
+ "shards": 1
499
+ },
500
+ {
501
+ "seconds": 1.1323460120001982,
502
+ "bytes": 7094094,
503
+ "pages": 25,
504
+ "shards": 3
505
+ },
506
+ {
507
+ "seconds": 1.3368760009998368,
508
+ "bytes": 10726853,
509
+ "pages": 39,
510
+ "shards": 3
511
+ },
512
+ {
513
+ "seconds": 0.9546346269999049,
514
+ "bytes": 5999756,
515
+ "pages": 29,
516
+ "shards": 2
517
+ },
518
+ {
519
+ "seconds": 1.1835868019988993,
520
+ "bytes": 7840439,
521
+ "pages": 38,
522
+ "shards": 3
523
+ },
524
+ {
525
+ "seconds": 1.00542208799925,
526
+ "bytes": 5360697,
527
+ "pages": 33,
528
+ "shards": 2
529
+ },
530
+ {
531
+ "seconds": 1.2967056479992607,
532
+ "bytes": 7612762,
533
+ "pages": 38,
534
+ "shards": 3
535
+ },
536
+ {
537
+ "seconds": 0.9550784620005288,
538
+ "bytes": 883731,
539
+ "pages": 26,
540
+ "shards": 1
541
+ },
542
+ {
543
+ "seconds": 1.1562814480002999,
544
+ "bytes": 11922123,
545
+ "pages": 40,
546
+ "shards": 3
547
+ },
548
+ {
549
+ "seconds": 1.2267546230013977,
550
+ "bytes": 11778233,
551
+ "pages": 33,
552
+ "shards": 4
553
+ },
554
+ {
555
+ "seconds": 0.9305929850015673,
556
+ "bytes": 1085853,
557
+ "pages": 35,
558
+ "shards": 2
559
+ },
560
+ {
561
+ "seconds": 1.4772485220000817,
562
+ "bytes": 7565247,
563
+ "pages": 36,
564
+ "shards": 3
565
  }
566
  ],
567
  "cache_key": {
trainer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4273939d74c5226bc57df9a209306193dff7da001a42417dfdf439575063da35
3
- size 721771007
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b45969c25feb44bef2bbc28e1a234c7ba36a717f6375ea0dba3053855528f94
3
+ size 721759935