{ "definition": "bits/byte = sum of NLL over text tokens / ln 2 / UTF-8 bytes; non-overlapping 1024-token windows; EOS targets excluded", "trainer_sha256": "0223c0830ed4ae323f6424038a2de7bfb6b425653f3591dd55844f95706f5d17", "tokenizer_sha256": "77eeebed509827f18b859ff159f29b2405d24d5b84381d6226f22e4fb6ca98d7", "sets": { "W": { "sha256": "234e7ec21bf2236bc74425591531f2c4772f8c49ff853d57f6fa16f33ee90ac7", "docs": 463, "text_bytes": 1430217, "tokens_text": 351268 }, "val": { "sha256": "748d13898e736666d96f1c9307222c52414a9b66b06bf212e7a07e765babc668", "docs": 2723, "text_bytes": 7232820, "tokens_text": 1748065 } }, "device": "cpu", "ckpts": [ { "step": 10000, "ckpt_sha256": "13a9130e6ac322c3a342c6bbcdf0838bdaa82e7e6962c0b4ab4ee1bdb677d2c8", "W": 1.246255139078163, "val": 1.2008817462071877 }, { "step": 20000, "ckpt_sha256": "78d637de184f406d22621b4512fc79da9d2b47f9ba532525aba44199505bdd5f", "W": 1.189575099180923, "val": 1.152323463429622 }, { "step": 30000, "ckpt_sha256": "2ec241ef98aaf7d54a15398bbb3d64dd2f0d3d6e0d562cd5e2aa4b7f7a468ac3", "W": 1.163382329460513, "val": 1.1278191393784163 }, { "step": 40000, "ckpt_sha256": "0bf61a0a7595c56f22af420dcd7a956a087c49100be258660fbc5ab109934b1b", "W": 1.1434992106638442, "val": 1.1109230609739182 }, { "step": 50000, "ckpt_sha256": "2c8189ed98f6bd27064205725ac1430c815cb4a718c764a57178632ff676b590", "W": 1.1290988704930747, "val": 1.096905167732812 }, { "step": 60000, "ckpt_sha256": "a24e66893894405f763a83ea28eee3432e8ccb6911f15e59715119ae1705089f", "W": 1.1144814554280478, "val": 1.0850306176283422 }, { "step": 70000, "ckpt_sha256": "2cedd2505161e340b2ef8ad79199d431ae54aec6cecac6d131f7d76dddfcea34", "W": 1.1024713768041312, "val": 1.0752361156563053 }, { "step": 80000, "ckpt_sha256": "f074891643fe2efa2bcf2e8545cd6ade5e024baf29fe47f161fcc43ac092c76c", "W": 1.0943567744308031, "val": 1.0677255240917687 }, { "step": 90000, "ckpt_sha256": "16f2089bd49d108383660a206a93551edacaa69ebe76686b65b2e32f9df5104a", "W": 1.0892155925274738, "val": 1.0633125873779654 }, { "step": 95000, "ckpt_sha256": "538505bc15e4332231b3e2958b02b7567348b3d43b8974e57f48526266879ab9", "W": 1.0882527260062658, "val": 1.062229520611975 } ] }