Updated model: 531 splits, 18.96 epochs, min_loss: 1.0162, min_ppl: 2.7628

Updated model: 524 splits, 18.71 epochs, min_loss: 1.0162, min_ppl: 2.7628

Updated model: 514 splits, 18.36 epochs, min_loss: 1.0164, min_ppl: 2.7632

Updated model: 498 splits, 17.79 epochs, min_loss: 1.0166, min_ppl: 2.7639

Updated model: 486 splits, 17.36 epochs, min_loss: 1.0174, min_ppl: 2.7661

Updated model: 477 splits, 17.04 epochs, min_loss: 1.0176, min_ppl: 2.7666

Updated model: 472 splits, 16.86 epochs, min_loss: 1.0176, min_ppl: 2.7666

Updated model: 461 splits, 16.46 epochs, min_loss: 1.0178, min_ppl: 2.7671

Updated model: 453 splits, 16.18 epochs, min_loss: 1.018, min_ppl: 2.7676

Updated model: 434 splits, 15.50 epochs, min_loss: 1.0184, min_ppl: 2.7689

More iterations

Few more iterations

Slight update

More heat

Decreasing the heat a bit

And another one

And another one

switching to hf hub

Another try

initial commit