{
  "data": "fineweb_edu_200M_v1024.uint16.bin",
  "base": "LowOnMind-300k",
  "derived_from": "DedeProGames/DynamicMind-Mini",
  "dataset": "HuggingFaceFW/fineweb-edu:sample-10BT",
  "tokenizer": "byte-level BPE 1024",
  "params": 296960,
  "seq_len": 512,
  "batch_size": 64,
  "grad_accum": 1,
  "max_steps": 6103,
  "total_tokens": 199983104,
  "lr": 0.002,
  "min_lr": 0.0002,
  "warmup_steps": 250,
  "weight_decay": 0.1,
  "grad_clip": 1.0,
  "val_tokens": 2000000,
  "eval_every": 500,
  "eval_batches": 40,
  "device": "cuda",
  "dtype": "bfloat16",
  "compile": true,
  "seed": 1337,
  "train_minutes": 42.6,
  "final_val_loss": 3.2982,
  "final_val_ppl": 27.063,
  "history": [
    {
      "step": 500,
      "val_loss": 3.8883,
      "val_ppl": 48.827
    },
    {
      "step": 1000,
      "val_loss": 3.621,
      "val_ppl": 37.375
    },
    {
      "step": 1500,
      "val_loss": 3.5287,
      "val_ppl": 34.079
    },
    {
      "step": 2000,
      "val_loss": 3.4824,
      "val_ppl": 32.537
    },
    {
      "step": 2500,
      "val_loss": 3.4508,
      "val_ppl": 31.524
    },
    {
      "step": 3000,
      "val_loss": 3.4226,
      "val_ppl": 30.65
    },
    {
      "step": 3500,
      "val_loss": 3.3997,
      "val_ppl": 29.955
    },
    {
      "step": 4000,
      "val_loss": 3.3725,
      "val_ppl": 29.151
    },
    {
      "step": 4500,
      "val_loss": 3.3489,
      "val_ppl": 28.471
    },
    {
      "step": 5000,
      "val_loss": 3.3408,
      "val_ppl": 28.241
    },
    {
      "step": 5500,
      "val_loss": 3.3165,
      "val_ppl": 27.565
    },
    {
      "step": 6000,
      "val_loss": 3.3251,
      "val_ppl": 27.801
    },
    {
      "step": 6103,
      "val_loss": 3.3125,
      "val_ppl": 27.454
    }
  ]
}