{
  "best_metric": 0.4445563852787018,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.704225352112676,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014084507042253521,
      "grad_norm": 8.346992492675781,
      "learning_rate": 5e-05,
      "loss": 12.2278,
      "step": 1
    },
    {
      "epoch": 0.014084507042253521,
      "eval_loss": 12.823960304260254,
      "eval_runtime": 13.7247,
      "eval_samples_per_second": 34.901,
      "eval_steps_per_second": 4.372,
      "step": 1
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 7.425861835479736,
      "learning_rate": 0.0001,
      "loss": 12.5554,
      "step": 2
    },
    {
      "epoch": 0.04225352112676056,
      "grad_norm": 8.908767700195312,
      "learning_rate": 9.989294616193017e-05,
      "loss": 12.1012,
      "step": 3
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 9.821554183959961,
      "learning_rate": 9.957224306869053e-05,
      "loss": 9.9978,
      "step": 4
    },
    {
      "epoch": 0.07042253521126761,
      "grad_norm": 10.156991004943848,
      "learning_rate": 9.903926402016153e-05,
      "loss": 8.096,
      "step": 5
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": 11.742984771728516,
      "learning_rate": 9.829629131445342e-05,
      "loss": 5.9819,
      "step": 6
    },
    {
      "epoch": 0.09859154929577464,
      "grad_norm": 8.830410957336426,
      "learning_rate": 9.73465064747553e-05,
      "loss": 4.2089,
      "step": 7
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 6.485323905944824,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.917,
      "step": 8
    },
    {
      "epoch": 0.1267605633802817,
      "grad_norm": 4.894802093505859,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.8889,
      "step": 9
    },
    {
      "epoch": 0.14084507042253522,
      "grad_norm": 4.750296592712402,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.4169,
      "step": 10
    },
    {
      "epoch": 0.15492957746478872,
      "grad_norm": 3.1973183155059814,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.0946,
      "step": 11
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 3.7573916912078857,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.0624,
      "step": 12
    },
    {
      "epoch": 0.18309859154929578,
      "grad_norm": 3.756410598754883,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.1211,
      "step": 13
    },
    {
      "epoch": 0.19718309859154928,
      "grad_norm": 7.301768779754639,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3218,
      "step": 14
    },
    {
      "epoch": 0.2112676056338028,
      "grad_norm": 4.617189407348633,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.9584,
      "step": 15
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 2.561586618423462,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.7993,
      "step": 16
    },
    {
      "epoch": 0.23943661971830985,
      "grad_norm": 1.7330591678619385,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.6989,
      "step": 17
    },
    {
      "epoch": 0.2535211267605634,
      "grad_norm": 1.1385722160339355,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5038,
      "step": 18
    },
    {
      "epoch": 0.2676056338028169,
      "grad_norm": 1.4021364450454712,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.6352,
      "step": 19
    },
    {
      "epoch": 0.28169014084507044,
      "grad_norm": 2.5990591049194336,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6112,
      "step": 20
    },
    {
      "epoch": 0.29577464788732394,
      "grad_norm": 1.0867429971694946,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.5304,
      "step": 21
    },
    {
      "epoch": 0.30985915492957744,
      "grad_norm": 1.5365735292434692,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.4338,
      "step": 22
    },
    {
      "epoch": 0.323943661971831,
      "grad_norm": 1.2048392295837402,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.4413,
      "step": 23
    },
    {
      "epoch": 0.3380281690140845,
      "grad_norm": 0.9102128148078918,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.353,
      "step": 24
    },
    {
      "epoch": 0.352112676056338,
      "grad_norm": 3.2107045650482178,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.3934,
      "step": 25
    },
    {
      "epoch": 0.352112676056338,
      "eval_loss": 0.5817620158195496,
      "eval_runtime": 13.7196,
      "eval_samples_per_second": 34.914,
      "eval_steps_per_second": 4.373,
      "step": 25
    },
    {
      "epoch": 0.36619718309859156,
      "grad_norm": 4.094692230224609,
      "learning_rate": 5e-05,
      "loss": 0.6193,
      "step": 26
    },
    {
      "epoch": 0.38028169014084506,
      "grad_norm": 4.389765739440918,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.8496,
      "step": 27
    },
    {
      "epoch": 0.39436619718309857,
      "grad_norm": 2.016075849533081,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.5172,
      "step": 28
    },
    {
      "epoch": 0.4084507042253521,
      "grad_norm": 2.776219129562378,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.6007,
      "step": 29
    },
    {
      "epoch": 0.4225352112676056,
      "grad_norm": 3.784762144088745,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.6056,
      "step": 30
    },
    {
      "epoch": 0.43661971830985913,
      "grad_norm": 2.235111713409424,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.522,
      "step": 31
    },
    {
      "epoch": 0.4507042253521127,
      "grad_norm": 2.2327880859375,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.5399,
      "step": 32
    },
    {
      "epoch": 0.4647887323943662,
      "grad_norm": 1.8651642799377441,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.5044,
      "step": 33
    },
    {
      "epoch": 0.4788732394366197,
      "grad_norm": 1.4466888904571533,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4427,
      "step": 34
    },
    {
      "epoch": 0.49295774647887325,
      "grad_norm": 0.9235767722129822,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.4311,
      "step": 35
    },
    {
      "epoch": 0.5070422535211268,
      "grad_norm": 0.9404734373092651,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.4195,
      "step": 36
    },
    {
      "epoch": 0.5211267605633803,
      "grad_norm": 0.7384967803955078,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.3606,
      "step": 37
    },
    {
      "epoch": 0.5352112676056338,
      "grad_norm": 1.4923155307769775,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.4469,
      "step": 38
    },
    {
      "epoch": 0.5492957746478874,
      "grad_norm": 1.5055233240127563,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.5305,
      "step": 39
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 0.910371720790863,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.4825,
      "step": 40
    },
    {
      "epoch": 0.5774647887323944,
      "grad_norm": 0.8596780896186829,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.4913,
      "step": 41
    },
    {
      "epoch": 0.5915492957746479,
      "grad_norm": 0.8048612475395203,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.4879,
      "step": 42
    },
    {
      "epoch": 0.6056338028169014,
      "grad_norm": 1.1381443738937378,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.4462,
      "step": 43
    },
    {
      "epoch": 0.6197183098591549,
      "grad_norm": 1.394750952720642,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.4769,
      "step": 44
    },
    {
      "epoch": 0.6338028169014085,
      "grad_norm": 1.6007133722305298,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.429,
      "step": 45
    },
    {
      "epoch": 0.647887323943662,
      "grad_norm": 0.9529777765274048,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.436,
      "step": 46
    },
    {
      "epoch": 0.6619718309859155,
      "grad_norm": 0.441651850938797,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.3942,
      "step": 47
    },
    {
      "epoch": 0.676056338028169,
      "grad_norm": 0.7304509878158569,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.3827,
      "step": 48
    },
    {
      "epoch": 0.6901408450704225,
      "grad_norm": 1.3514213562011719,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.3667,
      "step": 49
    },
    {
      "epoch": 0.704225352112676,
      "grad_norm": 2.4070658683776855,
      "learning_rate": 0.0,
      "loss": 0.3122,
      "step": 50
    },
    {
      "epoch": 0.704225352112676,
      "eval_loss": 0.4445563852787018,
      "eval_runtime": 13.7477,
      "eval_samples_per_second": 34.842,
      "eval_steps_per_second": 4.364,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.308600064850002e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}