{
  "best_metric": 6.818531036376953,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.17644464049404499,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035288928098809,
      "grad_norm": 2.5939738750457764,
      "learning_rate": 5e-05,
      "loss": 7.8965,
      "step": 1
    },
    {
      "epoch": 0.0035288928098809,
      "eval_loss": 7.643599987030029,
      "eval_runtime": 8.8561,
      "eval_samples_per_second": 215.558,
      "eval_steps_per_second": 26.987,
      "step": 1
    },
    {
      "epoch": 0.0070577856197618,
      "grad_norm": 2.4565248489379883,
      "learning_rate": 0.0001,
      "loss": 7.5246,
      "step": 2
    },
    {
      "epoch": 0.0105866784296427,
      "grad_norm": 2.5931267738342285,
      "learning_rate": 9.989294616193017e-05,
      "loss": 7.3228,
      "step": 3
    },
    {
      "epoch": 0.0141155712395236,
      "grad_norm": 2.5270028114318848,
      "learning_rate": 9.957224306869053e-05,
      "loss": 7.2838,
      "step": 4
    },
    {
      "epoch": 0.0176444640494045,
      "grad_norm": 2.776662826538086,
      "learning_rate": 9.903926402016153e-05,
      "loss": 7.3703,
      "step": 5
    },
    {
      "epoch": 0.0211733568592854,
      "grad_norm": 2.653928756713867,
      "learning_rate": 9.829629131445342e-05,
      "loss": 7.4135,
      "step": 6
    },
    {
      "epoch": 0.024702249669166298,
      "grad_norm": 2.8368570804595947,
      "learning_rate": 9.73465064747553e-05,
      "loss": 7.3779,
      "step": 7
    },
    {
      "epoch": 0.0282311424790472,
      "grad_norm": 3.0451459884643555,
      "learning_rate": 9.619397662556435e-05,
      "loss": 7.4949,
      "step": 8
    },
    {
      "epoch": 0.031760035288928096,
      "grad_norm": 2.848522901535034,
      "learning_rate": 9.484363707663442e-05,
      "loss": 7.3464,
      "step": 9
    },
    {
      "epoch": 0.035288928098809,
      "grad_norm": 3.732426404953003,
      "learning_rate": 9.330127018922194e-05,
      "loss": 7.2259,
      "step": 10
    },
    {
      "epoch": 0.0388178209086899,
      "grad_norm": 4.219879627227783,
      "learning_rate": 9.157348061512727e-05,
      "loss": 7.356,
      "step": 11
    },
    {
      "epoch": 0.0423467137185708,
      "grad_norm": 4.865793704986572,
      "learning_rate": 8.966766701456177e-05,
      "loss": 7.5016,
      "step": 12
    },
    {
      "epoch": 0.0458756065284517,
      "grad_norm": 1.8405283689498901,
      "learning_rate": 8.759199037394887e-05,
      "loss": 7.6854,
      "step": 13
    },
    {
      "epoch": 0.049404499338332596,
      "grad_norm": 1.2869133949279785,
      "learning_rate": 8.535533905932738e-05,
      "loss": 7.2134,
      "step": 14
    },
    {
      "epoch": 0.0529333921482135,
      "grad_norm": 1.372349739074707,
      "learning_rate": 8.296729075500344e-05,
      "loss": 7.1587,
      "step": 15
    },
    {
      "epoch": 0.0564622849580944,
      "grad_norm": 1.242587924003601,
      "learning_rate": 8.043807145043604e-05,
      "loss": 7.0516,
      "step": 16
    },
    {
      "epoch": 0.0599911777679753,
      "grad_norm": 1.3213739395141602,
      "learning_rate": 7.777851165098012e-05,
      "loss": 6.9568,
      "step": 17
    },
    {
      "epoch": 0.06352007057785619,
      "grad_norm": 1.4065548181533813,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.0263,
      "step": 18
    },
    {
      "epoch": 0.0670489633877371,
      "grad_norm": 1.4442555904388428,
      "learning_rate": 7.211443451095007e-05,
      "loss": 6.9204,
      "step": 19
    },
    {
      "epoch": 0.070577856197618,
      "grad_norm": 1.6347490549087524,
      "learning_rate": 6.91341716182545e-05,
      "loss": 6.8876,
      "step": 20
    },
    {
      "epoch": 0.0741067490074989,
      "grad_norm": 1.862315058708191,
      "learning_rate": 6.607197326515808e-05,
      "loss": 6.982,
      "step": 21
    },
    {
      "epoch": 0.0776356418173798,
      "grad_norm": 2.168375253677368,
      "learning_rate": 6.294095225512603e-05,
      "loss": 6.7858,
      "step": 22
    },
    {
      "epoch": 0.0811645346272607,
      "grad_norm": 2.661607265472412,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 6.827,
      "step": 23
    },
    {
      "epoch": 0.0846934274371416,
      "grad_norm": 3.688765525817871,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 6.8662,
      "step": 24
    },
    {
      "epoch": 0.08822232024702249,
      "grad_norm": 5.431340217590332,
      "learning_rate": 5.327015646150716e-05,
      "loss": 7.1321,
      "step": 25
    },
    {
      "epoch": 0.08822232024702249,
      "eval_loss": 6.946163177490234,
      "eval_runtime": 8.8186,
      "eval_samples_per_second": 216.475,
      "eval_steps_per_second": 27.102,
      "step": 25
    },
    {
      "epoch": 0.0917512130569034,
      "grad_norm": 1.1054739952087402,
      "learning_rate": 5e-05,
      "loss": 7.2183,
      "step": 26
    },
    {
      "epoch": 0.0952801058667843,
      "grad_norm": 0.9908803105354309,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 6.958,
      "step": 27
    },
    {
      "epoch": 0.09880899867666519,
      "grad_norm": 1.0078890323638916,
      "learning_rate": 4.347369038899744e-05,
      "loss": 7.0784,
      "step": 28
    },
    {
      "epoch": 0.1023378914865461,
      "grad_norm": 1.0495905876159668,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 6.9738,
      "step": 29
    },
    {
      "epoch": 0.105866784296427,
      "grad_norm": 1.1118749380111694,
      "learning_rate": 3.705904774487396e-05,
      "loss": 6.8487,
      "step": 30
    },
    {
      "epoch": 0.10939567710630789,
      "grad_norm": 1.258945345878601,
      "learning_rate": 3.392802673484193e-05,
      "loss": 6.8057,
      "step": 31
    },
    {
      "epoch": 0.1129245699161888,
      "grad_norm": 1.2230989933013916,
      "learning_rate": 3.086582838174551e-05,
      "loss": 6.9796,
      "step": 32
    },
    {
      "epoch": 0.1164534627260697,
      "grad_norm": 1.4328244924545288,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 6.7772,
      "step": 33
    },
    {
      "epoch": 0.1199823555359506,
      "grad_norm": 1.7075251340866089,
      "learning_rate": 2.500000000000001e-05,
      "loss": 6.9079,
      "step": 34
    },
    {
      "epoch": 0.12351124834583149,
      "grad_norm": 2.2108325958251953,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 6.6871,
      "step": 35
    },
    {
      "epoch": 0.12704014115571238,
      "grad_norm": 2.8738584518432617,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 6.7338,
      "step": 36
    },
    {
      "epoch": 0.1305690339655933,
      "grad_norm": 4.4806036949157715,
      "learning_rate": 1.703270924499656e-05,
      "loss": 6.7032,
      "step": 37
    },
    {
      "epoch": 0.1340979267754742,
      "grad_norm": 1.2014843225479126,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 7.2215,
      "step": 38
    },
    {
      "epoch": 0.13762681958535508,
      "grad_norm": 0.9526251554489136,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 7.0711,
      "step": 39
    },
    {
      "epoch": 0.141155712395236,
      "grad_norm": 0.9825794696807861,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 7.0598,
      "step": 40
    },
    {
      "epoch": 0.1446846052051169,
      "grad_norm": 0.9970250129699707,
      "learning_rate": 8.426519384872733e-06,
      "loss": 6.7972,
      "step": 41
    },
    {
      "epoch": 0.1482134980149978,
      "grad_norm": 1.0425372123718262,
      "learning_rate": 6.698729810778065e-06,
      "loss": 6.8431,
      "step": 42
    },
    {
      "epoch": 0.1517423908248787,
      "grad_norm": 1.1232349872589111,
      "learning_rate": 5.156362923365588e-06,
      "loss": 6.8156,
      "step": 43
    },
    {
      "epoch": 0.1552712836347596,
      "grad_norm": 1.303544282913208,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 6.6732,
      "step": 44
    },
    {
      "epoch": 0.1588001764446405,
      "grad_norm": 1.401859998703003,
      "learning_rate": 2.653493525244721e-06,
      "loss": 6.696,
      "step": 45
    },
    {
      "epoch": 0.1623290692545214,
      "grad_norm": 1.6703929901123047,
      "learning_rate": 1.70370868554659e-06,
      "loss": 6.8849,
      "step": 46
    },
    {
      "epoch": 0.1658579620644023,
      "grad_norm": 1.9721368551254272,
      "learning_rate": 9.607359798384785e-07,
      "loss": 6.7516,
      "step": 47
    },
    {
      "epoch": 0.1693868548742832,
      "grad_norm": 2.599738359451294,
      "learning_rate": 4.277569313094809e-07,
      "loss": 6.8387,
      "step": 48
    },
    {
      "epoch": 0.1729157476841641,
      "grad_norm": 3.7143712043762207,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 6.7818,
      "step": 49
    },
    {
      "epoch": 0.17644464049404499,
      "grad_norm": 5.192096710205078,
      "learning_rate": 0.0,
      "loss": 6.617,
      "step": 50
    },
    {
      "epoch": 0.17644464049404499,
      "eval_loss": 6.818531036376953,
      "eval_runtime": 8.8921,
      "eval_samples_per_second": 214.685,
      "eval_steps_per_second": 26.878,
      "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": 232013797785600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}