{
  "best_metric": 0.8269708752632141,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0023223409196470044,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.644681839294008e-05,
      "grad_norm": 3.092576503753662,
      "learning_rate": 1.018e-05,
      "loss": 0.997,
      "step": 1
    },
    {
      "epoch": 4.644681839294008e-05,
      "eval_loss": 1.5409296751022339,
      "eval_runtime": 162.8209,
      "eval_samples_per_second": 55.681,
      "eval_steps_per_second": 13.923,
      "step": 1
    },
    {
      "epoch": 9.289363678588016e-05,
      "grad_norm": 21.47955322265625,
      "learning_rate": 2.036e-05,
      "loss": 1.9273,
      "step": 2
    },
    {
      "epoch": 0.00013934045517882026,
      "grad_norm": 9.852048873901367,
      "learning_rate": 3.0539999999999996e-05,
      "loss": 1.6379,
      "step": 3
    },
    {
      "epoch": 0.00018578727357176033,
      "grad_norm": 17.509506225585938,
      "learning_rate": 4.072e-05,
      "loss": 1.4906,
      "step": 4
    },
    {
      "epoch": 0.00023223409196470042,
      "grad_norm": 14.546015739440918,
      "learning_rate": 5.09e-05,
      "loss": 1.4437,
      "step": 5
    },
    {
      "epoch": 0.0002786809103576405,
      "grad_norm": 5.5904154777526855,
      "learning_rate": 6.107999999999999e-05,
      "loss": 1.6272,
      "step": 6
    },
    {
      "epoch": 0.0003251277287505806,
      "grad_norm": 4.112157821655273,
      "learning_rate": 7.125999999999999e-05,
      "loss": 1.4437,
      "step": 7
    },
    {
      "epoch": 0.00037157454714352065,
      "grad_norm": 4.384551048278809,
      "learning_rate": 8.144e-05,
      "loss": 1.3646,
      "step": 8
    },
    {
      "epoch": 0.0004180213655364608,
      "grad_norm": 8.227641105651855,
      "learning_rate": 9.162e-05,
      "loss": 1.1622,
      "step": 9
    },
    {
      "epoch": 0.00046446818392940084,
      "grad_norm": 5.1519856452941895,
      "learning_rate": 0.0001018,
      "loss": 1.4487,
      "step": 10
    },
    {
      "epoch": 0.0005109150023223409,
      "grad_norm": 9.391843795776367,
      "learning_rate": 0.00010126421052631578,
      "loss": 1.2691,
      "step": 11
    },
    {
      "epoch": 0.000557361820715281,
      "grad_norm": 5.215498924255371,
      "learning_rate": 0.00010072842105263156,
      "loss": 0.9428,
      "step": 12
    },
    {
      "epoch": 0.000603808639108221,
      "grad_norm": 2.952871084213257,
      "learning_rate": 0.00010019263157894736,
      "loss": 1.0689,
      "step": 13
    },
    {
      "epoch": 0.0006502554575011612,
      "grad_norm": 2.8391802310943604,
      "learning_rate": 9.965684210526316e-05,
      "loss": 0.9291,
      "step": 14
    },
    {
      "epoch": 0.0006967022758941013,
      "grad_norm": 2.461745023727417,
      "learning_rate": 9.912105263157895e-05,
      "loss": 0.8318,
      "step": 15
    },
    {
      "epoch": 0.0007431490942870413,
      "grad_norm": 2.3736178874969482,
      "learning_rate": 9.858526315789473e-05,
      "loss": 0.5747,
      "step": 16
    },
    {
      "epoch": 0.0007895959126799814,
      "grad_norm": 3.788600444793701,
      "learning_rate": 9.804947368421052e-05,
      "loss": 0.9676,
      "step": 17
    },
    {
      "epoch": 0.0008360427310729215,
      "grad_norm": 3.9328246116638184,
      "learning_rate": 9.75136842105263e-05,
      "loss": 1.0193,
      "step": 18
    },
    {
      "epoch": 0.0008824895494658616,
      "grad_norm": 2.693528652191162,
      "learning_rate": 9.69778947368421e-05,
      "loss": 0.7466,
      "step": 19
    },
    {
      "epoch": 0.0009289363678588017,
      "grad_norm": 3.4937636852264404,
      "learning_rate": 9.644210526315789e-05,
      "loss": 0.8632,
      "step": 20
    },
    {
      "epoch": 0.0009753831862517418,
      "grad_norm": 2.1122593879699707,
      "learning_rate": 9.590631578947369e-05,
      "loss": 0.7247,
      "step": 21
    },
    {
      "epoch": 0.0010218300046446818,
      "grad_norm": 3.186523675918579,
      "learning_rate": 9.537052631578947e-05,
      "loss": 0.6886,
      "step": 22
    },
    {
      "epoch": 0.001068276823037622,
      "grad_norm": 2.758934497833252,
      "learning_rate": 9.483473684210526e-05,
      "loss": 0.6994,
      "step": 23
    },
    {
      "epoch": 0.001114723641430562,
      "grad_norm": 2.430767774581909,
      "learning_rate": 9.429894736842104e-05,
      "loss": 0.6421,
      "step": 24
    },
    {
      "epoch": 0.0011611704598235022,
      "grad_norm": 3.4728782176971436,
      "learning_rate": 9.376315789473684e-05,
      "loss": 0.8879,
      "step": 25
    },
    {
      "epoch": 0.001207617278216442,
      "grad_norm": 3.511162519454956,
      "learning_rate": 9.322736842105262e-05,
      "loss": 0.9696,
      "step": 26
    },
    {
      "epoch": 0.0012540640966093822,
      "grad_norm": 3.0230774879455566,
      "learning_rate": 9.269157894736842e-05,
      "loss": 0.9589,
      "step": 27
    },
    {
      "epoch": 0.0013005109150023223,
      "grad_norm": 2.1474082469940186,
      "learning_rate": 9.215578947368421e-05,
      "loss": 0.7707,
      "step": 28
    },
    {
      "epoch": 0.0013469577333952625,
      "grad_norm": 2.3117761611938477,
      "learning_rate": 9.162e-05,
      "loss": 0.7724,
      "step": 29
    },
    {
      "epoch": 0.0013934045517882026,
      "grad_norm": 1.9512385129928589,
      "learning_rate": 9.108421052631578e-05,
      "loss": 0.603,
      "step": 30
    },
    {
      "epoch": 0.0014398513701811425,
      "grad_norm": 6.22908878326416,
      "learning_rate": 9.054842105263158e-05,
      "loss": 1.0569,
      "step": 31
    },
    {
      "epoch": 0.0014862981885740826,
      "grad_norm": 2.2944276332855225,
      "learning_rate": 9.001263157894736e-05,
      "loss": 0.6613,
      "step": 32
    },
    {
      "epoch": 0.0015327450069670227,
      "grad_norm": 2.312437057495117,
      "learning_rate": 8.947684210526315e-05,
      "loss": 0.8758,
      "step": 33
    },
    {
      "epoch": 0.0015791918253599629,
      "grad_norm": 2.5488150119781494,
      "learning_rate": 8.894105263157895e-05,
      "loss": 0.635,
      "step": 34
    },
    {
      "epoch": 0.001625638643752903,
      "grad_norm": 3.658079147338867,
      "learning_rate": 8.840526315789473e-05,
      "loss": 1.0831,
      "step": 35
    },
    {
      "epoch": 0.001672085462145843,
      "grad_norm": 2.474161386489868,
      "learning_rate": 8.786947368421052e-05,
      "loss": 0.7918,
      "step": 36
    },
    {
      "epoch": 0.001718532280538783,
      "grad_norm": 2.5074217319488525,
      "learning_rate": 8.733368421052632e-05,
      "loss": 0.8514,
      "step": 37
    },
    {
      "epoch": 0.0017649790989317231,
      "grad_norm": 2.0377755165100098,
      "learning_rate": 8.67978947368421e-05,
      "loss": 0.6768,
      "step": 38
    },
    {
      "epoch": 0.0018114259173246632,
      "grad_norm": 2.2819857597351074,
      "learning_rate": 8.626210526315789e-05,
      "loss": 0.6528,
      "step": 39
    },
    {
      "epoch": 0.0018578727357176034,
      "grad_norm": 2.3973352909088135,
      "learning_rate": 8.572631578947367e-05,
      "loss": 0.8542,
      "step": 40
    },
    {
      "epoch": 0.0019043195541105435,
      "grad_norm": 2.628427267074585,
      "learning_rate": 8.519052631578947e-05,
      "loss": 0.8507,
      "step": 41
    },
    {
      "epoch": 0.0019507663725034836,
      "grad_norm": 3.116105556488037,
      "learning_rate": 8.465473684210527e-05,
      "loss": 0.9283,
      "step": 42
    },
    {
      "epoch": 0.0019972131908964235,
      "grad_norm": 3.5683062076568604,
      "learning_rate": 8.411894736842105e-05,
      "loss": 1.1937,
      "step": 43
    },
    {
      "epoch": 0.0020436600092893636,
      "grad_norm": 2.569610118865967,
      "learning_rate": 8.358315789473684e-05,
      "loss": 0.9237,
      "step": 44
    },
    {
      "epoch": 0.0020901068276823038,
      "grad_norm": 3.7425827980041504,
      "learning_rate": 8.304736842105262e-05,
      "loss": 1.3234,
      "step": 45
    },
    {
      "epoch": 0.002136553646075244,
      "grad_norm": 3.7030258178710938,
      "learning_rate": 8.251157894736841e-05,
      "loss": 0.7639,
      "step": 46
    },
    {
      "epoch": 0.002183000464468184,
      "grad_norm": 3.188816785812378,
      "learning_rate": 8.197578947368421e-05,
      "loss": 1.1931,
      "step": 47
    },
    {
      "epoch": 0.002229447282861124,
      "grad_norm": 5.445688724517822,
      "learning_rate": 8.144e-05,
      "loss": 0.8938,
      "step": 48
    },
    {
      "epoch": 0.0022758941012540643,
      "grad_norm": 2.3576200008392334,
      "learning_rate": 8.090421052631579e-05,
      "loss": 0.836,
      "step": 49
    },
    {
      "epoch": 0.0023223409196470044,
      "grad_norm": 22.260164260864258,
      "learning_rate": 8.036842105263158e-05,
      "loss": 1.0266,
      "step": 50
    },
    {
      "epoch": 0.0023223409196470044,
      "eval_loss": 0.8269708752632141,
      "eval_runtime": 162.7994,
      "eval_samples_per_second": 55.688,
      "eval_steps_per_second": 13.925,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3119728734240768.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}