{
  "best_metric": 3.255030632019043,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.2158894645941278,
  "eval_steps": 50,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008635578583765112,
      "eval_loss": 4.057919025421143,
      "eval_runtime": 6.7758,
      "eval_samples_per_second": 72.021,
      "eval_steps_per_second": 18.005,
      "step": 1
    },
    {
      "epoch": 0.008635578583765112,
      "grad_norm": 121.86174774169922,
      "learning_rate": 4.2800000000000004e-05,
      "loss": 7.3375,
      "step": 10
    },
    {
      "epoch": 0.017271157167530225,
      "grad_norm": 90.00106811523438,
      "learning_rate": 8.560000000000001e-05,
      "loss": 7.448,
      "step": 20
    },
    {
      "epoch": 0.025906735751295335,
      "grad_norm": 152.43508911132812,
      "learning_rate": 0.0001284,
      "loss": 7.1224,
      "step": 30
    },
    {
      "epoch": 0.03454231433506045,
      "grad_norm": 144.12196350097656,
      "learning_rate": 0.00017120000000000001,
      "loss": 6.7462,
      "step": 40
    },
    {
      "epoch": 0.04317789291882556,
      "grad_norm": 197.8842315673828,
      "learning_rate": 0.000214,
      "loss": 6.8277,
      "step": 50
    },
    {
      "epoch": 0.04317789291882556,
      "eval_loss": 3.404750108718872,
      "eval_runtime": 6.6326,
      "eval_samples_per_second": 73.576,
      "eval_steps_per_second": 18.394,
      "step": 50
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 76.07807922363281,
      "learning_rate": 0.00021373935337780118,
      "loss": 6.7798,
      "step": 60
    },
    {
      "epoch": 0.06044905008635579,
      "grad_norm": 108.3371810913086,
      "learning_rate": 0.00021295868335534802,
      "loss": 6.6601,
      "step": 70
    },
    {
      "epoch": 0.0690846286701209,
      "grad_norm": 270.08953857421875,
      "learning_rate": 0.0002116617932785172,
      "loss": 7.2544,
      "step": 80
    },
    {
      "epoch": 0.07772020725388601,
      "grad_norm": 76.67597961425781,
      "learning_rate": 0.00020985500146540012,
      "loss": 6.7622,
      "step": 90
    },
    {
      "epoch": 0.08635578583765112,
      "grad_norm": 66.3217544555664,
      "learning_rate": 0.0002075471104240922,
      "loss": 6.6867,
      "step": 100
    },
    {
      "epoch": 0.08635578583765112,
      "eval_loss": 3.255030632019043,
      "eval_runtime": 6.6535,
      "eval_samples_per_second": 73.345,
      "eval_steps_per_second": 18.336,
      "step": 100
    },
    {
      "epoch": 0.09499136442141623,
      "grad_norm": 70.40594482421875,
      "learning_rate": 0.00020474936396775828,
      "loss": 6.848,
      "step": 110
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 75.81895446777344,
      "learning_rate": 0.00020147539243590517,
      "loss": 6.3392,
      "step": 120
    },
    {
      "epoch": 0.11226252158894647,
      "grad_norm": 94.66860961914062,
      "learning_rate": 0.00019774114628873756,
      "loss": 6.5716,
      "step": 130
    },
    {
      "epoch": 0.12089810017271158,
      "grad_norm": 152.21823120117188,
      "learning_rate": 0.00019356481839811937,
      "loss": 6.9773,
      "step": 140
    },
    {
      "epoch": 0.12953367875647667,
      "grad_norm": 82.85447692871094,
      "learning_rate": 0.00018896675541373064,
      "loss": 6.645,
      "step": 150
    },
    {
      "epoch": 0.12953367875647667,
      "eval_loss": 3.5013442039489746,
      "eval_runtime": 6.6443,
      "eval_samples_per_second": 73.447,
      "eval_steps_per_second": 18.362,
      "step": 150
    },
    {
      "epoch": 0.1381692573402418,
      "grad_norm": 636.0718383789062,
      "learning_rate": 0.00018396935863623567,
      "loss": 7.1472,
      "step": 160
    },
    {
      "epoch": 0.14680483592400692,
      "grad_norm": 377.86871337890625,
      "learning_rate": 0.00017859697488039784,
      "loss": 8.351,
      "step": 170
    },
    {
      "epoch": 0.15544041450777202,
      "grad_norm": 492.2079162597656,
      "learning_rate": 0.00017287577785984542,
      "loss": 7.6491,
      "step": 180
    },
    {
      "epoch": 0.16407599309153714,
      "grad_norm": 1487.2916259765625,
      "learning_rate": 0.0001668336406713699,
      "loss": 10.3314,
      "step": 190
    },
    {
      "epoch": 0.17271157167530224,
      "grad_norm": 237.623046875,
      "learning_rate": 0.0001605,
      "loss": 13.55,
      "step": 200
    },
    {
      "epoch": 0.17271157167530224,
      "eval_loss": 4.735245227813721,
      "eval_runtime": 6.6489,
      "eval_samples_per_second": 73.396,
      "eval_steps_per_second": 18.349,
      "step": 200
    },
    {
      "epoch": 0.18134715025906736,
      "grad_norm": 98.97422790527344,
      "learning_rate": 0.00015390571270643128,
      "loss": 9.3309,
      "step": 210
    },
    {
      "epoch": 0.18998272884283246,
      "grad_norm": 93.46147155761719,
      "learning_rate": 0.0001470829054955026,
      "loss": 8.2994,
      "step": 220
    },
    {
      "epoch": 0.19861830742659758,
      "grad_norm": 134.19017028808594,
      "learning_rate": 0.00014006481839811937,
      "loss": 7.2788,
      "step": 230
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 61.017330169677734,
      "learning_rate": 0.00013288564282916442,
      "loss": 7.1896,
      "step": 240
    },
    {
      "epoch": 0.2158894645941278,
      "grad_norm": 32.051456451416016,
      "learning_rate": 0.00012558035501036158,
      "loss": 7.0567,
      "step": 250
    },
    {
      "epoch": 0.2158894645941278,
      "eval_loss": 3.3268649578094482,
      "eval_runtime": 6.6696,
      "eval_samples_per_second": 73.168,
      "eval_steps_per_second": 18.292,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2328505614336000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}