{
  "best_metric": 2.79083251953125,
  "best_model_checkpoint": "miner_id_24/checkpoint-450",
  "epoch": 0.026761819803746655,
  "eval_steps": 50,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.947071067499257e-05,
      "eval_loss": 3.244145631790161,
      "eval_runtime": 152.6741,
      "eval_samples_per_second": 46.373,
      "eval_steps_per_second": 11.593,
      "step": 1
    },
    {
      "epoch": 0.0005947071067499256,
      "grad_norm": 0.7733362317085266,
      "learning_rate": 4.3e-05,
      "loss": 3.1454,
      "step": 10
    },
    {
      "epoch": 0.0011894142134998512,
      "grad_norm": 0.8843149542808533,
      "learning_rate": 8.6e-05,
      "loss": 3.1051,
      "step": 20
    },
    {
      "epoch": 0.001784121320249777,
      "grad_norm": 1.0911622047424316,
      "learning_rate": 0.000129,
      "loss": 3.1398,
      "step": 30
    },
    {
      "epoch": 0.0023788284269997025,
      "grad_norm": 1.3399714231491089,
      "learning_rate": 0.000172,
      "loss": 3.0248,
      "step": 40
    },
    {
      "epoch": 0.0029735355337496285,
      "grad_norm": 2.3345842361450195,
      "learning_rate": 0.000215,
      "loss": 3.0162,
      "step": 50
    },
    {
      "epoch": 0.0029735355337496285,
      "eval_loss": 3.0040273666381836,
      "eval_runtime": 152.6861,
      "eval_samples_per_second": 46.37,
      "eval_steps_per_second": 11.592,
      "step": 50
    },
    {
      "epoch": 0.003568242640499554,
      "grad_norm": 0.7499136924743652,
      "learning_rate": 0.0002147381354029311,
      "loss": 2.9332,
      "step": 60
    },
    {
      "epoch": 0.004162949747249479,
      "grad_norm": 0.827118456363678,
      "learning_rate": 0.0002139538173897188,
      "loss": 2.9428,
      "step": 70
    },
    {
      "epoch": 0.004757656853999405,
      "grad_norm": 0.8964134454727173,
      "learning_rate": 0.0002126508670788841,
      "loss": 2.917,
      "step": 80
    },
    {
      "epoch": 0.0053523639607493305,
      "grad_norm": 1.1437286138534546,
      "learning_rate": 0.00021083563231336926,
      "loss": 2.9036,
      "step": 90
    },
    {
      "epoch": 0.005947071067499257,
      "grad_norm": 2.0146210193634033,
      "learning_rate": 0.00020851695673448515,
      "loss": 2.9321,
      "step": 100
    },
    {
      "epoch": 0.005947071067499257,
      "eval_loss": 2.9241762161254883,
      "eval_runtime": 152.9767,
      "eval_samples_per_second": 46.282,
      "eval_steps_per_second": 11.57,
      "step": 100
    },
    {
      "epoch": 0.006541778174249183,
      "grad_norm": 0.7368491888046265,
      "learning_rate": 0.00020570613669657956,
      "loss": 2.9719,
      "step": 110
    },
    {
      "epoch": 0.007136485280999108,
      "grad_norm": 0.8235340118408203,
      "learning_rate": 0.00020241686623233464,
      "loss": 2.9481,
      "step": 120
    },
    {
      "epoch": 0.007731192387749034,
      "grad_norm": 0.9127469062805176,
      "learning_rate": 0.00019866517033681577,
      "loss": 2.8795,
      "step": 130
    },
    {
      "epoch": 0.008325899494498959,
      "grad_norm": 1.1192858219146729,
      "learning_rate": 0.00019446932689530684,
      "loss": 2.8425,
      "step": 140
    },
    {
      "epoch": 0.008920606601248885,
      "grad_norm": 2.003065347671509,
      "learning_rate": 0.0001898497776352901,
      "loss": 2.8621,
      "step": 150
    },
    {
      "epoch": 0.008920606601248885,
      "eval_loss": 2.9108498096466064,
      "eval_runtime": 151.7844,
      "eval_samples_per_second": 46.645,
      "eval_steps_per_second": 11.661,
      "step": 150
    },
    {
      "epoch": 0.00951531370799881,
      "grad_norm": 0.6534820199012756,
      "learning_rate": 0.000184829028536405,
      "loss": 2.9198,
      "step": 160
    },
    {
      "epoch": 0.010110020814748736,
      "grad_norm": 0.7408804893493652,
      "learning_rate": 0.00017943154018357726,
      "loss": 2.9099,
      "step": 170
    },
    {
      "epoch": 0.010704727921498661,
      "grad_norm": 0.9117923378944397,
      "learning_rate": 0.00017368360859750824,
      "loss": 2.7631,
      "step": 180
    },
    {
      "epoch": 0.011299435028248588,
      "grad_norm": 0.9990629553794861,
      "learning_rate": 0.00016761323712310527,
      "loss": 2.7877,
      "step": 190
    },
    {
      "epoch": 0.011894142134998514,
      "grad_norm": 1.7992066144943237,
      "learning_rate": 0.00016125,
      "loss": 2.9707,
      "step": 200
    },
    {
      "epoch": 0.011894142134998514,
      "eval_loss": 2.8687682151794434,
      "eval_runtime": 151.6691,
      "eval_samples_per_second": 46.681,
      "eval_steps_per_second": 11.67,
      "step": 200
    },
    {
      "epoch": 0.012488849241748439,
      "grad_norm": 0.6635362505912781,
      "learning_rate": 0.0001546248982798258,
      "loss": 2.8439,
      "step": 210
    },
    {
      "epoch": 0.013083556348498365,
      "grad_norm": 0.7446403503417969,
      "learning_rate": 0.00014777020879221055,
      "loss": 2.7955,
      "step": 220
    },
    {
      "epoch": 0.01367826345524829,
      "grad_norm": 0.834824800491333,
      "learning_rate": 0.00014071932689530684,
      "loss": 2.8353,
      "step": 230
    },
    {
      "epoch": 0.014272970561998216,
      "grad_norm": 1.0048375129699707,
      "learning_rate": 0.00013350660377696428,
      "loss": 2.8452,
      "step": 240
    },
    {
      "epoch": 0.014867677668748141,
      "grad_norm": 1.9789893627166748,
      "learning_rate": 0.00012616717909919503,
      "loss": 2.8344,
      "step": 250
    },
    {
      "epoch": 0.014867677668748141,
      "eval_loss": 2.843684434890747,
      "eval_runtime": 156.5509,
      "eval_samples_per_second": 45.225,
      "eval_steps_per_second": 11.306,
      "step": 250
    },
    {
      "epoch": 0.015462384775498068,
      "grad_norm": 0.6162389516830444,
      "learning_rate": 0.00011873680980127275,
      "loss": 2.8784,
      "step": 260
    },
    {
      "epoch": 0.016057091882247992,
      "grad_norm": 0.7453039288520813,
      "learning_rate": 0.00011125169589551887,
      "loss": 2.8229,
      "step": 270
    },
    {
      "epoch": 0.016651798988997917,
      "grad_norm": 0.8477461338043213,
      "learning_rate": 0.00010374830410448118,
      "loss": 2.7984,
      "step": 280
    },
    {
      "epoch": 0.017246506095747845,
      "grad_norm": 0.9298999309539795,
      "learning_rate": 9.626319019872726e-05,
      "loss": 2.8242,
      "step": 290
    },
    {
      "epoch": 0.01784121320249777,
      "grad_norm": 1.780192494392395,
      "learning_rate": 8.883282090080499e-05,
      "loss": 2.806,
      "step": 300
    },
    {
      "epoch": 0.01784121320249777,
      "eval_loss": 2.81919264793396,
      "eval_runtime": 152.2132,
      "eval_samples_per_second": 46.514,
      "eval_steps_per_second": 11.628,
      "step": 300
    },
    {
      "epoch": 0.018435920309247695,
      "grad_norm": 0.6574707627296448,
      "learning_rate": 8.149339622303573e-05,
      "loss": 2.8579,
      "step": 310
    },
    {
      "epoch": 0.01903062741599762,
      "grad_norm": 0.7700655460357666,
      "learning_rate": 7.428067310469316e-05,
      "loss": 2.8334,
      "step": 320
    },
    {
      "epoch": 0.019625334522747548,
      "grad_norm": 0.9334675073623657,
      "learning_rate": 6.722979120778945e-05,
      "loss": 2.83,
      "step": 330
    },
    {
      "epoch": 0.020220041629497473,
      "grad_norm": 1.045379877090454,
      "learning_rate": 6.0375101720174165e-05,
      "loss": 2.7034,
      "step": 340
    },
    {
      "epoch": 0.020814748736247397,
      "grad_norm": 1.8645881414413452,
      "learning_rate": 5.3750000000000026e-05,
      "loss": 2.8473,
      "step": 350
    },
    {
      "epoch": 0.020814748736247397,
      "eval_loss": 2.807974100112915,
      "eval_runtime": 151.7178,
      "eval_samples_per_second": 46.666,
      "eval_steps_per_second": 11.666,
      "step": 350
    },
    {
      "epoch": 0.021409455842997322,
      "grad_norm": 0.6872610449790955,
      "learning_rate": 4.738676287689473e-05,
      "loss": 2.8492,
      "step": 360
    },
    {
      "epoch": 0.02200416294974725,
      "grad_norm": 0.7925031781196594,
      "learning_rate": 4.131639140249173e-05,
      "loss": 2.8009,
      "step": 370
    },
    {
      "epoch": 0.022598870056497175,
      "grad_norm": 0.9018983244895935,
      "learning_rate": 3.5568459816422774e-05,
      "loss": 2.8143,
      "step": 380
    },
    {
      "epoch": 0.0231935771632471,
      "grad_norm": 1.0778685808181763,
      "learning_rate": 3.017097146359502e-05,
      "loss": 2.7583,
      "step": 390
    },
    {
      "epoch": 0.023788284269997028,
      "grad_norm": 1.6764299869537354,
      "learning_rate": 2.5150222364709875e-05,
      "loss": 2.7238,
      "step": 400
    },
    {
      "epoch": 0.023788284269997028,
      "eval_loss": 2.7967422008514404,
      "eval_runtime": 152.1562,
      "eval_samples_per_second": 46.531,
      "eval_steps_per_second": 11.633,
      "step": 400
    },
    {
      "epoch": 0.024382991376746953,
      "grad_norm": 0.7588967084884644,
      "learning_rate": 2.053067310469316e-05,
      "loss": 2.855,
      "step": 410
    },
    {
      "epoch": 0.024977698483496878,
      "grad_norm": 0.7385247945785522,
      "learning_rate": 1.633482966318421e-05,
      "loss": 2.7904,
      "step": 420
    },
    {
      "epoch": 0.025572405590246802,
      "grad_norm": 0.8757428526878357,
      "learning_rate": 1.2583133767665349e-05,
      "loss": 2.7639,
      "step": 430
    },
    {
      "epoch": 0.02616711269699673,
      "grad_norm": 1.0848084688186646,
      "learning_rate": 9.293863303420395e-06,
      "loss": 2.7639,
      "step": 440
    },
    {
      "epoch": 0.026761819803746655,
      "grad_norm": 2.063558578491211,
      "learning_rate": 6.483043265514856e-06,
      "loss": 2.8008,
      "step": 450
    },
    {
      "epoch": 0.026761819803746655,
      "eval_loss": 2.79083251953125,
      "eval_runtime": 153.2642,
      "eval_samples_per_second": 46.195,
      "eval_steps_per_second": 11.549,
      "step": 450
    }
  ],
  "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4744780492308480.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}