{
  "best_metric": 1.936466932296753,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.026634705020641896,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.326941004128379e-05,
      "eval_loss": 3.0679404735565186,
      "eval_runtime": 533.8467,
      "eval_samples_per_second": 14.808,
      "eval_steps_per_second": 3.703,
      "step": 1
    },
    {
      "epoch": 0.0005326941004128379,
      "grad_norm": 3.2132368087768555,
      "learning_rate": 4.22e-05,
      "loss": 3.0593,
      "step": 10
    },
    {
      "epoch": 0.0010653882008256758,
      "grad_norm": 2.378092050552368,
      "learning_rate": 8.44e-05,
      "loss": 2.6858,
      "step": 20
    },
    {
      "epoch": 0.0015980823012385138,
      "grad_norm": 3.411348819732666,
      "learning_rate": 0.0001266,
      "loss": 2.4182,
      "step": 30
    },
    {
      "epoch": 0.0021307764016513515,
      "grad_norm": 3.3911640644073486,
      "learning_rate": 0.0001688,
      "loss": 2.1554,
      "step": 40
    },
    {
      "epoch": 0.0026634705020641895,
      "grad_norm": 3.3872954845428467,
      "learning_rate": 0.000211,
      "loss": 2.2891,
      "step": 50
    },
    {
      "epoch": 0.0026634705020641895,
      "eval_loss": 2.337301254272461,
      "eval_runtime": 532.5912,
      "eval_samples_per_second": 14.843,
      "eval_steps_per_second": 3.712,
      "step": 50
    },
    {
      "epoch": 0.0031961646024770275,
      "grad_norm": 4.0618438720703125,
      "learning_rate": 0.00021074300730241147,
      "loss": 2.6631,
      "step": 60
    },
    {
      "epoch": 0.0037288587028898655,
      "grad_norm": 2.6760034561157227,
      "learning_rate": 0.00020997328125223568,
      "loss": 2.3427,
      "step": 70
    },
    {
      "epoch": 0.004261552803302703,
      "grad_norm": 2.3804855346679688,
      "learning_rate": 0.0002086945718774165,
      "loss": 2.2906,
      "step": 80
    },
    {
      "epoch": 0.004794246903715541,
      "grad_norm": 2.9891622066497803,
      "learning_rate": 0.00020691310892149265,
      "loss": 2.2366,
      "step": 90
    },
    {
      "epoch": 0.005326941004128379,
      "grad_norm": 2.7837183475494385,
      "learning_rate": 0.00020463757149291335,
      "loss": 2.1066,
      "step": 100
    },
    {
      "epoch": 0.005326941004128379,
      "eval_loss": 2.2396671772003174,
      "eval_runtime": 534.4715,
      "eval_samples_per_second": 14.79,
      "eval_steps_per_second": 3.699,
      "step": 100
    },
    {
      "epoch": 0.005859635104541217,
      "grad_norm": 2.4550390243530273,
      "learning_rate": 0.0002018790457812944,
      "loss": 2.5823,
      "step": 110
    },
    {
      "epoch": 0.006392329204954055,
      "grad_norm": 2.8835442066192627,
      "learning_rate": 0.0001986509710466168,
      "loss": 2.1514,
      "step": 120
    },
    {
      "epoch": 0.006925023305366893,
      "grad_norm": 2.5225555896759033,
      "learning_rate": 0.00019496907414450293,
      "loss": 2.1257,
      "step": 130
    },
    {
      "epoch": 0.007457717405779731,
      "grad_norm": 3.0806941986083984,
      "learning_rate": 0.00019085129290655697,
      "loss": 2.0863,
      "step": 140
    },
    {
      "epoch": 0.007990411506192568,
      "grad_norm": 3.4714853763580322,
      "learning_rate": 0.00018631768874905217,
      "loss": 2.1402,
      "step": 150
    },
    {
      "epoch": 0.007990411506192568,
      "eval_loss": 2.1884541511535645,
      "eval_runtime": 533.3853,
      "eval_samples_per_second": 14.82,
      "eval_steps_per_second": 3.707,
      "step": 150
    },
    {
      "epoch": 0.008523105606605406,
      "grad_norm": 3.440795421600342,
      "learning_rate": 0.0001813903489357277,
      "loss": 2.3961,
      "step": 160
    },
    {
      "epoch": 0.009055799707018244,
      "grad_norm": 2.553541660308838,
      "learning_rate": 0.00017609327897085954,
      "loss": 2.0502,
      "step": 170
    },
    {
      "epoch": 0.009588493807431082,
      "grad_norm": 2.7053887844085693,
      "learning_rate": 0.00017045228564685694,
      "loss": 1.9734,
      "step": 180
    },
    {
      "epoch": 0.01012118790784392,
      "grad_norm": 2.8302621841430664,
      "learning_rate": 0.0001644948513161638,
      "loss": 1.986,
      "step": 190
    },
    {
      "epoch": 0.010653882008256758,
      "grad_norm": 2.9765737056732178,
      "learning_rate": 0.00015825,
      "loss": 2.0361,
      "step": 200
    },
    {
      "epoch": 0.010653882008256758,
      "eval_loss": 2.130861282348633,
      "eval_runtime": 533.2758,
      "eval_samples_per_second": 14.823,
      "eval_steps_per_second": 3.707,
      "step": 200
    },
    {
      "epoch": 0.011186576108669596,
      "grad_norm": 3.183436870574951,
      "learning_rate": 0.00015174815598624768,
      "loss": 2.3303,
      "step": 210
    },
    {
      "epoch": 0.011719270209082434,
      "grad_norm": 2.889716863632202,
      "learning_rate": 0.00014502099560537873,
      "loss": 2.0327,
      "step": 220
    },
    {
      "epoch": 0.012251964309495272,
      "grad_norm": 3.0211775302886963,
      "learning_rate": 0.00013810129290655696,
      "loss": 1.9539,
      "step": 230
    },
    {
      "epoch": 0.01278465840990811,
      "grad_norm": 2.7339537143707275,
      "learning_rate": 0.00013102275998576495,
      "loss": 2.051,
      "step": 240
    },
    {
      "epoch": 0.013317352510320948,
      "grad_norm": 2.893467426300049,
      "learning_rate": 0.00012381988274386116,
      "loss": 1.8673,
      "step": 250
    },
    {
      "epoch": 0.013317352510320948,
      "eval_loss": 2.0931496620178223,
      "eval_runtime": 532.4929,
      "eval_samples_per_second": 14.845,
      "eval_steps_per_second": 3.713,
      "step": 250
    },
    {
      "epoch": 0.013850046610733786,
      "grad_norm": 2.5460901260375977,
      "learning_rate": 0.00011652775287473745,
      "loss": 2.2428,
      "step": 260
    },
    {
      "epoch": 0.014382740711146624,
      "grad_norm": 3.3399200439453125,
      "learning_rate": 0.00010918189690211387,
      "loss": 2.0206,
      "step": 270
    },
    {
      "epoch": 0.014915434811559462,
      "grad_norm": 2.6262121200561523,
      "learning_rate": 0.00010181810309788618,
      "loss": 2.0444,
      "step": 280
    },
    {
      "epoch": 0.0154481289119723,
      "grad_norm": 2.6797196865081787,
      "learning_rate": 9.447224712526258e-05,
      "loss": 2.0037,
      "step": 290
    },
    {
      "epoch": 0.015980823012385136,
      "grad_norm": 3.1483330726623535,
      "learning_rate": 8.718011725613886e-05,
      "loss": 1.8715,
      "step": 300
    },
    {
      "epoch": 0.015980823012385136,
      "eval_loss": 2.036539077758789,
      "eval_runtime": 531.097,
      "eval_samples_per_second": 14.884,
      "eval_steps_per_second": 3.722,
      "step": 300
    },
    {
      "epoch": 0.016513517112797974,
      "grad_norm": 2.244508743286133,
      "learning_rate": 7.997724001423507e-05,
      "loss": 2.4281,
      "step": 310
    },
    {
      "epoch": 0.017046211213210812,
      "grad_norm": 2.197800874710083,
      "learning_rate": 7.289870709344306e-05,
      "loss": 2.1108,
      "step": 320
    },
    {
      "epoch": 0.01757890531362365,
      "grad_norm": 2.820525884628296,
      "learning_rate": 6.597900439462128e-05,
      "loss": 2.123,
      "step": 330
    },
    {
      "epoch": 0.018111599414036488,
      "grad_norm": 2.3880505561828613,
      "learning_rate": 5.9251844013752326e-05,
      "loss": 1.9026,
      "step": 340
    },
    {
      "epoch": 0.018644293514449326,
      "grad_norm": 2.7764363288879395,
      "learning_rate": 5.275000000000002e-05,
      "loss": 1.9069,
      "step": 350
    },
    {
      "epoch": 0.018644293514449326,
      "eval_loss": 1.9905914068222046,
      "eval_runtime": 531.6414,
      "eval_samples_per_second": 14.869,
      "eval_steps_per_second": 3.719,
      "step": 350
    },
    {
      "epoch": 0.019176987614862164,
      "grad_norm": 2.4365758895874023,
      "learning_rate": 4.650514868383623e-05,
      "loss": 2.1774,
      "step": 360
    },
    {
      "epoch": 0.019709681715275002,
      "grad_norm": 2.4096992015838623,
      "learning_rate": 4.054771435314305e-05,
      "loss": 1.9757,
      "step": 370
    },
    {
      "epoch": 0.02024237581568784,
      "grad_norm": 2.4260826110839844,
      "learning_rate": 3.4906721029140495e-05,
      "loss": 1.8704,
      "step": 380
    },
    {
      "epoch": 0.020775069916100678,
      "grad_norm": 2.498000144958496,
      "learning_rate": 2.9609651064272323e-05,
      "loss": 1.736,
      "step": 390
    },
    {
      "epoch": 0.021307764016513516,
      "grad_norm": 2.5754637718200684,
      "learning_rate": 2.468231125094783e-05,
      "loss": 1.9859,
      "step": 400
    },
    {
      "epoch": 0.021307764016513516,
      "eval_loss": 1.95258367061615,
      "eval_runtime": 530.922,
      "eval_samples_per_second": 14.889,
      "eval_steps_per_second": 3.724,
      "step": 400
    },
    {
      "epoch": 0.021840458116926354,
      "grad_norm": 2.3538734912872314,
      "learning_rate": 2.0148707093443057e-05,
      "loss": 2.1522,
      "step": 410
    },
    {
      "epoch": 0.022373152217339192,
      "grad_norm": 2.6439859867095947,
      "learning_rate": 1.603092585549706e-05,
      "loss": 1.7433,
      "step": 420
    },
    {
      "epoch": 0.02290584631775203,
      "grad_norm": 2.6570234298706055,
      "learning_rate": 1.2349028953383204e-05,
      "loss": 1.9083,
      "step": 430
    },
    {
      "epoch": 0.023438540418164868,
      "grad_norm": 2.4057772159576416,
      "learning_rate": 9.120954218705596e-06,
      "loss": 1.8574,
      "step": 440
    },
    {
      "epoch": 0.023971234518577706,
      "grad_norm": 2.666785478591919,
      "learning_rate": 6.362428507086673e-06,
      "loss": 1.7853,
      "step": 450
    },
    {
      "epoch": 0.023971234518577706,
      "eval_loss": 1.9402557611465454,
      "eval_runtime": 535.1798,
      "eval_samples_per_second": 14.771,
      "eval_steps_per_second": 3.694,
      "step": 450
    },
    {
      "epoch": 0.024503928618990544,
      "grad_norm": 2.5038259029388428,
      "learning_rate": 4.0868910785073565e-06,
      "loss": 2.1247,
      "step": 460
    },
    {
      "epoch": 0.025036622719403382,
      "grad_norm": 2.3825926780700684,
      "learning_rate": 2.3054281225835e-06,
      "loss": 1.9837,
      "step": 470
    },
    {
      "epoch": 0.02556931681981622,
      "grad_norm": 2.523310422897339,
      "learning_rate": 1.026718747764327e-06,
      "loss": 1.8865,
      "step": 480
    },
    {
      "epoch": 0.026102010920229058,
      "grad_norm": 2.702605962753296,
      "learning_rate": 2.5699269758854715e-07,
      "loss": 1.8519,
      "step": 490
    },
    {
      "epoch": 0.026634705020641896,
      "grad_norm": 2.631019115447998,
      "learning_rate": 0.0,
      "loss": 1.9505,
      "step": 500
    },
    {
      "epoch": 0.026634705020641896,
      "eval_loss": 1.936466932296753,
      "eval_runtime": 533.4244,
      "eval_samples_per_second": 14.819,
      "eval_steps_per_second": 3.706,
      "step": 500
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0681938748637184e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}