{
  "best_metric": 0.1643463671207428,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.212630236019562,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00042526047203912394,
      "eval_loss": 0.6095050573348999,
      "eval_runtime": 72.3902,
      "eval_samples_per_second": 13.676,
      "eval_steps_per_second": 3.426,
      "step": 1
    },
    {
      "epoch": 0.00425260472039124,
      "grad_norm": 0.8989177346229553,
      "learning_rate": 4.2600000000000005e-05,
      "loss": 0.2704,
      "step": 10
    },
    {
      "epoch": 0.00850520944078248,
      "grad_norm": 0.80766361951828,
      "learning_rate": 8.520000000000001e-05,
      "loss": 0.2043,
      "step": 20
    },
    {
      "epoch": 0.01275781416117372,
      "grad_norm": 1.4762111902236938,
      "learning_rate": 0.0001278,
      "loss": 0.2043,
      "step": 30
    },
    {
      "epoch": 0.01701041888156496,
      "grad_norm": 1.0572073459625244,
      "learning_rate": 0.00017040000000000002,
      "loss": 0.2232,
      "step": 40
    },
    {
      "epoch": 0.0212630236019562,
      "grad_norm": 4.580044269561768,
      "learning_rate": 0.000213,
      "loss": 0.2669,
      "step": 50
    },
    {
      "epoch": 0.0212630236019562,
      "eval_loss": 0.2905704379081726,
      "eval_runtime": 72.2977,
      "eval_samples_per_second": 13.693,
      "eval_steps_per_second": 3.43,
      "step": 50
    },
    {
      "epoch": 0.02551562832234744,
      "grad_norm": 0.48462969064712524,
      "learning_rate": 0.00021274057135267128,
      "loss": 0.1732,
      "step": 60
    },
    {
      "epoch": 0.02976823304273868,
      "grad_norm": 0.7520514726638794,
      "learning_rate": 0.00021196354932097723,
      "loss": 0.1737,
      "step": 70
    },
    {
      "epoch": 0.03402083776312992,
      "grad_norm": 0.733476996421814,
      "learning_rate": 0.0002106727194781503,
      "loss": 0.1691,
      "step": 80
    },
    {
      "epoch": 0.03827344248352116,
      "grad_norm": 1.303952932357788,
      "learning_rate": 0.00020887437061743096,
      "loss": 0.2693,
      "step": 90
    },
    {
      "epoch": 0.0425260472039124,
      "grad_norm": 2.432600975036621,
      "learning_rate": 0.00020657726411369925,
      "loss": 0.2541,
      "step": 100
    },
    {
      "epoch": 0.0425260472039124,
      "eval_loss": 0.2186073362827301,
      "eval_runtime": 72.3365,
      "eval_samples_per_second": 13.686,
      "eval_steps_per_second": 3.428,
      "step": 100
    },
    {
      "epoch": 0.04677865192430364,
      "grad_norm": 0.3898923099040985,
      "learning_rate": 0.000203792591238937,
      "loss": 0.1503,
      "step": 110
    },
    {
      "epoch": 0.05103125664469488,
      "grad_norm": 0.5413680672645569,
      "learning_rate": 0.0002005339186394757,
      "loss": 0.1434,
      "step": 120
    },
    {
      "epoch": 0.05528386136508612,
      "grad_norm": 0.783905029296875,
      "learning_rate": 0.00019681712224065936,
      "loss": 0.1696,
      "step": 130
    },
    {
      "epoch": 0.05953646608547736,
      "grad_norm": 1.4847009181976318,
      "learning_rate": 0.0001926603099009319,
      "loss": 0.2174,
      "step": 140
    },
    {
      "epoch": 0.0637890708058686,
      "grad_norm": 2.3255372047424316,
      "learning_rate": 0.00018808373319217114,
      "loss": 0.275,
      "step": 150
    },
    {
      "epoch": 0.0637890708058686,
      "eval_loss": 0.2177441269159317,
      "eval_runtime": 72.4141,
      "eval_samples_per_second": 13.671,
      "eval_steps_per_second": 3.425,
      "step": 150
    },
    {
      "epoch": 0.06804167552625984,
      "grad_norm": 0.3854157626628876,
      "learning_rate": 0.00018310968873606635,
      "loss": 0.1658,
      "step": 160
    },
    {
      "epoch": 0.07229428024665108,
      "grad_norm": 0.4845024049282074,
      "learning_rate": 0.0001777624095772184,
      "loss": 0.1831,
      "step": 170
    },
    {
      "epoch": 0.07654688496704232,
      "grad_norm": 0.9749467968940735,
      "learning_rate": 0.0001720679471221826,
      "loss": 0.1933,
      "step": 180
    },
    {
      "epoch": 0.08079948968743356,
      "grad_norm": 0.8443153500556946,
      "learning_rate": 0.00016605404421963453,
      "loss": 0.2047,
      "step": 190
    },
    {
      "epoch": 0.0850520944078248,
      "grad_norm": 1.4500705003738403,
      "learning_rate": 0.00015975,
      "loss": 0.2931,
      "step": 200
    },
    {
      "epoch": 0.0850520944078248,
      "eval_loss": 0.20021717250347137,
      "eval_runtime": 72.6074,
      "eval_samples_per_second": 13.635,
      "eval_steps_per_second": 3.416,
      "step": 200
    },
    {
      "epoch": 0.08930469912821604,
      "grad_norm": 0.5776247978210449,
      "learning_rate": 0.00015318652713303674,
      "loss": 0.16,
      "step": 210
    },
    {
      "epoch": 0.09355730384860728,
      "grad_norm": 0.5547011494636536,
      "learning_rate": 0.00014639560219879464,
      "loss": 0.1446,
      "step": 220
    },
    {
      "epoch": 0.09780990856899852,
      "grad_norm": 0.702063798904419,
      "learning_rate": 0.0001394103099009319,
      "loss": 0.1747,
      "step": 230
    },
    {
      "epoch": 0.10206251328938976,
      "grad_norm": 0.9604615569114685,
      "learning_rate": 0.0001322646818813646,
      "loss": 0.2264,
      "step": 240
    },
    {
      "epoch": 0.106315118009781,
      "grad_norm": 2.0104331970214844,
      "learning_rate": 0.0001249935309215281,
      "loss": 0.254,
      "step": 250
    },
    {
      "epoch": 0.106315118009781,
      "eval_loss": 0.1977642923593521,
      "eval_runtime": 72.6924,
      "eval_samples_per_second": 13.619,
      "eval_steps_per_second": 3.412,
      "step": 250
    },
    {
      "epoch": 0.11056772273017224,
      "grad_norm": 0.3492359220981598,
      "learning_rate": 0.0001176322813380051,
      "loss": 0.1203,
      "step": 260
    },
    {
      "epoch": 0.11482032745056348,
      "grad_norm": 0.4210224449634552,
      "learning_rate": 0.00011021679639881638,
      "loss": 0.1282,
      "step": 270
    },
    {
      "epoch": 0.11907293217095472,
      "grad_norm": 0.927093505859375,
      "learning_rate": 0.00010278320360118368,
      "loss": 0.1669,
      "step": 280
    },
    {
      "epoch": 0.12332553689134595,
      "grad_norm": 1.108055830001831,
      "learning_rate": 9.536771866199493e-05,
      "loss": 0.1855,
      "step": 290
    },
    {
      "epoch": 0.1275781416117372,
      "grad_norm": 1.8096457719802856,
      "learning_rate": 8.800646907847192e-05,
      "loss": 0.2914,
      "step": 300
    },
    {
      "epoch": 0.1275781416117372,
      "eval_loss": 0.187950000166893,
      "eval_runtime": 72.7518,
      "eval_samples_per_second": 13.608,
      "eval_steps_per_second": 3.409,
      "step": 300
    },
    {
      "epoch": 0.13183074633212843,
      "grad_norm": 0.4479442834854126,
      "learning_rate": 8.07353181186354e-05,
      "loss": 0.124,
      "step": 310
    },
    {
      "epoch": 0.13608335105251967,
      "grad_norm": 0.41207781434059143,
      "learning_rate": 7.35896900990681e-05,
      "loss": 0.1531,
      "step": 320
    },
    {
      "epoch": 0.14033595577291091,
      "grad_norm": 0.9523985981941223,
      "learning_rate": 6.660439780120536e-05,
      "loss": 0.1732,
      "step": 330
    },
    {
      "epoch": 0.14458856049330215,
      "grad_norm": 1.1972426176071167,
      "learning_rate": 5.981347286696324e-05,
      "loss": 0.1977,
      "step": 340
    },
    {
      "epoch": 0.1488411652136934,
      "grad_norm": 1.7219096422195435,
      "learning_rate": 5.325000000000002e-05,
      "loss": 0.1944,
      "step": 350
    },
    {
      "epoch": 0.1488411652136934,
      "eval_loss": 0.17624303698539734,
      "eval_runtime": 72.6437,
      "eval_samples_per_second": 13.628,
      "eval_steps_per_second": 3.414,
      "step": 350
    },
    {
      "epoch": 0.15309376993408463,
      "grad_norm": 0.34478458762168884,
      "learning_rate": 4.6945955780365475e-05,
      "loss": 0.1069,
      "step": 360
    },
    {
      "epoch": 0.15734637465447587,
      "grad_norm": 0.7543050646781921,
      "learning_rate": 4.0932052877817393e-05,
      "loss": 0.1509,
      "step": 370
    },
    {
      "epoch": 0.1615989793748671,
      "grad_norm": 0.7749956846237183,
      "learning_rate": 3.523759042278163e-05,
      "loss": 0.1447,
      "step": 380
    },
    {
      "epoch": 0.16585158409525835,
      "grad_norm": 0.8737692832946777,
      "learning_rate": 2.989031126393367e-05,
      "loss": 0.2315,
      "step": 390
    },
    {
      "epoch": 0.1701041888156496,
      "grad_norm": 1.4741559028625488,
      "learning_rate": 2.4916266807828855e-05,
      "loss": 0.234,
      "step": 400
    },
    {
      "epoch": 0.1701041888156496,
      "eval_loss": 0.16768178343772888,
      "eval_runtime": 72.7753,
      "eval_samples_per_second": 13.604,
      "eval_steps_per_second": 3.408,
      "step": 400
    },
    {
      "epoch": 0.17435679353604083,
      "grad_norm": 0.32338669896125793,
      "learning_rate": 2.033969009906811e-05,
      "loss": 0.1204,
      "step": 410
    },
    {
      "epoch": 0.17860939825643207,
      "grad_norm": 0.5574338436126709,
      "learning_rate": 1.6182877759340637e-05,
      "loss": 0.1627,
      "step": 420
    },
    {
      "epoch": 0.1828620029768233,
      "grad_norm": 0.619001030921936,
      "learning_rate": 1.2466081360524275e-05,
      "loss": 0.1113,
      "step": 430
    },
    {
      "epoch": 0.18711460769721455,
      "grad_norm": 0.8440791368484497,
      "learning_rate": 9.207408761062996e-06,
      "loss": 0.1754,
      "step": 440
    },
    {
      "epoch": 0.1913672124176058,
      "grad_norm": 1.8180017471313477,
      "learning_rate": 6.422735886300764e-06,
      "loss": 0.2486,
      "step": 450
    },
    {
      "epoch": 0.1913672124176058,
      "eval_loss": 0.16511203348636627,
      "eval_runtime": 72.2907,
      "eval_samples_per_second": 13.695,
      "eval_steps_per_second": 3.431,
      "step": 450
    },
    {
      "epoch": 0.19561981713799703,
      "grad_norm": 0.3398416042327881,
      "learning_rate": 4.125629382569038e-06,
      "loss": 0.1377,
      "step": 460
    },
    {
      "epoch": 0.19987242185838827,
      "grad_norm": 0.6524055004119873,
      "learning_rate": 2.327280521849694e-06,
      "loss": 0.1348,
      "step": 470
    },
    {
      "epoch": 0.2041250265787795,
      "grad_norm": 0.5883779525756836,
      "learning_rate": 1.0364506790227565e-06,
      "loss": 0.1782,
      "step": 480
    },
    {
      "epoch": 0.20837763129917075,
      "grad_norm": 0.6829372644424438,
      "learning_rate": 2.5942864732872295e-07,
      "loss": 0.181,
      "step": 490
    },
    {
      "epoch": 0.212630236019562,
      "grad_norm": 1.7673338651657104,
      "learning_rate": 0.0,
      "loss": 0.2541,
      "step": 500
    },
    {
      "epoch": 0.212630236019562,
      "eval_loss": 0.1643463671207428,
      "eval_runtime": 72.4913,
      "eval_samples_per_second": 13.657,
      "eval_steps_per_second": 3.421,
      "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": 1.1238426161656627e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}