{
  "best_global_step": 300,
  "best_metric": 0.37665891647338867,
  "best_model_checkpoint": "/workspace/anchor/olmo-urban/train/checkpoint-300",
  "epoch": 0.32094142818935545,
  "eval_steps": 50,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005349023803155924,
      "grad_norm": 11.332925796508789,
      "learning_rate": 1.7021276595744682e-05,
      "loss": 7.0706,
      "step": 5
    },
    {
      "epoch": 0.010698047606311848,
      "grad_norm": 6.2103447914123535,
      "learning_rate": 3.829787234042553e-05,
      "loss": 6.4977,
      "step": 10
    },
    {
      "epoch": 0.016047071409467772,
      "grad_norm": 4.533832550048828,
      "learning_rate": 5.9574468085106384e-05,
      "loss": 5.6125,
      "step": 15
    },
    {
      "epoch": 0.021396095212623697,
      "grad_norm": 3.615572214126587,
      "learning_rate": 8.085106382978723e-05,
      "loss": 4.7692,
      "step": 20
    },
    {
      "epoch": 0.026745119015779622,
      "grad_norm": 2.759181022644043,
      "learning_rate": 0.00010212765957446809,
      "loss": 3.9879,
      "step": 25
    },
    {
      "epoch": 0.032094142818935543,
      "grad_norm": 7.817636966705322,
      "learning_rate": 0.00012340425531914893,
      "loss": 3.339,
      "step": 30
    },
    {
      "epoch": 0.03744316662209147,
      "grad_norm": 1.8590707778930664,
      "learning_rate": 0.0001446808510638298,
      "loss": 2.782,
      "step": 35
    },
    {
      "epoch": 0.042792190425247394,
      "grad_norm": 1.6293493509292603,
      "learning_rate": 0.00016595744680851065,
      "loss": 2.0399,
      "step": 40
    },
    {
      "epoch": 0.04814121422840332,
      "grad_norm": 1.9784948825836182,
      "learning_rate": 0.0001872340425531915,
      "loss": 1.7934,
      "step": 45
    },
    {
      "epoch": 0.053490238031559244,
      "grad_norm": 1.2116178274154663,
      "learning_rate": 0.00019999749676283775,
      "loss": 1.3086,
      "step": 50
    },
    {
      "epoch": 0.053490238031559244,
      "eval_loss": 0.8905913829803467,
      "eval_runtime": 230.3688,
      "eval_samples_per_second": 1.667,
      "eval_steps_per_second": 0.833,
      "step": 50
    },
    {
      "epoch": 0.05883926183471516,
      "grad_norm": 1.6632639169692993,
      "learning_rate": 0.00019996933678400946,
      "loss": 1.1475,
      "step": 55
    },
    {
      "epoch": 0.06418828563787109,
      "grad_norm": 1.2125474214553833,
      "learning_rate": 0.00019990989662046818,
      "loss": 0.9136,
      "step": 60
    },
    {
      "epoch": 0.06953730944102701,
      "grad_norm": 1.0796895027160645,
      "learning_rate": 0.00019981919487090972,
      "loss": 0.8924,
      "step": 65
    },
    {
      "epoch": 0.07488633324418294,
      "grad_norm": 0.9552472829818726,
      "learning_rate": 0.00019969725991571128,
      "loss": 0.8299,
      "step": 70
    },
    {
      "epoch": 0.08023535704733886,
      "grad_norm": 0.7944055199623108,
      "learning_rate": 0.00019954412990805107,
      "loss": 0.7001,
      "step": 75
    },
    {
      "epoch": 0.08558438085049479,
      "grad_norm": 0.7805637121200562,
      "learning_rate": 0.0001993598527619703,
      "loss": 0.8231,
      "step": 80
    },
    {
      "epoch": 0.09093340465365071,
      "grad_norm": 0.6794283986091614,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.8797,
      "step": 85
    },
    {
      "epoch": 0.09628242845680664,
      "grad_norm": 0.6624935269355774,
      "learning_rate": 0.00019889809742202455,
      "loss": 0.6609,
      "step": 90
    },
    {
      "epoch": 0.10163145225996256,
      "grad_norm": 0.8070583939552307,
      "learning_rate": 0.0001986207637103857,
      "loss": 0.8429,
      "step": 95
    },
    {
      "epoch": 0.10698047606311849,
      "grad_norm": 0.7406468391418457,
      "learning_rate": 0.00019831257177957044,
      "loss": 0.6952,
      "step": 100
    },
    {
      "epoch": 0.10698047606311849,
      "eval_loss": 0.4853295385837555,
      "eval_runtime": 112.3115,
      "eval_samples_per_second": 3.419,
      "eval_steps_per_second": 1.71,
      "step": 100
    },
    {
      "epoch": 0.1123294998662744,
      "grad_norm": 0.672978937625885,
      "learning_rate": 0.00019797361806215332,
      "loss": 0.4831,
      "step": 105
    },
    {
      "epoch": 0.11767852366943032,
      "grad_norm": 0.6432732939720154,
      "learning_rate": 0.000197604008616004,
      "loss": 0.7488,
      "step": 110
    },
    {
      "epoch": 0.12302754747258625,
      "grad_norm": 0.8533371686935425,
      "learning_rate": 0.00019720385909110198,
      "loss": 0.6459,
      "step": 115
    },
    {
      "epoch": 0.12837657127574217,
      "grad_norm": 0.7265816926956177,
      "learning_rate": 0.0001967732946933499,
      "loss": 0.6682,
      "step": 120
    },
    {
      "epoch": 0.1337255950788981,
      "grad_norm": 0.7138218879699707,
      "learning_rate": 0.00019631245014539698,
      "loss": 0.6458,
      "step": 125
    },
    {
      "epoch": 0.13907461888205402,
      "grad_norm": 0.681537389755249,
      "learning_rate": 0.0001958214696444846,
      "loss": 0.7498,
      "step": 130
    },
    {
      "epoch": 0.14442364268520994,
      "grad_norm": 0.7001609206199646,
      "learning_rate": 0.0001953005068173272,
      "loss": 0.5161,
      "step": 135
    },
    {
      "epoch": 0.14977266648836587,
      "grad_norm": 0.6696146130561829,
      "learning_rate": 0.00019474972467204297,
      "loss": 0.6795,
      "step": 140
    },
    {
      "epoch": 0.15512169029152179,
      "grad_norm": 0.781279981136322,
      "learning_rate": 0.00019416929554714888,
      "loss": 0.6418,
      "step": 145
    },
    {
      "epoch": 0.16047071409467772,
      "grad_norm": 0.5625928044319153,
      "learning_rate": 0.0001935594010576362,
      "loss": 0.5244,
      "step": 150
    },
    {
      "epoch": 0.16047071409467772,
      "eval_loss": 0.4266001880168915,
      "eval_runtime": 111.8623,
      "eval_samples_per_second": 3.433,
      "eval_steps_per_second": 1.716,
      "step": 150
    },
    {
      "epoch": 0.16581973789783364,
      "grad_norm": 0.5409214496612549,
      "learning_rate": 0.000192920232038144,
      "loss": 0.7282,
      "step": 155
    },
    {
      "epoch": 0.17116876170098957,
      "grad_norm": 0.6080542206764221,
      "learning_rate": 0.0001922519884832469,
      "loss": 0.8597,
      "step": 160
    },
    {
      "epoch": 0.17651778550414549,
      "grad_norm": 0.650615930557251,
      "learning_rate": 0.00019155487948487748,
      "loss": 0.4898,
      "step": 165
    },
    {
      "epoch": 0.18186680930730142,
      "grad_norm": 0.5822589993476868,
      "learning_rate": 0.0001908291231669019,
      "loss": 0.6313,
      "step": 170
    },
    {
      "epoch": 0.18721583311045734,
      "grad_norm": 0.5433451533317566,
      "learning_rate": 0.00019007494661686935,
      "loss": 0.5673,
      "step": 175
    },
    {
      "epoch": 0.19256485691361327,
      "grad_norm": 0.6697724461555481,
      "learning_rate": 0.00018929258581495685,
      "loss": 0.5888,
      "step": 180
    },
    {
      "epoch": 0.19791388071676919,
      "grad_norm": 0.7195097208023071,
      "learning_rate": 0.0001884822855601316,
      "loss": 0.5925,
      "step": 185
    },
    {
      "epoch": 0.20326290451992512,
      "grad_norm": 0.704847514629364,
      "learning_rate": 0.00018764429939355392,
      "loss": 0.6258,
      "step": 190
    },
    {
      "epoch": 0.20861192832308104,
      "grad_norm": 0.7211595177650452,
      "learning_rate": 0.00018677888951924474,
      "loss": 0.6023,
      "step": 195
    },
    {
      "epoch": 0.21396095212623698,
      "grad_norm": 0.5733616948127747,
      "learning_rate": 0.00018588632672204264,
      "loss": 0.4632,
      "step": 200
    },
    {
      "epoch": 0.21396095212623698,
      "eval_loss": 0.4046805799007416,
      "eval_runtime": 112.0258,
      "eval_samples_per_second": 3.428,
      "eval_steps_per_second": 1.714,
      "step": 200
    },
    {
      "epoch": 0.2193099759293929,
      "grad_norm": 0.6266054511070251,
      "learning_rate": 0.00018496689028287572,
      "loss": 0.6243,
      "step": 205
    },
    {
      "epoch": 0.2246589997325488,
      "grad_norm": 0.4841332733631134,
      "learning_rate": 0.00018402086789137546,
      "loss": 0.6397,
      "step": 210
    },
    {
      "epoch": 0.23000802353570474,
      "grad_norm": 0.566580057144165,
      "learning_rate": 0.00018304855555585894,
      "loss": 0.5517,
      "step": 215
    },
    {
      "epoch": 0.23535704733886065,
      "grad_norm": 0.411471426486969,
      "learning_rate": 0.00018205025751070875,
      "loss": 0.5346,
      "step": 220
    },
    {
      "epoch": 0.2407060711420166,
      "grad_norm": 0.48397207260131836,
      "learning_rate": 0.00018102628612117865,
      "loss": 0.3205,
      "step": 225
    },
    {
      "epoch": 0.2460550949451725,
      "grad_norm": 0.6768320798873901,
      "learning_rate": 0.0001799769617856552,
      "loss": 0.6892,
      "step": 230
    },
    {
      "epoch": 0.2514041187483284,
      "grad_norm": 0.6652664542198181,
      "learning_rate": 0.00017890261283540562,
      "loss": 0.541,
      "step": 235
    },
    {
      "epoch": 0.25675314255148435,
      "grad_norm": 0.4666398763656616,
      "learning_rate": 0.00017780357543184397,
      "loss": 0.4365,
      "step": 240
    },
    {
      "epoch": 0.2621021663546403,
      "grad_norm": 0.5831547975540161,
      "learning_rate": 0.0001766801934613467,
      "loss": 0.598,
      "step": 245
    },
    {
      "epoch": 0.2674511901577962,
      "grad_norm": 0.5607553124427795,
      "learning_rate": 0.00017553281842765169,
      "loss": 0.5548,
      "step": 250
    },
    {
      "epoch": 0.2674511901577962,
      "eval_loss": 0.3891582489013672,
      "eval_runtime": 111.8073,
      "eval_samples_per_second": 3.434,
      "eval_steps_per_second": 1.717,
      "step": 250
    },
    {
      "epoch": 0.2728002139609521,
      "grad_norm": 0.5996724367141724,
      "learning_rate": 0.00017436180934187308,
      "loss": 0.4506,
      "step": 255
    },
    {
      "epoch": 0.27814923776410805,
      "grad_norm": 0.5043736100196838,
      "learning_rate": 0.00017316753261016783,
      "loss": 0.526,
      "step": 260
    },
    {
      "epoch": 0.283498261567264,
      "grad_norm": 0.5816839337348938,
      "learning_rate": 0.00017195036191908797,
      "loss": 0.3911,
      "step": 265
    },
    {
      "epoch": 0.28884728537041987,
      "grad_norm": 0.5987787842750549,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.6858,
      "step": 270
    },
    {
      "epoch": 0.2941963091735758,
      "grad_norm": 0.5184270739555359,
      "learning_rate": 0.00016944886910319173,
      "loss": 0.5402,
      "step": 275
    },
    {
      "epoch": 0.29954533297673175,
      "grad_norm": 0.7627037763595581,
      "learning_rate": 0.00016816532968995328,
      "loss": 0.6015,
      "step": 280
    },
    {
      "epoch": 0.3048943567798877,
      "grad_norm": 0.572108805179596,
      "learning_rate": 0.00016686046149558736,
      "loss": 0.4313,
      "step": 285
    },
    {
      "epoch": 0.31024338058304357,
      "grad_norm": 0.5677588582038879,
      "learning_rate": 0.0001655346728104704,
      "loss": 0.475,
      "step": 290
    },
    {
      "epoch": 0.3155924043861995,
      "grad_norm": 0.5855934619903564,
      "learning_rate": 0.0001641883784709541,
      "loss": 0.6212,
      "step": 295
    },
    {
      "epoch": 0.32094142818935545,
      "grad_norm": 0.5541160106658936,
      "learning_rate": 0.00016282199972956425,
      "loss": 0.6327,
      "step": 300
    },
    {
      "epoch": 0.32094142818935545,
      "eval_loss": 0.37665891647338867,
      "eval_runtime": 111.5698,
      "eval_samples_per_second": 3.442,
      "eval_steps_per_second": 1.721,
      "step": 300
    }
  ],
  "logging_steps": 5,
  "max_steps": 935,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.001
      },
      "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": 8.51144340450558e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}