{
  "best_global_step": 300,
  "best_metric": 0.2526017129421234,
  "best_model_checkpoint": "/workspace/anchor/olmo-urban-web-s1/train/checkpoint-300",
  "epoch": 0.32064128256513025,
  "eval_steps": 50,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005344021376085505,
      "grad_norm": 1.4617443084716797,
      "learning_rate": 1.7021276595744682e-05,
      "loss": 1.0758,
      "step": 5
    },
    {
      "epoch": 0.01068804275217101,
      "grad_norm": 1.6716994047164917,
      "learning_rate": 3.829787234042553e-05,
      "loss": 1.1134,
      "step": 10
    },
    {
      "epoch": 0.01603206412825651,
      "grad_norm": 1.0386888980865479,
      "learning_rate": 5.9574468085106384e-05,
      "loss": 0.9629,
      "step": 15
    },
    {
      "epoch": 0.02137608550434202,
      "grad_norm": 0.9053958654403687,
      "learning_rate": 8.085106382978723e-05,
      "loss": 0.7759,
      "step": 20
    },
    {
      "epoch": 0.026720106880427523,
      "grad_norm": 1.0113734006881714,
      "learning_rate": 0.00010212765957446809,
      "loss": 0.8132,
      "step": 25
    },
    {
      "epoch": 0.03206412825651302,
      "grad_norm": 1.6664739847183228,
      "learning_rate": 0.00012340425531914893,
      "loss": 0.589,
      "step": 30
    },
    {
      "epoch": 0.03740814963259853,
      "grad_norm": 1.371498942375183,
      "learning_rate": 0.0001446808510638298,
      "loss": 0.5526,
      "step": 35
    },
    {
      "epoch": 0.04275217100868404,
      "grad_norm": 1.5877903699874878,
      "learning_rate": 0.00016595744680851065,
      "loss": 0.601,
      "step": 40
    },
    {
      "epoch": 0.04809619238476954,
      "grad_norm": 1.66953444480896,
      "learning_rate": 0.0001872340425531915,
      "loss": 0.6285,
      "step": 45
    },
    {
      "epoch": 0.053440213760855046,
      "grad_norm": 1.1356960535049438,
      "learning_rate": 0.00019999750239122662,
      "loss": 0.5928,
      "step": 50
    },
    {
      "epoch": 0.053440213760855046,
      "eval_loss": 0.35381627082824707,
      "eval_runtime": 185.2576,
      "eval_samples_per_second": 2.073,
      "eval_steps_per_second": 1.036,
      "step": 50
    },
    {
      "epoch": 0.058784235136940546,
      "grad_norm": 1.224514365196228,
      "learning_rate": 0.0001999694057253083,
      "loss": 0.5057,
      "step": 55
    },
    {
      "epoch": 0.06412825651302605,
      "grad_norm": 1.0710302591323853,
      "learning_rate": 0.00019991009918336413,
      "loss": 0.5798,
      "step": 60
    },
    {
      "epoch": 0.06947227788911156,
      "grad_norm": 0.8703950643539429,
      "learning_rate": 0.00019981960128055687,
      "loss": 0.6109,
      "step": 65
    },
    {
      "epoch": 0.07481629926519706,
      "grad_norm": 0.6615566611289978,
      "learning_rate": 0.0001996979402698136,
      "loss": 0.7009,
      "step": 70
    },
    {
      "epoch": 0.08016032064128256,
      "grad_norm": 0.722378671169281,
      "learning_rate": 0.00019954515413300516,
      "loss": 0.5366,
      "step": 75
    },
    {
      "epoch": 0.08550434201736808,
      "grad_norm": 0.5970469117164612,
      "learning_rate": 0.00019936129056908865,
      "loss": 0.5127,
      "step": 80
    },
    {
      "epoch": 0.09084836339345358,
      "grad_norm": 0.7550004720687866,
      "learning_rate": 0.00019914640697921585,
      "loss": 0.39,
      "step": 85
    },
    {
      "epoch": 0.09619238476953908,
      "grad_norm": 0.6147840023040771,
      "learning_rate": 0.00019890057044881306,
      "loss": 0.4667,
      "step": 90
    },
    {
      "epoch": 0.10153640614562458,
      "grad_norm": 0.5167994499206543,
      "learning_rate": 0.0001986238577266374,
      "loss": 0.5543,
      "step": 95
    },
    {
      "epoch": 0.10688042752171009,
      "grad_norm": 0.6303970217704773,
      "learning_rate": 0.00019831635520081625,
      "loss": 0.395,
      "step": 100
    },
    {
      "epoch": 0.10688042752171009,
      "eval_loss": 0.28593334555625916,
      "eval_runtime": 175.6975,
      "eval_samples_per_second": 2.186,
      "eval_steps_per_second": 1.093,
      "step": 100
    },
    {
      "epoch": 0.11222444889779559,
      "grad_norm": 0.523565411567688,
      "learning_rate": 0.00019797815887187726,
      "loss": 0.6554,
      "step": 105
    },
    {
      "epoch": 0.11756847027388109,
      "grad_norm": 0.6083654165267944,
      "learning_rate": 0.00019760937432277786,
      "loss": 0.6498,
      "step": 110
    },
    {
      "epoch": 0.1229124916499666,
      "grad_norm": 0.608196496963501,
      "learning_rate": 0.0001972101166859425,
      "loss": 0.3087,
      "step": 115
    },
    {
      "epoch": 0.1282565130260521,
      "grad_norm": 0.5090125799179077,
      "learning_rate": 0.0001967805106073192,
      "loss": 0.4591,
      "step": 120
    },
    {
      "epoch": 0.13360053440213762,
      "grad_norm": 0.5765124559402466,
      "learning_rate": 0.00019632069020746572,
      "loss": 0.4734,
      "step": 125
    },
    {
      "epoch": 0.13894455577822312,
      "grad_norm": 0.5430421829223633,
      "learning_rate": 0.00019583079903967785,
      "loss": 0.6134,
      "step": 130
    },
    {
      "epoch": 0.14428857715430862,
      "grad_norm": 0.5796396732330322,
      "learning_rate": 0.000195310990045173,
      "loss": 0.5722,
      "step": 135
    },
    {
      "epoch": 0.14963259853039412,
      "grad_norm": 0.40826624631881714,
      "learning_rate": 0.0001947614255053428,
      "loss": 0.5951,
      "step": 140
    },
    {
      "epoch": 0.15497661990647962,
      "grad_norm": 0.6580771207809448,
      "learning_rate": 0.00019418227699108956,
      "loss": 0.4965,
      "step": 145
    },
    {
      "epoch": 0.16032064128256512,
      "grad_norm": 0.4422876834869385,
      "learning_rate": 0.00019357372530926322,
      "loss": 0.4078,
      "step": 150
    },
    {
      "epoch": 0.16032064128256512,
      "eval_loss": 0.268439918756485,
      "eval_runtime": 177.0304,
      "eval_samples_per_second": 2.169,
      "eval_steps_per_second": 1.085,
      "step": 150
    },
    {
      "epoch": 0.16566466265865062,
      "grad_norm": 0.38482171297073364,
      "learning_rate": 0.00019293596044621416,
      "loss": 0.4386,
      "step": 155
    },
    {
      "epoch": 0.17100868403473615,
      "grad_norm": 0.5199833512306213,
      "learning_rate": 0.00019226918150848068,
      "loss": 0.5075,
      "step": 160
    },
    {
      "epoch": 0.17635270541082165,
      "grad_norm": 0.5420163869857788,
      "learning_rate": 0.00019157359666062903,
      "loss": 0.5338,
      "step": 165
    },
    {
      "epoch": 0.18169672678690715,
      "grad_norm": 0.5685029625892639,
      "learning_rate": 0.00019084942306026568,
      "loss": 0.4238,
      "step": 170
    },
    {
      "epoch": 0.18704074816299265,
      "grad_norm": 0.7327029705047607,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.54,
      "step": 175
    },
    {
      "epoch": 0.19238476953907815,
      "grad_norm": 0.4946307837963104,
      "learning_rate": 0.00018931622278807212,
      "loss": 0.4307,
      "step": 180
    },
    {
      "epoch": 0.19772879091516365,
      "grad_norm": 0.55298912525177,
      "learning_rate": 0.00018850767477258753,
      "loss": 0.5265,
      "step": 185
    },
    {
      "epoch": 0.20307281229124916,
      "grad_norm": 0.35687363147735596,
      "learning_rate": 0.00018767149516784874,
      "loss": 0.3356,
      "step": 190
    },
    {
      "epoch": 0.20841683366733466,
      "grad_norm": 0.41278213262557983,
      "learning_rate": 0.00018680794502434018,
      "loss": 0.2975,
      "step": 195
    },
    {
      "epoch": 0.21376085504342018,
      "grad_norm": 0.5663429498672485,
      "learning_rate": 0.00018591729393747187,
      "loss": 0.5197,
      "step": 200
    },
    {
      "epoch": 0.21376085504342018,
      "eval_loss": 0.2623557150363922,
      "eval_runtime": 177.0995,
      "eval_samples_per_second": 2.168,
      "eval_steps_per_second": 1.084,
      "step": 200
    },
    {
      "epoch": 0.21910487641950568,
      "grad_norm": 0.5710906386375427,
      "learning_rate": 0.0001849998199634131,
      "loss": 0.5684,
      "step": 205
    },
    {
      "epoch": 0.22444889779559118,
      "grad_norm": 0.4171600639820099,
      "learning_rate": 0.00018405580953228493,
      "loss": 0.4445,
      "step": 210
    },
    {
      "epoch": 0.22979291917167669,
      "grad_norm": 0.5666216611862183,
      "learning_rate": 0.00018308555735873844,
      "loss": 0.5581,
      "step": 215
    },
    {
      "epoch": 0.23513694054776219,
      "grad_norm": 0.380841463804245,
      "learning_rate": 0.0001820893663499464,
      "loss": 0.3777,
      "step": 220
    },
    {
      "epoch": 0.24048096192384769,
      "grad_norm": 0.4977319836616516,
      "learning_rate": 0.00018106754751103735,
      "loss": 0.4253,
      "step": 225
    },
    {
      "epoch": 0.2458249832999332,
      "grad_norm": 0.5510649085044861,
      "learning_rate": 0.00018002041984800174,
      "loss": 0.3551,
      "step": 230
    },
    {
      "epoch": 0.2511690046760187,
      "grad_norm": 0.5505735874176025,
      "learning_rate": 0.00017894831026809985,
      "loss": 0.4329,
      "step": 235
    },
    {
      "epoch": 0.2565130260521042,
      "grad_norm": 0.4923292398452759,
      "learning_rate": 0.00017785155347780352,
      "loss": 0.4755,
      "step": 240
    },
    {
      "epoch": 0.2618570474281897,
      "grad_norm": 0.3667859733104706,
      "learning_rate": 0.00017673049187830252,
      "loss": 0.3059,
      "step": 245
    },
    {
      "epoch": 0.26720106880427524,
      "grad_norm": 0.6907548308372498,
      "learning_rate": 0.00017558547545860868,
      "loss": 0.5768,
      "step": 250
    },
    {
      "epoch": 0.26720106880427524,
      "eval_loss": 0.25615957379341125,
      "eval_runtime": 177.8601,
      "eval_samples_per_second": 2.159,
      "eval_steps_per_second": 1.08,
      "step": 250
    },
    {
      "epoch": 0.2725450901803607,
      "grad_norm": 0.5314492583274841,
      "learning_rate": 0.0001744168616862918,
      "loss": 0.5453,
      "step": 255
    },
    {
      "epoch": 0.27788911155644624,
      "grad_norm": 0.5275250673294067,
      "learning_rate": 0.00017322501539587988,
      "loss": 0.6083,
      "step": 260
    },
    {
      "epoch": 0.2832331329325317,
      "grad_norm": 0.5360549688339233,
      "learning_rate": 0.00017201030867496005,
      "loss": 0.5318,
      "step": 265
    },
    {
      "epoch": 0.28857715430861725,
      "grad_norm": 0.5346860289573669,
      "learning_rate": 0.00017077312074801498,
      "loss": 0.476,
      "step": 270
    },
    {
      "epoch": 0.2939211756847027,
      "grad_norm": 0.618037223815918,
      "learning_rate": 0.00016951383785803115,
      "loss": 0.5626,
      "step": 275
    },
    {
      "epoch": 0.29926519706078825,
      "grad_norm": 0.6231545805931091,
      "learning_rate": 0.00016823285314591593,
      "loss": 0.5372,
      "step": 280
    },
    {
      "epoch": 0.3046092184368738,
      "grad_norm": 0.5328637361526489,
      "learning_rate": 0.00016693056652776126,
      "loss": 0.5355,
      "step": 285
    },
    {
      "epoch": 0.30995323981295925,
      "grad_norm": 0.4961908459663391,
      "learning_rate": 0.00016560738456999232,
      "loss": 0.2616,
      "step": 290
    },
    {
      "epoch": 0.3152972611890448,
      "grad_norm": 0.5630390644073486,
      "learning_rate": 0.00016426372036243945,
      "loss": 0.4521,
      "step": 295
    },
    {
      "epoch": 0.32064128256513025,
      "grad_norm": 0.5601023435592651,
      "learning_rate": 0.00016289999338937427,
      "loss": 0.4487,
      "step": 300
    },
    {
      "epoch": 0.32064128256513025,
      "eval_loss": 0.2526017129421234,
      "eval_runtime": 175.8477,
      "eval_samples_per_second": 2.184,
      "eval_steps_per_second": 1.092,
      "step": 300
    }
  ],
  "logging_steps": 5,
  "max_steps": 936,
  "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": 8.163962850308751e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}