{
  "best_global_step": 1313,
  "best_metric": 0.512985110282898,
  "best_model_checkpoint": "outputs_v3/checkpoint-1313",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1313,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007618322064565279,
      "grad_norm": 1.4868226051330566,
      "learning_rate": 0.0,
      "loss": 2.9396,
      "step": 1
    },
    {
      "epoch": 0.019045805161413198,
      "grad_norm": 1.2571601867675781,
      "learning_rate": 1.008403361344538e-05,
      "loss": 2.7963,
      "step": 25
    },
    {
      "epoch": 0.038091610322826396,
      "grad_norm": 0.6987431645393372,
      "learning_rate": 2.058823529411765e-05,
      "loss": 2.1442,
      "step": 50
    },
    {
      "epoch": 0.0571374154842396,
      "grad_norm": 0.3330633044242859,
      "learning_rate": 3.1092436974789916e-05,
      "loss": 1.1326,
      "step": 75
    },
    {
      "epoch": 0.07618322064565279,
      "grad_norm": 0.23947548866271973,
      "learning_rate": 4.159663865546219e-05,
      "loss": 0.7952,
      "step": 100
    },
    {
      "epoch": 0.09522902580706599,
      "grad_norm": 0.3273511528968811,
      "learning_rate": 4.9999788640180545e-05,
      "loss": 0.6819,
      "step": 125
    },
    {
      "epoch": 0.1142748309684792,
      "grad_norm": 0.1918083131313324,
      "learning_rate": 4.999239142174581e-05,
      "loss": 0.6792,
      "step": 150
    },
    {
      "epoch": 0.1333206361298924,
      "grad_norm": 0.22439052164554596,
      "learning_rate": 4.9974429785904524e-05,
      "loss": 0.6258,
      "step": 175
    },
    {
      "epoch": 0.15236644129130558,
      "grad_norm": 0.24658527970314026,
      "learning_rate": 4.994591132513616e-05,
      "loss": 0.6512,
      "step": 200
    },
    {
      "epoch": 0.1714122464527188,
      "grad_norm": 0.24695466458797455,
      "learning_rate": 4.990684809434646e-05,
      "loss": 0.6244,
      "step": 225
    },
    {
      "epoch": 0.19045805161413198,
      "grad_norm": 0.26622363924980164,
      "learning_rate": 4.985725660577184e-05,
      "loss": 0.5796,
      "step": 250
    },
    {
      "epoch": 0.2095038567755452,
      "grad_norm": 0.2716868817806244,
      "learning_rate": 4.979715782199951e-05,
      "loss": 0.6268,
      "step": 275
    },
    {
      "epoch": 0.2285496619369584,
      "grad_norm": 0.2595020830631256,
      "learning_rate": 4.972657714710653e-05,
      "loss": 0.5945,
      "step": 300
    },
    {
      "epoch": 0.24759546709837157,
      "grad_norm": 0.26612213253974915,
      "learning_rate": 4.9645544415921344e-05,
      "loss": 0.5592,
      "step": 325
    },
    {
      "epoch": 0.2666412722597848,
      "grad_norm": 0.24327930808067322,
      "learning_rate": 4.955409388141243e-05,
      "loss": 0.631,
      "step": 350
    },
    {
      "epoch": 0.285687077421198,
      "grad_norm": 0.2701154947280884,
      "learning_rate": 4.9452264200209426e-05,
      "loss": 0.569,
      "step": 375
    },
    {
      "epoch": 0.30473288258261116,
      "grad_norm": 0.2970716953277588,
      "learning_rate": 4.9340098416262714e-05,
      "loss": 0.5791,
      "step": 400
    },
    {
      "epoch": 0.32377868774402435,
      "grad_norm": 0.26807665824890137,
      "learning_rate": 4.921764394264855e-05,
      "loss": 0.5411,
      "step": 425
    },
    {
      "epoch": 0.3428244929054376,
      "grad_norm": 0.2829282283782959,
      "learning_rate": 4.908495254152731e-05,
      "loss": 0.5746,
      "step": 450
    },
    {
      "epoch": 0.3618702980668508,
      "grad_norm": 0.3086259961128235,
      "learning_rate": 4.8942080302263306e-05,
      "loss": 0.5579,
      "step": 475
    },
    {
      "epoch": 0.38091610322826397,
      "grad_norm": 0.2836249768733978,
      "learning_rate": 4.878908761771554e-05,
      "loss": 0.5702,
      "step": 500
    },
    {
      "epoch": 0.39996190838967716,
      "grad_norm": 0.31077441573143005,
      "learning_rate": 4.862603915870933e-05,
      "loss": 0.542,
      "step": 525
    },
    {
      "epoch": 0.4190077135510904,
      "grad_norm": 0.25948625802993774,
      "learning_rate": 4.845300384669958e-05,
      "loss": 0.5407,
      "step": 550
    },
    {
      "epoch": 0.4380535187125036,
      "grad_norm": 0.26232826709747314,
      "learning_rate": 4.827005482463733e-05,
      "loss": 0.5419,
      "step": 575
    },
    {
      "epoch": 0.4570993238739168,
      "grad_norm": 0.31146982312202454,
      "learning_rate": 4.807726942605184e-05,
      "loss": 0.5637,
      "step": 600
    },
    {
      "epoch": 0.47614512903532996,
      "grad_norm": 0.2727930247783661,
      "learning_rate": 4.7874729142361285e-05,
      "loss": 0.5695,
      "step": 625
    },
    {
      "epoch": 0.49519093419674315,
      "grad_norm": 0.2699703872203827,
      "learning_rate": 4.76625195884259e-05,
      "loss": 0.5232,
      "step": 650
    },
    {
      "epoch": 0.5142367393581564,
      "grad_norm": 0.29125288128852844,
      "learning_rate": 4.7440730466358116e-05,
      "loss": 0.5954,
      "step": 675
    },
    {
      "epoch": 0.5332825445195696,
      "grad_norm": 0.2931804060935974,
      "learning_rate": 4.720945552760503e-05,
      "loss": 0.5733,
      "step": 700
    },
    {
      "epoch": 0.5523283496809828,
      "grad_norm": 0.298470139503479,
      "learning_rate": 4.69687925333191e-05,
      "loss": 0.5817,
      "step": 725
    },
    {
      "epoch": 0.571374154842396,
      "grad_norm": 0.2937164306640625,
      "learning_rate": 4.6718843213034067e-05,
      "loss": 0.5482,
      "step": 750
    },
    {
      "epoch": 0.5904199600038091,
      "grad_norm": 0.31254154443740845,
      "learning_rate": 4.645971322166327e-05,
      "loss": 0.5594,
      "step": 775
    },
    {
      "epoch": 0.6094657651652223,
      "grad_norm": 0.2997235953807831,
      "learning_rate": 4.619151209483878e-05,
      "loss": 0.5867,
      "step": 800
    },
    {
      "epoch": 0.6285115703266355,
      "grad_norm": 0.3079950213432312,
      "learning_rate": 4.591435320261011e-05,
      "loss": 0.5839,
      "step": 825
    },
    {
      "epoch": 0.6475573754880487,
      "grad_norm": 0.2768675982952118,
      "learning_rate": 4.5628353701522055e-05,
      "loss": 0.5709,
      "step": 850
    },
    {
      "epoch": 0.666603180649462,
      "grad_norm": 0.2898074686527252,
      "learning_rate": 4.533363448509204e-05,
      "loss": 0.5604,
      "step": 875
    },
    {
      "epoch": 0.6856489858108752,
      "grad_norm": 0.3034629225730896,
      "learning_rate": 4.503032013270774e-05,
      "loss": 0.527,
      "step": 900
    },
    {
      "epoch": 0.7046947909722884,
      "grad_norm": 0.3099200129508972,
      "learning_rate": 4.471853885696673e-05,
      "loss": 0.5484,
      "step": 925
    },
    {
      "epoch": 0.7237405961337016,
      "grad_norm": 0.27591314911842346,
      "learning_rate": 4.4398422449480356e-05,
      "loss": 0.539,
      "step": 950
    },
    {
      "epoch": 0.7427864012951148,
      "grad_norm": 0.297590434551239,
      "learning_rate": 4.407010622516469e-05,
      "loss": 0.5427,
      "step": 975
    },
    {
      "epoch": 0.7618322064565279,
      "grad_norm": 0.2939580976963043,
      "learning_rate": 4.373372896504215e-05,
      "loss": 0.5544,
      "step": 1000
    },
    {
      "epoch": 0.7808780116179411,
      "grad_norm": 0.3100650906562805,
      "learning_rate": 4.338943285757812e-05,
      "loss": 0.5418,
      "step": 1025
    },
    {
      "epoch": 0.7999238167793543,
      "grad_norm": 0.31046804785728455,
      "learning_rate": 4.303736343857704e-05,
      "loss": 0.5492,
      "step": 1050
    },
    {
      "epoch": 0.8189696219407675,
      "grad_norm": 0.31424999237060547,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.5501,
      "step": 1075
    },
    {
      "epoch": 0.8380154271021808,
      "grad_norm": 0.3023451268672943,
      "learning_rate": 4.2310503175375484e-05,
      "loss": 0.5701,
      "step": 1100
    },
    {
      "epoch": 0.857061232263594,
      "grad_norm": 0.2925208806991577,
      "learning_rate": 4.1936019578892394e-05,
      "loss": 0.5296,
      "step": 1125
    },
    {
      "epoch": 0.8761070374250072,
      "grad_norm": 0.2963685691356659,
      "learning_rate": 4.1554377036431816e-05,
      "loss": 0.5826,
      "step": 1150
    },
    {
      "epoch": 0.8951528425864204,
      "grad_norm": 0.30757901072502136,
      "learning_rate": 4.116573687033583e-05,
      "loss": 0.5844,
      "step": 1175
    },
    {
      "epoch": 0.9141986477478335,
      "grad_norm": 0.3231395184993744,
      "learning_rate": 4.0770263360879435e-05,
      "loss": 0.5727,
      "step": 1200
    },
    {
      "epoch": 0.9332444529092467,
      "grad_norm": 0.29189741611480713,
      "learning_rate": 4.0368123676828385e-05,
      "loss": 0.5553,
      "step": 1225
    },
    {
      "epoch": 0.9522902580706599,
      "grad_norm": 0.3302098512649536,
      "learning_rate": 3.995948780477605e-05,
      "loss": 0.5463,
      "step": 1250
    },
    {
      "epoch": 0.9713360632320731,
      "grad_norm": 0.340754896402359,
      "learning_rate": 3.954452847728919e-05,
      "loss": 0.5442,
      "step": 1275
    },
    {
      "epoch": 0.9903818683934863,
      "grad_norm": 0.302099347114563,
      "learning_rate": 3.912342109989296e-05,
      "loss": 0.5517,
      "step": 1300
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.512985110282898,
      "eval_runtime": 190.5141,
      "eval_samples_per_second": 19.458,
      "eval_steps_per_second": 4.866,
      "step": 1313
    }
  ],
  "logging_steps": 25,
  "max_steps": 3939,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "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": 2.450179662830715e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}