{
  "best_global_step": 10000,
  "best_metric": 0.024344714358448982,
  "best_model_checkpoint": "/cluster/project/sachan/heejin/RaDME/Arts_t5_f0/checkpoint-10000",
  "epoch": 12.846865364850977,
  "eval_steps": 5000,
  "global_step": 25000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2569373072970195,
      "grad_norm": 0.17562313377857208,
      "learning_rate": 4.9150306643368624e-05,
      "loss": 0.5717,
      "step": 500
    },
    {
      "epoch": 0.513874614594039,
      "grad_norm": 0.10371646285057068,
      "learning_rate": 4.8293760920957963e-05,
      "loss": 0.0339,
      "step": 1000
    },
    {
      "epoch": 0.7708119218910586,
      "grad_norm": 0.14652925729751587,
      "learning_rate": 4.74372151985473e-05,
      "loss": 0.0318,
      "step": 1500
    },
    {
      "epoch": 1.027749229188078,
      "grad_norm": 0.13600969314575195,
      "learning_rate": 4.658066947613664e-05,
      "loss": 0.0311,
      "step": 2000
    },
    {
      "epoch": 1.2846865364850977,
      "grad_norm": 0.0706079825758934,
      "learning_rate": 4.572412375372598e-05,
      "loss": 0.0295,
      "step": 2500
    },
    {
      "epoch": 1.541623843782117,
      "grad_norm": 1.7536998987197876,
      "learning_rate": 4.486757803131531e-05,
      "loss": 0.0315,
      "step": 3000
    },
    {
      "epoch": 1.7985611510791366,
      "grad_norm": 0.10474766790866852,
      "learning_rate": 4.401103230890465e-05,
      "loss": 0.029,
      "step": 3500
    },
    {
      "epoch": 2.055498458376156,
      "grad_norm": 0.549686849117279,
      "learning_rate": 4.315448658649399e-05,
      "loss": 0.0284,
      "step": 4000
    },
    {
      "epoch": 2.3124357656731758,
      "grad_norm": 0.09790255129337311,
      "learning_rate": 4.2297940864083324e-05,
      "loss": 0.0283,
      "step": 4500
    },
    {
      "epoch": 2.5693730729701953,
      "grad_norm": 0.09890051931142807,
      "learning_rate": 4.144139514167266e-05,
      "loss": 0.0269,
      "step": 5000
    },
    {
      "epoch": 2.5693730729701953,
      "eval_loss": 0.02565159648656845,
      "eval_runtime": 178.3077,
      "eval_samples_per_second": 14.542,
      "eval_steps_per_second": 3.64,
      "step": 5000
    },
    {
      "epoch": 2.826310380267215,
      "grad_norm": 0.10465002059936523,
      "learning_rate": 4.0584849419262e-05,
      "loss": 0.0266,
      "step": 5500
    },
    {
      "epoch": 3.0832476875642345,
      "grad_norm": 0.10655808448791504,
      "learning_rate": 3.9728303696851334e-05,
      "loss": 0.0266,
      "step": 6000
    },
    {
      "epoch": 3.3401849948612536,
      "grad_norm": 0.09030739963054657,
      "learning_rate": 3.8871757974440674e-05,
      "loss": 0.0257,
      "step": 6500
    },
    {
      "epoch": 3.597122302158273,
      "grad_norm": 0.077540323138237,
      "learning_rate": 3.801521225203001e-05,
      "loss": 0.0247,
      "step": 7000
    },
    {
      "epoch": 3.854059609455293,
      "grad_norm": 0.17392417788505554,
      "learning_rate": 3.715866652961935e-05,
      "loss": 0.0256,
      "step": 7500
    },
    {
      "epoch": 4.110996916752312,
      "grad_norm": 0.3808821141719818,
      "learning_rate": 3.630212080720869e-05,
      "loss": 0.0245,
      "step": 8000
    },
    {
      "epoch": 4.367934224049332,
      "grad_norm": 0.07896172255277634,
      "learning_rate": 3.544557508479803e-05,
      "loss": 0.0239,
      "step": 8500
    },
    {
      "epoch": 4.6248715313463515,
      "grad_norm": 0.08702714741230011,
      "learning_rate": 3.458902936238736e-05,
      "loss": 0.0238,
      "step": 9000
    },
    {
      "epoch": 4.881808838643371,
      "grad_norm": 0.10166553407907486,
      "learning_rate": 3.37324836399767e-05,
      "loss": 0.0238,
      "step": 9500
    },
    {
      "epoch": 5.138746145940391,
      "grad_norm": 0.11367424577474594,
      "learning_rate": 3.287593791756604e-05,
      "loss": 0.0227,
      "step": 10000
    },
    {
      "epoch": 5.138746145940391,
      "eval_loss": 0.024344714358448982,
      "eval_runtime": 178.7234,
      "eval_samples_per_second": 14.508,
      "eval_steps_per_second": 3.631,
      "step": 10000
    },
    {
      "epoch": 5.39568345323741,
      "grad_norm": 0.06953849643468857,
      "learning_rate": 3.201939219515538e-05,
      "loss": 0.0222,
      "step": 10500
    },
    {
      "epoch": 5.65262076053443,
      "grad_norm": 0.14536646008491516,
      "learning_rate": 3.116284647274472e-05,
      "loss": 0.0217,
      "step": 11000
    },
    {
      "epoch": 5.909558067831449,
      "grad_norm": 0.1506756693124771,
      "learning_rate": 3.0306300750334055e-05,
      "loss": 0.0221,
      "step": 11500
    },
    {
      "epoch": 6.166495375128469,
      "grad_norm": 0.07476528733968735,
      "learning_rate": 2.9449755027923394e-05,
      "loss": 0.0217,
      "step": 12000
    },
    {
      "epoch": 6.423432682425489,
      "grad_norm": 0.11400212347507477,
      "learning_rate": 2.859320930551273e-05,
      "loss": 0.0208,
      "step": 12500
    },
    {
      "epoch": 6.680369989722507,
      "grad_norm": 0.07216424494981766,
      "learning_rate": 2.773666358310207e-05,
      "loss": 0.0204,
      "step": 13000
    },
    {
      "epoch": 6.937307297019527,
      "grad_norm": 0.12992289662361145,
      "learning_rate": 2.6880117860691405e-05,
      "loss": 0.02,
      "step": 13500
    },
    {
      "epoch": 7.194244604316546,
      "grad_norm": 0.06588713079690933,
      "learning_rate": 2.6023572138280744e-05,
      "loss": 0.0191,
      "step": 14000
    },
    {
      "epoch": 7.451181911613566,
      "grad_norm": 0.1124558374285698,
      "learning_rate": 2.5167026415870083e-05,
      "loss": 0.0186,
      "step": 14500
    },
    {
      "epoch": 7.708119218910586,
      "grad_norm": 0.11662375181913376,
      "learning_rate": 2.431048069345942e-05,
      "loss": 0.0188,
      "step": 15000
    },
    {
      "epoch": 7.708119218910586,
      "eval_loss": 0.027120616286993027,
      "eval_runtime": 179.5611,
      "eval_samples_per_second": 14.441,
      "eval_steps_per_second": 3.614,
      "step": 15000
    },
    {
      "epoch": 7.965056526207605,
      "grad_norm": 0.05247975140810013,
      "learning_rate": 2.3453934971048754e-05,
      "loss": 0.0185,
      "step": 15500
    },
    {
      "epoch": 8.221993833504625,
      "grad_norm": 0.1325894296169281,
      "learning_rate": 2.2597389248638093e-05,
      "loss": 0.0167,
      "step": 16000
    },
    {
      "epoch": 8.478931140801645,
      "grad_norm": 0.1109691709280014,
      "learning_rate": 2.174084352622743e-05,
      "loss": 0.0171,
      "step": 16500
    },
    {
      "epoch": 8.735868448098664,
      "grad_norm": 0.1451205462217331,
      "learning_rate": 2.088429780381677e-05,
      "loss": 0.0167,
      "step": 17000
    },
    {
      "epoch": 8.992805755395683,
      "grad_norm": 0.18753716349601746,
      "learning_rate": 2.0027752081406107e-05,
      "loss": 0.0176,
      "step": 17500
    },
    {
      "epoch": 9.249743062692703,
      "grad_norm": 0.3178722858428955,
      "learning_rate": 1.9171206358995443e-05,
      "loss": 0.0151,
      "step": 18000
    },
    {
      "epoch": 9.506680369989722,
      "grad_norm": 0.23986810445785522,
      "learning_rate": 1.8314660636584782e-05,
      "loss": 0.0156,
      "step": 18500
    },
    {
      "epoch": 9.763617677286742,
      "grad_norm": 0.1744610071182251,
      "learning_rate": 1.745811491417412e-05,
      "loss": 0.0154,
      "step": 19000
    },
    {
      "epoch": 10.020554984583761,
      "grad_norm": 0.23001733422279358,
      "learning_rate": 1.6601569191763457e-05,
      "loss": 0.0155,
      "step": 19500
    },
    {
      "epoch": 10.277492291880781,
      "grad_norm": 0.17580315470695496,
      "learning_rate": 1.5745023469352796e-05,
      "loss": 0.0136,
      "step": 20000
    },
    {
      "epoch": 10.277492291880781,
      "eval_loss": 0.03201943263411522,
      "eval_runtime": 184.1169,
      "eval_samples_per_second": 14.083,
      "eval_steps_per_second": 3.525,
      "step": 20000
    },
    {
      "epoch": 10.5344295991778,
      "grad_norm": 0.137004092335701,
      "learning_rate": 1.4888477746942134e-05,
      "loss": 0.0134,
      "step": 20500
    },
    {
      "epoch": 10.79136690647482,
      "grad_norm": 0.209578737616539,
      "learning_rate": 1.403193202453147e-05,
      "loss": 0.0138,
      "step": 21000
    },
    {
      "epoch": 11.04830421377184,
      "grad_norm": 0.17923501133918762,
      "learning_rate": 1.3175386302120807e-05,
      "loss": 0.0135,
      "step": 21500
    },
    {
      "epoch": 11.30524152106886,
      "grad_norm": 0.23782482743263245,
      "learning_rate": 1.2318840579710146e-05,
      "loss": 0.0125,
      "step": 22000
    },
    {
      "epoch": 11.562178828365878,
      "grad_norm": 0.1997631937265396,
      "learning_rate": 1.1462294857299482e-05,
      "loss": 0.0123,
      "step": 22500
    },
    {
      "epoch": 11.819116135662899,
      "grad_norm": 0.185743510723114,
      "learning_rate": 1.0605749134888821e-05,
      "loss": 0.0122,
      "step": 23000
    },
    {
      "epoch": 12.076053442959918,
      "grad_norm": 0.21140512824058533,
      "learning_rate": 9.749203412478158e-06,
      "loss": 0.012,
      "step": 23500
    },
    {
      "epoch": 12.332990750256938,
      "grad_norm": 0.1282157599925995,
      "learning_rate": 8.892657690067496e-06,
      "loss": 0.0114,
      "step": 24000
    },
    {
      "epoch": 12.589928057553957,
      "grad_norm": 0.23103195428848267,
      "learning_rate": 8.036111967656835e-06,
      "loss": 0.0111,
      "step": 24500
    },
    {
      "epoch": 12.846865364850977,
      "grad_norm": 0.14510518312454224,
      "learning_rate": 7.1795662452461724e-06,
      "loss": 0.0112,
      "step": 25000
    },
    {
      "epoch": 12.846865364850977,
      "eval_loss": 0.038895536214113235,
      "eval_runtime": 178.5696,
      "eval_samples_per_second": 14.521,
      "eval_steps_per_second": 3.634,
      "step": 25000
    }
  ],
  "logging_steps": 500,
  "max_steps": 29190,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 5000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.165047296e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}