{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1497,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 1.2907918691635132,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.3493,
      "step": 25
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.2323806285858154,
      "learning_rate": 6.533333333333334e-05,
      "loss": 1.1043,
      "step": 50
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.096836805343628,
      "learning_rate": 9.866666666666668e-05,
      "loss": 0.9079,
      "step": 75
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.9220419526100159,
      "learning_rate": 0.000132,
      "loss": 0.8502,
      "step": 100
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.9188351631164551,
      "learning_rate": 0.00016533333333333333,
      "loss": 0.7941,
      "step": 125
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.9083553552627563,
      "learning_rate": 0.00019866666666666668,
      "loss": 0.7949,
      "step": 150
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.7864977717399597,
      "learning_rate": 0.00019643652561247217,
      "loss": 0.7836,
      "step": 175
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.8785583972930908,
      "learning_rate": 0.00019272457312546402,
      "loss": 0.775,
      "step": 200
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.7661826014518738,
      "learning_rate": 0.00018901262063845584,
      "loss": 0.7749,
      "step": 225
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.8582839965820312,
      "learning_rate": 0.00018530066815144767,
      "loss": 0.7408,
      "step": 250
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.8379924297332764,
      "learning_rate": 0.00018158871566443952,
      "loss": 0.7563,
      "step": 275
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.8311147093772888,
      "learning_rate": 0.00017787676317743134,
      "loss": 0.7645,
      "step": 300
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.8674755096435547,
      "learning_rate": 0.00017416481069042317,
      "loss": 0.7558,
      "step": 325
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.725708544254303,
      "learning_rate": 0.00017045285820341502,
      "loss": 0.7442,
      "step": 350
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.676539421081543,
      "learning_rate": 0.00016674090571640684,
      "loss": 0.758,
      "step": 375
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.7118335962295532,
      "learning_rate": 0.00016302895322939867,
      "loss": 0.7181,
      "step": 400
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.7514967918395996,
      "learning_rate": 0.00015931700074239052,
      "loss": 0.7415,
      "step": 425
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.6775885224342346,
      "learning_rate": 0.00015560504825538234,
      "loss": 0.7106,
      "step": 450
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.7105979323387146,
      "learning_rate": 0.0001518930957683742,
      "loss": 0.7078,
      "step": 475
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6819420456886292,
      "learning_rate": 0.00014818114328136602,
      "loss": 0.726,
      "step": 500
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.7699077129364014,
      "learning_rate": 0.00014446919079435784,
      "loss": 0.6885,
      "step": 525
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.6890037059783936,
      "learning_rate": 0.0001407572383073497,
      "loss": 0.6874,
      "step": 550
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.7747482657432556,
      "learning_rate": 0.00013704528582034152,
      "loss": 0.6822,
      "step": 575
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.7736285328865051,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.6905,
      "step": 600
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.0000784397125244,
      "learning_rate": 0.0001296213808463252,
      "loss": 0.6844,
      "step": 625
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.6599183082580566,
      "learning_rate": 0.00012590942835931702,
      "loss": 0.6783,
      "step": 650
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.7472581267356873,
      "learning_rate": 0.00012219747587230884,
      "loss": 0.6976,
      "step": 675
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.7868366241455078,
      "learning_rate": 0.00011848552338530068,
      "loss": 0.687,
      "step": 700
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.7280272841453552,
      "learning_rate": 0.0001147735708982925,
      "loss": 0.6795,
      "step": 725
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.7689390182495117,
      "learning_rate": 0.00011106161841128435,
      "loss": 0.6667,
      "step": 750
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.7489085793495178,
      "learning_rate": 0.00010734966592427618,
      "loss": 0.668,
      "step": 775
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.7128411531448364,
      "learning_rate": 0.000103637713437268,
      "loss": 0.7063,
      "step": 800
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.7407069802284241,
      "learning_rate": 9.992576095025984e-05,
      "loss": 0.6566,
      "step": 825
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.7692396640777588,
      "learning_rate": 9.621380846325168e-05,
      "loss": 0.6735,
      "step": 850
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.7389003038406372,
      "learning_rate": 9.250185597624351e-05,
      "loss": 0.6641,
      "step": 875
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.8007437586784363,
      "learning_rate": 8.878990348923534e-05,
      "loss": 0.6426,
      "step": 900
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.762878954410553,
      "learning_rate": 8.507795100222718e-05,
      "loss": 0.7014,
      "step": 925
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.685552179813385,
      "learning_rate": 8.136599851521901e-05,
      "loss": 0.6667,
      "step": 950
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.7692657113075256,
      "learning_rate": 7.765404602821085e-05,
      "loss": 0.6695,
      "step": 975
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.758256733417511,
      "learning_rate": 7.394209354120267e-05,
      "loss": 0.6859,
      "step": 1000
    },
    {
      "epoch": 2.05,
      "grad_norm": 0.7138740420341492,
      "learning_rate": 7.023014105419451e-05,
      "loss": 0.6221,
      "step": 1025
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.781160831451416,
      "learning_rate": 6.651818856718635e-05,
      "loss": 0.6256,
      "step": 1050
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.7872413992881775,
      "learning_rate": 6.280623608017817e-05,
      "loss": 0.6126,
      "step": 1075
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.8612145185470581,
      "learning_rate": 5.9094283593170005e-05,
      "loss": 0.5982,
      "step": 1100
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.8253654837608337,
      "learning_rate": 5.538233110616184e-05,
      "loss": 0.5968,
      "step": 1125
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.7710873484611511,
      "learning_rate": 5.167037861915368e-05,
      "loss": 0.628,
      "step": 1150
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.8175609111785889,
      "learning_rate": 4.795842613214551e-05,
      "loss": 0.6342,
      "step": 1175
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.8151463270187378,
      "learning_rate": 4.424647364513734e-05,
      "loss": 0.6434,
      "step": 1200
    },
    {
      "epoch": 2.45,
      "grad_norm": 0.8666600584983826,
      "learning_rate": 4.053452115812918e-05,
      "loss": 0.6046,
      "step": 1225
    },
    {
      "epoch": 2.51,
      "grad_norm": 0.9800847768783569,
      "learning_rate": 3.682256867112101e-05,
      "loss": 0.6037,
      "step": 1250
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.8552590608596802,
      "learning_rate": 3.311061618411285e-05,
      "loss": 0.6284,
      "step": 1275
    },
    {
      "epoch": 2.61,
      "grad_norm": 0.8620779514312744,
      "learning_rate": 2.939866369710468e-05,
      "loss": 0.636,
      "step": 1300
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.8995267748832703,
      "learning_rate": 2.5686711210096513e-05,
      "loss": 0.614,
      "step": 1325
    },
    {
      "epoch": 2.71,
      "grad_norm": 0.7862620949745178,
      "learning_rate": 2.1974758723088344e-05,
      "loss": 0.6499,
      "step": 1350
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.8439193964004517,
      "learning_rate": 1.826280623608018e-05,
      "loss": 0.6094,
      "step": 1375
    },
    {
      "epoch": 2.81,
      "grad_norm": 0.8704841136932373,
      "learning_rate": 1.4550853749072013e-05,
      "loss": 0.6121,
      "step": 1400
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.8250275254249573,
      "learning_rate": 1.0838901262063845e-05,
      "loss": 0.6127,
      "step": 1425
    },
    {
      "epoch": 2.91,
      "grad_norm": 0.7634843587875366,
      "learning_rate": 7.12694877505568e-06,
      "loss": 0.6159,
      "step": 1450
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.829576313495636,
      "learning_rate": 3.414996288047513e-06,
      "loss": 0.5931,
      "step": 1475
    }
  ],
  "logging_steps": 25,
  "max_steps": 1497,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2.6185387210702848e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}