{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5252100840336135,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01050420168067227,
      "grad_norm": 2.691126585006714,
      "learning_rate": 4.98249299719888e-05,
      "loss": 1.6756,
      "step": 10
    },
    {
      "epoch": 0.02100840336134454,
      "grad_norm": 1.9124071598052979,
      "learning_rate": 4.96498599439776e-05,
      "loss": 0.5155,
      "step": 20
    },
    {
      "epoch": 0.031512605042016806,
      "grad_norm": 1.1180588006973267,
      "learning_rate": 4.947478991596639e-05,
      "loss": 0.4521,
      "step": 30
    },
    {
      "epoch": 0.04201680672268908,
      "grad_norm": 0.7634907364845276,
      "learning_rate": 4.9299719887955186e-05,
      "loss": 0.3732,
      "step": 40
    },
    {
      "epoch": 0.052521008403361345,
      "grad_norm": 0.6673978567123413,
      "learning_rate": 4.912464985994398e-05,
      "loss": 0.3832,
      "step": 50
    },
    {
      "epoch": 0.052521008403361345,
      "eval_loss": 0.424630731344223,
      "eval_runtime": 13.4948,
      "eval_samples_per_second": 35.569,
      "eval_steps_per_second": 2.223,
      "step": 50
    },
    {
      "epoch": 0.06302521008403361,
      "grad_norm": 0.6445392370223999,
      "learning_rate": 4.8949579831932775e-05,
      "loss": 0.3386,
      "step": 60
    },
    {
      "epoch": 0.07352941176470588,
      "grad_norm": 0.5743226408958435,
      "learning_rate": 4.877450980392157e-05,
      "loss": 0.3443,
      "step": 70
    },
    {
      "epoch": 0.08403361344537816,
      "grad_norm": 0.6735454201698303,
      "learning_rate": 4.859943977591036e-05,
      "loss": 0.3212,
      "step": 80
    },
    {
      "epoch": 0.09453781512605042,
      "grad_norm": 0.660349428653717,
      "learning_rate": 4.8424369747899164e-05,
      "loss": 0.3379,
      "step": 90
    },
    {
      "epoch": 0.10504201680672269,
      "grad_norm": 0.8036162853240967,
      "learning_rate": 4.824929971988796e-05,
      "loss": 0.3177,
      "step": 100
    },
    {
      "epoch": 0.10504201680672269,
      "eval_loss": 0.3798685073852539,
      "eval_runtime": 13.5369,
      "eval_samples_per_second": 35.459,
      "eval_steps_per_second": 2.216,
      "step": 100
    },
    {
      "epoch": 0.11554621848739496,
      "grad_norm": 0.6827962398529053,
      "learning_rate": 4.807422969187675e-05,
      "loss": 0.3405,
      "step": 110
    },
    {
      "epoch": 0.12605042016806722,
      "grad_norm": 0.5923526287078857,
      "learning_rate": 4.7899159663865554e-05,
      "loss": 0.3324,
      "step": 120
    },
    {
      "epoch": 0.13655462184873948,
      "grad_norm": 0.6476097106933594,
      "learning_rate": 4.772408963585435e-05,
      "loss": 0.3216,
      "step": 130
    },
    {
      "epoch": 0.14705882352941177,
      "grad_norm": 0.5536680221557617,
      "learning_rate": 4.7549019607843135e-05,
      "loss": 0.3425,
      "step": 140
    },
    {
      "epoch": 0.15756302521008403,
      "grad_norm": 0.5725419521331787,
      "learning_rate": 4.7373949579831936e-05,
      "loss": 0.3062,
      "step": 150
    },
    {
      "epoch": 0.15756302521008403,
      "eval_loss": 0.36464938521385193,
      "eval_runtime": 13.5257,
      "eval_samples_per_second": 35.488,
      "eval_steps_per_second": 2.218,
      "step": 150
    },
    {
      "epoch": 0.16806722689075632,
      "grad_norm": 0.6459401249885559,
      "learning_rate": 4.719887955182073e-05,
      "loss": 0.327,
      "step": 160
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.7749695181846619,
      "learning_rate": 4.7023809523809525e-05,
      "loss": 0.3146,
      "step": 170
    },
    {
      "epoch": 0.18907563025210083,
      "grad_norm": 0.7452580332756042,
      "learning_rate": 4.684873949579832e-05,
      "loss": 0.3024,
      "step": 180
    },
    {
      "epoch": 0.19957983193277312,
      "grad_norm": 0.632286012172699,
      "learning_rate": 4.667366946778712e-05,
      "loss": 0.3157,
      "step": 190
    },
    {
      "epoch": 0.21008403361344538,
      "grad_norm": 0.6443158984184265,
      "learning_rate": 4.6498599439775914e-05,
      "loss": 0.3039,
      "step": 200
    },
    {
      "epoch": 0.21008403361344538,
      "eval_loss": 0.35029926896095276,
      "eval_runtime": 13.5332,
      "eval_samples_per_second": 35.468,
      "eval_steps_per_second": 2.217,
      "step": 200
    },
    {
      "epoch": 0.22058823529411764,
      "grad_norm": 0.6045960783958435,
      "learning_rate": 4.632352941176471e-05,
      "loss": 0.313,
      "step": 210
    },
    {
      "epoch": 0.23109243697478993,
      "grad_norm": 0.5544140338897705,
      "learning_rate": 4.61484593837535e-05,
      "loss": 0.2992,
      "step": 220
    },
    {
      "epoch": 0.2415966386554622,
      "grad_norm": 0.45881810784339905,
      "learning_rate": 4.59733893557423e-05,
      "loss": 0.2889,
      "step": 230
    },
    {
      "epoch": 0.25210084033613445,
      "grad_norm": 0.6315861344337463,
      "learning_rate": 4.579831932773109e-05,
      "loss": 0.3055,
      "step": 240
    },
    {
      "epoch": 0.26260504201680673,
      "grad_norm": 0.7058202624320984,
      "learning_rate": 4.562324929971989e-05,
      "loss": 0.2897,
      "step": 250
    },
    {
      "epoch": 0.26260504201680673,
      "eval_loss": 0.3452460467815399,
      "eval_runtime": 13.5256,
      "eval_samples_per_second": 35.488,
      "eval_steps_per_second": 2.218,
      "step": 250
    },
    {
      "epoch": 0.27310924369747897,
      "grad_norm": 0.7277679443359375,
      "learning_rate": 4.5448179271708687e-05,
      "loss": 0.3119,
      "step": 260
    },
    {
      "epoch": 0.28361344537815125,
      "grad_norm": 0.6311895251274109,
      "learning_rate": 4.527310924369748e-05,
      "loss": 0.296,
      "step": 270
    },
    {
      "epoch": 0.29411764705882354,
      "grad_norm": 0.5600409507751465,
      "learning_rate": 4.5098039215686275e-05,
      "loss": 0.3027,
      "step": 280
    },
    {
      "epoch": 0.30462184873949577,
      "grad_norm": 0.583111047744751,
      "learning_rate": 4.4922969187675076e-05,
      "loss": 0.3005,
      "step": 290
    },
    {
      "epoch": 0.31512605042016806,
      "grad_norm": 0.6667417287826538,
      "learning_rate": 4.474789915966387e-05,
      "loss": 0.2924,
      "step": 300
    },
    {
      "epoch": 0.31512605042016806,
      "eval_loss": 0.34308406710624695,
      "eval_runtime": 13.5267,
      "eval_samples_per_second": 35.485,
      "eval_steps_per_second": 2.218,
      "step": 300
    },
    {
      "epoch": 0.32563025210084034,
      "grad_norm": 0.6434429883956909,
      "learning_rate": 4.4572829131652665e-05,
      "loss": 0.2893,
      "step": 310
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": 0.5765148401260376,
      "learning_rate": 4.439775910364146e-05,
      "loss": 0.2842,
      "step": 320
    },
    {
      "epoch": 0.34663865546218486,
      "grad_norm": 0.5374988317489624,
      "learning_rate": 4.422268907563025e-05,
      "loss": 0.2838,
      "step": 330
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.5548204779624939,
      "learning_rate": 4.404761904761905e-05,
      "loss": 0.2708,
      "step": 340
    },
    {
      "epoch": 0.36764705882352944,
      "grad_norm": 0.5466386079788208,
      "learning_rate": 4.387254901960784e-05,
      "loss": 0.2833,
      "step": 350
    },
    {
      "epoch": 0.36764705882352944,
      "eval_loss": 0.3345324695110321,
      "eval_runtime": 13.5203,
      "eval_samples_per_second": 35.502,
      "eval_steps_per_second": 2.219,
      "step": 350
    },
    {
      "epoch": 0.37815126050420167,
      "grad_norm": 0.655726432800293,
      "learning_rate": 4.369747899159664e-05,
      "loss": 0.2842,
      "step": 360
    },
    {
      "epoch": 0.38865546218487396,
      "grad_norm": 0.6633383631706238,
      "learning_rate": 4.352240896358544e-05,
      "loss": 0.2752,
      "step": 370
    },
    {
      "epoch": 0.39915966386554624,
      "grad_norm": 0.549430787563324,
      "learning_rate": 4.334733893557423e-05,
      "loss": 0.2918,
      "step": 380
    },
    {
      "epoch": 0.4096638655462185,
      "grad_norm": 0.49975866079330444,
      "learning_rate": 4.317226890756303e-05,
      "loss": 0.2733,
      "step": 390
    },
    {
      "epoch": 0.42016806722689076,
      "grad_norm": 0.5723116397857666,
      "learning_rate": 4.2997198879551826e-05,
      "loss": 0.2852,
      "step": 400
    },
    {
      "epoch": 0.42016806722689076,
      "eval_loss": 0.334602415561676,
      "eval_runtime": 13.5187,
      "eval_samples_per_second": 35.506,
      "eval_steps_per_second": 2.219,
      "step": 400
    },
    {
      "epoch": 0.43067226890756305,
      "grad_norm": 0.6224997639656067,
      "learning_rate": 4.2822128851540614e-05,
      "loss": 0.2982,
      "step": 410
    },
    {
      "epoch": 0.4411764705882353,
      "grad_norm": 0.548751711845398,
      "learning_rate": 4.2647058823529415e-05,
      "loss": 0.2867,
      "step": 420
    },
    {
      "epoch": 0.45168067226890757,
      "grad_norm": 0.5709792971611023,
      "learning_rate": 4.247198879551821e-05,
      "loss": 0.2588,
      "step": 430
    },
    {
      "epoch": 0.46218487394957986,
      "grad_norm": 0.537171483039856,
      "learning_rate": 4.2296918767507e-05,
      "loss": 0.2782,
      "step": 440
    },
    {
      "epoch": 0.4726890756302521,
      "grad_norm": 0.5505544543266296,
      "learning_rate": 4.21218487394958e-05,
      "loss": 0.2703,
      "step": 450
    },
    {
      "epoch": 0.4726890756302521,
      "eval_loss": 0.3293306231498718,
      "eval_runtime": 13.5091,
      "eval_samples_per_second": 35.532,
      "eval_steps_per_second": 2.221,
      "step": 450
    },
    {
      "epoch": 0.4831932773109244,
      "grad_norm": 0.5049700736999512,
      "learning_rate": 4.19467787114846e-05,
      "loss": 0.2439,
      "step": 460
    },
    {
      "epoch": 0.49369747899159666,
      "grad_norm": 0.6546272039413452,
      "learning_rate": 4.177170868347339e-05,
      "loss": 0.2747,
      "step": 470
    },
    {
      "epoch": 0.5042016806722689,
      "grad_norm": 0.4740765690803528,
      "learning_rate": 4.159663865546219e-05,
      "loss": 0.2692,
      "step": 480
    },
    {
      "epoch": 0.5147058823529411,
      "grad_norm": 0.5289779901504517,
      "learning_rate": 4.142156862745099e-05,
      "loss": 0.29,
      "step": 490
    },
    {
      "epoch": 0.5252100840336135,
      "grad_norm": 0.5422542095184326,
      "learning_rate": 4.1246498599439776e-05,
      "loss": 0.2721,
      "step": 500
    },
    {
      "epoch": 0.5252100840336135,
      "eval_loss": 0.32664668560028076,
      "eval_runtime": 13.4992,
      "eval_samples_per_second": 35.558,
      "eval_steps_per_second": 2.222,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 2856,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.977409027624141e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}