{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0183299389002036,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020366598778004074,
      "grad_norm": 0.12626299262046814,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.7006,
      "mean_token_accuracy": 0.6053715996444226,
      "step": 10
    },
    {
      "epoch": 0.04073319755600815,
      "grad_norm": 0.2351449579000473,
      "learning_rate": 0.00019994755690455152,
      "loss": 1.5214,
      "mean_token_accuracy": 0.6368309155106544,
      "step": 20
    },
    {
      "epoch": 0.06109979633401222,
      "grad_norm": 0.32846614718437195,
      "learning_rate": 0.0001995283421166614,
      "loss": 1.5662,
      "mean_token_accuracy": 0.6361105382442475,
      "step": 30
    },
    {
      "epoch": 0.0814663951120163,
      "grad_norm": 0.24607931077480316,
      "learning_rate": 0.00019869167087338907,
      "loss": 1.4452,
      "mean_token_accuracy": 0.6645107805728913,
      "step": 40
    },
    {
      "epoch": 0.10183299389002037,
      "grad_norm": 0.21988731622695923,
      "learning_rate": 0.00019744105246469263,
      "loss": 1.3939,
      "mean_token_accuracy": 0.6644507594406605,
      "step": 50
    },
    {
      "epoch": 0.12219959266802444,
      "grad_norm": 0.18629378080368042,
      "learning_rate": 0.00019578173241879872,
      "loss": 1.3307,
      "mean_token_accuracy": 0.671517875790596,
      "step": 60
    },
    {
      "epoch": 0.1425661914460285,
      "grad_norm": 0.19982416927814484,
      "learning_rate": 0.00019372067050063438,
      "loss": 1.3089,
      "mean_token_accuracy": 0.6763716876506806,
      "step": 70
    },
    {
      "epoch": 0.1629327902240326,
      "grad_norm": 0.1744842529296875,
      "learning_rate": 0.00019126651152015403,
      "loss": 1.3482,
      "mean_token_accuracy": 0.6714572340250016,
      "step": 80
    },
    {
      "epoch": 0.18329938900203666,
      "grad_norm": 0.22721126675605774,
      "learning_rate": 0.00018842954907300236,
      "loss": 1.4167,
      "mean_token_accuracy": 0.6588860973715782,
      "step": 90
    },
    {
      "epoch": 0.20366598778004075,
      "grad_norm": 0.17914065718650818,
      "learning_rate": 0.00018522168236559695,
      "loss": 1.3608,
      "mean_token_accuracy": 0.6660649880766869,
      "step": 100
    },
    {
      "epoch": 0.2240325865580448,
      "grad_norm": 0.1730283796787262,
      "learning_rate": 0.0001816563663057211,
      "loss": 1.4223,
      "mean_token_accuracy": 0.6599490791559219,
      "step": 110
    },
    {
      "epoch": 0.24439918533604887,
      "grad_norm": 0.17649827897548676,
      "learning_rate": 0.00017774855506796496,
      "loss": 1.3737,
      "mean_token_accuracy": 0.6688225455582142,
      "step": 120
    },
    {
      "epoch": 0.26476578411405294,
      "grad_norm": 0.17069195210933685,
      "learning_rate": 0.00017351463937072004,
      "loss": 1.3767,
      "mean_token_accuracy": 0.6619200393557548,
      "step": 130
    },
    {
      "epoch": 0.285132382892057,
      "grad_norm": 0.1913885921239853,
      "learning_rate": 0.00016897237772781044,
      "loss": 1.4375,
      "mean_token_accuracy": 0.6498532116413116,
      "step": 140
    },
    {
      "epoch": 0.3054989816700611,
      "grad_norm": 0.17547893524169922,
      "learning_rate": 0.000164140821963114,
      "loss": 1.3268,
      "mean_token_accuracy": 0.6731642320752144,
      "step": 150
    },
    {
      "epoch": 0.3258655804480652,
      "grad_norm": 0.16026997566223145,
      "learning_rate": 0.00015904023730059228,
      "loss": 1.4003,
      "mean_token_accuracy": 0.663200007379055,
      "step": 160
    },
    {
      "epoch": 0.34623217922606925,
      "grad_norm": 0.15250708162784576,
      "learning_rate": 0.0001536920173648984,
      "loss": 1.2856,
      "mean_token_accuracy": 0.6764356568455696,
      "step": 170
    },
    {
      "epoch": 0.3665987780040733,
      "grad_norm": 0.13922956585884094,
      "learning_rate": 0.00014811859444908052,
      "loss": 1.3469,
      "mean_token_accuracy": 0.6688723161816597,
      "step": 180
    },
    {
      "epoch": 0.3869653767820774,
      "grad_norm": 0.16509701311588287,
      "learning_rate": 0.00014234334542574906,
      "loss": 1.3352,
      "mean_token_accuracy": 0.6676128759980202,
      "step": 190
    },
    {
      "epoch": 0.4073319755600815,
      "grad_norm": 0.14618448913097382,
      "learning_rate": 0.00013639049369634876,
      "loss": 1.3593,
      "mean_token_accuracy": 0.6654890060424805,
      "step": 200
    },
    {
      "epoch": 0.42769857433808556,
      "grad_norm": 0.16653190553188324,
      "learning_rate": 0.00013028500758979506,
      "loss": 1.328,
      "mean_token_accuracy": 0.6699673473834992,
      "step": 210
    },
    {
      "epoch": 0.4480651731160896,
      "grad_norm": 0.146384596824646,
      "learning_rate": 0.00012405249563662537,
      "loss": 1.2914,
      "mean_token_accuracy": 0.6747352227568626,
      "step": 220
    },
    {
      "epoch": 0.4684317718940937,
      "grad_norm": 0.16215957701206207,
      "learning_rate": 0.0001177190991579223,
      "loss": 1.3342,
      "mean_token_accuracy": 0.6690372809767723,
      "step": 230
    },
    {
      "epoch": 0.48879837067209775,
      "grad_norm": 0.17549686133861542,
      "learning_rate": 0.00011131138261952845,
      "loss": 1.2852,
      "mean_token_accuracy": 0.6783039927482605,
      "step": 240
    },
    {
      "epoch": 0.5091649694501018,
      "grad_norm": 0.14437216520309448,
      "learning_rate": 0.00010485622221144484,
      "loss": 1.3264,
      "mean_token_accuracy": 0.6815439119935036,
      "step": 250
    },
    {
      "epoch": 0.5295315682281059,
      "grad_norm": 0.139692023396492,
      "learning_rate": 9.838069311974986e-05,
      "loss": 1.3195,
      "mean_token_accuracy": 0.6713656410574913,
      "step": 260
    },
    {
      "epoch": 0.5498981670061099,
      "grad_norm": 0.16701075434684753,
      "learning_rate": 9.19119559638596e-05,
      "loss": 1.3618,
      "mean_token_accuracy": 0.6655304417014122,
      "step": 270
    },
    {
      "epoch": 0.570264765784114,
      "grad_norm": 0.15681137144565582,
      "learning_rate": 8.5477142875451e-05,
      "loss": 1.3549,
      "mean_token_accuracy": 0.6620298072695732,
      "step": 280
    },
    {
      "epoch": 0.5906313645621182,
      "grad_norm": 0.1511278599500656,
      "learning_rate": 7.91032436968725e-05,
      "loss": 1.3159,
      "mean_token_accuracy": 0.6778326541185379,
      "step": 290
    },
    {
      "epoch": 0.6109979633401222,
      "grad_norm": 0.16071146726608276,
      "learning_rate": 7.281699277636572e-05,
      "loss": 1.3977,
      "mean_token_accuracy": 0.6576820626854897,
      "step": 300
    },
    {
      "epoch": 0.6313645621181263,
      "grad_norm": 0.1634049415588379,
      "learning_rate": 6.664475683491796e-05,
      "loss": 1.3118,
      "mean_token_accuracy": 0.6826698362827301,
      "step": 310
    },
    {
      "epoch": 0.6517311608961304,
      "grad_norm": 0.15096673369407654,
      "learning_rate": 6.061242437507131e-05,
      "loss": 1.3492,
      "mean_token_accuracy": 0.6674635127186775,
      "step": 320
    },
    {
      "epoch": 0.6720977596741344,
      "grad_norm": 0.16971102356910706,
      "learning_rate": 5.474529709554612e-05,
      "loss": 1.4399,
      "mean_token_accuracy": 0.6552789464592934,
      "step": 330
    },
    {
      "epoch": 0.6924643584521385,
      "grad_norm": 0.14999577403068542,
      "learning_rate": 4.9067983767123736e-05,
      "loss": 1.4486,
      "mean_token_accuracy": 0.6491607405245304,
      "step": 340
    },
    {
      "epoch": 0.7128309572301426,
      "grad_norm": 0.16720150411128998,
      "learning_rate": 4.360429701490934e-05,
      "loss": 1.3931,
      "mean_token_accuracy": 0.6607658788561821,
      "step": 350
    },
    {
      "epoch": 0.7331975560081466,
      "grad_norm": 0.138802170753479,
      "learning_rate": 3.8377153439907266e-05,
      "loss": 1.2131,
      "mean_token_accuracy": 0.6939047828316689,
      "step": 360
    },
    {
      "epoch": 0.7535641547861507,
      "grad_norm": 0.18726502358913422,
      "learning_rate": 3.340847749883191e-05,
      "loss": 1.2142,
      "mean_token_accuracy": 0.6881774321198464,
      "step": 370
    },
    {
      "epoch": 0.7739307535641547,
      "grad_norm": 0.190961092710495,
      "learning_rate": 2.8719109545317103e-05,
      "loss": 1.3967,
      "mean_token_accuracy": 0.6626075744628906,
      "step": 380
    },
    {
      "epoch": 0.7942973523421588,
      "grad_norm": 0.14274843037128448,
      "learning_rate": 2.432871841823047e-05,
      "loss": 1.3339,
      "mean_token_accuracy": 0.671070359647274,
      "step": 390
    },
    {
      "epoch": 0.814663951120163,
      "grad_norm": 0.1557278335094452,
      "learning_rate": 2.025571894372794e-05,
      "loss": 1.296,
      "mean_token_accuracy": 0.6788829267024994,
      "step": 400
    },
    {
      "epoch": 0.835030549898167,
      "grad_norm": 0.17218472063541412,
      "learning_rate": 1.65171946970729e-05,
      "loss": 1.2488,
      "mean_token_accuracy": 0.6864925757050514,
      "step": 410
    },
    {
      "epoch": 0.8553971486761711,
      "grad_norm": 0.14736278355121613,
      "learning_rate": 1.3128826348184887e-05,
      "loss": 1.3984,
      "mean_token_accuracy": 0.6586415357887745,
      "step": 420
    },
    {
      "epoch": 0.8757637474541752,
      "grad_norm": 0.16238394379615784,
      "learning_rate": 1.010482589146048e-05,
      "loss": 1.2756,
      "mean_token_accuracy": 0.6823231220245362,
      "step": 430
    },
    {
      "epoch": 0.8961303462321792,
      "grad_norm": 0.1799972802400589,
      "learning_rate": 7.457877035729588e-06,
      "loss": 1.3597,
      "mean_token_accuracy": 0.6700396433472633,
      "step": 440
    },
    {
      "epoch": 0.9164969450101833,
      "grad_norm": 0.18641585111618042,
      "learning_rate": 5.199082004372957e-06,
      "loss": 1.2676,
      "mean_token_accuracy": 0.6873666003346444,
      "step": 450
    },
    {
      "epoch": 0.9368635437881874,
      "grad_norm": 0.15163969993591309,
      "learning_rate": 3.3379149687388867e-06,
      "loss": 1.3899,
      "mean_token_accuracy": 0.6645716562867164,
      "step": 460
    },
    {
      "epoch": 0.9572301425661914,
      "grad_norm": 0.15963105857372284,
      "learning_rate": 1.882182310176095e-06,
      "loss": 1.342,
      "mean_token_accuracy": 0.6667100310325622,
      "step": 470
    },
    {
      "epoch": 0.9775967413441955,
      "grad_norm": 0.14211098849773407,
      "learning_rate": 8.379898773574924e-07,
      "loss": 1.3966,
      "mean_token_accuracy": 0.6606692716479301,
      "step": 480
    },
    {
      "epoch": 0.9979633401221996,
      "grad_norm": 0.16811959445476532,
      "learning_rate": 2.0971737622883515e-07,
      "loss": 1.4444,
      "mean_token_accuracy": 0.655492453277111,
      "step": 490
    },
    {
      "epoch": 1.0183299389002036,
      "grad_norm": 0.17285843193531036,
      "learning_rate": 0.0,
      "loss": 1.3099,
      "mean_token_accuracy": 0.6747938022017479,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.528555810816e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}