{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.5579014715291106,
  "eval_steps": 200,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025591810620601407,
      "grad_norm": 78.5,
      "learning_rate": 1.35e-07,
      "loss": 2.687112236022949,
      "step": 10
    },
    {
      "epoch": 0.05118362124120281,
      "grad_norm": 117.0,
      "learning_rate": 2.85e-07,
      "loss": 2.8489315032958986,
      "step": 20
    },
    {
      "epoch": 0.07677543186180422,
      "grad_norm": 302.0,
      "learning_rate": 4.3499999999999996e-07,
      "loss": 2.7195245742797853,
      "step": 30
    },
    {
      "epoch": 0.10236724248240563,
      "grad_norm": 328.0,
      "learning_rate": 5.85e-07,
      "loss": 2.9164562225341797,
      "step": 40
    },
    {
      "epoch": 0.12795905310300704,
      "grad_norm": 109.5,
      "learning_rate": 7.350000000000001e-07,
      "loss": 2.7758764266967773,
      "step": 50
    },
    {
      "epoch": 0.15355086372360843,
      "grad_norm": 137.0,
      "learning_rate": 8.85e-07,
      "loss": 2.842637825012207,
      "step": 60
    },
    {
      "epoch": 0.17914267434420986,
      "grad_norm": 230.0,
      "learning_rate": 1.035e-06,
      "loss": 2.8522205352783203,
      "step": 70
    },
    {
      "epoch": 0.20473448496481125,
      "grad_norm": 183.0,
      "learning_rate": 1.185e-06,
      "loss": 2.8120689392089844,
      "step": 80
    },
    {
      "epoch": 0.23032629558541268,
      "grad_norm": 178.0,
      "learning_rate": 1.3350000000000001e-06,
      "loss": 2.547420883178711,
      "step": 90
    },
    {
      "epoch": 0.2559181062060141,
      "grad_norm": 57.25,
      "learning_rate": 1.485e-06,
      "loss": 2.685759735107422,
      "step": 100
    },
    {
      "epoch": 0.28150991682661547,
      "grad_norm": 162.0,
      "learning_rate": 1.6350000000000002e-06,
      "loss": 2.9074512481689454,
      "step": 110
    },
    {
      "epoch": 0.30710172744721687,
      "grad_norm": 133.0,
      "learning_rate": 1.785e-06,
      "loss": 2.6075531005859376,
      "step": 120
    },
    {
      "epoch": 0.3326935380678183,
      "grad_norm": 76.0,
      "learning_rate": 1.935e-06,
      "loss": 2.26098575592041,
      "step": 130
    },
    {
      "epoch": 0.3582853486884197,
      "grad_norm": 95.0,
      "learning_rate": 2.085e-06,
      "loss": 2.113755226135254,
      "step": 140
    },
    {
      "epoch": 0.3838771593090211,
      "grad_norm": 96.5,
      "learning_rate": 2.235e-06,
      "loss": 2.3181507110595705,
      "step": 150
    },
    {
      "epoch": 0.4094689699296225,
      "grad_norm": 122.0,
      "learning_rate": 2.385e-06,
      "loss": 2.0230716705322265,
      "step": 160
    },
    {
      "epoch": 0.4350607805502239,
      "grad_norm": 167.0,
      "learning_rate": 2.535e-06,
      "loss": 2.166606140136719,
      "step": 170
    },
    {
      "epoch": 0.46065259117082535,
      "grad_norm": 103.0,
      "learning_rate": 2.685e-06,
      "loss": 2.094511795043945,
      "step": 180
    },
    {
      "epoch": 0.48624440179142675,
      "grad_norm": 97.5,
      "learning_rate": 2.835e-06,
      "loss": 1.9705234527587892,
      "step": 190
    },
    {
      "epoch": 0.5118362124120281,
      "grad_norm": 136.0,
      "learning_rate": 2.9850000000000002e-06,
      "loss": 1.8970783233642579,
      "step": 200
    },
    {
      "epoch": 0.5118362124120281,
      "eval_loss": 0.3652507960796356,
      "eval_runtime": 20.6147,
      "eval_samples_per_second": 97.018,
      "eval_steps_per_second": 3.056,
      "step": 200
    },
    {
      "epoch": 0.5374280230326296,
      "grad_norm": 75.0,
      "learning_rate": 2.9850000000000002e-06,
      "loss": 1.8157735824584962,
      "step": 210
    },
    {
      "epoch": 0.5630198336532309,
      "grad_norm": 170.0,
      "learning_rate": 2.9683333333333334e-06,
      "loss": 1.7747406005859374,
      "step": 220
    },
    {
      "epoch": 0.5886116442738324,
      "grad_norm": 117.5,
      "learning_rate": 2.9516666666666666e-06,
      "loss": 1.8584400177001954,
      "step": 230
    },
    {
      "epoch": 0.6142034548944337,
      "grad_norm": 55.5,
      "learning_rate": 2.9350000000000003e-06,
      "loss": 1.7559932708740233,
      "step": 240
    },
    {
      "epoch": 0.6397952655150352,
      "grad_norm": 111.5,
      "learning_rate": 2.9183333333333335e-06,
      "loss": 1.938743782043457,
      "step": 250
    },
    {
      "epoch": 0.6653870761356366,
      "grad_norm": 153.0,
      "learning_rate": 2.9016666666666667e-06,
      "loss": 1.6487155914306642,
      "step": 260
    },
    {
      "epoch": 0.690978886756238,
      "grad_norm": 83.0,
      "learning_rate": 2.885e-06,
      "loss": 1.5814908027648926,
      "step": 270
    },
    {
      "epoch": 0.7165706973768394,
      "grad_norm": 50.75,
      "learning_rate": 2.8683333333333335e-06,
      "loss": 1.5237090110778808,
      "step": 280
    },
    {
      "epoch": 0.7421625079974408,
      "grad_norm": 79.0,
      "learning_rate": 2.8516666666666668e-06,
      "loss": 1.5812367439270019,
      "step": 290
    },
    {
      "epoch": 0.7677543186180422,
      "grad_norm": 61.25,
      "learning_rate": 2.835e-06,
      "loss": 1.499494743347168,
      "step": 300
    },
    {
      "epoch": 0.7933461292386437,
      "grad_norm": 104.5,
      "learning_rate": 2.818333333333333e-06,
      "loss": 1.393200969696045,
      "step": 310
    },
    {
      "epoch": 0.818937939859245,
      "grad_norm": 101.5,
      "learning_rate": 2.801666666666667e-06,
      "loss": 1.5071249961853028,
      "step": 320
    },
    {
      "epoch": 0.8445297504798465,
      "grad_norm": 109.5,
      "learning_rate": 2.785e-06,
      "loss": 1.3955337524414062,
      "step": 330
    },
    {
      "epoch": 0.8701215611004478,
      "grad_norm": 86.0,
      "learning_rate": 2.7683333333333337e-06,
      "loss": 1.1970922470092773,
      "step": 340
    },
    {
      "epoch": 0.8957133717210493,
      "grad_norm": 127.0,
      "learning_rate": 2.751666666666667e-06,
      "loss": 1.4966418266296386,
      "step": 350
    },
    {
      "epoch": 0.9213051823416507,
      "grad_norm": 60.0,
      "learning_rate": 2.735e-06,
      "loss": 1.5355607986450195,
      "step": 360
    },
    {
      "epoch": 0.946896992962252,
      "grad_norm": 110.0,
      "learning_rate": 2.7183333333333333e-06,
      "loss": 1.2876726150512696,
      "step": 370
    },
    {
      "epoch": 0.9724888035828535,
      "grad_norm": 61.75,
      "learning_rate": 2.701666666666667e-06,
      "loss": 1.4528013229370118,
      "step": 380
    },
    {
      "epoch": 0.9980806142034548,
      "grad_norm": 73.0,
      "learning_rate": 2.685e-06,
      "loss": 1.4765524864196777,
      "step": 390
    },
    {
      "epoch": 1.0230326295585412,
      "grad_norm": 43.5,
      "learning_rate": 2.6683333333333333e-06,
      "loss": 1.31887845993042,
      "step": 400
    },
    {
      "epoch": 1.0230326295585412,
      "eval_loss": 0.25503993034362793,
      "eval_runtime": 20.8252,
      "eval_samples_per_second": 96.037,
      "eval_steps_per_second": 3.025,
      "step": 400
    },
    {
      "epoch": 1.0486244401791427,
      "grad_norm": 116.5,
      "learning_rate": 2.6516666666666665e-06,
      "loss": 1.2159116744995118,
      "step": 410
    },
    {
      "epoch": 1.0742162507997441,
      "grad_norm": 124.5,
      "learning_rate": 2.6349999999999998e-06,
      "loss": 1.346174716949463,
      "step": 420
    },
    {
      "epoch": 1.0998080614203456,
      "grad_norm": 70.0,
      "learning_rate": 2.6183333333333334e-06,
      "loss": 1.3012319564819337,
      "step": 430
    },
    {
      "epoch": 1.1253998720409468,
      "grad_norm": 78.5,
      "learning_rate": 2.6016666666666666e-06,
      "loss": 1.2842123985290528,
      "step": 440
    },
    {
      "epoch": 1.1509916826615483,
      "grad_norm": 95.5,
      "learning_rate": 2.5850000000000002e-06,
      "loss": 1.1591164588928222,
      "step": 450
    },
    {
      "epoch": 1.1765834932821497,
      "grad_norm": 119.5,
      "learning_rate": 2.5683333333333334e-06,
      "loss": 1.28289794921875,
      "step": 460
    },
    {
      "epoch": 1.2021753039027512,
      "grad_norm": 47.25,
      "learning_rate": 2.5516666666666667e-06,
      "loss": 1.2217205047607422,
      "step": 470
    },
    {
      "epoch": 1.2277671145233526,
      "grad_norm": 61.0,
      "learning_rate": 2.535e-06,
      "loss": 1.3094758987426758,
      "step": 480
    },
    {
      "epoch": 1.2533589251439539,
      "grad_norm": 125.5,
      "learning_rate": 2.5183333333333335e-06,
      "loss": 1.0260610580444336,
      "step": 490
    },
    {
      "epoch": 1.2789507357645553,
      "grad_norm": 52.75,
      "learning_rate": 2.5016666666666667e-06,
      "loss": 1.3739563941955566,
      "step": 500
    },
    {
      "epoch": 1.3045425463851568,
      "grad_norm": 101.5,
      "learning_rate": 2.4850000000000003e-06,
      "loss": 1.1762229919433593,
      "step": 510
    },
    {
      "epoch": 1.3301343570057582,
      "grad_norm": 74.0,
      "learning_rate": 2.4683333333333336e-06,
      "loss": 1.2967172622680665,
      "step": 520
    },
    {
      "epoch": 1.3557261676263597,
      "grad_norm": 57.25,
      "learning_rate": 2.4516666666666668e-06,
      "loss": 1.260681438446045,
      "step": 530
    },
    {
      "epoch": 1.381317978246961,
      "grad_norm": 88.0,
      "learning_rate": 2.435e-06,
      "loss": 1.0191940307617187,
      "step": 540
    },
    {
      "epoch": 1.4069097888675623,
      "grad_norm": 129.0,
      "learning_rate": 2.418333333333333e-06,
      "loss": 1.0855172157287598,
      "step": 550
    },
    {
      "epoch": 1.4325015994881638,
      "grad_norm": 74.0,
      "learning_rate": 2.401666666666667e-06,
      "loss": 1.1898975372314453,
      "step": 560
    },
    {
      "epoch": 1.4580934101087653,
      "grad_norm": 54.25,
      "learning_rate": 2.385e-06,
      "loss": 1.1281633377075195,
      "step": 570
    },
    {
      "epoch": 1.4836852207293667,
      "grad_norm": 86.5,
      "learning_rate": 2.3683333333333332e-06,
      "loss": 1.4006970405578614,
      "step": 580
    },
    {
      "epoch": 1.509277031349968,
      "grad_norm": 96.5,
      "learning_rate": 2.3516666666666665e-06,
      "loss": 1.1684344291687012,
      "step": 590
    },
    {
      "epoch": 1.5348688419705694,
      "grad_norm": 110.0,
      "learning_rate": 2.335e-06,
      "loss": 1.2921236038208008,
      "step": 600
    },
    {
      "epoch": 1.5348688419705694,
      "eval_loss": 0.2259225696325302,
      "eval_runtime": 21.0241,
      "eval_samples_per_second": 95.129,
      "eval_steps_per_second": 2.997,
      "step": 600
    },
    {
      "epoch": 1.5604606525911708,
      "grad_norm": 88.5,
      "learning_rate": 2.3183333333333333e-06,
      "loss": 1.076922607421875,
      "step": 610
    },
    {
      "epoch": 1.586052463211772,
      "grad_norm": 105.0,
      "learning_rate": 2.301666666666667e-06,
      "loss": 1.0854657173156739,
      "step": 620
    },
    {
      "epoch": 1.6116442738323737,
      "grad_norm": 70.5,
      "learning_rate": 2.285e-06,
      "loss": 1.244626522064209,
      "step": 630
    },
    {
      "epoch": 1.637236084452975,
      "grad_norm": 30.0,
      "learning_rate": 2.2683333333333334e-06,
      "loss": 1.047581386566162,
      "step": 640
    },
    {
      "epoch": 1.6628278950735764,
      "grad_norm": 59.75,
      "learning_rate": 2.2516666666666666e-06,
      "loss": 1.1024110794067383,
      "step": 650
    },
    {
      "epoch": 1.6884197056941779,
      "grad_norm": 67.0,
      "learning_rate": 2.235e-06,
      "loss": 1.0247148513793944,
      "step": 660
    },
    {
      "epoch": 1.714011516314779,
      "grad_norm": 66.0,
      "learning_rate": 2.2183333333333334e-06,
      "loss": 1.162140464782715,
      "step": 670
    },
    {
      "epoch": 1.7396033269353808,
      "grad_norm": 79.5,
      "learning_rate": 2.2016666666666666e-06,
      "loss": 1.058082389831543,
      "step": 680
    },
    {
      "epoch": 1.765195137555982,
      "grad_norm": 103.5,
      "learning_rate": 2.1850000000000003e-06,
      "loss": 1.0551362037658691,
      "step": 690
    },
    {
      "epoch": 1.7907869481765835,
      "grad_norm": 41.5,
      "learning_rate": 2.1683333333333335e-06,
      "loss": 1.0396892547607421,
      "step": 700
    },
    {
      "epoch": 1.816378758797185,
      "grad_norm": 84.0,
      "learning_rate": 2.1516666666666667e-06,
      "loss": 1.0307888984680176,
      "step": 710
    },
    {
      "epoch": 1.8419705694177864,
      "grad_norm": 13.0625,
      "learning_rate": 2.135e-06,
      "loss": 1.1348337173461913,
      "step": 720
    },
    {
      "epoch": 1.8675623800383878,
      "grad_norm": 60.5,
      "learning_rate": 2.1183333333333335e-06,
      "loss": 1.1178834915161133,
      "step": 730
    },
    {
      "epoch": 1.893154190658989,
      "grad_norm": 90.5,
      "learning_rate": 2.1016666666666667e-06,
      "loss": 0.8540509223937989,
      "step": 740
    },
    {
      "epoch": 1.9187460012795905,
      "grad_norm": 68.0,
      "learning_rate": 2.085e-06,
      "loss": 1.0177457809448243,
      "step": 750
    },
    {
      "epoch": 1.944337811900192,
      "grad_norm": 56.75,
      "learning_rate": 2.068333333333333e-06,
      "loss": 0.9258890151977539,
      "step": 760
    },
    {
      "epoch": 1.9699296225207934,
      "grad_norm": 105.5,
      "learning_rate": 2.0516666666666668e-06,
      "loss": 1.1195788383483887,
      "step": 770
    },
    {
      "epoch": 1.9955214331413949,
      "grad_norm": 65.5,
      "learning_rate": 2.035e-06,
      "loss": 1.0428399085998534,
      "step": 780
    },
    {
      "epoch": 2.0204734484964813,
      "grad_norm": 199.0,
      "learning_rate": 2.0183333333333336e-06,
      "loss": 1.0544426918029786,
      "step": 790
    },
    {
      "epoch": 2.0460652591170825,
      "grad_norm": 62.0,
      "learning_rate": 2.001666666666667e-06,
      "loss": 0.9359260559082031,
      "step": 800
    },
    {
      "epoch": 2.0460652591170825,
      "eval_loss": 0.20818977057933807,
      "eval_runtime": 20.9478,
      "eval_samples_per_second": 95.475,
      "eval_steps_per_second": 3.007,
      "step": 800
    },
    {
      "epoch": 2.071657069737684,
      "grad_norm": 78.0,
      "learning_rate": 1.985e-06,
      "loss": 1.1695940017700195,
      "step": 810
    },
    {
      "epoch": 2.0972488803582854,
      "grad_norm": 51.75,
      "learning_rate": 1.9683333333333333e-06,
      "loss": 1.0586297988891602,
      "step": 820
    },
    {
      "epoch": 2.1228406909788866,
      "grad_norm": 63.25,
      "learning_rate": 1.951666666666667e-06,
      "loss": 0.9728346824645996,
      "step": 830
    },
    {
      "epoch": 2.1484325015994883,
      "grad_norm": 97.0,
      "learning_rate": 1.935e-06,
      "loss": 1.2120585441589355,
      "step": 840
    },
    {
      "epoch": 2.1740243122200895,
      "grad_norm": 78.5,
      "learning_rate": 1.9183333333333333e-06,
      "loss": 1.0046463012695312,
      "step": 850
    },
    {
      "epoch": 2.199616122840691,
      "grad_norm": 82.5,
      "learning_rate": 1.9016666666666665e-06,
      "loss": 1.0721829414367676,
      "step": 860
    },
    {
      "epoch": 2.2252079334612924,
      "grad_norm": 88.0,
      "learning_rate": 1.885e-06,
      "loss": 0.8954225540161133,
      "step": 870
    },
    {
      "epoch": 2.2507997440818936,
      "grad_norm": 56.25,
      "learning_rate": 1.8683333333333334e-06,
      "loss": 1.1441267013549805,
      "step": 880
    },
    {
      "epoch": 2.2763915547024953,
      "grad_norm": 86.5,
      "learning_rate": 1.8516666666666668e-06,
      "loss": 0.9673049926757813,
      "step": 890
    },
    {
      "epoch": 2.3019833653230966,
      "grad_norm": 107.5,
      "learning_rate": 1.8350000000000002e-06,
      "loss": 0.9580348014831543,
      "step": 900
    },
    {
      "epoch": 2.3275751759436982,
      "grad_norm": 47.75,
      "learning_rate": 1.8183333333333334e-06,
      "loss": 1.026679801940918,
      "step": 910
    },
    {
      "epoch": 2.3531669865642995,
      "grad_norm": 54.5,
      "learning_rate": 1.8016666666666666e-06,
      "loss": 0.9906099319458008,
      "step": 920
    },
    {
      "epoch": 2.3787587971849007,
      "grad_norm": 64.5,
      "learning_rate": 1.785e-06,
      "loss": 1.017255687713623,
      "step": 930
    },
    {
      "epoch": 2.4043506078055024,
      "grad_norm": 47.75,
      "learning_rate": 1.7683333333333333e-06,
      "loss": 0.8187576293945312,
      "step": 940
    },
    {
      "epoch": 2.4299424184261036,
      "grad_norm": 116.5,
      "learning_rate": 1.7516666666666667e-06,
      "loss": 1.147125816345215,
      "step": 950
    },
    {
      "epoch": 2.4555342290467053,
      "grad_norm": 75.5,
      "learning_rate": 1.7350000000000001e-06,
      "loss": 1.1997849464416503,
      "step": 960
    },
    {
      "epoch": 2.4811260396673065,
      "grad_norm": 42.0,
      "learning_rate": 1.7183333333333335e-06,
      "loss": 0.8572607040405273,
      "step": 970
    },
    {
      "epoch": 2.5067178502879077,
      "grad_norm": 120.0,
      "learning_rate": 1.7016666666666665e-06,
      "loss": 0.9942266464233398,
      "step": 980
    },
    {
      "epoch": 2.5323096609085094,
      "grad_norm": 81.0,
      "learning_rate": 1.685e-06,
      "loss": 0.9823317527770996,
      "step": 990
    },
    {
      "epoch": 2.5579014715291106,
      "grad_norm": 34.5,
      "learning_rate": 1.6683333333333334e-06,
      "loss": 1.0651761054992677,
      "step": 1000
    },
    {
      "epoch": 2.5579014715291106,
      "eval_loss": 0.20452462136745453,
      "eval_runtime": 20.9772,
      "eval_samples_per_second": 95.341,
      "eval_steps_per_second": 3.003,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3839710759498547e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}