{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 200,
  "global_step": 1900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013157894736842105,
      "grad_norm": 1.0702310800552368,
      "learning_rate": 8.421052631578948e-05,
      "loss": 1.8087,
      "step": 25
    },
    {
      "epoch": 0.02631578947368421,
      "grad_norm": 0.2948034405708313,
      "learning_rate": 0.00017192982456140353,
      "loss": 0.7073,
      "step": 50
    },
    {
      "epoch": 0.039473684210526314,
      "grad_norm": 0.17908604443073273,
      "learning_rate": 0.00019995801573733038,
      "loss": 0.578,
      "step": 75
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.20526789128780365,
      "learning_rate": 0.00019974382771078473,
      "loss": 0.5612,
      "step": 100
    },
    {
      "epoch": 0.06578947368421052,
      "grad_norm": 0.15455342829227448,
      "learning_rate": 0.00019934852677927834,
      "loss": 0.5241,
      "step": 125
    },
    {
      "epoch": 0.07894736842105263,
      "grad_norm": 0.19250690937042236,
      "learning_rate": 0.00019877283072256436,
      "loss": 0.4877,
      "step": 150
    },
    {
      "epoch": 0.09210526315789473,
      "grad_norm": 0.23086217045783997,
      "learning_rate": 0.00019801778487836048,
      "loss": 0.5016,
      "step": 175
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.15365199744701385,
      "learning_rate": 0.00019708476024424477,
      "loss": 0.4901,
      "step": 200
    },
    {
      "epoch": 0.11842105263157894,
      "grad_norm": 0.1698853224515915,
      "learning_rate": 0.00019597545098822504,
      "loss": 0.5259,
      "step": 225
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 0.20590293407440186,
      "learning_rate": 0.00019469187137250148,
      "loss": 0.4931,
      "step": 250
    },
    {
      "epoch": 0.14473684210526316,
      "grad_norm": 0.11492488533258438,
      "learning_rate": 0.00019323635209600841,
      "loss": 0.5297,
      "step": 275
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 0.18778519332408905,
      "learning_rate": 0.00019161153606237651,
      "loss": 0.4535,
      "step": 300
    },
    {
      "epoch": 0.17105263157894737,
      "grad_norm": 0.17645391821861267,
      "learning_rate": 0.00018982037358099963,
      "loss": 0.506,
      "step": 325
    },
    {
      "epoch": 0.18421052631578946,
      "grad_norm": 0.16658815741539001,
      "learning_rate": 0.00018786611700992044,
      "loss": 0.5277,
      "step": 350
    },
    {
      "epoch": 0.19736842105263158,
      "grad_norm": 0.1993815302848816,
      "learning_rate": 0.0001857523148502617,
      "loss": 0.5231,
      "step": 375
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.18013229966163635,
      "learning_rate": 0.00018348280530292713,
      "loss": 0.5433,
      "step": 400
    },
    {
      "epoch": 0.2236842105263158,
      "grad_norm": 0.16449177265167236,
      "learning_rate": 0.00018106170929927035,
      "loss": 0.466,
      "step": 425
    },
    {
      "epoch": 0.23684210526315788,
      "grad_norm": 0.18737125396728516,
      "learning_rate": 0.0001784934230183882,
      "loss": 0.4607,
      "step": 450
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.19233852624893188,
      "learning_rate": 0.00017578260990462372,
      "loss": 0.467,
      "step": 475
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 0.17257486283779144,
      "learning_rate": 0.00017293419219977486,
      "loss": 0.5052,
      "step": 500
    },
    {
      "epoch": 0.27631578947368424,
      "grad_norm": 0.1492719203233719,
      "learning_rate": 0.0001699533420053832,
      "loss": 0.4509,
      "step": 525
    },
    {
      "epoch": 0.2894736842105263,
      "grad_norm": 0.1736605167388916,
      "learning_rate": 0.0001668454718913325,
      "loss": 0.4505,
      "step": 550
    },
    {
      "epoch": 0.3026315789473684,
      "grad_norm": 0.2424936443567276,
      "learning_rate": 0.00016361622506780944,
      "loss": 0.4605,
      "step": 575
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.20284713804721832,
      "learning_rate": 0.0001602714651384722,
      "loss": 0.473,
      "step": 600
    },
    {
      "epoch": 0.32894736842105265,
      "grad_norm": 0.17443042993545532,
      "learning_rate": 0.0001568172654534328,
      "loss": 0.507,
      "step": 625
    },
    {
      "epoch": 0.34210526315789475,
      "grad_norm": 0.28264591097831726,
      "learning_rate": 0.0001532598980813858,
      "loss": 0.4671,
      "step": 650
    },
    {
      "epoch": 0.35526315789473684,
      "grad_norm": 0.19260287284851074,
      "learning_rate": 0.0001496058224209082,
      "loss": 0.4186,
      "step": 675
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.2163992077112198,
      "learning_rate": 0.00014586167347160846,
      "loss": 0.4269,
      "step": 700
    },
    {
      "epoch": 0.3815789473684211,
      "grad_norm": 0.21860243380069733,
      "learning_rate": 0.00014203424978642337,
      "loss": 0.4372,
      "step": 725
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 0.20048438012599945,
      "learning_rate": 0.00013813050112693778,
      "loss": 0.4827,
      "step": 750
    },
    {
      "epoch": 0.40789473684210525,
      "grad_norm": 0.1739310771226883,
      "learning_rate": 0.00013415751584414215,
      "loss": 0.3971,
      "step": 775
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.17237462103366852,
      "learning_rate": 0.00013012250800754284,
      "loss": 0.504,
      "step": 800
    },
    {
      "epoch": 0.4342105263157895,
      "grad_norm": 0.19956211745738983,
      "learning_rate": 0.0001260328043059947,
      "loss": 0.4915,
      "step": 825
    },
    {
      "epoch": 0.4473684210526316,
      "grad_norm": 0.18533027172088623,
      "learning_rate": 0.00012189583074404174,
      "loss": 0.4485,
      "step": 850
    },
    {
      "epoch": 0.4605263157894737,
      "grad_norm": 0.16435177624225616,
      "learning_rate": 0.0001177190991579223,
      "loss": 0.4291,
      "step": 875
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.1816023886203766,
      "learning_rate": 0.00011351019357572274,
      "loss": 0.4372,
      "step": 900
    },
    {
      "epoch": 0.4868421052631579,
      "grad_norm": 0.20043207705020905,
      "learning_rate": 0.00010927675644644666,
      "loss": 0.4254,
      "step": 925
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.18538975715637207,
      "learning_rate": 0.0001050264747630043,
      "loss": 0.4201,
      "step": 950
    },
    {
      "epoch": 0.5131578947368421,
      "grad_norm": 0.1710897535085678,
      "learning_rate": 0.00010076706610432009,
      "loss": 0.4715,
      "step": 975
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.4187946319580078,
      "learning_rate": 9.650626462190294e-05,
      "loss": 0.4448,
      "step": 1000
    },
    {
      "epoch": 0.5394736842105263,
      "grad_norm": 0.16618722677230835,
      "learning_rate": 9.2251806996324e-05,
      "loss": 0.508,
      "step": 1025
    },
    {
      "epoch": 0.5526315789473685,
      "grad_norm": 0.1595749408006668,
      "learning_rate": 8.801141838910238e-05,
      "loss": 0.4503,
      "step": 1050
    },
    {
      "epoch": 0.5657894736842105,
      "grad_norm": 0.2164568454027176,
      "learning_rate": 8.379279841550693e-05,
      "loss": 0.4799,
      "step": 1075
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.2523704469203949,
      "learning_rate": 7.960360716374442e-05,
      "loss": 0.3955,
      "step": 1100
    },
    {
      "epoch": 0.5921052631578947,
      "grad_norm": 0.23244792222976685,
      "learning_rate": 7.54514512859201e-05,
      "loss": 0.396,
      "step": 1125
    },
    {
      "epoch": 0.6052631578947368,
      "grad_norm": 0.10795140266418457,
      "learning_rate": 7.134387018602659e-05,
      "loss": 0.4064,
      "step": 1150
    },
    {
      "epoch": 0.618421052631579,
      "grad_norm": 0.1937549114227295,
      "learning_rate": 6.728832233004054e-05,
      "loss": 0.4566,
      "step": 1175
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.15512731671333313,
      "learning_rate": 6.329217170298507e-05,
      "loss": 0.5042,
      "step": 1200
    },
    {
      "epoch": 0.6447368421052632,
      "grad_norm": 0.2448330819606781,
      "learning_rate": 5.936267443754863e-05,
      "loss": 0.4398,
      "step": 1225
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 0.20559287071228027,
      "learning_rate": 5.550696563854032e-05,
      "loss": 0.422,
      "step": 1250
    },
    {
      "epoch": 0.6710526315789473,
      "grad_norm": 0.3416135311126709,
      "learning_rate": 5.173204642710514e-05,
      "loss": 0.4069,
      "step": 1275
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 1.1135472059249878,
      "learning_rate": 4.804477122822432e-05,
      "loss": 0.4197,
      "step": 1300
    },
    {
      "epoch": 0.6973684210526315,
      "grad_norm": 0.27472543716430664,
      "learning_rate": 4.4451835324583326e-05,
      "loss": 0.3944,
      "step": 1325
    },
    {
      "epoch": 0.7105263157894737,
      "grad_norm": 0.24637529253959656,
      "learning_rate": 4.0959762699407766e-05,
      "loss": 0.4211,
      "step": 1350
    },
    {
      "epoch": 0.7236842105263158,
      "grad_norm": 0.22961419820785522,
      "learning_rate": 3.7574894190341404e-05,
      "loss": 0.4369,
      "step": 1375
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.22714322805404663,
      "learning_rate": 3.430337597587622e-05,
      "loss": 0.4229,
      "step": 1400
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.20898780226707458,
      "learning_rate": 3.1151148415241035e-05,
      "loss": 0.4327,
      "step": 1425
    },
    {
      "epoch": 0.7631578947368421,
      "grad_norm": 0.2385832816362381,
      "learning_rate": 2.8123935262012447e-05,
      "loss": 0.4715,
      "step": 1450
    },
    {
      "epoch": 0.7763157894736842,
      "grad_norm": 0.2600831389427185,
      "learning_rate": 2.5227233271034322e-05,
      "loss": 0.4083,
      "step": 1475
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.27272310853004456,
      "learning_rate": 2.2466302217517133e-05,
      "loss": 0.4683,
      "step": 1500
    },
    {
      "epoch": 0.8026315789473685,
      "grad_norm": 0.24727025628089905,
      "learning_rate": 1.984615534644032e-05,
      "loss": 0.4563,
      "step": 1525
    },
    {
      "epoch": 0.8157894736842105,
      "grad_norm": 0.2413598895072937,
      "learning_rate": 1.7371550269599323e-05,
      "loss": 0.4579,
      "step": 1550
    },
    {
      "epoch": 0.8289473684210527,
      "grad_norm": 0.24908898770809174,
      "learning_rate": 1.50469803268267e-05,
      "loss": 0.4381,
      "step": 1575
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.26172706484794617,
      "learning_rate": 1.2876666427072703e-05,
      "loss": 0.4518,
      "step": 1600
    },
    {
      "epoch": 0.8552631578947368,
      "grad_norm": 0.12177186459302902,
      "learning_rate": 1.0864549384160927e-05,
      "loss": 0.4513,
      "step": 1625
    },
    {
      "epoch": 0.868421052631579,
      "grad_norm": 0.30838099122047424,
      "learning_rate": 9.014282761135084e-06,
      "loss": 0.3842,
      "step": 1650
    },
    {
      "epoch": 0.881578947368421,
      "grad_norm": 0.17628367245197296,
      "learning_rate": 7.329226236190201e-06,
      "loss": 0.4688,
      "step": 1675
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.2564370632171631,
      "learning_rate": 5.81243950223419e-06,
      "loss": 0.4317,
      "step": 1700
    },
    {
      "epoch": 0.9078947368421053,
      "grad_norm": 0.23841506242752075,
      "learning_rate": 4.4666767111569474e-06,
      "loss": 0.4026,
      "step": 1725
    },
    {
      "epoch": 0.9210526315789473,
      "grad_norm": 0.15477114915847778,
      "learning_rate": 3.294381472894781e-06,
      "loss": 0.3961,
      "step": 1750
    },
    {
      "epoch": 0.9342105263157895,
      "grad_norm": 0.23830120265483856,
      "learning_rate": 2.2976824183709835e-06,
      "loss": 0.4551,
      "step": 1775
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.25201982259750366,
      "learning_rate": 1.4783893343691458e-06,
      "loss": 0.4004,
      "step": 1800
    },
    {
      "epoch": 0.9605263157894737,
      "grad_norm": 0.2426755726337433,
      "learning_rate": 8.379898773574924e-07,
      "loss": 0.4222,
      "step": 1825
    },
    {
      "epoch": 0.9736842105263158,
      "grad_norm": 0.16299939155578613,
      "learning_rate": 3.7764687223110773e-07,
      "loss": 0.393,
      "step": 1850
    },
    {
      "epoch": 0.9868421052631579,
      "grad_norm": 0.18138697743415833,
      "learning_rate": 9.8196200877132e-08,
      "loss": 0.4552,
      "step": 1875
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.24889549612998962,
      "learning_rate": 1.452843966354145e-10,
      "loss": 0.454,
      "step": 1900
    }
  ],
  "logging_steps": 25,
  "max_steps": 1900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.246950527006618e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}