{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06257604727968016,
  "eval_steps": 150,
  "global_step": 180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006952894142186686,
      "grad_norm": 5.413117383066536,
      "learning_rate": 6.944444444444445e-07,
      "loss": 2.3653,
      "step": 2
    },
    {
      "epoch": 0.0013905788284373371,
      "grad_norm": 5.092870612337868,
      "learning_rate": 1.388888888888889e-06,
      "loss": 2.5001,
      "step": 4
    },
    {
      "epoch": 0.0020858682426560054,
      "grad_norm": 3.6285625961711943,
      "learning_rate": 2.0833333333333334e-06,
      "loss": 2.3759,
      "step": 6
    },
    {
      "epoch": 0.0027811576568746743,
      "grad_norm": 2.5025911526151075,
      "learning_rate": 2.777777777777778e-06,
      "loss": 1.944,
      "step": 8
    },
    {
      "epoch": 0.0034764470710933427,
      "grad_norm": 3.077266049542496,
      "learning_rate": 3.4722222222222224e-06,
      "loss": 2.2504,
      "step": 10
    },
    {
      "epoch": 0.004171736485312011,
      "grad_norm": 4.068243939187174,
      "learning_rate": 4.166666666666667e-06,
      "loss": 2.0637,
      "step": 12
    },
    {
      "epoch": 0.00486702589953068,
      "grad_norm": 3.511444738830971,
      "learning_rate": 4.861111111111111e-06,
      "loss": 2.3604,
      "step": 14
    },
    {
      "epoch": 0.0055623153137493485,
      "grad_norm": 5.925744892256934,
      "learning_rate": 5.555555555555556e-06,
      "loss": 2.6528,
      "step": 16
    },
    {
      "epoch": 0.0062576047279680165,
      "grad_norm": 2.7950114871483405,
      "learning_rate": 6.25e-06,
      "loss": 2.3229,
      "step": 18
    },
    {
      "epoch": 0.006952894142186685,
      "grad_norm": 6.586211843766182,
      "learning_rate": 6.944444444444445e-06,
      "loss": 2.342,
      "step": 20
    },
    {
      "epoch": 0.0076481835564053535,
      "grad_norm": 4.902839955269193,
      "learning_rate": 7.63888888888889e-06,
      "loss": 2.4188,
      "step": 22
    },
    {
      "epoch": 0.008343472970624021,
      "grad_norm": 4.257062809771645,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.7957,
      "step": 24
    },
    {
      "epoch": 0.009038762384842691,
      "grad_norm": 4.460352004615699,
      "learning_rate": 9.027777777777777e-06,
      "loss": 2.0726,
      "step": 26
    },
    {
      "epoch": 0.00973405179906136,
      "grad_norm": 5.858061506133739,
      "learning_rate": 9.722222222222223e-06,
      "loss": 2.0455,
      "step": 28
    },
    {
      "epoch": 0.010429341213280027,
      "grad_norm": 4.331946668100709,
      "learning_rate": 1.0416666666666668e-05,
      "loss": 1.7645,
      "step": 30
    },
    {
      "epoch": 0.011124630627498697,
      "grad_norm": 5.428742204187391,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 1.7446,
      "step": 32
    },
    {
      "epoch": 0.011819920041717365,
      "grad_norm": 2.485909286541028,
      "learning_rate": 1.1805555555555555e-05,
      "loss": 1.5885,
      "step": 34
    },
    {
      "epoch": 0.012515209455936033,
      "grad_norm": 3.2602949308730222,
      "learning_rate": 1.25e-05,
      "loss": 1.1014,
      "step": 36
    },
    {
      "epoch": 0.013210498870154701,
      "grad_norm": 4.962187747415964,
      "learning_rate": 1.3194444444444446e-05,
      "loss": 1.3588,
      "step": 38
    },
    {
      "epoch": 0.01390578828437337,
      "grad_norm": 7.627756894198461,
      "learning_rate": 1.388888888888889e-05,
      "loss": 1.4014,
      "step": 40
    },
    {
      "epoch": 0.014601077698592039,
      "grad_norm": 2.821848388410092,
      "learning_rate": 1.4583333333333335e-05,
      "loss": 1.0959,
      "step": 42
    },
    {
      "epoch": 0.015296367112810707,
      "grad_norm": 10.989320944549025,
      "learning_rate": 1.527777777777778e-05,
      "loss": 1.739,
      "step": 44
    },
    {
      "epoch": 0.015991656527029375,
      "grad_norm": 4.300936602591115,
      "learning_rate": 1.597222222222222e-05,
      "loss": 1.1078,
      "step": 46
    },
    {
      "epoch": 0.016686945941248043,
      "grad_norm": 3.7539663261019856,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.2701,
      "step": 48
    },
    {
      "epoch": 0.017382235355466714,
      "grad_norm": 2.589248169352173,
      "learning_rate": 1.736111111111111e-05,
      "loss": 1.4452,
      "step": 50
    },
    {
      "epoch": 0.018077524769685382,
      "grad_norm": 3.6679301322156177,
      "learning_rate": 1.8055555555555555e-05,
      "loss": 1.4243,
      "step": 52
    },
    {
      "epoch": 0.01877281418390405,
      "grad_norm": 2.0885660923860074,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 1.4453,
      "step": 54
    },
    {
      "epoch": 0.01946810359812272,
      "grad_norm": 2.955353237610474,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 1.5388,
      "step": 56
    },
    {
      "epoch": 0.020163393012341387,
      "grad_norm": 3.0527006398487018,
      "learning_rate": 2.013888888888889e-05,
      "loss": 1.4043,
      "step": 58
    },
    {
      "epoch": 0.020858682426560055,
      "grad_norm": 1.9862208864154767,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 1.1007,
      "step": 60
    },
    {
      "epoch": 0.021553971840778723,
      "grad_norm": 2.347361178472164,
      "learning_rate": 2.152777777777778e-05,
      "loss": 0.9291,
      "step": 62
    },
    {
      "epoch": 0.022249261254997394,
      "grad_norm": 2.4812993223105995,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.9592,
      "step": 64
    },
    {
      "epoch": 0.022944550669216062,
      "grad_norm": 1.639333831845777,
      "learning_rate": 2.2916666666666667e-05,
      "loss": 1.0645,
      "step": 66
    },
    {
      "epoch": 0.02363984008343473,
      "grad_norm": 2.92858351082494,
      "learning_rate": 2.361111111111111e-05,
      "loss": 1.4269,
      "step": 68
    },
    {
      "epoch": 0.024335129497653398,
      "grad_norm": 2.8503434812871604,
      "learning_rate": 2.4305555555555558e-05,
      "loss": 0.7829,
      "step": 70
    },
    {
      "epoch": 0.025030418911872066,
      "grad_norm": 2.4875590459354107,
      "learning_rate": 2.5e-05,
      "loss": 0.9733,
      "step": 72
    },
    {
      "epoch": 0.025725708326090734,
      "grad_norm": 5.2567545525905075,
      "learning_rate": 2.5694444444444445e-05,
      "loss": 1.3559,
      "step": 74
    },
    {
      "epoch": 0.026420997740309402,
      "grad_norm": 4.68745753567611,
      "learning_rate": 2.6388888888888892e-05,
      "loss": 1.1499,
      "step": 76
    },
    {
      "epoch": 0.027116287154528074,
      "grad_norm": 2.810345453706711,
      "learning_rate": 2.7083333333333332e-05,
      "loss": 0.8636,
      "step": 78
    },
    {
      "epoch": 0.02781157656874674,
      "grad_norm": 3.0144493626195388,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.9274,
      "step": 80
    },
    {
      "epoch": 0.02850686598296541,
      "grad_norm": 2.3263036535508523,
      "learning_rate": 2.8472222222222223e-05,
      "loss": 1.3979,
      "step": 82
    },
    {
      "epoch": 0.029202155397184078,
      "grad_norm": 1.6009019341419857,
      "learning_rate": 2.916666666666667e-05,
      "loss": 0.9039,
      "step": 84
    },
    {
      "epoch": 0.029897444811402746,
      "grad_norm": 2.0637506891442294,
      "learning_rate": 2.9861111111111113e-05,
      "loss": 1.5187,
      "step": 86
    },
    {
      "epoch": 0.030592734225621414,
      "grad_norm": 1.5533001268209932,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.8937,
      "step": 88
    },
    {
      "epoch": 0.03128802363984008,
      "grad_norm": 1.9974857545819733,
      "learning_rate": 3.125e-05,
      "loss": 0.8218,
      "step": 90
    },
    {
      "epoch": 0.03198331305405875,
      "grad_norm": 1.871899331408953,
      "learning_rate": 3.194444444444444e-05,
      "loss": 1.2451,
      "step": 92
    },
    {
      "epoch": 0.03267860246827742,
      "grad_norm": 1.591601830348497,
      "learning_rate": 3.263888888888889e-05,
      "loss": 0.7485,
      "step": 94
    },
    {
      "epoch": 0.033373891882496086,
      "grad_norm": 2.404166647711005,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.1587,
      "step": 96
    },
    {
      "epoch": 0.03406918129671476,
      "grad_norm": 1.581080788392888,
      "learning_rate": 3.402777777777778e-05,
      "loss": 0.9578,
      "step": 98
    },
    {
      "epoch": 0.03476447071093343,
      "grad_norm": 2.1551207338771547,
      "learning_rate": 3.472222222222222e-05,
      "loss": 1.1305,
      "step": 100
    },
    {
      "epoch": 0.0354597601251521,
      "grad_norm": 4.2246272812704,
      "learning_rate": 3.541666666666667e-05,
      "loss": 1.04,
      "step": 102
    },
    {
      "epoch": 0.036155049539370765,
      "grad_norm": 2.5526898161765588,
      "learning_rate": 3.611111111111111e-05,
      "loss": 1.0743,
      "step": 104
    },
    {
      "epoch": 0.03685033895358943,
      "grad_norm": 1.9784815137623597,
      "learning_rate": 3.6805555555555556e-05,
      "loss": 0.9667,
      "step": 106
    },
    {
      "epoch": 0.0375456283678081,
      "grad_norm": 1.9131648200880944,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.8951,
      "step": 108
    },
    {
      "epoch": 0.03824091778202677,
      "grad_norm": 3.9405296351174575,
      "learning_rate": 3.8194444444444444e-05,
      "loss": 1.222,
      "step": 110
    },
    {
      "epoch": 0.03893620719624544,
      "grad_norm": 13.764861545850291,
      "learning_rate": 3.888888888888889e-05,
      "loss": 1.0497,
      "step": 112
    },
    {
      "epoch": 0.039631496610464105,
      "grad_norm": 3.998123122175411,
      "learning_rate": 3.958333333333333e-05,
      "loss": 1.0901,
      "step": 114
    },
    {
      "epoch": 0.04032678602468277,
      "grad_norm": 3.126193921423756,
      "learning_rate": 4.027777777777778e-05,
      "loss": 1.1143,
      "step": 116
    },
    {
      "epoch": 0.04102207543890144,
      "grad_norm": 2.7839926692610613,
      "learning_rate": 4.0972222222222225e-05,
      "loss": 1.1637,
      "step": 118
    },
    {
      "epoch": 0.04171736485312011,
      "grad_norm": 2.591162621161276,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.0624,
      "step": 120
    },
    {
      "epoch": 0.04241265426733878,
      "grad_norm": 1.4930703711545332,
      "learning_rate": 4.236111111111111e-05,
      "loss": 1.0239,
      "step": 122
    },
    {
      "epoch": 0.043107943681557445,
      "grad_norm": 4.355150070532966,
      "learning_rate": 4.305555555555556e-05,
      "loss": 1.266,
      "step": 124
    },
    {
      "epoch": 0.04380323309577612,
      "grad_norm": 1.8285608876277135,
      "learning_rate": 4.375e-05,
      "loss": 1.0667,
      "step": 126
    },
    {
      "epoch": 0.04449852250999479,
      "grad_norm": 2.1848832742617055,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.7549,
      "step": 128
    },
    {
      "epoch": 0.045193811924213456,
      "grad_norm": 3.547857947451226,
      "learning_rate": 4.5138888888888894e-05,
      "loss": 0.7974,
      "step": 130
    },
    {
      "epoch": 0.045889101338432124,
      "grad_norm": 3.372457028128184,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 1.0482,
      "step": 132
    },
    {
      "epoch": 0.04658439075265079,
      "grad_norm": 2.2871138548091703,
      "learning_rate": 4.652777777777778e-05,
      "loss": 0.8246,
      "step": 134
    },
    {
      "epoch": 0.04727968016686946,
      "grad_norm": 1.7489408054743605,
      "learning_rate": 4.722222222222222e-05,
      "loss": 1.0011,
      "step": 136
    },
    {
      "epoch": 0.04797496958108813,
      "grad_norm": 1.944650349232646,
      "learning_rate": 4.791666666666667e-05,
      "loss": 0.7828,
      "step": 138
    },
    {
      "epoch": 0.048670258995306796,
      "grad_norm": 2.321619459307342,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 1.02,
      "step": 140
    },
    {
      "epoch": 0.049365548409525464,
      "grad_norm": 5.317732559595606,
      "learning_rate": 4.930555555555556e-05,
      "loss": 0.9539,
      "step": 142
    },
    {
      "epoch": 0.05006083782374413,
      "grad_norm": 1.5887292172279854,
      "learning_rate": 5e-05,
      "loss": 0.7961,
      "step": 144
    },
    {
      "epoch": 0.0507561272379628,
      "grad_norm": 2.9987019111854964,
      "learning_rate": 5.069444444444444e-05,
      "loss": 1.0018,
      "step": 146
    },
    {
      "epoch": 0.05145141665218147,
      "grad_norm": 5.63878906132749,
      "learning_rate": 5.138888888888889e-05,
      "loss": 0.9278,
      "step": 148
    },
    {
      "epoch": 0.052146706066400136,
      "grad_norm": 2.4849685204332834,
      "learning_rate": 5.208333333333334e-05,
      "loss": 0.7531,
      "step": 150
    },
    {
      "epoch": 0.052146706066400136,
      "eval_loss": 0.9286500215530396,
      "eval_runtime": 711.2619,
      "eval_samples_per_second": 6.808,
      "eval_steps_per_second": 0.214,
      "step": 150
    },
    {
      "epoch": 0.052841995480618804,
      "grad_norm": 3.4927981580288776,
      "learning_rate": 5.2777777777777784e-05,
      "loss": 0.7422,
      "step": 152
    },
    {
      "epoch": 0.05353728489483748,
      "grad_norm": 2.6593724943984682,
      "learning_rate": 5.3472222222222224e-05,
      "loss": 0.7762,
      "step": 154
    },
    {
      "epoch": 0.05423257430905615,
      "grad_norm": 2.99709354088536,
      "learning_rate": 5.4166666666666664e-05,
      "loss": 0.8658,
      "step": 156
    },
    {
      "epoch": 0.054927863723274815,
      "grad_norm": 3.9196361623391414,
      "learning_rate": 5.486111111111112e-05,
      "loss": 1.1783,
      "step": 158
    },
    {
      "epoch": 0.05562315313749348,
      "grad_norm": 3.022562685608673,
      "learning_rate": 5.555555555555556e-05,
      "loss": 1.0602,
      "step": 160
    },
    {
      "epoch": 0.05631844255171215,
      "grad_norm": 3.292942684053579,
      "learning_rate": 5.6250000000000005e-05,
      "loss": 0.8561,
      "step": 162
    },
    {
      "epoch": 0.05701373196593082,
      "grad_norm": 2.397775023338686,
      "learning_rate": 5.6944444444444445e-05,
      "loss": 0.9561,
      "step": 164
    },
    {
      "epoch": 0.05770902138014949,
      "grad_norm": 3.0546714312119643,
      "learning_rate": 5.7638888888888886e-05,
      "loss": 0.8274,
      "step": 166
    },
    {
      "epoch": 0.058404310794368156,
      "grad_norm": 2.4021883380894393,
      "learning_rate": 5.833333333333334e-05,
      "loss": 0.8492,
      "step": 168
    },
    {
      "epoch": 0.059099600208586824,
      "grad_norm": 2.6052829770116293,
      "learning_rate": 5.902777777777778e-05,
      "loss": 1.1005,
      "step": 170
    },
    {
      "epoch": 0.05979488962280549,
      "grad_norm": 1.6838192892320467,
      "learning_rate": 5.972222222222223e-05,
      "loss": 1.0157,
      "step": 172
    },
    {
      "epoch": 0.06049017903702416,
      "grad_norm": 3.98880214871885,
      "learning_rate": 6.041666666666667e-05,
      "loss": 0.8136,
      "step": 174
    },
    {
      "epoch": 0.06118546845124283,
      "grad_norm": 4.81494345341073,
      "learning_rate": 6.111111111111112e-05,
      "loss": 0.9475,
      "step": 176
    },
    {
      "epoch": 0.061880757865461496,
      "grad_norm": 1.9926278890091862,
      "learning_rate": 6.180555555555556e-05,
      "loss": 0.6549,
      "step": 178
    },
    {
      "epoch": 0.06257604727968016,
      "grad_norm": 1.750353030728397,
      "learning_rate": 6.25e-05,
      "loss": 1.1442,
      "step": 180
    }
  ],
  "logging_steps": 2,
  "max_steps": 5752,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 90,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 715535969943552.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}