{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3846153846153846,
  "eval_steps": 10,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006153846153846154,
      "eval_loss": 1.845949411392212,
      "eval_runtime": 1.9761,
      "eval_samples_per_second": 57.69,
      "eval_steps_per_second": 3.036,
      "step": 2
    },
    {
      "epoch": 0.03076923076923077,
      "grad_norm": 29.46457290649414,
      "learning_rate": 7.692307692307694e-07,
      "loss": 1.944,
      "step": 10
    },
    {
      "epoch": 0.03076923076923077,
      "eval_loss": 1.7965577840805054,
      "eval_runtime": 1.9506,
      "eval_samples_per_second": 58.444,
      "eval_steps_per_second": 3.076,
      "step": 10
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 14.49207878112793,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 1.6999,
      "step": 20
    },
    {
      "epoch": 0.06153846153846154,
      "eval_loss": 1.5032916069030762,
      "eval_runtime": 1.9599,
      "eval_samples_per_second": 58.168,
      "eval_steps_per_second": 3.061,
      "step": 20
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 11.355466842651367,
      "learning_rate": 2.307692307692308e-06,
      "loss": 1.1499,
      "step": 30
    },
    {
      "epoch": 0.09230769230769231,
      "eval_loss": 0.8391174674034119,
      "eval_runtime": 1.9437,
      "eval_samples_per_second": 58.65,
      "eval_steps_per_second": 3.087,
      "step": 30
    },
    {
      "epoch": 0.12307692307692308,
      "grad_norm": 5.648468017578125,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 0.7194,
      "step": 40
    },
    {
      "epoch": 0.12307692307692308,
      "eval_loss": 0.6716201305389404,
      "eval_runtime": 1.9517,
      "eval_samples_per_second": 58.411,
      "eval_steps_per_second": 3.074,
      "step": 40
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 5.752841949462891,
      "learning_rate": 3.846153846153847e-06,
      "loss": 0.6811,
      "step": 50
    },
    {
      "epoch": 0.15384615384615385,
      "eval_loss": 0.6289324164390564,
      "eval_runtime": 1.952,
      "eval_samples_per_second": 58.401,
      "eval_steps_per_second": 3.074,
      "step": 50
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 3.414722204208374,
      "learning_rate": 4.615384615384616e-06,
      "loss": 0.5924,
      "step": 60
    },
    {
      "epoch": 0.18461538461538463,
      "eval_loss": 0.6140013337135315,
      "eval_runtime": 1.94,
      "eval_samples_per_second": 58.762,
      "eval_steps_per_second": 3.093,
      "step": 60
    },
    {
      "epoch": 0.2153846153846154,
      "grad_norm": 5.556036949157715,
      "learning_rate": 5.384615384615385e-06,
      "loss": 0.6135,
      "step": 70
    },
    {
      "epoch": 0.2153846153846154,
      "eval_loss": 0.6054026484489441,
      "eval_runtime": 1.9659,
      "eval_samples_per_second": 57.988,
      "eval_steps_per_second": 3.052,
      "step": 70
    },
    {
      "epoch": 0.24615384615384617,
      "grad_norm": 4.436710834503174,
      "learning_rate": 6.153846153846155e-06,
      "loss": 0.5952,
      "step": 80
    },
    {
      "epoch": 0.24615384615384617,
      "eval_loss": 0.5986860990524292,
      "eval_runtime": 1.9428,
      "eval_samples_per_second": 58.677,
      "eval_steps_per_second": 3.088,
      "step": 80
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 3.496018409729004,
      "learning_rate": 6.923076923076923e-06,
      "loss": 0.5887,
      "step": 90
    },
    {
      "epoch": 0.27692307692307694,
      "eval_loss": 0.594973623752594,
      "eval_runtime": 1.9468,
      "eval_samples_per_second": 58.558,
      "eval_steps_per_second": 3.082,
      "step": 90
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 2.3540539741516113,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.5634,
      "step": 100
    },
    {
      "epoch": 0.3076923076923077,
      "eval_loss": 0.5954164266586304,
      "eval_runtime": 1.948,
      "eval_samples_per_second": 58.521,
      "eval_steps_per_second": 3.08,
      "step": 100
    },
    {
      "epoch": 0.3384615384615385,
      "grad_norm": 2.9880635738372803,
      "learning_rate": 8.461538461538462e-06,
      "loss": 0.5827,
      "step": 110
    },
    {
      "epoch": 0.3384615384615385,
      "eval_loss": 0.5955133438110352,
      "eval_runtime": 1.9432,
      "eval_samples_per_second": 58.667,
      "eval_steps_per_second": 3.088,
      "step": 110
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 1.9405996799468994,
      "learning_rate": 9.230769230769232e-06,
      "loss": 0.5726,
      "step": 120
    },
    {
      "epoch": 0.36923076923076925,
      "eval_loss": 0.5951128602027893,
      "eval_runtime": 1.9715,
      "eval_samples_per_second": 57.824,
      "eval_steps_per_second": 3.043,
      "step": 120
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.9948021173477173,
      "learning_rate": 1e-05,
      "loss": 0.6488,
      "step": 130
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.5964463949203491,
      "eval_runtime": 2.1032,
      "eval_samples_per_second": 54.203,
      "eval_steps_per_second": 2.853,
      "step": 130
    },
    {
      "epoch": 0.4307692307692308,
      "grad_norm": 1.95350980758667,
      "learning_rate": 1.076923076923077e-05,
      "loss": 0.6218,
      "step": 140
    },
    {
      "epoch": 0.4307692307692308,
      "eval_loss": 0.5996471047401428,
      "eval_runtime": 1.9539,
      "eval_samples_per_second": 58.345,
      "eval_steps_per_second": 3.071,
      "step": 140
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 3.840015411376953,
      "learning_rate": 1.1538461538461538e-05,
      "loss": 0.5585,
      "step": 150
    },
    {
      "epoch": 0.46153846153846156,
      "eval_loss": 0.6000372767448425,
      "eval_runtime": 1.9457,
      "eval_samples_per_second": 58.592,
      "eval_steps_per_second": 3.084,
      "step": 150
    },
    {
      "epoch": 0.49230769230769234,
      "grad_norm": 2.345364809036255,
      "learning_rate": 1.230769230769231e-05,
      "loss": 0.5314,
      "step": 160
    },
    {
      "epoch": 0.49230769230769234,
      "eval_loss": 0.6025042533874512,
      "eval_runtime": 1.9398,
      "eval_samples_per_second": 58.768,
      "eval_steps_per_second": 3.093,
      "step": 160
    },
    {
      "epoch": 0.5230769230769231,
      "grad_norm": 3.162071704864502,
      "learning_rate": 1.3076923076923078e-05,
      "loss": 0.6901,
      "step": 170
    },
    {
      "epoch": 0.5230769230769231,
      "eval_loss": 0.598171055316925,
      "eval_runtime": 1.9419,
      "eval_samples_per_second": 58.705,
      "eval_steps_per_second": 3.09,
      "step": 170
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 3.9432108402252197,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 0.6604,
      "step": 180
    },
    {
      "epoch": 0.5538461538461539,
      "eval_loss": 0.5974885821342468,
      "eval_runtime": 1.9664,
      "eval_samples_per_second": 57.975,
      "eval_steps_per_second": 3.051,
      "step": 180
    },
    {
      "epoch": 0.5846153846153846,
      "grad_norm": 1.904718279838562,
      "learning_rate": 1.4615384615384615e-05,
      "loss": 0.5806,
      "step": 190
    },
    {
      "epoch": 0.5846153846153846,
      "eval_loss": 0.6012160778045654,
      "eval_runtime": 2.082,
      "eval_samples_per_second": 54.755,
      "eval_steps_per_second": 2.882,
      "step": 190
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 2.2823173999786377,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.588,
      "step": 200
    },
    {
      "epoch": 0.6153846153846154,
      "eval_loss": 0.6052933931350708,
      "eval_runtime": 1.9613,
      "eval_samples_per_second": 58.124,
      "eval_steps_per_second": 3.059,
      "step": 200
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 1.8020161390304565,
      "learning_rate": 1.6153846153846154e-05,
      "loss": 0.5826,
      "step": 210
    },
    {
      "epoch": 0.6461538461538462,
      "eval_loss": 0.6047356724739075,
      "eval_runtime": 1.9487,
      "eval_samples_per_second": 58.5,
      "eval_steps_per_second": 3.079,
      "step": 210
    },
    {
      "epoch": 0.676923076923077,
      "grad_norm": 1.8297995328903198,
      "learning_rate": 1.6923076923076924e-05,
      "loss": 0.5442,
      "step": 220
    },
    {
      "epoch": 0.676923076923077,
      "eval_loss": 0.6105689406394958,
      "eval_runtime": 2.0567,
      "eval_samples_per_second": 55.429,
      "eval_steps_per_second": 2.917,
      "step": 220
    },
    {
      "epoch": 0.7076923076923077,
      "grad_norm": 1.8141131401062012,
      "learning_rate": 1.7692307692307694e-05,
      "loss": 0.602,
      "step": 230
    },
    {
      "epoch": 0.7076923076923077,
      "eval_loss": 0.6149886250495911,
      "eval_runtime": 2.1951,
      "eval_samples_per_second": 51.933,
      "eval_steps_per_second": 2.733,
      "step": 230
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 2.093683958053589,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 0.6103,
      "step": 240
    },
    {
      "epoch": 0.7384615384615385,
      "eval_loss": 0.621900200843811,
      "eval_runtime": 1.9465,
      "eval_samples_per_second": 58.567,
      "eval_steps_per_second": 3.082,
      "step": 240
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 1.840038776397705,
      "learning_rate": 1.923076923076923e-05,
      "loss": 0.5775,
      "step": 250
    },
    {
      "epoch": 0.7692307692307693,
      "eval_loss": 0.6232128739356995,
      "eval_runtime": 1.9883,
      "eval_samples_per_second": 57.334,
      "eval_steps_per_second": 3.018,
      "step": 250
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.7329185009002686,
      "learning_rate": 2e-05,
      "loss": 0.6808,
      "step": 260
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.6226441264152527,
      "eval_runtime": 1.9469,
      "eval_samples_per_second": 58.553,
      "eval_steps_per_second": 3.082,
      "step": 260
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 2.738678455352783,
      "learning_rate": 1.999909877856721e-05,
      "loss": 0.5833,
      "step": 270
    },
    {
      "epoch": 0.8307692307692308,
      "eval_loss": 0.6240194439888,
      "eval_runtime": 1.9419,
      "eval_samples_per_second": 58.706,
      "eval_steps_per_second": 3.09,
      "step": 270
    },
    {
      "epoch": 0.8615384615384616,
      "grad_norm": 2.0359909534454346,
      "learning_rate": 1.9996395276708856e-05,
      "loss": 0.691,
      "step": 280
    },
    {
      "epoch": 0.8615384615384616,
      "eval_loss": 0.6267117857933044,
      "eval_runtime": 1.939,
      "eval_samples_per_second": 58.794,
      "eval_steps_per_second": 3.094,
      "step": 280
    },
    {
      "epoch": 0.8923076923076924,
      "grad_norm": 1.7706685066223145,
      "learning_rate": 1.9991889981715696e-05,
      "loss": 0.6404,
      "step": 290
    },
    {
      "epoch": 0.8923076923076924,
      "eval_loss": 0.6222097873687744,
      "eval_runtime": 1.9533,
      "eval_samples_per_second": 58.363,
      "eval_steps_per_second": 3.072,
      "step": 290
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 2.129652976989746,
      "learning_rate": 1.9985583705641418e-05,
      "loss": 0.7109,
      "step": 300
    },
    {
      "epoch": 0.9230769230769231,
      "eval_loss": 0.6229674816131592,
      "eval_runtime": 1.9467,
      "eval_samples_per_second": 58.561,
      "eval_steps_per_second": 3.082,
      "step": 300
    },
    {
      "epoch": 0.9538461538461539,
      "grad_norm": 1.8439427614212036,
      "learning_rate": 1.9977477585156252e-05,
      "loss": 0.6623,
      "step": 310
    },
    {
      "epoch": 0.9538461538461539,
      "eval_loss": 0.6273208856582642,
      "eval_runtime": 2.0985,
      "eval_samples_per_second": 54.324,
      "eval_steps_per_second": 2.859,
      "step": 310
    },
    {
      "epoch": 0.9846153846153847,
      "grad_norm": 2.1446306705474854,
      "learning_rate": 1.9967573081342103e-05,
      "loss": 0.5583,
      "step": 320
    },
    {
      "epoch": 0.9846153846153847,
      "eval_loss": 0.6260280013084412,
      "eval_runtime": 1.9521,
      "eval_samples_per_second": 58.398,
      "eval_steps_per_second": 3.074,
      "step": 320
    },
    {
      "epoch": 1.0153846153846153,
      "grad_norm": 1.9259562492370605,
      "learning_rate": 1.9955871979429188e-05,
      "loss": 0.4857,
      "step": 330
    },
    {
      "epoch": 1.0153846153846153,
      "eval_loss": 0.6497873067855835,
      "eval_runtime": 1.9489,
      "eval_samples_per_second": 58.496,
      "eval_steps_per_second": 3.079,
      "step": 330
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 1.8625404834747314,
      "learning_rate": 1.9942376388474282e-05,
      "loss": 0.4152,
      "step": 340
    },
    {
      "epoch": 1.0461538461538462,
      "eval_loss": 0.6430822014808655,
      "eval_runtime": 1.9534,
      "eval_samples_per_second": 58.358,
      "eval_steps_per_second": 3.071,
      "step": 340
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 1.1712415218353271,
      "learning_rate": 1.992708874098054e-05,
      "loss": 0.3459,
      "step": 350
    },
    {
      "epoch": 1.0769230769230769,
      "eval_loss": 0.671064019203186,
      "eval_runtime": 1.9772,
      "eval_samples_per_second": 57.658,
      "eval_steps_per_second": 3.035,
      "step": 350
    },
    {
      "epoch": 1.1076923076923078,
      "grad_norm": 1.0710129737854004,
      "learning_rate": 1.9910011792459086e-05,
      "loss": 0.4307,
      "step": 360
    },
    {
      "epoch": 1.1076923076923078,
      "eval_loss": 0.6545295119285583,
      "eval_runtime": 2.0822,
      "eval_samples_per_second": 54.749,
      "eval_steps_per_second": 2.882,
      "step": 360
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 1.839811086654663,
      "learning_rate": 1.989114862093232e-05,
      "loss": 0.4084,
      "step": 370
    },
    {
      "epoch": 1.1384615384615384,
      "eval_loss": 0.6743721961975098,
      "eval_runtime": 1.962,
      "eval_samples_per_second": 58.105,
      "eval_steps_per_second": 3.058,
      "step": 370
    },
    {
      "epoch": 1.1692307692307693,
      "grad_norm": 2.2416107654571533,
      "learning_rate": 1.9870502626379127e-05,
      "loss": 0.4203,
      "step": 380
    },
    {
      "epoch": 1.1692307692307693,
      "eval_loss": 0.6703702211380005,
      "eval_runtime": 2.0871,
      "eval_samples_per_second": 54.621,
      "eval_steps_per_second": 2.875,
      "step": 380
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.8775320053100586,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 0.3056,
      "step": 390
    },
    {
      "epoch": 1.2,
      "eval_loss": 0.680027425289154,
      "eval_runtime": 2.0739,
      "eval_samples_per_second": 54.97,
      "eval_steps_per_second": 2.893,
      "step": 390
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 2.1544764041900635,
      "learning_rate": 1.9823877374156647e-05,
      "loss": 0.4332,
      "step": 400
    },
    {
      "epoch": 1.2307692307692308,
      "eval_loss": 0.6662920117378235,
      "eval_runtime": 1.9498,
      "eval_samples_per_second": 58.466,
      "eval_steps_per_second": 3.077,
      "step": 400
    },
    {
      "epoch": 1.2615384615384615,
      "grad_norm": 1.740652084350586,
      "learning_rate": 1.979790652042268e-05,
      "loss": 0.3707,
      "step": 410
    },
    {
      "epoch": 1.2615384615384615,
      "eval_loss": 0.6721649765968323,
      "eval_runtime": 1.9421,
      "eval_samples_per_second": 58.699,
      "eval_steps_per_second": 3.089,
      "step": 410
    },
    {
      "epoch": 1.2923076923076924,
      "grad_norm": 1.8645464181900024,
      "learning_rate": 1.977016965001817e-05,
      "loss": 0.412,
      "step": 420
    },
    {
      "epoch": 1.2923076923076924,
      "eval_loss": 0.6605477333068848,
      "eval_runtime": 1.9455,
      "eval_samples_per_second": 58.597,
      "eval_steps_per_second": 3.084,
      "step": 420
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 1.3930943012237549,
      "learning_rate": 1.9740671762355548e-05,
      "loss": 0.388,
      "step": 430
    },
    {
      "epoch": 1.323076923076923,
      "eval_loss": 0.6649342775344849,
      "eval_runtime": 1.9497,
      "eval_samples_per_second": 58.471,
      "eval_steps_per_second": 3.077,
      "step": 430
    },
    {
      "epoch": 1.353846153846154,
      "grad_norm": 1.8291655778884888,
      "learning_rate": 1.9709418174260523e-05,
      "loss": 0.4118,
      "step": 440
    },
    {
      "epoch": 1.353846153846154,
      "eval_loss": 0.6680696606636047,
      "eval_runtime": 2.0262,
      "eval_samples_per_second": 56.262,
      "eval_steps_per_second": 2.961,
      "step": 440
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 1.1135263442993164,
      "learning_rate": 1.9676414519013782e-05,
      "loss": 0.3205,
      "step": 450
    },
    {
      "epoch": 1.3846153846153846,
      "eval_loss": 0.6739374995231628,
      "eval_runtime": 1.9443,
      "eval_samples_per_second": 58.633,
      "eval_steps_per_second": 3.086,
      "step": 450
    }
  ],
  "logging_steps": 10,
  "max_steps": 2600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 50,
  "total_flos": 3.925941994651648e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}