{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 443,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011299435028248588,
      "grad_norm": 1.2254456281661987,
      "learning_rate": 1.0810810810810812e-06,
      "loss": 1.3157,
      "step": 5
    },
    {
      "epoch": 0.022598870056497175,
      "grad_norm": 1.2222959995269775,
      "learning_rate": 2.4324324324324325e-06,
      "loss": 1.3831,
      "step": 10
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 0.7486730813980103,
      "learning_rate": 3.7837837837837835e-06,
      "loss": 1.3448,
      "step": 15
    },
    {
      "epoch": 0.04519774011299435,
      "grad_norm": 0.7303342819213867,
      "learning_rate": 5.135135135135135e-06,
      "loss": 1.2883,
      "step": 20
    },
    {
      "epoch": 0.05649717514124294,
      "grad_norm": 0.6827901005744934,
      "learning_rate": 6.486486486486487e-06,
      "loss": 1.2782,
      "step": 25
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 0.6475429534912109,
      "learning_rate": 7.837837837837838e-06,
      "loss": 1.2937,
      "step": 30
    },
    {
      "epoch": 0.07909604519774012,
      "grad_norm": 0.5939517617225647,
      "learning_rate": 9.18918918918919e-06,
      "loss": 1.2553,
      "step": 35
    },
    {
      "epoch": 0.0903954802259887,
      "grad_norm": 0.5064879655838013,
      "learning_rate": 1.0540540540540541e-05,
      "loss": 1.2067,
      "step": 40
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": 0.6584354639053345,
      "learning_rate": 1.1891891891891893e-05,
      "loss": 1.2246,
      "step": 45
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 0.4975661337375641,
      "learning_rate": 1.3243243243243242e-05,
      "loss": 1.2558,
      "step": 50
    },
    {
      "epoch": 0.12429378531073447,
      "grad_norm": 0.5031336545944214,
      "learning_rate": 1.4594594594594596e-05,
      "loss": 1.2726,
      "step": 55
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 0.4471903443336487,
      "learning_rate": 1.5945945945945947e-05,
      "loss": 1.2089,
      "step": 60
    },
    {
      "epoch": 0.14689265536723164,
      "grad_norm": 0.5343024134635925,
      "learning_rate": 1.72972972972973e-05,
      "loss": 1.2018,
      "step": 65
    },
    {
      "epoch": 0.15819209039548024,
      "grad_norm": 0.47138091921806335,
      "learning_rate": 1.864864864864865e-05,
      "loss": 1.2826,
      "step": 70
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 0.490500271320343,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 1.2116,
      "step": 75
    },
    {
      "epoch": 0.1807909604519774,
      "grad_norm": 0.5078205466270447,
      "learning_rate": 2.135135135135135e-05,
      "loss": 1.1873,
      "step": 80
    },
    {
      "epoch": 0.192090395480226,
      "grad_norm": 1.9143681526184082,
      "learning_rate": 2.2702702702702705e-05,
      "loss": 1.2159,
      "step": 85
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": 0.5685150027275085,
      "learning_rate": 2.4054054054054056e-05,
      "loss": 1.1666,
      "step": 90
    },
    {
      "epoch": 0.21468926553672316,
      "grad_norm": 0.5490728616714478,
      "learning_rate": 2.5405405405405408e-05,
      "loss": 1.1348,
      "step": 95
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 0.5205124020576477,
      "learning_rate": 2.6756756756756756e-05,
      "loss": 1.1213,
      "step": 100
    },
    {
      "epoch": 0.23728813559322035,
      "grad_norm": 0.4488866925239563,
      "learning_rate": 2.8108108108108107e-05,
      "loss": 1.1414,
      "step": 105
    },
    {
      "epoch": 0.24858757062146894,
      "grad_norm": 0.4913260340690613,
      "learning_rate": 2.945945945945946e-05,
      "loss": 1.139,
      "step": 110
    },
    {
      "epoch": 0.2598870056497175,
      "grad_norm": 0.5297622084617615,
      "learning_rate": 2.9999849508725208e-05,
      "loss": 1.134,
      "step": 115
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 0.6094189882278442,
      "learning_rate": 2.9998929850759165e-05,
      "loss": 1.1023,
      "step": 120
    },
    {
      "epoch": 0.2824858757062147,
      "grad_norm": 0.6322339177131653,
      "learning_rate": 2.9997174192288006e-05,
      "loss": 1.1164,
      "step": 125
    },
    {
      "epoch": 0.2937853107344633,
      "grad_norm": 0.6201522946357727,
      "learning_rate": 2.999458263116747e-05,
      "loss": 1.1188,
      "step": 130
    },
    {
      "epoch": 0.3050847457627119,
      "grad_norm": 0.5387688875198364,
      "learning_rate": 2.9991155311844292e-05,
      "loss": 1.0651,
      "step": 135
    },
    {
      "epoch": 0.3163841807909605,
      "grad_norm": 0.5230715274810791,
      "learning_rate": 2.998689242534815e-05,
      "loss": 1.0626,
      "step": 140
    },
    {
      "epoch": 0.327683615819209,
      "grad_norm": 0.5703102946281433,
      "learning_rate": 2.9981794209281003e-05,
      "loss": 1.0626,
      "step": 145
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 0.5561928153038025,
      "learning_rate": 2.997586094780388e-05,
      "loss": 1.0494,
      "step": 150
    },
    {
      "epoch": 0.3502824858757062,
      "grad_norm": 0.6391568183898926,
      "learning_rate": 2.9969092971621006e-05,
      "loss": 1.05,
      "step": 155
    },
    {
      "epoch": 0.3615819209039548,
      "grad_norm": 0.6165516376495361,
      "learning_rate": 2.9961490657961404e-05,
      "loss": 1.0617,
      "step": 160
    },
    {
      "epoch": 0.3728813559322034,
      "grad_norm": 0.6393241286277771,
      "learning_rate": 2.9953054430557835e-05,
      "loss": 1.0036,
      "step": 165
    },
    {
      "epoch": 0.384180790960452,
      "grad_norm": 0.6466289758682251,
      "learning_rate": 2.9943784759623205e-05,
      "loss": 1.0362,
      "step": 170
    },
    {
      "epoch": 0.3954802259887006,
      "grad_norm": 0.7020736932754517,
      "learning_rate": 2.993368216182435e-05,
      "loss": 1.0052,
      "step": 175
    },
    {
      "epoch": 0.4067796610169492,
      "grad_norm": 0.630094051361084,
      "learning_rate": 2.992274720025323e-05,
      "loss": 1.0279,
      "step": 180
    },
    {
      "epoch": 0.4180790960451977,
      "grad_norm": 0.629647433757782,
      "learning_rate": 2.9910980484395555e-05,
      "loss": 1.0309,
      "step": 185
    },
    {
      "epoch": 0.4293785310734463,
      "grad_norm": 0.6576105952262878,
      "learning_rate": 2.989838267009681e-05,
      "loss": 0.9227,
      "step": 190
    },
    {
      "epoch": 0.4406779661016949,
      "grad_norm": 0.6078037023544312,
      "learning_rate": 2.988495445952569e-05,
      "loss": 1.0005,
      "step": 195
    },
    {
      "epoch": 0.4519774011299435,
      "grad_norm": 0.657957911491394,
      "learning_rate": 2.9870696601134994e-05,
      "loss": 0.9715,
      "step": 200
    },
    {
      "epoch": 0.4632768361581921,
      "grad_norm": 0.6783279180526733,
      "learning_rate": 2.9855609889619864e-05,
      "loss": 0.927,
      "step": 205
    },
    {
      "epoch": 0.4745762711864407,
      "grad_norm": 0.6905434727668762,
      "learning_rate": 2.983969516587352e-05,
      "loss": 0.9506,
      "step": 210
    },
    {
      "epoch": 0.4858757062146893,
      "grad_norm": 0.8056045174598694,
      "learning_rate": 2.9822953316940393e-05,
      "loss": 0.9867,
      "step": 215
    },
    {
      "epoch": 0.4971751412429379,
      "grad_norm": 0.7994968295097351,
      "learning_rate": 2.9805385275966658e-05,
      "loss": 0.9489,
      "step": 220
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 0.7940033078193665,
      "learning_rate": 2.978699202214826e-05,
      "loss": 0.9538,
      "step": 225
    },
    {
      "epoch": 0.519774011299435,
      "grad_norm": 0.7576586604118347,
      "learning_rate": 2.97677745806763e-05,
      "loss": 0.9529,
      "step": 230
    },
    {
      "epoch": 0.5310734463276836,
      "grad_norm": 0.8559620976448059,
      "learning_rate": 2.9747734022679913e-05,
      "loss": 0.9188,
      "step": 235
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 0.9041480422019958,
      "learning_rate": 2.9726871465166567e-05,
      "loss": 0.9145,
      "step": 240
    },
    {
      "epoch": 0.5536723163841808,
      "grad_norm": 0.7606709003448486,
      "learning_rate": 2.970518807095979e-05,
      "loss": 0.9179,
      "step": 245
    },
    {
      "epoch": 0.5649717514124294,
      "grad_norm": 0.904378354549408,
      "learning_rate": 2.9682685048634384e-05,
      "loss": 0.8682,
      "step": 250
    },
    {
      "epoch": 0.576271186440678,
      "grad_norm": 0.8670118451118469,
      "learning_rate": 2.9659363652449027e-05,
      "loss": 0.9448,
      "step": 255
    },
    {
      "epoch": 0.5875706214689266,
      "grad_norm": 0.7508774399757385,
      "learning_rate": 2.9635225182276387e-05,
      "loss": 0.9223,
      "step": 260
    },
    {
      "epoch": 0.5988700564971752,
      "grad_norm": 0.6919876933097839,
      "learning_rate": 2.961027098353067e-05,
      "loss": 0.8971,
      "step": 265
    },
    {
      "epoch": 0.6101694915254238,
      "grad_norm": 0.7949540615081787,
      "learning_rate": 2.9584502447092623e-05,
      "loss": 0.91,
      "step": 270
    },
    {
      "epoch": 0.6214689265536724,
      "grad_norm": 0.7679325938224792,
      "learning_rate": 2.9557921009232013e-05,
      "loss": 0.903,
      "step": 275
    },
    {
      "epoch": 0.632768361581921,
      "grad_norm": 0.8364932537078857,
      "learning_rate": 2.953052815152757e-05,
      "loss": 0.8941,
      "step": 280
    },
    {
      "epoch": 0.6440677966101694,
      "grad_norm": 0.8773370981216431,
      "learning_rate": 2.950232540078442e-05,
      "loss": 0.8812,
      "step": 285
    },
    {
      "epoch": 0.655367231638418,
      "grad_norm": 1.0121004581451416,
      "learning_rate": 2.947331432894896e-05,
      "loss": 0.901,
      "step": 290
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.8700821995735168,
      "learning_rate": 2.9443496553021268e-05,
      "loss": 0.8385,
      "step": 295
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 0.8492361903190613,
      "learning_rate": 2.9412873734964973e-05,
      "loss": 0.8498,
      "step": 300
    },
    {
      "epoch": 0.6892655367231638,
      "grad_norm": 0.860744833946228,
      "learning_rate": 2.938144758161459e-05,
      "loss": 0.8381,
      "step": 305
    },
    {
      "epoch": 0.7005649717514124,
      "grad_norm": 0.8146252036094666,
      "learning_rate": 2.934921984458043e-05,
      "loss": 0.8505,
      "step": 310
    },
    {
      "epoch": 0.711864406779661,
      "grad_norm": 0.828873336315155,
      "learning_rate": 2.931619232015094e-05,
      "loss": 0.8359,
      "step": 315
    },
    {
      "epoch": 0.7231638418079096,
      "grad_norm": 0.8928766250610352,
      "learning_rate": 2.9282366849192596e-05,
      "loss": 0.8697,
      "step": 320
    },
    {
      "epoch": 0.7344632768361582,
      "grad_norm": 0.8543341755867004,
      "learning_rate": 2.924774531704729e-05,
      "loss": 0.7961,
      "step": 325
    },
    {
      "epoch": 0.7457627118644068,
      "grad_norm": 0.8456112146377563,
      "learning_rate": 2.921232965342725e-05,
      "loss": 0.8298,
      "step": 330
    },
    {
      "epoch": 0.7570621468926554,
      "grad_norm": 0.8231430053710938,
      "learning_rate": 2.9176121832307487e-05,
      "loss": 0.7866,
      "step": 335
    },
    {
      "epoch": 0.768361581920904,
      "grad_norm": 0.8562153577804565,
      "learning_rate": 2.9139123871815762e-05,
      "loss": 0.7833,
      "step": 340
    },
    {
      "epoch": 0.7796610169491526,
      "grad_norm": 0.8552905917167664,
      "learning_rate": 2.9101337834120113e-05,
      "loss": 0.7777,
      "step": 345
    },
    {
      "epoch": 0.7909604519774012,
      "grad_norm": 0.9859520792961121,
      "learning_rate": 2.9062765825313887e-05,
      "loss": 0.8016,
      "step": 350
    },
    {
      "epoch": 0.8022598870056498,
      "grad_norm": 0.867014467716217,
      "learning_rate": 2.9023409995298406e-05,
      "loss": 0.7895,
      "step": 355
    },
    {
      "epoch": 0.8135593220338984,
      "grad_norm": 0.890496015548706,
      "learning_rate": 2.8983272537663082e-05,
      "loss": 0.7795,
      "step": 360
    },
    {
      "epoch": 0.8248587570621468,
      "grad_norm": 0.9742592573165894,
      "learning_rate": 2.8942355689563166e-05,
      "loss": 0.7661,
      "step": 365
    },
    {
      "epoch": 0.8361581920903954,
      "grad_norm": 0.855208694934845,
      "learning_rate": 2.890066173159509e-05,
      "loss": 0.7863,
      "step": 370
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 0.9460350871086121,
      "learning_rate": 2.8858192987669303e-05,
      "loss": 0.7475,
      "step": 375
    },
    {
      "epoch": 0.8587570621468926,
      "grad_norm": 0.9050624966621399,
      "learning_rate": 2.881495182488077e-05,
      "loss": 0.739,
      "step": 380
    },
    {
      "epoch": 0.8700564971751412,
      "grad_norm": 0.8351825475692749,
      "learning_rate": 2.8770940653377047e-05,
      "loss": 0.7322,
      "step": 385
    },
    {
      "epoch": 0.8813559322033898,
      "grad_norm": 0.9222843050956726,
      "learning_rate": 2.8726161926223904e-05,
      "loss": 0.7435,
      "step": 390
    },
    {
      "epoch": 0.8926553672316384,
      "grad_norm": 0.8897649645805359,
      "learning_rate": 2.8680618139268643e-05,
      "loss": 0.7229,
      "step": 395
    },
    {
      "epoch": 0.903954802259887,
      "grad_norm": 1.0437895059585571,
      "learning_rate": 2.8634311831000966e-05,
      "loss": 0.7132,
      "step": 400
    },
    {
      "epoch": 0.9152542372881356,
      "grad_norm": 0.9872046113014221,
      "learning_rate": 2.8587245582411475e-05,
      "loss": 0.7257,
      "step": 405
    },
    {
      "epoch": 0.9265536723163842,
      "grad_norm": 0.9081714749336243,
      "learning_rate": 2.8539422016847834e-05,
      "loss": 0.6956,
      "step": 410
    },
    {
      "epoch": 0.9378531073446328,
      "grad_norm": 0.9939802289009094,
      "learning_rate": 2.8490843799868556e-05,
      "loss": 0.723,
      "step": 415
    },
    {
      "epoch": 0.9491525423728814,
      "grad_norm": 0.8449594974517822,
      "learning_rate": 2.8441513639094396e-05,
      "loss": 0.7294,
      "step": 420
    },
    {
      "epoch": 0.96045197740113,
      "grad_norm": 0.9042068719863892,
      "learning_rate": 2.8391434284057466e-05,
      "loss": 0.6565,
      "step": 425
    },
    {
      "epoch": 0.9717514124293786,
      "grad_norm": 0.9338545203208923,
      "learning_rate": 2.8340608526047995e-05,
      "loss": 0.711,
      "step": 430
    },
    {
      "epoch": 0.9830508474576272,
      "grad_norm": 0.9345859885215759,
      "learning_rate": 2.82890391979587e-05,
      "loss": 0.7006,
      "step": 435
    },
    {
      "epoch": 0.9943502824858758,
      "grad_norm": 0.9804854393005371,
      "learning_rate": 2.8236729174126948e-05,
      "loss": 0.7183,
      "step": 440
    }
  ],
  "logging_steps": 5,
  "max_steps": 2215,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.402730716005663e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}