{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.807692307692307,
  "eval_steps": 500,
  "global_step": 515,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 3.364804983139038,
      "learning_rate": 7.692307692307693e-05,
      "loss": 1.4034,
      "step": 10
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 1.2244789600372314,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.4222,
      "step": 20
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 1.535311222076416,
      "learning_rate": 0.00019996698220143899,
      "loss": 0.2313,
      "step": 30
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.9641413688659668,
      "learning_rate": 0.0001995957823217325,
      "loss": 0.1714,
      "step": 40
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 1.1909210681915283,
      "learning_rate": 0.00019881364700727823,
      "loss": 0.148,
      "step": 50
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.9179659485816956,
      "learning_rate": 0.0001976238033738033,
      "loss": 0.1358,
      "step": 60
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 1.524248719215393,
      "learning_rate": 0.00019603116075480955,
      "loss": 0.1366,
      "step": 70
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.7116435766220093,
      "learning_rate": 0.00019404229044550433,
      "loss": 0.1132,
      "step": 80
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 0.4233417510986328,
      "learning_rate": 0.00019166539858942255,
      "loss": 0.1099,
      "step": 90
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.3895157277584076,
      "learning_rate": 0.00018891029231961207,
      "loss": 0.0973,
      "step": 100
    },
    {
      "epoch": 4.230769230769231,
      "grad_norm": 0.6012492179870605,
      "learning_rate": 0.0001857883392940837,
      "loss": 0.0974,
      "step": 110
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 0.4354020059108734,
      "learning_rate": 0.00018231242079248512,
      "loss": 0.0853,
      "step": 120
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6374463438987732,
      "learning_rate": 0.00017849687856752208,
      "loss": 0.0814,
      "step": 130
    },
    {
      "epoch": 5.384615384615385,
      "grad_norm": 0.4828743636608124,
      "learning_rate": 0.00017435745567042095,
      "loss": 0.083,
      "step": 140
    },
    {
      "epoch": 5.769230769230769,
      "grad_norm": 0.2791459560394287,
      "learning_rate": 0.00016991123149458738,
      "loss": 0.0769,
      "step": 150
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 0.3161262273788452,
      "learning_rate": 0.00016517655130547437,
      "loss": 0.0819,
      "step": 160
    },
    {
      "epoch": 6.538461538461538,
      "grad_norm": 0.5798579454421997,
      "learning_rate": 0.00016017295054742046,
      "loss": 0.0688,
      "step": 170
    },
    {
      "epoch": 6.923076923076923,
      "grad_norm": 0.38132503628730774,
      "learning_rate": 0.00015492107423977167,
      "loss": 0.0618,
      "step": 180
    },
    {
      "epoch": 7.3076923076923075,
      "grad_norm": 0.4480208158493042,
      "learning_rate": 0.00014944259179486066,
      "loss": 0.0678,
      "step": 190
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 0.3681942820549011,
      "learning_rate": 0.00014376010760930728,
      "loss": 0.0629,
      "step": 200
    },
    {
      "epoch": 8.076923076923077,
      "grad_norm": 0.5002759695053101,
      "learning_rate": 0.00013789706779754327,
      "loss": 0.0655,
      "step": 210
    },
    {
      "epoch": 8.461538461538462,
      "grad_norm": 0.4140470325946808,
      "learning_rate": 0.00013187766345238222,
      "loss": 0.0623,
      "step": 220
    },
    {
      "epoch": 8.846153846153847,
      "grad_norm": 0.37125447392463684,
      "learning_rate": 0.0001257267308317845,
      "loss": 0.0584,
      "step": 230
    },
    {
      "epoch": 9.23076923076923,
      "grad_norm": 0.3931460976600647,
      "learning_rate": 0.0001194696488836495,
      "loss": 0.0615,
      "step": 240
    },
    {
      "epoch": 9.615384615384615,
      "grad_norm": 0.4081181287765503,
      "learning_rate": 0.00011313223453145201,
      "loss": 0.0541,
      "step": 250
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.42426028847694397,
      "learning_rate": 0.0001067406361527768,
      "loss": 0.0591,
      "step": 260
    },
    {
      "epoch": 10.384615384615385,
      "grad_norm": 0.389825701713562,
      "learning_rate": 0.00010032122569026283,
      "loss": 0.0565,
      "step": 270
    },
    {
      "epoch": 10.76923076923077,
      "grad_norm": 0.4282422363758087,
      "learning_rate": 9.390048984011096e-05,
      "loss": 0.0492,
      "step": 280
    },
    {
      "epoch": 11.153846153846153,
      "grad_norm": 0.33358335494995117,
      "learning_rate": 8.750492076711439e-05,
      "loss": 0.0462,
      "step": 290
    },
    {
      "epoch": 11.538461538461538,
      "grad_norm": 0.3536369204521179,
      "learning_rate": 8.1160906797126e-05,
      "loss": 0.0547,
      "step": 300
    },
    {
      "epoch": 11.923076923076923,
      "grad_norm": 0.3393729329109192,
      "learning_rate": 7.489462353796793e-05,
      "loss": 0.0539,
      "step": 310
    },
    {
      "epoch": 12.307692307692308,
      "grad_norm": 0.26623183488845825,
      "learning_rate": 6.87319258780234e-05,
      "loss": 0.04,
      "step": 320
    },
    {
      "epoch": 12.692307692307692,
      "grad_norm": 0.34395718574523926,
      "learning_rate": 6.269824130812645e-05,
      "loss": 0.0493,
      "step": 330
    },
    {
      "epoch": 13.076923076923077,
      "grad_norm": 0.2601974904537201,
      "learning_rate": 5.681846500690884e-05,
      "loss": 0.054,
      "step": 340
    },
    {
      "epoch": 13.461538461538462,
      "grad_norm": 0.20003391802310944,
      "learning_rate": 5.111685712248364e-05,
      "loss": 0.0489,
      "step": 350
    },
    {
      "epoch": 13.846153846153847,
      "grad_norm": 0.20917710661888123,
      "learning_rate": 4.56169426742856e-05,
      "loss": 0.0536,
      "step": 360
    },
    {
      "epoch": 14.23076923076923,
      "grad_norm": 0.2096697986125946,
      "learning_rate": 4.03414144880767e-05,
      "loss": 0.0436,
      "step": 370
    },
    {
      "epoch": 14.615384615384615,
      "grad_norm": 0.2338918149471283,
      "learning_rate": 3.53120395646092e-05,
      "loss": 0.0413,
      "step": 380
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.2506970465183258,
      "learning_rate": 3.054956926827332e-05,
      "loss": 0.0418,
      "step": 390
    },
    {
      "epoch": 15.384615384615385,
      "grad_norm": 0.16216574609279633,
      "learning_rate": 2.60736537062932e-05,
      "loss": 0.0346,
      "step": 400
    },
    {
      "epoch": 15.76923076923077,
      "grad_norm": 0.26421189308166504,
      "learning_rate": 2.1902760651745958e-05,
      "loss": 0.0457,
      "step": 410
    },
    {
      "epoch": 16.153846153846153,
      "grad_norm": 0.2853449881076813,
      "learning_rate": 1.8054099344929832e-05,
      "loss": 0.0432,
      "step": 420
    },
    {
      "epoch": 16.53846153846154,
      "grad_norm": 0.2742384672164917,
      "learning_rate": 1.454354948747909e-05,
      "loss": 0.0411,
      "step": 430
    },
    {
      "epoch": 16.923076923076923,
      "grad_norm": 0.2132396250963211,
      "learning_rate": 1.1385595722199438e-05,
      "loss": 0.0372,
      "step": 440
    },
    {
      "epoch": 17.307692307692307,
      "grad_norm": 0.23929736018180847,
      "learning_rate": 8.593267868960675e-06,
      "loss": 0.0336,
      "step": 450
    },
    {
      "epoch": 17.692307692307693,
      "grad_norm": 0.16594846546649933,
      "learning_rate": 6.178087163236645e-06,
      "loss": 0.0383,
      "step": 460
    },
    {
      "epoch": 18.076923076923077,
      "grad_norm": 0.18442106246948242,
      "learning_rate": 4.1500187191131466e-06,
      "loss": 0.0361,
      "step": 470
    },
    {
      "epoch": 18.46153846153846,
      "grad_norm": 0.20087499916553497,
      "learning_rate": 2.5174304129033653e-06,
      "loss": 0.036,
      "step": 480
    },
    {
      "epoch": 18.846153846153847,
      "grad_norm": 0.24509386718273163,
      "learning_rate": 1.287058357018278e-06,
      "loss": 0.0335,
      "step": 490
    },
    {
      "epoch": 19.23076923076923,
      "grad_norm": 0.22717131674289703,
      "learning_rate": 4.639791065478738e-07,
      "loss": 0.0381,
      "step": 500
    },
    {
      "epoch": 19.615384615384617,
      "grad_norm": 0.14815658330917358,
      "learning_rate": 5.158871322984427e-08,
      "loss": 0.0374,
      "step": 510
    },
    {
      "epoch": 19.807692307692307,
      "step": 515,
      "total_flos": 7.15348914538104e+16,
      "train_loss": 0.10100355527354675,
      "train_runtime": 643.3659,
      "train_samples_per_second": 51.231,
      "train_steps_per_second": 0.8
    }
  ],
  "logging_steps": 10,
  "max_steps": 515,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.15348914538104e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}