{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.99949609473419,
  "eval_steps": 500,
  "global_step": 683,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016082826556767352,
      "grad_norm": 65.62212371826172,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 0.8077,
      "step": 10
    },
    {
      "epoch": 0.032165653113534705,
      "grad_norm": 50.16935729980469,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 0.6155,
      "step": 20
    },
    {
      "epoch": 0.048248479670302054,
      "grad_norm": 32.083778381347656,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.5188,
      "step": 30
    },
    {
      "epoch": 0.06433130622706941,
      "grad_norm": 27.791507720947266,
      "learning_rate": 2.8571428571428574e-05,
      "loss": 0.4476,
      "step": 40
    },
    {
      "epoch": 0.08041413278383676,
      "grad_norm": 33.207706451416016,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.4035,
      "step": 50
    },
    {
      "epoch": 0.09649695934060411,
      "grad_norm": 29.39824104309082,
      "learning_rate": 3.99995163828731e-05,
      "loss": 0.373,
      "step": 60
    },
    {
      "epoch": 0.11257978589737146,
      "grad_norm": 27.801868438720703,
      "learning_rate": 3.999407595879474e-05,
      "loss": 0.33,
      "step": 70
    },
    {
      "epoch": 0.12866261245413882,
      "grad_norm": 27.443641662597656,
      "learning_rate": 3.998259223910273e-05,
      "loss": 0.3121,
      "step": 80
    },
    {
      "epoch": 0.14474543901090617,
      "grad_norm": 27.026424407958984,
      "learning_rate": 3.9965068694800805e-05,
      "loss": 0.2868,
      "step": 90
    },
    {
      "epoch": 0.16082826556767352,
      "grad_norm": 27.81942367553711,
      "learning_rate": 3.9941510622455766e-05,
      "loss": 0.2675,
      "step": 100
    },
    {
      "epoch": 0.17691109212444087,
      "grad_norm": 27.47068214416504,
      "learning_rate": 3.9911925142596474e-05,
      "loss": 0.252,
      "step": 110
    },
    {
      "epoch": 0.19299391868120822,
      "grad_norm": 27.166418075561523,
      "learning_rate": 3.9876321197561714e-05,
      "loss": 0.233,
      "step": 120
    },
    {
      "epoch": 0.20907674523797556,
      "grad_norm": 26.941362380981445,
      "learning_rate": 3.983470954879728e-05,
      "loss": 0.2216,
      "step": 130
    },
    {
      "epoch": 0.2251595717947429,
      "grad_norm": 25.84792709350586,
      "learning_rate": 3.9787102773603325e-05,
      "loss": 0.2057,
      "step": 140
    },
    {
      "epoch": 0.2412423983515103,
      "grad_norm": 24.429794311523438,
      "learning_rate": 3.973351526133279e-05,
      "loss": 0.1997,
      "step": 150
    },
    {
      "epoch": 0.25732522490827764,
      "grad_norm": 25.138715744018555,
      "learning_rate": 3.967396320904215e-05,
      "loss": 0.1799,
      "step": 160
    },
    {
      "epoch": 0.273408051465045,
      "grad_norm": 23.31828498840332,
      "learning_rate": 3.960846461659586e-05,
      "loss": 0.1778,
      "step": 170
    },
    {
      "epoch": 0.28949087802181234,
      "grad_norm": 27.868120193481445,
      "learning_rate": 3.953703928122569e-05,
      "loss": 0.17,
      "step": 180
    },
    {
      "epoch": 1.018596079745351,
      "grad_norm": 23.8084659576416,
      "learning_rate": 3.945970879154704e-05,
      "loss": 0.1812,
      "step": 190
    },
    {
      "epoch": 1.0722063997319484,
      "grad_norm": 28.152708053588867,
      "learning_rate": 3.9376496521033636e-05,
      "loss": 0.1811,
      "step": 200
    },
    {
      "epoch": 1.1258167197185458,
      "grad_norm": 25.456472396850586,
      "learning_rate": 3.92874276209528e-05,
      "loss": 0.1703,
      "step": 210
    },
    {
      "epoch": 1.1794270397051432,
      "grad_norm": 24.26827049255371,
      "learning_rate": 3.919252901276339e-05,
      "loss": 0.1772,
      "step": 220
    },
    {
      "epoch": 1.2330373596917408,
      "grad_norm": 23.77770233154297,
      "learning_rate": 3.909182937997866e-05,
      "loss": 0.1654,
      "step": 230
    },
    {
      "epoch": 1.2866476796783382,
      "grad_norm": 24.42105484008789,
      "learning_rate": 3.8985359159496516e-05,
      "loss": 0.1504,
      "step": 240
    },
    {
      "epoch": 1.3402579996649355,
      "grad_norm": 24.336668014526367,
      "learning_rate": 3.8873150532399885e-05,
      "loss": 0.1368,
      "step": 250
    },
    {
      "epoch": 1.393868319651533,
      "grad_norm": 24.254329681396484,
      "learning_rate": 3.8755237414229834e-05,
      "loss": 0.1454,
      "step": 260
    },
    {
      "epoch": 1.4474786396381303,
      "grad_norm": 25.233129501342773,
      "learning_rate": 3.8631655444734414e-05,
      "loss": 0.1373,
      "step": 270
    },
    {
      "epoch": 1.5010889596247279,
      "grad_norm": 23.18859100341797,
      "learning_rate": 3.850244197709641e-05,
      "loss": 0.1341,
      "step": 280
    },
    {
      "epoch": 1.554699279611325,
      "grad_norm": 24.764631271362305,
      "learning_rate": 3.8367636066643224e-05,
      "loss": 0.139,
      "step": 290
    },
    {
      "epoch": 1.6083095995979226,
      "grad_norm": 23.146198272705078,
      "learning_rate": 3.822727845904216e-05,
      "loss": 0.1256,
      "step": 300
    },
    {
      "epoch": 1.66191991958452,
      "grad_norm": 23.295623779296875,
      "learning_rate": 3.808141157798492e-05,
      "loss": 0.1206,
      "step": 310
    },
    {
      "epoch": 1.7155302395711174,
      "grad_norm": 21.969825744628906,
      "learning_rate": 3.793007951236485e-05,
      "loss": 0.12,
      "step": 320
    },
    {
      "epoch": 1.769140559557715,
      "grad_norm": 21.317886352539062,
      "learning_rate": 3.777332800295088e-05,
      "loss": 0.1116,
      "step": 330
    },
    {
      "epoch": 1.8227508795443121,
      "grad_norm": 23.39339256286621,
      "learning_rate": 3.7611204428562175e-05,
      "loss": 0.1129,
      "step": 340
    },
    {
      "epoch": 1.8763611995309097,
      "grad_norm": 27.18583869934082,
      "learning_rate": 3.74437577917477e-05,
      "loss": 0.109,
      "step": 350
    },
    {
      "epoch": 1.9299715195175071,
      "grad_norm": 21.890743255615234,
      "learning_rate": 3.727103870397495e-05,
      "loss": 0.1021,
      "step": 360
    },
    {
      "epoch": 1.9835818395041045,
      "grad_norm": 23.11468505859375,
      "learning_rate": 3.709309937033247e-05,
      "loss": 0.1003,
      "step": 370
    },
    {
      "epoch": 2.022323003275384,
      "grad_norm": 25.56001853942871,
      "learning_rate": 3.6909993573750586e-05,
      "loss": 0.1186,
      "step": 380
    },
    {
      "epoch": 2.054572940287226,
      "grad_norm": 23.89845085144043,
      "learning_rate": 3.6721776658745335e-05,
      "loss": 0.1298,
      "step": 390
    },
    {
      "epoch": 2.086822877299068,
      "grad_norm": 24.464975357055664,
      "learning_rate": 3.652850551469031e-05,
      "loss": 0.1265,
      "step": 400
    },
    {
      "epoch": 2.1190728143109094,
      "grad_norm": 23.46689796447754,
      "learning_rate": 3.63302385586216e-05,
      "loss": 0.1248,
      "step": 410
    },
    {
      "epoch": 2.1513227513227515,
      "grad_norm": 21.452667236328125,
      "learning_rate": 3.6127035717581035e-05,
      "loss": 0.1128,
      "step": 420
    },
    {
      "epoch": 2.183572688334593,
      "grad_norm": 22.750587463378906,
      "learning_rate": 3.59189584105029e-05,
      "loss": 0.1068,
      "step": 430
    },
    {
      "epoch": 2.215822625346435,
      "grad_norm": 23.539155960083008,
      "learning_rate": 3.570606952964991e-05,
      "loss": 0.1089,
      "step": 440
    },
    {
      "epoch": 2.2480725623582765,
      "grad_norm": 22.286226272583008,
      "learning_rate": 3.54884334216036e-05,
      "loss": 0.1012,
      "step": 450
    },
    {
      "epoch": 2.2803224993701185,
      "grad_norm": 25.91316795349121,
      "learning_rate": 3.526611586781547e-05,
      "loss": 0.1085,
      "step": 460
    },
    {
      "epoch": 2.31257243638196,
      "grad_norm": 25.620323181152344,
      "learning_rate": 3.503918406472411e-05,
      "loss": 0.0935,
      "step": 470
    },
    {
      "epoch": 2.344822373393802,
      "grad_norm": 20.377058029174805,
      "learning_rate": 3.480770660344486e-05,
      "loss": 0.0982,
      "step": 480
    },
    {
      "epoch": 2.377072310405644,
      "grad_norm": 20.553796768188477,
      "learning_rate": 3.457175344903783e-05,
      "loss": 0.084,
      "step": 490
    },
    {
      "epoch": 2.4093222474174856,
      "grad_norm": 20.02320671081543,
      "learning_rate": 3.433139591936068e-05,
      "loss": 0.0964,
      "step": 500
    },
    {
      "epoch": 2.441572184429327,
      "grad_norm": 21.293182373046875,
      "learning_rate": 3.4086706663512454e-05,
      "loss": 0.0835,
      "step": 510
    },
    {
      "epoch": 2.4738221214411693,
      "grad_norm": 19.96319580078125,
      "learning_rate": 3.3837759639875113e-05,
      "loss": 0.0785,
      "step": 520
    },
    {
      "epoch": 2.506072058453011,
      "grad_norm": 22.20425796508789,
      "learning_rate": 3.358463009375927e-05,
      "loss": 0.0779,
      "step": 530
    },
    {
      "epoch": 2.5383219954648526,
      "grad_norm": 18.57112693786621,
      "learning_rate": 3.332739453466098e-05,
      "loss": 0.0814,
      "step": 540
    },
    {
      "epoch": 2.5705719324766942,
      "grad_norm": 20.270761489868164,
      "learning_rate": 3.306613071313641e-05,
      "loss": 0.0808,
      "step": 550
    },
    {
      "epoch": 2.602821869488536,
      "grad_norm": 19.787559509277344,
      "learning_rate": 3.280091759730144e-05,
      "loss": 0.0743,
      "step": 560
    },
    {
      "epoch": 2.635071806500378,
      "grad_norm": 18.70611572265625,
      "learning_rate": 3.25318353489631e-05,
      "loss": 0.0757,
      "step": 570
    },
    {
      "epoch": 2.6673217435122196,
      "grad_norm": 20.557205200195312,
      "learning_rate": 3.2258965299390465e-05,
      "loss": 0.0692,
      "step": 580
    },
    {
      "epoch": 2.6995716805240617,
      "grad_norm": 20.602092742919922,
      "learning_rate": 3.1982389924731805e-05,
      "loss": 0.0699,
      "step": 590
    },
    {
      "epoch": 2.7318216175359034,
      "grad_norm": 22.87337303161621,
      "learning_rate": 3.17021928210859e-05,
      "loss": 0.0662,
      "step": 600
    },
    {
      "epoch": 2.764071554547745,
      "grad_norm": 22.488433837890625,
      "learning_rate": 3.141845867923469e-05,
      "loss": 0.0799,
      "step": 610
    },
    {
      "epoch": 2.7963214915595866,
      "grad_norm": 20.05706787109375,
      "learning_rate": 3.113127325904519e-05,
      "loss": 0.0665,
      "step": 620
    },
    {
      "epoch": 2.8285714285714287,
      "grad_norm": 18.822357177734375,
      "learning_rate": 3.084072336354812e-05,
      "loss": 0.0668,
      "step": 630
    },
    {
      "epoch": 2.8608213655832704,
      "grad_norm": 17.79743194580078,
      "learning_rate": 3.05468968127014e-05,
      "loss": 0.0604,
      "step": 640
    },
    {
      "epoch": 2.893071302595112,
      "grad_norm": 19.10596466064453,
      "learning_rate": 3.0249882416846117e-05,
      "loss": 0.059,
      "step": 650
    },
    {
      "epoch": 2.925321239606954,
      "grad_norm": 20.25804328918457,
      "learning_rate": 2.9949769949863266e-05,
      "loss": 0.0646,
      "step": 660
    },
    {
      "epoch": 2.9575711766187958,
      "grad_norm": 19.09357452392578,
      "learning_rate": 2.96466501220392e-05,
      "loss": 0.0569,
      "step": 670
    },
    {
      "epoch": 2.9898211136306374,
      "grad_norm": 15.293481826782227,
      "learning_rate": 2.934061455264802e-05,
      "loss": 0.0574,
      "step": 680
    },
    {
      "epoch": 2.99949609473419,
      "step": 683,
      "total_flos": 6.564245582272266e+17,
      "train_loss": 0.1658007610769258,
      "train_runtime": 25935.882,
      "train_samples_per_second": 9.206,
      "train_steps_per_second": 0.072
    }
  ],
  "logging_steps": 10,
  "max_steps": 1863,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.564245582272266e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}