{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9971469329529246,
  "eval_steps": 500,
  "global_step": 525,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05706134094151213,
      "grad_norm": 14.191660560442434,
      "learning_rate": 5e-06,
      "loss": 1.1357,
      "step": 10
    },
    {
      "epoch": 0.11412268188302425,
      "grad_norm": 3.2725072406272364,
      "learning_rate": 5e-06,
      "loss": 0.9928,
      "step": 20
    },
    {
      "epoch": 0.17118402282453637,
      "grad_norm": 4.495391053372432,
      "learning_rate": 5e-06,
      "loss": 0.9322,
      "step": 30
    },
    {
      "epoch": 0.2282453637660485,
      "grad_norm": 5.085341885044574,
      "learning_rate": 5e-06,
      "loss": 0.8899,
      "step": 40
    },
    {
      "epoch": 0.28530670470756064,
      "grad_norm": 4.5927160200176855,
      "learning_rate": 5e-06,
      "loss": 0.8676,
      "step": 50
    },
    {
      "epoch": 0.34236804564907275,
      "grad_norm": 1.6911849555640204,
      "learning_rate": 5e-06,
      "loss": 0.8394,
      "step": 60
    },
    {
      "epoch": 0.39942938659058486,
      "grad_norm": 1.466261010867929,
      "learning_rate": 5e-06,
      "loss": 0.8166,
      "step": 70
    },
    {
      "epoch": 0.456490727532097,
      "grad_norm": 1.5136151777383209,
      "learning_rate": 5e-06,
      "loss": 0.8095,
      "step": 80
    },
    {
      "epoch": 0.5135520684736091,
      "grad_norm": 1.2618165735232854,
      "learning_rate": 5e-06,
      "loss": 0.8023,
      "step": 90
    },
    {
      "epoch": 0.5706134094151213,
      "grad_norm": 1.6421126077036754,
      "learning_rate": 5e-06,
      "loss": 0.7912,
      "step": 100
    },
    {
      "epoch": 0.6276747503566333,
      "grad_norm": 0.9444257126116525,
      "learning_rate": 5e-06,
      "loss": 0.7844,
      "step": 110
    },
    {
      "epoch": 0.6847360912981455,
      "grad_norm": 1.0658378058753986,
      "learning_rate": 5e-06,
      "loss": 0.7821,
      "step": 120
    },
    {
      "epoch": 0.7417974322396577,
      "grad_norm": 1.0219994955594212,
      "learning_rate": 5e-06,
      "loss": 0.7761,
      "step": 130
    },
    {
      "epoch": 0.7988587731811697,
      "grad_norm": 1.0628427150837625,
      "learning_rate": 5e-06,
      "loss": 0.7747,
      "step": 140
    },
    {
      "epoch": 0.8559201141226819,
      "grad_norm": 0.9619954966621683,
      "learning_rate": 5e-06,
      "loss": 0.7722,
      "step": 150
    },
    {
      "epoch": 0.912981455064194,
      "grad_norm": 0.8603887735435021,
      "learning_rate": 5e-06,
      "loss": 0.7698,
      "step": 160
    },
    {
      "epoch": 0.9700427960057061,
      "grad_norm": 0.8416466459767842,
      "learning_rate": 5e-06,
      "loss": 0.7665,
      "step": 170
    },
    {
      "epoch": 0.9985734664764622,
      "eval_loss": 0.7644989490509033,
      "eval_runtime": 121.9669,
      "eval_samples_per_second": 38.707,
      "eval_steps_per_second": 0.607,
      "step": 175
    },
    {
      "epoch": 1.027817403708987,
      "grad_norm": 0.8822220105180665,
      "learning_rate": 5e-06,
      "loss": 0.7951,
      "step": 180
    },
    {
      "epoch": 1.0848787446504993,
      "grad_norm": 0.8529113410206094,
      "learning_rate": 5e-06,
      "loss": 0.7077,
      "step": 190
    },
    {
      "epoch": 1.1419400855920114,
      "grad_norm": 1.6886404017331722,
      "learning_rate": 5e-06,
      "loss": 0.7039,
      "step": 200
    },
    {
      "epoch": 1.1990014265335236,
      "grad_norm": 1.5586898240952252,
      "learning_rate": 5e-06,
      "loss": 0.7018,
      "step": 210
    },
    {
      "epoch": 1.2560627674750355,
      "grad_norm": 1.0565182550630585,
      "learning_rate": 5e-06,
      "loss": 0.6986,
      "step": 220
    },
    {
      "epoch": 1.313124108416548,
      "grad_norm": 0.8847228395407172,
      "learning_rate": 5e-06,
      "loss": 0.7016,
      "step": 230
    },
    {
      "epoch": 1.3701854493580599,
      "grad_norm": 0.7426270405443446,
      "learning_rate": 5e-06,
      "loss": 0.7005,
      "step": 240
    },
    {
      "epoch": 1.427246790299572,
      "grad_norm": 1.031506144419473,
      "learning_rate": 5e-06,
      "loss": 0.7047,
      "step": 250
    },
    {
      "epoch": 1.4843081312410842,
      "grad_norm": 0.8734427470796896,
      "learning_rate": 5e-06,
      "loss": 0.7011,
      "step": 260
    },
    {
      "epoch": 1.5413694721825963,
      "grad_norm": 1.057801790522887,
      "learning_rate": 5e-06,
      "loss": 0.6988,
      "step": 270
    },
    {
      "epoch": 1.5984308131241085,
      "grad_norm": 0.8415840230824246,
      "learning_rate": 5e-06,
      "loss": 0.6987,
      "step": 280
    },
    {
      "epoch": 1.6554921540656204,
      "grad_norm": 0.827701826950944,
      "learning_rate": 5e-06,
      "loss": 0.7045,
      "step": 290
    },
    {
      "epoch": 1.7125534950071328,
      "grad_norm": 0.7740671969466235,
      "learning_rate": 5e-06,
      "loss": 0.6981,
      "step": 300
    },
    {
      "epoch": 1.7696148359486448,
      "grad_norm": 0.8907728175194645,
      "learning_rate": 5e-06,
      "loss": 0.7043,
      "step": 310
    },
    {
      "epoch": 1.826676176890157,
      "grad_norm": 0.7591532846679572,
      "learning_rate": 5e-06,
      "loss": 0.7002,
      "step": 320
    },
    {
      "epoch": 1.883737517831669,
      "grad_norm": 1.037223455268037,
      "learning_rate": 5e-06,
      "loss": 0.7029,
      "step": 330
    },
    {
      "epoch": 1.940798858773181,
      "grad_norm": 0.9095266922636082,
      "learning_rate": 5e-06,
      "loss": 0.7038,
      "step": 340
    },
    {
      "epoch": 1.9978601997146934,
      "grad_norm": 0.8437114369311308,
      "learning_rate": 5e-06,
      "loss": 0.6988,
      "step": 350
    },
    {
      "epoch": 1.9978601997146934,
      "eval_loss": 0.752321720123291,
      "eval_runtime": 119.2436,
      "eval_samples_per_second": 39.591,
      "eval_steps_per_second": 0.621,
      "step": 350
    },
    {
      "epoch": 2.055634807417974,
      "grad_norm": 0.7992701008382876,
      "learning_rate": 5e-06,
      "loss": 0.697,
      "step": 360
    },
    {
      "epoch": 2.1126961483594866,
      "grad_norm": 0.9009096072867547,
      "learning_rate": 5e-06,
      "loss": 0.6309,
      "step": 370
    },
    {
      "epoch": 2.1697574893009985,
      "grad_norm": 0.9335524571114746,
      "learning_rate": 5e-06,
      "loss": 0.6301,
      "step": 380
    },
    {
      "epoch": 2.226818830242511,
      "grad_norm": 0.9107893164568975,
      "learning_rate": 5e-06,
      "loss": 0.6274,
      "step": 390
    },
    {
      "epoch": 2.283880171184023,
      "grad_norm": 0.8275181427943094,
      "learning_rate": 5e-06,
      "loss": 0.631,
      "step": 400
    },
    {
      "epoch": 2.340941512125535,
      "grad_norm": 0.7487796908821762,
      "learning_rate": 5e-06,
      "loss": 0.6321,
      "step": 410
    },
    {
      "epoch": 2.398002853067047,
      "grad_norm": 1.1741881512767371,
      "learning_rate": 5e-06,
      "loss": 0.6352,
      "step": 420
    },
    {
      "epoch": 2.455064194008559,
      "grad_norm": 0.9540225993983626,
      "learning_rate": 5e-06,
      "loss": 0.6356,
      "step": 430
    },
    {
      "epoch": 2.512125534950071,
      "grad_norm": 0.9795761392377677,
      "learning_rate": 5e-06,
      "loss": 0.635,
      "step": 440
    },
    {
      "epoch": 2.5691868758915835,
      "grad_norm": 0.7321465764810406,
      "learning_rate": 5e-06,
      "loss": 0.6349,
      "step": 450
    },
    {
      "epoch": 2.626248216833096,
      "grad_norm": 0.8103933471152502,
      "learning_rate": 5e-06,
      "loss": 0.6355,
      "step": 460
    },
    {
      "epoch": 2.683309557774608,
      "grad_norm": 1.0066498655926475,
      "learning_rate": 5e-06,
      "loss": 0.6377,
      "step": 470
    },
    {
      "epoch": 2.7403708987161197,
      "grad_norm": 0.9338836682210027,
      "learning_rate": 5e-06,
      "loss": 0.6367,
      "step": 480
    },
    {
      "epoch": 2.797432239657632,
      "grad_norm": 0.8149026499533006,
      "learning_rate": 5e-06,
      "loss": 0.6382,
      "step": 490
    },
    {
      "epoch": 2.854493580599144,
      "grad_norm": 0.8107310696209651,
      "learning_rate": 5e-06,
      "loss": 0.6357,
      "step": 500
    },
    {
      "epoch": 2.911554921540656,
      "grad_norm": 0.78901956302398,
      "learning_rate": 5e-06,
      "loss": 0.6363,
      "step": 510
    },
    {
      "epoch": 2.9686162624821684,
      "grad_norm": 0.8105645400500955,
      "learning_rate": 5e-06,
      "loss": 0.644,
      "step": 520
    },
    {
      "epoch": 2.9971469329529246,
      "eval_loss": 0.7613628506660461,
      "eval_runtime": 124.0128,
      "eval_samples_per_second": 38.069,
      "eval_steps_per_second": 0.597,
      "step": 525
    },
    {
      "epoch": 2.9971469329529246,
      "step": 525,
      "total_flos": 879185174200320.0,
      "train_loss": 0.7275740219297864,
      "train_runtime": 16864.3599,
      "train_samples_per_second": 15.956,
      "train_steps_per_second": 0.031
    }
  ],
  "logging_steps": 10,
  "max_steps": 525,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 879185174200320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}