{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6416295353278166,
  "eval_steps": 32,
  "global_step": 378,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001697432633142372,
      "eval_loss": 2.4177019596099854,
      "eval_runtime": 13.7303,
      "eval_samples_per_second": 18.135,
      "eval_steps_per_second": 18.135,
      "step": 1
    },
    {
      "epoch": 0.016974326331423723,
      "grad_norm": 0.5538016557693481,
      "learning_rate": 1e-05,
      "loss": 2.2236,
      "step": 10
    },
    {
      "epoch": 0.033948652662847446,
      "grad_norm": 0.7852675318717957,
      "learning_rate": 9.989726963751683e-06,
      "loss": 2.4165,
      "step": 20
    },
    {
      "epoch": 0.050922978994271166,
      "grad_norm": 0.4371705651283264,
      "learning_rate": 9.95895006911623e-06,
      "loss": 2.5564,
      "step": 30
    },
    {
      "epoch": 0.05431784426055591,
      "eval_loss": 2.3971197605133057,
      "eval_runtime": 14.2456,
      "eval_samples_per_second": 17.479,
      "eval_steps_per_second": 17.479,
      "step": 32
    },
    {
      "epoch": 0.06789730532569489,
      "grad_norm": 0.8462035655975342,
      "learning_rate": 9.907795784955327e-06,
      "loss": 2.3432,
      "step": 40
    },
    {
      "epoch": 0.08487163165711861,
      "grad_norm": 0.9292763471603394,
      "learning_rate": 9.836474315195148e-06,
      "loss": 2.276,
      "step": 50
    },
    {
      "epoch": 0.10184595798854233,
      "grad_norm": 0.9029847979545593,
      "learning_rate": 9.745278735053345e-06,
      "loss": 2.3619,
      "step": 60
    },
    {
      "epoch": 0.10863568852111181,
      "eval_loss": 2.334070920944214,
      "eval_runtime": 14.5899,
      "eval_samples_per_second": 17.067,
      "eval_steps_per_second": 17.067,
      "step": 64
    },
    {
      "epoch": 0.11882028431996605,
      "grad_norm": 0.857122004032135,
      "learning_rate": 9.63458378673011e-06,
      "loss": 2.2851,
      "step": 70
    },
    {
      "epoch": 0.13579461065138979,
      "grad_norm": 0.931951642036438,
      "learning_rate": 9.504844339512096e-06,
      "loss": 2.3657,
      "step": 80
    },
    {
      "epoch": 0.1527689369828135,
      "grad_norm": 1.322995662689209,
      "learning_rate": 9.356593520616948e-06,
      "loss": 2.3112,
      "step": 90
    },
    {
      "epoch": 0.16295353278166771,
      "eval_loss": 2.282419443130493,
      "eval_runtime": 14.7626,
      "eval_samples_per_second": 16.867,
      "eval_steps_per_second": 16.867,
      "step": 96
    },
    {
      "epoch": 0.16974326331423722,
      "grad_norm": 0.8094339966773987,
      "learning_rate": 9.190440524459203e-06,
      "loss": 2.3695,
      "step": 100
    },
    {
      "epoch": 0.18671758964566093,
      "grad_norm": 0.723338782787323,
      "learning_rate": 9.007068109339783e-06,
      "loss": 2.2478,
      "step": 110
    },
    {
      "epoch": 0.20369191597708466,
      "grad_norm": 0.7135640978813171,
      "learning_rate": 8.807229791845673e-06,
      "loss": 2.1921,
      "step": 120
    },
    {
      "epoch": 0.21727137704222363,
      "eval_loss": 2.2477967739105225,
      "eval_runtime": 14.6761,
      "eval_samples_per_second": 16.966,
      "eval_steps_per_second": 16.966,
      "step": 128
    },
    {
      "epoch": 0.22066624230850837,
      "grad_norm": 0.772994339466095,
      "learning_rate": 8.591746750488639e-06,
      "loss": 2.1553,
      "step": 130
    },
    {
      "epoch": 0.2376405686399321,
      "grad_norm": 1.070949673652649,
      "learning_rate": 8.361504451306585e-06,
      "loss": 2.1614,
      "step": 140
    },
    {
      "epoch": 0.2546148949713558,
      "grad_norm": 0.636782705783844,
      "learning_rate": 8.117449009293668e-06,
      "loss": 2.0752,
      "step": 150
    },
    {
      "epoch": 0.27158922130277957,
      "grad_norm": 0.9331526756286621,
      "learning_rate": 7.860583300610849e-06,
      "loss": 2.2286,
      "step": 160
    },
    {
      "epoch": 0.27158922130277957,
      "eval_loss": 2.2229602336883545,
      "eval_runtime": 14.5584,
      "eval_samples_per_second": 17.104,
      "eval_steps_per_second": 17.104,
      "step": 160
    },
    {
      "epoch": 0.2885635476342033,
      "grad_norm": 0.8503024578094482,
      "learning_rate": 7.591962841552627e-06,
      "loss": 1.9789,
      "step": 170
    },
    {
      "epoch": 0.305537873965627,
      "grad_norm": 0.9481040239334106,
      "learning_rate": 7.312691451204178e-06,
      "loss": 2.1179,
      "step": 180
    },
    {
      "epoch": 0.3225122002970507,
      "grad_norm": 0.854963481426239,
      "learning_rate": 7.023916715611969e-06,
      "loss": 2.297,
      "step": 190
    },
    {
      "epoch": 0.32590706556333543,
      "eval_loss": 2.204796552658081,
      "eval_runtime": 14.6745,
      "eval_samples_per_second": 16.968,
      "eval_steps_per_second": 16.968,
      "step": 192
    },
    {
      "epoch": 0.33948652662847445,
      "grad_norm": 0.70894455909729,
      "learning_rate": 6.726825272106539e-06,
      "loss": 2.1591,
      "step": 200
    },
    {
      "epoch": 0.35646085295989816,
      "grad_norm": 0.7739590406417847,
      "learning_rate": 6.4226379331551625e-06,
      "loss": 2.1628,
      "step": 210
    },
    {
      "epoch": 0.37343517929132186,
      "grad_norm": 1.1449049711227417,
      "learning_rate": 6.112604669781572e-06,
      "loss": 2.196,
      "step": 220
    },
    {
      "epoch": 0.38022490982389134,
      "eval_loss": 2.1902246475219727,
      "eval_runtime": 14.9629,
      "eval_samples_per_second": 16.641,
      "eval_steps_per_second": 16.641,
      "step": 224
    },
    {
      "epoch": 0.3904095056227456,
      "grad_norm": 0.9429897665977478,
      "learning_rate": 5.797999475166897e-06,
      "loss": 2.1209,
      "step": 230
    },
    {
      "epoch": 0.40738383195416933,
      "grad_norm": 0.6817293167114258,
      "learning_rate": 5.480115129538409e-06,
      "loss": 2.078,
      "step": 240
    },
    {
      "epoch": 0.42435815828559303,
      "grad_norm": 1.0392802953720093,
      "learning_rate": 5.160257887858278e-06,
      "loss": 2.019,
      "step": 250
    },
    {
      "epoch": 0.43454275408444726,
      "eval_loss": 2.18066143989563,
      "eval_runtime": 14.9609,
      "eval_samples_per_second": 16.643,
      "eval_steps_per_second": 16.643,
      "step": 256
    },
    {
      "epoch": 0.44133248461701674,
      "grad_norm": 1.4284169673919678,
      "learning_rate": 4.839742112141725e-06,
      "loss": 2.1248,
      "step": 260
    },
    {
      "epoch": 0.4583068109484405,
      "grad_norm": 1.103446364402771,
      "learning_rate": 4.5198848704615915e-06,
      "loss": 2.2042,
      "step": 270
    },
    {
      "epoch": 0.4752811372798642,
      "grad_norm": 0.9654069542884827,
      "learning_rate": 4.2020005248331056e-06,
      "loss": 2.0661,
      "step": 280
    },
    {
      "epoch": 0.48886059834500317,
      "eval_loss": 2.1737821102142334,
      "eval_runtime": 14.6586,
      "eval_samples_per_second": 16.987,
      "eval_steps_per_second": 16.987,
      "step": 288
    },
    {
      "epoch": 0.4922554636112879,
      "grad_norm": 1.2110482454299927,
      "learning_rate": 3.887395330218429e-06,
      "loss": 2.1245,
      "step": 290
    },
    {
      "epoch": 0.5092297899427116,
      "grad_norm": 0.9131014943122864,
      "learning_rate": 3.5773620668448384e-06,
      "loss": 1.9854,
      "step": 300
    },
    {
      "epoch": 0.5262041162741353,
      "grad_norm": 0.8336049914360046,
      "learning_rate": 3.273174727893463e-06,
      "loss": 2.0522,
      "step": 310
    },
    {
      "epoch": 0.5431784426055591,
      "grad_norm": 0.8388031721115112,
      "learning_rate": 2.976083284388031e-06,
      "loss": 2.2818,
      "step": 320
    },
    {
      "epoch": 0.5431784426055591,
      "eval_loss": 2.169279098510742,
      "eval_runtime": 14.6962,
      "eval_samples_per_second": 16.943,
      "eval_steps_per_second": 16.943,
      "step": 320
    },
    {
      "epoch": 0.5601527689369828,
      "grad_norm": 1.1344929933547974,
      "learning_rate": 2.687308548795825e-06,
      "loss": 2.153,
      "step": 330
    },
    {
      "epoch": 0.5771270952684066,
      "grad_norm": 0.5925095081329346,
      "learning_rate": 2.408037158447375e-06,
      "loss": 2.1837,
      "step": 340
    },
    {
      "epoch": 0.5941014215998303,
      "grad_norm": 0.7718944549560547,
      "learning_rate": 2.139416699389153e-06,
      "loss": 2.1624,
      "step": 350
    },
    {
      "epoch": 0.597496286866115,
      "eval_loss": 2.1667089462280273,
      "eval_runtime": 14.721,
      "eval_samples_per_second": 16.915,
      "eval_steps_per_second": 16.915,
      "step": 352
    },
    {
      "epoch": 0.611075747931254,
      "grad_norm": 0.9826621413230896,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 2.1559,
      "step": 360
    },
    {
      "epoch": 0.6280500742626777,
      "grad_norm": 1.0323383808135986,
      "learning_rate": 1.6384955486934157e-06,
      "loss": 2.0834,
      "step": 370
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 63,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.20029415211008e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}