{
  "best_metric": 1.805577039718628,
  "best_model_checkpoint": "./results/checkpoint-800",
  "epoch": 1.5230842455973346,
  "eval_steps": 200,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01903855306996668,
      "grad_norm": 0.17994017899036407,
      "learning_rate": 5e-05,
      "loss": 2.1247,
      "step": 10
    },
    {
      "epoch": 0.03807710613993336,
      "grad_norm": 0.27629706263542175,
      "learning_rate": 0.0001,
      "loss": 2.0758,
      "step": 20
    },
    {
      "epoch": 0.05711565920990005,
      "grad_norm": 0.4726850092411041,
      "learning_rate": 0.00015,
      "loss": 2.0858,
      "step": 30
    },
    {
      "epoch": 0.07615421227986673,
      "grad_norm": 0.5583528876304626,
      "learning_rate": 0.0002,
      "loss": 2.0593,
      "step": 40
    },
    {
      "epoch": 0.09519276534983341,
      "grad_norm": 0.5730186104774475,
      "learning_rate": 0.00025,
      "loss": 2.0161,
      "step": 50
    },
    {
      "epoch": 0.1142313184198001,
      "grad_norm": 0.48230308294296265,
      "learning_rate": 0.0003,
      "loss": 1.9764,
      "step": 60
    },
    {
      "epoch": 0.13326987148976677,
      "grad_norm": 0.44312751293182373,
      "learning_rate": 0.00035,
      "loss": 1.9557,
      "step": 70
    },
    {
      "epoch": 0.15230842455973345,
      "grad_norm": 0.4186476171016693,
      "learning_rate": 0.0004,
      "loss": 1.9422,
      "step": 80
    },
    {
      "epoch": 0.17134697762970014,
      "grad_norm": 0.38540077209472656,
      "learning_rate": 0.00045000000000000004,
      "loss": 1.9189,
      "step": 90
    },
    {
      "epoch": 0.19038553069966682,
      "grad_norm": 0.35501590371131897,
      "learning_rate": 0.0005,
      "loss": 1.9254,
      "step": 100
    },
    {
      "epoch": 0.2094240837696335,
      "grad_norm": 0.40440383553504944,
      "learning_rate": 0.000498019801980198,
      "loss": 1.9032,
      "step": 110
    },
    {
      "epoch": 0.2284626368396002,
      "grad_norm": 0.39570745825767517,
      "learning_rate": 0.000496039603960396,
      "loss": 1.9029,
      "step": 120
    },
    {
      "epoch": 0.24750118990956688,
      "grad_norm": 0.4123484790325165,
      "learning_rate": 0.0004940594059405941,
      "loss": 1.8735,
      "step": 130
    },
    {
      "epoch": 0.26653974297953353,
      "grad_norm": 0.37050503492355347,
      "learning_rate": 0.0004920792079207921,
      "loss": 1.8739,
      "step": 140
    },
    {
      "epoch": 0.28557829604950025,
      "grad_norm": 0.4047178030014038,
      "learning_rate": 0.0004900990099009901,
      "loss": 1.8659,
      "step": 150
    },
    {
      "epoch": 0.3046168491194669,
      "grad_norm": 0.3643397092819214,
      "learning_rate": 0.0004881188118811881,
      "loss": 1.8689,
      "step": 160
    },
    {
      "epoch": 0.3236554021894336,
      "grad_norm": 0.37609240412712097,
      "learning_rate": 0.00048613861386138615,
      "loss": 1.8599,
      "step": 170
    },
    {
      "epoch": 0.3426939552594003,
      "grad_norm": 0.3859333395957947,
      "learning_rate": 0.00048415841584158414,
      "loss": 1.8441,
      "step": 180
    },
    {
      "epoch": 0.361732508329367,
      "grad_norm": 0.3943149447441101,
      "learning_rate": 0.0004821782178217822,
      "loss": 1.8366,
      "step": 190
    },
    {
      "epoch": 0.38077106139933364,
      "grad_norm": 0.41318005323410034,
      "learning_rate": 0.0004801980198019802,
      "loss": 1.8381,
      "step": 200
    },
    {
      "epoch": 0.38077106139933364,
      "eval_loss": 1.8646808862686157,
      "eval_runtime": 4.2162,
      "eval_samples_per_second": 23.718,
      "eval_steps_per_second": 1.66,
      "step": 200
    },
    {
      "epoch": 0.39980961446930036,
      "grad_norm": 0.3635823726654053,
      "learning_rate": 0.0004782178217821782,
      "loss": 1.8292,
      "step": 210
    },
    {
      "epoch": 0.418848167539267,
      "grad_norm": 0.3529907166957855,
      "learning_rate": 0.00047623762376237624,
      "loss": 1.8444,
      "step": 220
    },
    {
      "epoch": 0.43788672060923367,
      "grad_norm": 0.3581302762031555,
      "learning_rate": 0.00047425742574257423,
      "loss": 1.8352,
      "step": 230
    },
    {
      "epoch": 0.4569252736792004,
      "grad_norm": 0.3584224581718445,
      "learning_rate": 0.0004722772277227723,
      "loss": 1.8319,
      "step": 240
    },
    {
      "epoch": 0.47596382674916704,
      "grad_norm": 0.3439520299434662,
      "learning_rate": 0.0004702970297029703,
      "loss": 1.8296,
      "step": 250
    },
    {
      "epoch": 0.49500237981913375,
      "grad_norm": 0.3635288178920746,
      "learning_rate": 0.00046831683168316833,
      "loss": 1.8294,
      "step": 260
    },
    {
      "epoch": 0.5140409328891005,
      "grad_norm": 0.3621940612792969,
      "learning_rate": 0.0004663366336633664,
      "loss": 1.8245,
      "step": 270
    },
    {
      "epoch": 0.5330794859590671,
      "grad_norm": 0.3562050759792328,
      "learning_rate": 0.0004643564356435644,
      "loss": 1.8051,
      "step": 280
    },
    {
      "epoch": 0.5521180390290338,
      "grad_norm": 0.3374086618423462,
      "learning_rate": 0.00046237623762376243,
      "loss": 1.8205,
      "step": 290
    },
    {
      "epoch": 0.5711565920990005,
      "grad_norm": 0.33458590507507324,
      "learning_rate": 0.0004603960396039604,
      "loss": 1.8238,
      "step": 300
    },
    {
      "epoch": 0.5901951451689672,
      "grad_norm": 0.3511849045753479,
      "learning_rate": 0.0004584158415841584,
      "loss": 1.8074,
      "step": 310
    },
    {
      "epoch": 0.6092336982389338,
      "grad_norm": 0.3680996000766754,
      "learning_rate": 0.00045643564356435647,
      "loss": 1.8349,
      "step": 320
    },
    {
      "epoch": 0.6282722513089005,
      "grad_norm": 0.33489343523979187,
      "learning_rate": 0.00045445544554455447,
      "loss": 1.8304,
      "step": 330
    },
    {
      "epoch": 0.6473108043788672,
      "grad_norm": 0.3262704908847809,
      "learning_rate": 0.0004524752475247525,
      "loss": 1.8179,
      "step": 340
    },
    {
      "epoch": 0.6663493574488338,
      "grad_norm": 0.33311426639556885,
      "learning_rate": 0.0004504950495049505,
      "loss": 1.8075,
      "step": 350
    },
    {
      "epoch": 0.6853879105188005,
      "grad_norm": 0.3391004800796509,
      "learning_rate": 0.0004485148514851485,
      "loss": 1.8124,
      "step": 360
    },
    {
      "epoch": 0.7044264635887673,
      "grad_norm": 0.34050452709198,
      "learning_rate": 0.00044653465346534656,
      "loss": 1.8184,
      "step": 370
    },
    {
      "epoch": 0.723465016658734,
      "grad_norm": 0.320922315120697,
      "learning_rate": 0.00044455445544554456,
      "loss": 1.8129,
      "step": 380
    },
    {
      "epoch": 0.7425035697287006,
      "grad_norm": 0.3578341007232666,
      "learning_rate": 0.0004425742574257426,
      "loss": 1.7989,
      "step": 390
    },
    {
      "epoch": 0.7615421227986673,
      "grad_norm": 0.31143978238105774,
      "learning_rate": 0.0004405940594059406,
      "loss": 1.8054,
      "step": 400
    },
    {
      "epoch": 0.7615421227986673,
      "eval_loss": 1.829106330871582,
      "eval_runtime": 4.2436,
      "eval_samples_per_second": 23.565,
      "eval_steps_per_second": 1.65,
      "step": 400
    },
    {
      "epoch": 0.780580675868634,
      "grad_norm": 0.3297821581363678,
      "learning_rate": 0.0004386138613861386,
      "loss": 1.8165,
      "step": 410
    },
    {
      "epoch": 0.7996192289386007,
      "grad_norm": 0.33798128366470337,
      "learning_rate": 0.00043663366336633665,
      "loss": 1.8001,
      "step": 420
    },
    {
      "epoch": 0.8186577820085673,
      "grad_norm": 0.3441774547100067,
      "learning_rate": 0.00043465346534653465,
      "loss": 1.8057,
      "step": 430
    },
    {
      "epoch": 0.837696335078534,
      "grad_norm": 0.30104541778564453,
      "learning_rate": 0.0004326732673267327,
      "loss": 1.8122,
      "step": 440
    },
    {
      "epoch": 0.8567348881485007,
      "grad_norm": 0.31903618574142456,
      "learning_rate": 0.0004306930693069307,
      "loss": 1.8099,
      "step": 450
    },
    {
      "epoch": 0.8757734412184673,
      "grad_norm": 0.31247204542160034,
      "learning_rate": 0.0004287128712871287,
      "loss": 1.8132,
      "step": 460
    },
    {
      "epoch": 0.894811994288434,
      "grad_norm": 0.3191291391849518,
      "learning_rate": 0.00042673267326732674,
      "loss": 1.8143,
      "step": 470
    },
    {
      "epoch": 0.9138505473584008,
      "grad_norm": 0.3244192600250244,
      "learning_rate": 0.00042475247524752474,
      "loss": 1.7999,
      "step": 480
    },
    {
      "epoch": 0.9328891004283675,
      "grad_norm": 0.37674182653427124,
      "learning_rate": 0.0004227722772277228,
      "loss": 1.8097,
      "step": 490
    },
    {
      "epoch": 0.9519276534983341,
      "grad_norm": 0.31393611431121826,
      "learning_rate": 0.0004207920792079208,
      "loss": 1.802,
      "step": 500
    },
    {
      "epoch": 0.9709662065683008,
      "grad_norm": 0.3186231255531311,
      "learning_rate": 0.0004188118811881188,
      "loss": 1.8043,
      "step": 510
    },
    {
      "epoch": 0.9900047596382675,
      "grad_norm": 0.2924995422363281,
      "learning_rate": 0.00041683168316831683,
      "loss": 1.792,
      "step": 520
    },
    {
      "epoch": 1.009043312708234,
      "grad_norm": 0.3129435181617737,
      "learning_rate": 0.00041485148514851483,
      "loss": 1.8009,
      "step": 530
    },
    {
      "epoch": 1.028081865778201,
      "grad_norm": 0.2927923798561096,
      "learning_rate": 0.0004128712871287129,
      "loss": 1.8011,
      "step": 540
    },
    {
      "epoch": 1.0471204188481675,
      "grad_norm": 0.2918388545513153,
      "learning_rate": 0.0004108910891089109,
      "loss": 1.7946,
      "step": 550
    },
    {
      "epoch": 1.0661589719181341,
      "grad_norm": 0.2885777950286865,
      "learning_rate": 0.0004089108910891089,
      "loss": 1.8075,
      "step": 560
    },
    {
      "epoch": 1.085197524988101,
      "grad_norm": 0.30024921894073486,
      "learning_rate": 0.0004069306930693069,
      "loss": 1.7824,
      "step": 570
    },
    {
      "epoch": 1.1042360780580676,
      "grad_norm": 0.2903335988521576,
      "learning_rate": 0.000404950495049505,
      "loss": 1.7954,
      "step": 580
    },
    {
      "epoch": 1.1232746311280342,
      "grad_norm": 0.3008085787296295,
      "learning_rate": 0.000402970297029703,
      "loss": 1.7969,
      "step": 590
    },
    {
      "epoch": 1.142313184198001,
      "grad_norm": 0.29621192812919617,
      "learning_rate": 0.000400990099009901,
      "loss": 1.7803,
      "step": 600
    },
    {
      "epoch": 1.142313184198001,
      "eval_loss": 1.8143733739852905,
      "eval_runtime": 4.1557,
      "eval_samples_per_second": 24.063,
      "eval_steps_per_second": 1.684,
      "step": 600
    },
    {
      "epoch": 1.1613517372679676,
      "grad_norm": 0.30486541986465454,
      "learning_rate": 0.000399009900990099,
      "loss": 1.8,
      "step": 610
    },
    {
      "epoch": 1.1803902903379344,
      "grad_norm": 0.2792316675186157,
      "learning_rate": 0.00039702970297029707,
      "loss": 1.7822,
      "step": 620
    },
    {
      "epoch": 1.199428843407901,
      "grad_norm": 0.2918599545955658,
      "learning_rate": 0.00039504950495049506,
      "loss": 1.7808,
      "step": 630
    },
    {
      "epoch": 1.2184673964778676,
      "grad_norm": 0.2980496883392334,
      "learning_rate": 0.0003930693069306931,
      "loss": 1.7952,
      "step": 640
    },
    {
      "epoch": 1.2375059495478344,
      "grad_norm": 0.31613168120384216,
      "learning_rate": 0.0003910891089108911,
      "loss": 1.7996,
      "step": 650
    },
    {
      "epoch": 1.256544502617801,
      "grad_norm": 0.30946284532546997,
      "learning_rate": 0.0003891089108910891,
      "loss": 1.791,
      "step": 660
    },
    {
      "epoch": 1.2755830556877679,
      "grad_norm": 0.28848570585250854,
      "learning_rate": 0.00038712871287128716,
      "loss": 1.782,
      "step": 670
    },
    {
      "epoch": 1.2946216087577345,
      "grad_norm": 0.2725277543067932,
      "learning_rate": 0.00038514851485148515,
      "loss": 1.7847,
      "step": 680
    },
    {
      "epoch": 1.313660161827701,
      "grad_norm": 0.2864035665988922,
      "learning_rate": 0.0003831683168316832,
      "loss": 1.7938,
      "step": 690
    },
    {
      "epoch": 1.332698714897668,
      "grad_norm": 0.30256739258766174,
      "learning_rate": 0.0003811881188118812,
      "loss": 1.7947,
      "step": 700
    },
    {
      "epoch": 1.3517372679676345,
      "grad_norm": 0.2603744864463806,
      "learning_rate": 0.0003792079207920792,
      "loss": 1.8028,
      "step": 710
    },
    {
      "epoch": 1.370775821037601,
      "grad_norm": 0.3716331124305725,
      "learning_rate": 0.00037722772277227725,
      "loss": 1.7722,
      "step": 720
    },
    {
      "epoch": 1.389814374107568,
      "grad_norm": 0.35902512073516846,
      "learning_rate": 0.00037524752475247524,
      "loss": 1.7916,
      "step": 730
    },
    {
      "epoch": 1.4088529271775345,
      "grad_norm": 0.28538694977760315,
      "learning_rate": 0.0003732673267326733,
      "loss": 1.7812,
      "step": 740
    },
    {
      "epoch": 1.4278914802475011,
      "grad_norm": 0.29331693053245544,
      "learning_rate": 0.0003712871287128713,
      "loss": 1.7983,
      "step": 750
    },
    {
      "epoch": 1.446930033317468,
      "grad_norm": 0.31655997037887573,
      "learning_rate": 0.0003693069306930693,
      "loss": 1.7983,
      "step": 760
    },
    {
      "epoch": 1.4659685863874345,
      "grad_norm": 0.29052191972732544,
      "learning_rate": 0.00036732673267326734,
      "loss": 1.8021,
      "step": 770
    },
    {
      "epoch": 1.4850071394574011,
      "grad_norm": 0.2977640628814697,
      "learning_rate": 0.00036534653465346533,
      "loss": 1.7702,
      "step": 780
    },
    {
      "epoch": 1.504045692527368,
      "grad_norm": 0.27408239245414734,
      "learning_rate": 0.0003633663366336634,
      "loss": 1.7836,
      "step": 790
    },
    {
      "epoch": 1.5230842455973346,
      "grad_norm": 0.29241588711738586,
      "learning_rate": 0.0003613861386138614,
      "loss": 1.8005,
      "step": 800
    },
    {
      "epoch": 1.5230842455973346,
      "eval_loss": 1.805577039718628,
      "eval_runtime": 4.2437,
      "eval_samples_per_second": 23.564,
      "eval_steps_per_second": 1.649,
      "step": 800
    }
  ],
  "logging_steps": 10,
  "max_steps": 2625,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3184333317668864e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}