{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9991431019708654,
  "eval_steps": 500,
  "global_step": 583,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01713796058269066,
      "grad_norm": 0.4733077883720398,
      "learning_rate": 4.971412235563179e-05,
      "loss": 2.5254,
      "step": 10
    },
    {
      "epoch": 0.03427592116538132,
      "grad_norm": 0.44018083810806274,
      "learning_rate": 4.9428244711263584e-05,
      "loss": 1.8284,
      "step": 20
    },
    {
      "epoch": 0.05141388174807198,
      "grad_norm": 0.7213996648788452,
      "learning_rate": 4.914236706689537e-05,
      "loss": 1.2128,
      "step": 30
    },
    {
      "epoch": 0.06855184233076264,
      "grad_norm": 0.6227633953094482,
      "learning_rate": 4.8856489422527165e-05,
      "loss": 0.6727,
      "step": 40
    },
    {
      "epoch": 0.0856898029134533,
      "grad_norm": 0.2804420590400696,
      "learning_rate": 4.8570611778158946e-05,
      "loss": 0.3089,
      "step": 50
    },
    {
      "epoch": 0.10282776349614396,
      "grad_norm": 0.10756277292966843,
      "learning_rate": 4.828473413379074e-05,
      "loss": 0.2448,
      "step": 60
    },
    {
      "epoch": 0.11996572407883462,
      "grad_norm": 0.11257284879684448,
      "learning_rate": 4.799885648942253e-05,
      "loss": 0.2268,
      "step": 70
    },
    {
      "epoch": 0.13710368466152528,
      "grad_norm": 0.09793874621391296,
      "learning_rate": 4.771297884505432e-05,
      "loss": 0.2328,
      "step": 80
    },
    {
      "epoch": 0.15424164524421594,
      "grad_norm": 0.10177452117204666,
      "learning_rate": 4.742710120068611e-05,
      "loss": 0.2183,
      "step": 90
    },
    {
      "epoch": 0.1713796058269066,
      "grad_norm": 0.09770502895116806,
      "learning_rate": 4.7141223556317895e-05,
      "loss": 0.1971,
      "step": 100
    },
    {
      "epoch": 0.18851756640959727,
      "grad_norm": 0.11037880927324295,
      "learning_rate": 4.685534591194969e-05,
      "loss": 0.1996,
      "step": 110
    },
    {
      "epoch": 0.20565552699228792,
      "grad_norm": 0.11869871616363525,
      "learning_rate": 4.656946826758148e-05,
      "loss": 0.2044,
      "step": 120
    },
    {
      "epoch": 0.22279348757497858,
      "grad_norm": 0.10279687494039536,
      "learning_rate": 4.628359062321327e-05,
      "loss": 0.1782,
      "step": 130
    },
    {
      "epoch": 0.23993144815766923,
      "grad_norm": 0.10952438414096832,
      "learning_rate": 4.599771297884506e-05,
      "loss": 0.1837,
      "step": 140
    },
    {
      "epoch": 0.2570694087403599,
      "grad_norm": 0.13122445344924927,
      "learning_rate": 4.5711835334476845e-05,
      "loss": 0.1907,
      "step": 150
    },
    {
      "epoch": 0.27420736932305056,
      "grad_norm": 0.11156395077705383,
      "learning_rate": 4.542595769010863e-05,
      "loss": 0.1748,
      "step": 160
    },
    {
      "epoch": 0.2913453299057412,
      "grad_norm": 0.1657029241323471,
      "learning_rate": 4.5140080045740427e-05,
      "loss": 0.1704,
      "step": 170
    },
    {
      "epoch": 0.30848329048843187,
      "grad_norm": 0.11676887422800064,
      "learning_rate": 4.4854202401372214e-05,
      "loss": 0.16,
      "step": 180
    },
    {
      "epoch": 0.32562125107112255,
      "grad_norm": 0.17466452717781067,
      "learning_rate": 4.4568324757004e-05,
      "loss": 0.1705,
      "step": 190
    },
    {
      "epoch": 0.3427592116538132,
      "grad_norm": 0.1373518407344818,
      "learning_rate": 4.4282447112635795e-05,
      "loss": 0.1663,
      "step": 200
    },
    {
      "epoch": 0.35989717223650386,
      "grad_norm": 0.11815926432609558,
      "learning_rate": 4.399656946826758e-05,
      "loss": 0.1562,
      "step": 210
    },
    {
      "epoch": 0.37703513281919454,
      "grad_norm": 0.12364204227924347,
      "learning_rate": 4.3710691823899376e-05,
      "loss": 0.1655,
      "step": 220
    },
    {
      "epoch": 0.39417309340188517,
      "grad_norm": 0.11595863103866577,
      "learning_rate": 4.3424814179531164e-05,
      "loss": 0.1621,
      "step": 230
    },
    {
      "epoch": 0.41131105398457585,
      "grad_norm": 0.11320952326059341,
      "learning_rate": 4.313893653516296e-05,
      "loss": 0.1523,
      "step": 240
    },
    {
      "epoch": 0.4284490145672665,
      "grad_norm": 0.12280760705471039,
      "learning_rate": 4.285305889079474e-05,
      "loss": 0.1711,
      "step": 250
    },
    {
      "epoch": 0.44558697514995715,
      "grad_norm": 0.12085650116205215,
      "learning_rate": 4.256718124642653e-05,
      "loss": 0.1548,
      "step": 260
    },
    {
      "epoch": 0.46272493573264784,
      "grad_norm": 0.1491166651248932,
      "learning_rate": 4.228130360205832e-05,
      "loss": 0.1631,
      "step": 270
    },
    {
      "epoch": 0.47986289631533846,
      "grad_norm": 0.16156260669231415,
      "learning_rate": 4.199542595769011e-05,
      "loss": 0.1624,
      "step": 280
    },
    {
      "epoch": 0.49700085689802914,
      "grad_norm": 0.12156664580106735,
      "learning_rate": 4.17095483133219e-05,
      "loss": 0.1383,
      "step": 290
    },
    {
      "epoch": 0.5141388174807198,
      "grad_norm": 0.11533980071544647,
      "learning_rate": 4.142367066895369e-05,
      "loss": 0.1539,
      "step": 300
    },
    {
      "epoch": 0.5312767780634104,
      "grad_norm": 0.1386200189590454,
      "learning_rate": 4.113779302458548e-05,
      "loss": 0.1525,
      "step": 310
    },
    {
      "epoch": 0.5484147386461011,
      "grad_norm": 0.16111765801906586,
      "learning_rate": 4.085191538021727e-05,
      "loss": 0.14,
      "step": 320
    },
    {
      "epoch": 0.5655526992287918,
      "grad_norm": 0.151380717754364,
      "learning_rate": 4.0566037735849064e-05,
      "loss": 0.1492,
      "step": 330
    },
    {
      "epoch": 0.5826906598114824,
      "grad_norm": 0.15228472650051117,
      "learning_rate": 4.028016009148085e-05,
      "loss": 0.157,
      "step": 340
    },
    {
      "epoch": 0.5998286203941731,
      "grad_norm": 0.11199972033500671,
      "learning_rate": 3.999428244711264e-05,
      "loss": 0.1492,
      "step": 350
    },
    {
      "epoch": 0.6169665809768637,
      "grad_norm": 0.17204181849956512,
      "learning_rate": 3.9708404802744425e-05,
      "loss": 0.1504,
      "step": 360
    },
    {
      "epoch": 0.6341045415595544,
      "grad_norm": 0.13271720707416534,
      "learning_rate": 3.942252715837621e-05,
      "loss": 0.1604,
      "step": 370
    },
    {
      "epoch": 0.6512425021422451,
      "grad_norm": 0.15998151898384094,
      "learning_rate": 3.913664951400801e-05,
      "loss": 0.148,
      "step": 380
    },
    {
      "epoch": 0.6683804627249358,
      "grad_norm": 0.12898313999176025,
      "learning_rate": 3.8850771869639794e-05,
      "loss": 0.1492,
      "step": 390
    },
    {
      "epoch": 0.6855184233076264,
      "grad_norm": 0.13998836278915405,
      "learning_rate": 3.856489422527159e-05,
      "loss": 0.1548,
      "step": 400
    },
    {
      "epoch": 0.702656383890317,
      "grad_norm": 0.14940115809440613,
      "learning_rate": 3.8279016580903375e-05,
      "loss": 0.1432,
      "step": 410
    },
    {
      "epoch": 0.7197943444730077,
      "grad_norm": 0.13358236849308014,
      "learning_rate": 3.799313893653517e-05,
      "loss": 0.1459,
      "step": 420
    },
    {
      "epoch": 0.7369323050556984,
      "grad_norm": 0.1597578376531601,
      "learning_rate": 3.7707261292166957e-05,
      "loss": 0.1351,
      "step": 430
    },
    {
      "epoch": 0.7540702656383891,
      "grad_norm": 0.12782897055149078,
      "learning_rate": 3.7421383647798744e-05,
      "loss": 0.1392,
      "step": 440
    },
    {
      "epoch": 0.7712082262210797,
      "grad_norm": 0.13537828624248505,
      "learning_rate": 3.713550600343053e-05,
      "loss": 0.1402,
      "step": 450
    },
    {
      "epoch": 0.7883461868037703,
      "grad_norm": 0.17046277225017548,
      "learning_rate": 3.684962835906232e-05,
      "loss": 0.1227,
      "step": 460
    },
    {
      "epoch": 0.805484147386461,
      "grad_norm": 0.16829894483089447,
      "learning_rate": 3.656375071469411e-05,
      "loss": 0.133,
      "step": 470
    },
    {
      "epoch": 0.8226221079691517,
      "grad_norm": 0.17760640382766724,
      "learning_rate": 3.62778730703259e-05,
      "loss": 0.1361,
      "step": 480
    },
    {
      "epoch": 0.8397600685518424,
      "grad_norm": 0.1783646047115326,
      "learning_rate": 3.5991995425957694e-05,
      "loss": 0.1272,
      "step": 490
    },
    {
      "epoch": 0.856898029134533,
      "grad_norm": 0.1848060041666031,
      "learning_rate": 3.570611778158948e-05,
      "loss": 0.1281,
      "step": 500
    },
    {
      "epoch": 0.8740359897172236,
      "grad_norm": 0.1244303435087204,
      "learning_rate": 3.5420240137221275e-05,
      "loss": 0.1276,
      "step": 510
    },
    {
      "epoch": 0.8911739502999143,
      "grad_norm": 0.1454310566186905,
      "learning_rate": 3.513436249285306e-05,
      "loss": 0.1334,
      "step": 520
    },
    {
      "epoch": 0.908311910882605,
      "grad_norm": 0.17194361984729767,
      "learning_rate": 3.484848484848485e-05,
      "loss": 0.1271,
      "step": 530
    },
    {
      "epoch": 0.9254498714652957,
      "grad_norm": 0.15851227939128876,
      "learning_rate": 3.456260720411664e-05,
      "loss": 0.1304,
      "step": 540
    },
    {
      "epoch": 0.9425878320479862,
      "grad_norm": 0.1614447981119156,
      "learning_rate": 3.4276729559748424e-05,
      "loss": 0.1256,
      "step": 550
    },
    {
      "epoch": 0.9597257926306769,
      "grad_norm": 0.19016973674297333,
      "learning_rate": 3.399085191538022e-05,
      "loss": 0.1329,
      "step": 560
    },
    {
      "epoch": 0.9768637532133676,
      "grad_norm": 0.15122413635253906,
      "learning_rate": 3.3704974271012005e-05,
      "loss": 0.1228,
      "step": 570
    },
    {
      "epoch": 0.9940017137960583,
      "grad_norm": 0.15631020069122314,
      "learning_rate": 3.34190966266438e-05,
      "loss": 0.1235,
      "step": 580
    },
    {
      "epoch": 0.9991431019708654,
      "eval_loss": 0.15606513619422913,
      "eval_runtime": 439.0741,
      "eval_samples_per_second": 10.932,
      "eval_steps_per_second": 1.367,
      "step": 583
    }
  ],
  "logging_steps": 10,
  "max_steps": 1749,
  "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": 4.356382410355507e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}