{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.003338898163606,
  "eval_steps": 50,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022259321090706732,
      "grad_norm": 0.6662815809249878,
      "learning_rate": 7.3529411764705884e-06,
      "loss": 1.2136,
      "step": 5
    },
    {
      "epoch": 0.044518642181413465,
      "grad_norm": 0.9986972212791443,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 1.2704,
      "step": 10
    },
    {
      "epoch": 0.0667779632721202,
      "grad_norm": 1.0016194581985474,
      "learning_rate": 2.2058823529411766e-05,
      "loss": 1.1674,
      "step": 15
    },
    {
      "epoch": 0.08903728436282693,
      "grad_norm": 0.4482230246067047,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 1.1745,
      "step": 20
    },
    {
      "epoch": 0.11129660545353366,
      "grad_norm": 0.32080814242362976,
      "learning_rate": 3.6764705882352945e-05,
      "loss": 1.1222,
      "step": 25
    },
    {
      "epoch": 0.1335559265442404,
      "grad_norm": 0.3496420979499817,
      "learning_rate": 4.411764705882353e-05,
      "loss": 1.1505,
      "step": 30
    },
    {
      "epoch": 0.15581524763494714,
      "grad_norm": 0.40206676721572876,
      "learning_rate": 5.147058823529411e-05,
      "loss": 1.1051,
      "step": 35
    },
    {
      "epoch": 0.17807456872565386,
      "grad_norm": 0.34886816143989563,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.0896,
      "step": 40
    },
    {
      "epoch": 0.2003338898163606,
      "grad_norm": 0.3876524269580841,
      "learning_rate": 6.61764705882353e-05,
      "loss": 1.1052,
      "step": 45
    },
    {
      "epoch": 0.22259321090706732,
      "grad_norm": 0.42603397369384766,
      "learning_rate": 7.352941176470589e-05,
      "loss": 1.0529,
      "step": 50
    },
    {
      "epoch": 0.22259321090706732,
      "eval_loss": 1.0506384372711182,
      "eval_runtime": 63.5224,
      "eval_samples_per_second": 12.578,
      "eval_steps_per_second": 1.574,
      "step": 50
    },
    {
      "epoch": 0.24485253199777407,
      "grad_norm": 0.42488643527030945,
      "learning_rate": 8.088235294117648e-05,
      "loss": 1.0093,
      "step": 55
    },
    {
      "epoch": 0.2671118530884808,
      "grad_norm": 0.46560072898864746,
      "learning_rate": 8.823529411764706e-05,
      "loss": 0.9961,
      "step": 60
    },
    {
      "epoch": 0.28937117417918756,
      "grad_norm": 0.4789991080760956,
      "learning_rate": 9.558823529411765e-05,
      "loss": 0.96,
      "step": 65
    },
    {
      "epoch": 0.3116304952698943,
      "grad_norm": 0.5202014446258545,
      "learning_rate": 9.999729465939036e-05,
      "loss": 1.0675,
      "step": 70
    },
    {
      "epoch": 0.333889816360601,
      "grad_norm": 0.49772489070892334,
      "learning_rate": 9.996686293953675e-05,
      "loss": 0.9783,
      "step": 75
    },
    {
      "epoch": 0.3561491374513077,
      "grad_norm": 0.4958195984363556,
      "learning_rate": 9.990263847374976e-05,
      "loss": 0.9948,
      "step": 80
    },
    {
      "epoch": 0.3784084585420145,
      "grad_norm": 0.5104294419288635,
      "learning_rate": 9.98046646972368e-05,
      "loss": 1.0261,
      "step": 85
    },
    {
      "epoch": 0.4006677796327212,
      "grad_norm": 0.41805458068847656,
      "learning_rate": 9.96730078699698e-05,
      "loss": 0.9852,
      "step": 90
    },
    {
      "epoch": 0.42292710072342793,
      "grad_norm": 0.4951586425304413,
      "learning_rate": 9.950775703187354e-05,
      "loss": 0.9717,
      "step": 95
    },
    {
      "epoch": 0.44518642181413465,
      "grad_norm": 0.44999977946281433,
      "learning_rate": 9.930902394260747e-05,
      "loss": 1.0382,
      "step": 100
    },
    {
      "epoch": 0.44518642181413465,
      "eval_loss": 0.9870203137397766,
      "eval_runtime": 62.5821,
      "eval_samples_per_second": 12.767,
      "eval_steps_per_second": 1.598,
      "step": 100
    },
    {
      "epoch": 0.4674457429048414,
      "grad_norm": 0.4562780559062958,
      "learning_rate": 9.907694300598237e-05,
      "loss": 0.9566,
      "step": 105
    },
    {
      "epoch": 0.48970506399554814,
      "grad_norm": 0.42032694816589355,
      "learning_rate": 9.881167117906275e-05,
      "loss": 1.0088,
      "step": 110
    },
    {
      "epoch": 0.5119643850862549,
      "grad_norm": 0.4715286195278168,
      "learning_rate": 9.851338786601614e-05,
      "loss": 0.952,
      "step": 115
    },
    {
      "epoch": 0.5342237061769616,
      "grad_norm": 0.43396106362342834,
      "learning_rate": 9.818229479678158e-05,
      "loss": 0.9474,
      "step": 120
    },
    {
      "epoch": 0.5564830272676683,
      "grad_norm": 0.4831869900226593,
      "learning_rate": 9.781861589063895e-05,
      "loss": 0.9822,
      "step": 125
    },
    {
      "epoch": 0.5787423483583751,
      "grad_norm": 0.4437423050403595,
      "learning_rate": 9.742259710477177e-05,
      "loss": 0.9948,
      "step": 130
    },
    {
      "epoch": 0.6010016694490818,
      "grad_norm": 0.42239800095558167,
      "learning_rate": 9.699450626792548e-05,
      "loss": 1.0358,
      "step": 135
    },
    {
      "epoch": 0.6232609905397886,
      "grad_norm": 0.3968772888183594,
      "learning_rate": 9.653463289927411e-05,
      "loss": 0.9488,
      "step": 140
    },
    {
      "epoch": 0.6455203116304953,
      "grad_norm": 0.4016033709049225,
      "learning_rate": 9.604328801261746e-05,
      "loss": 0.9543,
      "step": 145
    },
    {
      "epoch": 0.667779632721202,
      "grad_norm": 0.3789500892162323,
      "learning_rate": 9.55208039060416e-05,
      "loss": 0.9517,
      "step": 150
    },
    {
      "epoch": 0.667779632721202,
      "eval_loss": 0.9664375185966492,
      "eval_runtime": 62.5254,
      "eval_samples_per_second": 12.779,
      "eval_steps_per_second": 1.599,
      "step": 150
    },
    {
      "epoch": 0.6900389538119087,
      "grad_norm": 0.42804014682769775,
      "learning_rate": 9.496753393718453e-05,
      "loss": 1.0225,
      "step": 155
    },
    {
      "epoch": 0.7122982749026154,
      "grad_norm": 0.4701464772224426,
      "learning_rate": 9.438385228425938e-05,
      "loss": 0.9765,
      "step": 160
    },
    {
      "epoch": 0.7345575959933222,
      "grad_norm": 0.4485417604446411,
      "learning_rate": 9.377015369299651e-05,
      "loss": 1.0122,
      "step": 165
    },
    {
      "epoch": 0.756816917084029,
      "grad_norm": 0.4678383767604828,
      "learning_rate": 9.312685320967564e-05,
      "loss": 1.0016,
      "step": 170
    },
    {
      "epoch": 0.7790762381747357,
      "grad_norm": 0.46723246574401855,
      "learning_rate": 9.245438590042887e-05,
      "loss": 0.9604,
      "step": 175
    },
    {
      "epoch": 0.8013355592654424,
      "grad_norm": 0.40324416756629944,
      "learning_rate": 9.175320655700406e-05,
      "loss": 0.9903,
      "step": 180
    },
    {
      "epoch": 0.8235948803561491,
      "grad_norm": 0.4134933650493622,
      "learning_rate": 9.102378938918764e-05,
      "loss": 0.9012,
      "step": 185
    },
    {
      "epoch": 0.8458542014468559,
      "grad_norm": 0.4861450791358948,
      "learning_rate": 9.026662770409522e-05,
      "loss": 0.9666,
      "step": 190
    },
    {
      "epoch": 0.8681135225375626,
      "grad_norm": 0.46025416254997253,
      "learning_rate": 8.948223357254636e-05,
      "loss": 0.9406,
      "step": 195
    },
    {
      "epoch": 0.8903728436282693,
      "grad_norm": 0.45446667075157166,
      "learning_rate": 8.86711374827494e-05,
      "loss": 0.9871,
      "step": 200
    },
    {
      "epoch": 0.8903728436282693,
      "eval_loss": 0.9560968279838562,
      "eval_runtime": 62.5387,
      "eval_samples_per_second": 12.776,
      "eval_steps_per_second": 1.599,
      "step": 200
    },
    {
      "epoch": 0.9126321647189761,
      "grad_norm": 0.44481343030929565,
      "learning_rate": 8.783388798153074e-05,
      "loss": 1.0485,
      "step": 205
    },
    {
      "epoch": 0.9348914858096828,
      "grad_norm": 0.3908093273639679,
      "learning_rate": 8.697105130335085e-05,
      "loss": 0.943,
      "step": 210
    },
    {
      "epoch": 0.9571508069003896,
      "grad_norm": 0.4595666527748108,
      "learning_rate": 8.608321098735811e-05,
      "loss": 1.0317,
      "step": 215
    },
    {
      "epoch": 0.9794101279910963,
      "grad_norm": 0.4300236403942108,
      "learning_rate": 8.517096748273951e-05,
      "loss": 0.9079,
      "step": 220
    },
    {
      "epoch": 1.001669449081803,
      "grad_norm": 0.42982354760169983,
      "learning_rate": 8.423493774263493e-05,
      "loss": 0.9856,
      "step": 225
    },
    {
      "epoch": 1.0239287701725097,
      "grad_norm": 0.43644052743911743,
      "learning_rate": 8.327575480688985e-05,
      "loss": 0.9443,
      "step": 230
    },
    {
      "epoch": 1.0461880912632164,
      "grad_norm": 0.4620282053947449,
      "learning_rate": 8.229406737392843e-05,
      "loss": 0.9307,
      "step": 235
    },
    {
      "epoch": 1.0684474123539232,
      "grad_norm": 0.4973452687263489,
      "learning_rate": 8.129053936203687e-05,
      "loss": 0.9211,
      "step": 240
    },
    {
      "epoch": 1.0907067334446299,
      "grad_norm": 0.4471150040626526,
      "learning_rate": 8.026584946035331e-05,
      "loss": 0.8556,
      "step": 245
    },
    {
      "epoch": 1.1129660545353366,
      "grad_norm": 0.4626604914665222,
      "learning_rate": 7.92206906698682e-05,
      "loss": 0.8805,
      "step": 250
    },
    {
      "epoch": 1.1129660545353366,
      "eval_loss": 0.9515854120254517,
      "eval_runtime": 62.5564,
      "eval_samples_per_second": 12.772,
      "eval_steps_per_second": 1.599,
      "step": 250
    },
    {
      "epoch": 1.1352253756260433,
      "grad_norm": 0.4923231899738312,
      "learning_rate": 7.815576983474562e-05,
      "loss": 0.9766,
      "step": 255
    },
    {
      "epoch": 1.1574846967167502,
      "grad_norm": 0.5031096339225769,
      "learning_rate": 7.707180716428237e-05,
      "loss": 0.9154,
      "step": 260
    },
    {
      "epoch": 1.179744017807457,
      "grad_norm": 0.46800029277801514,
      "learning_rate": 7.596953574582814e-05,
      "loss": 0.9189,
      "step": 265
    },
    {
      "epoch": 1.2020033388981637,
      "grad_norm": 0.5481358170509338,
      "learning_rate": 7.484970104899624e-05,
      "loss": 0.9032,
      "step": 270
    },
    {
      "epoch": 1.2242626599888704,
      "grad_norm": 0.5768924951553345,
      "learning_rate": 7.371306042150012e-05,
      "loss": 0.9209,
      "step": 275
    },
    {
      "epoch": 1.2465219810795771,
      "grad_norm": 0.5290476083755493,
      "learning_rate": 7.256038257695687e-05,
      "loss": 0.8781,
      "step": 280
    },
    {
      "epoch": 1.2687813021702838,
      "grad_norm": 0.5345566868782043,
      "learning_rate": 7.139244707500363e-05,
      "loss": 0.9094,
      "step": 285
    },
    {
      "epoch": 1.2910406232609906,
      "grad_norm": 0.51719069480896,
      "learning_rate": 7.021004379407909e-05,
      "loss": 0.8804,
      "step": 290
    },
    {
      "epoch": 1.3132999443516973,
      "grad_norm": 0.4983583390712738,
      "learning_rate": 6.901397239722616e-05,
      "loss": 0.9081,
      "step": 295
    },
    {
      "epoch": 1.335559265442404,
      "grad_norm": 0.5766102075576782,
      "learning_rate": 6.780504179127734e-05,
      "loss": 0.8714,
      "step": 300
    },
    {
      "epoch": 1.335559265442404,
      "eval_loss": 0.9486159682273865,
      "eval_runtime": 62.5468,
      "eval_samples_per_second": 12.774,
      "eval_steps_per_second": 1.599,
      "step": 300
    },
    {
      "epoch": 1.3578185865331107,
      "grad_norm": 0.5398675799369812,
      "learning_rate": 6.658406957978862e-05,
      "loss": 0.921,
      "step": 305
    },
    {
      "epoch": 1.3800779076238174,
      "grad_norm": 0.5467468500137329,
      "learning_rate": 6.535188151009143e-05,
      "loss": 0.8828,
      "step": 310
    },
    {
      "epoch": 1.4023372287145242,
      "grad_norm": 0.5757557153701782,
      "learning_rate": 6.41093109148373e-05,
      "loss": 0.9417,
      "step": 315
    },
    {
      "epoch": 1.4245965498052309,
      "grad_norm": 0.5766004920005798,
      "learning_rate": 6.28571981484123e-05,
      "loss": 0.8331,
      "step": 320
    },
    {
      "epoch": 1.4468558708959378,
      "grad_norm": 0.6180554628372192,
      "learning_rate": 6.159639001860277e-05,
      "loss": 0.8924,
      "step": 325
    },
    {
      "epoch": 1.4691151919866443,
      "grad_norm": 0.5856440663337708,
      "learning_rate": 6.032773921389655e-05,
      "loss": 0.8868,
      "step": 330
    },
    {
      "epoch": 1.4913745130773512,
      "grad_norm": 0.5318928360939026,
      "learning_rate": 5.905210372680704e-05,
      "loss": 0.9377,
      "step": 335
    },
    {
      "epoch": 1.5136338341680577,
      "grad_norm": 0.6072263717651367,
      "learning_rate": 5.7770346273610254e-05,
      "loss": 0.9368,
      "step": 340
    },
    {
      "epoch": 1.5358931552587647,
      "grad_norm": 0.5962588787078857,
      "learning_rate": 5.648333371088706e-05,
      "loss": 0.9315,
      "step": 345
    },
    {
      "epoch": 1.5581524763494712,
      "grad_norm": 0.5635940432548523,
      "learning_rate": 5.519193644926535e-05,
      "loss": 0.9306,
      "step": 350
    },
    {
      "epoch": 1.5581524763494712,
      "eval_loss": 0.942983090877533,
      "eval_runtime": 62.5313,
      "eval_samples_per_second": 12.778,
      "eval_steps_per_second": 1.599,
      "step": 350
    },
    {
      "epoch": 1.5804117974401781,
      "grad_norm": 0.5850438475608826,
      "learning_rate": 5.389702786475862e-05,
      "loss": 0.9122,
      "step": 355
    },
    {
      "epoch": 1.6026711185308848,
      "grad_norm": 0.5826383829116821,
      "learning_rate": 5.2599483708099016e-05,
      "loss": 0.9005,
      "step": 360
    },
    {
      "epoch": 1.6249304396215916,
      "grad_norm": 0.5365060567855835,
      "learning_rate": 5.130018151246445e-05,
      "loss": 0.8918,
      "step": 365
    },
    {
      "epoch": 1.6471897607122983,
      "grad_norm": 0.5675637722015381,
      "learning_rate": 5e-05,
      "loss": 0.9157,
      "step": 370
    },
    {
      "epoch": 1.669449081803005,
      "grad_norm": 0.6204765439033508,
      "learning_rate": 4.869981848753556e-05,
      "loss": 0.8914,
      "step": 375
    },
    {
      "epoch": 1.6917084028937117,
      "grad_norm": 0.5928322672843933,
      "learning_rate": 4.740051629190099e-05,
      "loss": 0.8721,
      "step": 380
    },
    {
      "epoch": 1.7139677239844184,
      "grad_norm": 0.5092572569847107,
      "learning_rate": 4.61029721352414e-05,
      "loss": 0.8573,
      "step": 385
    },
    {
      "epoch": 1.7362270450751254,
      "grad_norm": 0.6391741633415222,
      "learning_rate": 4.480806355073467e-05,
      "loss": 0.907,
      "step": 390
    },
    {
      "epoch": 1.7584863661658319,
      "grad_norm": 0.6126671433448792,
      "learning_rate": 4.351666628911295e-05,
      "loss": 0.8023,
      "step": 395
    },
    {
      "epoch": 1.7807456872565388,
      "grad_norm": 0.6055718660354614,
      "learning_rate": 4.2229653726389765e-05,
      "loss": 0.8914,
      "step": 400
    },
    {
      "epoch": 1.7807456872565388,
      "eval_loss": 0.9382885098457336,
      "eval_runtime": 62.4923,
      "eval_samples_per_second": 12.786,
      "eval_steps_per_second": 1.6,
      "step": 400
    },
    {
      "epoch": 1.8030050083472453,
      "grad_norm": 0.5169083476066589,
      "learning_rate": 4.094789627319298e-05,
      "loss": 0.9202,
      "step": 405
    },
    {
      "epoch": 1.8252643294379522,
      "grad_norm": 0.5566220879554749,
      "learning_rate": 3.967226078610347e-05,
      "loss": 0.8758,
      "step": 410
    },
    {
      "epoch": 1.8475236505286587,
      "grad_norm": 0.568168580532074,
      "learning_rate": 3.840360998139724e-05,
      "loss": 0.8854,
      "step": 415
    },
    {
      "epoch": 1.8697829716193657,
      "grad_norm": 0.5981225371360779,
      "learning_rate": 3.714280185158771e-05,
      "loss": 0.9467,
      "step": 420
    },
    {
      "epoch": 1.8920422927100722,
      "grad_norm": 0.6130527257919312,
      "learning_rate": 3.589068908516271e-05,
      "loss": 0.8456,
      "step": 425
    },
    {
      "epoch": 1.9143016138007791,
      "grad_norm": 0.5936880111694336,
      "learning_rate": 3.464811848990859e-05,
      "loss": 0.9022,
      "step": 430
    },
    {
      "epoch": 1.9365609348914858,
      "grad_norm": 0.6016620397567749,
      "learning_rate": 3.341593042021138e-05,
      "loss": 0.9057,
      "step": 435
    },
    {
      "epoch": 1.9588202559821926,
      "grad_norm": 0.6164581179618835,
      "learning_rate": 3.219495820872265e-05,
      "loss": 0.8907,
      "step": 440
    },
    {
      "epoch": 1.9810795770728993,
      "grad_norm": 0.582241952419281,
      "learning_rate": 3.098602760277385e-05,
      "loss": 0.9133,
      "step": 445
    },
    {
      "epoch": 2.003338898163606,
      "grad_norm": 0.5405800938606262,
      "learning_rate": 2.978995620592092e-05,
      "loss": 0.8567,
      "step": 450
    },
    {
      "epoch": 2.003338898163606,
      "eval_loss": 0.9342555999755859,
      "eval_runtime": 62.5282,
      "eval_samples_per_second": 12.778,
      "eval_steps_per_second": 1.599,
      "step": 450
    }
  ],
  "logging_steps": 5,
  "max_steps": 672,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.259026931200819e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}