{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9975804500362933,
  "eval_steps": 100,
  "global_step": 516,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.019356399709654006,
      "grad_norm": 138.9804229736328,
      "learning_rate": 1.9230769230769234e-06,
      "loss": 12.7521,
      "step": 5
    },
    {
      "epoch": 0.03871279941930801,
      "grad_norm": 131.12530517578125,
      "learning_rate": 3.846153846153847e-06,
      "loss": 12.3043,
      "step": 10
    },
    {
      "epoch": 0.05806919912896201,
      "grad_norm": 132.73741149902344,
      "learning_rate": 5.769230769230769e-06,
      "loss": 11.6601,
      "step": 15
    },
    {
      "epoch": 0.07742559883861602,
      "grad_norm": 116.79450988769531,
      "learning_rate": 7.692307692307694e-06,
      "loss": 9.3473,
      "step": 20
    },
    {
      "epoch": 0.09678199854827002,
      "grad_norm": 157.67100524902344,
      "learning_rate": 9.615384615384616e-06,
      "loss": 5.6238,
      "step": 25
    },
    {
      "epoch": 0.11613839825792402,
      "grad_norm": 180.53184509277344,
      "learning_rate": 9.918367346938776e-06,
      "loss": 1.7325,
      "step": 30
    },
    {
      "epoch": 0.13549479796757802,
      "grad_norm": 9.246004104614258,
      "learning_rate": 9.816326530612245e-06,
      "loss": 0.9398,
      "step": 35
    },
    {
      "epoch": 0.15485119767723204,
      "grad_norm": 5.716113567352295,
      "learning_rate": 9.714285714285715e-06,
      "loss": 0.6635,
      "step": 40
    },
    {
      "epoch": 0.17420759738688604,
      "grad_norm": 7.727076053619385,
      "learning_rate": 9.612244897959185e-06,
      "loss": 0.6727,
      "step": 45
    },
    {
      "epoch": 0.19356399709654004,
      "grad_norm": 3.486781597137451,
      "learning_rate": 9.510204081632653e-06,
      "loss": 0.7927,
      "step": 50
    },
    {
      "epoch": 0.21292039680619404,
      "grad_norm": 6.413691520690918,
      "learning_rate": 9.408163265306123e-06,
      "loss": 0.6644,
      "step": 55
    },
    {
      "epoch": 0.23227679651584804,
      "grad_norm": 8.30860424041748,
      "learning_rate": 9.306122448979593e-06,
      "loss": 0.5873,
      "step": 60
    },
    {
      "epoch": 0.25163319622550206,
      "grad_norm": 12.624951362609863,
      "learning_rate": 9.204081632653062e-06,
      "loss": 0.6874,
      "step": 65
    },
    {
      "epoch": 0.27098959593515604,
      "grad_norm": 5.089308261871338,
      "learning_rate": 9.102040816326532e-06,
      "loss": 0.6638,
      "step": 70
    },
    {
      "epoch": 0.29034599564481006,
      "grad_norm": 1.7342802286148071,
      "learning_rate": 9e-06,
      "loss": 0.5861,
      "step": 75
    },
    {
      "epoch": 0.3097023953544641,
      "grad_norm": 22.078353881835938,
      "learning_rate": 8.89795918367347e-06,
      "loss": 0.6546,
      "step": 80
    },
    {
      "epoch": 0.32905879506411806,
      "grad_norm": 7.25566291809082,
      "learning_rate": 8.79591836734694e-06,
      "loss": 0.458,
      "step": 85
    },
    {
      "epoch": 0.3484151947737721,
      "grad_norm": 6.364375591278076,
      "learning_rate": 8.69387755102041e-06,
      "loss": 0.6717,
      "step": 90
    },
    {
      "epoch": 0.36777159448342606,
      "grad_norm": 0.05223466455936432,
      "learning_rate": 8.591836734693878e-06,
      "loss": 0.5166,
      "step": 95
    },
    {
      "epoch": 0.3871279941930801,
      "grad_norm": 1.938957691192627,
      "learning_rate": 8.489795918367347e-06,
      "loss": 0.5055,
      "step": 100
    },
    {
      "epoch": 0.3871279941930801,
      "eval_loss": 0.6117367148399353,
      "eval_mse": 0.611736709770115,
      "eval_runtime": 12.0657,
      "eval_samples_per_second": 36.053,
      "eval_steps_per_second": 18.068,
      "step": 100
    },
    {
      "epoch": 0.4064843939027341,
      "grad_norm": 10.325569152832031,
      "learning_rate": 8.387755102040817e-06,
      "loss": 0.5831,
      "step": 105
    },
    {
      "epoch": 0.4258407936123881,
      "grad_norm": 7.4597249031066895,
      "learning_rate": 8.285714285714287e-06,
      "loss": 0.6331,
      "step": 110
    },
    {
      "epoch": 0.4451971933220421,
      "grad_norm": 9.280782699584961,
      "learning_rate": 8.183673469387757e-06,
      "loss": 0.7987,
      "step": 115
    },
    {
      "epoch": 0.4645535930316961,
      "grad_norm": 3.89896559715271,
      "learning_rate": 8.081632653061225e-06,
      "loss": 0.4998,
      "step": 120
    },
    {
      "epoch": 0.4839099927413501,
      "grad_norm": 6.190971851348877,
      "learning_rate": 7.979591836734695e-06,
      "loss": 0.6448,
      "step": 125
    },
    {
      "epoch": 0.5032663924510041,
      "grad_norm": 11.814096450805664,
      "learning_rate": 7.877551020408164e-06,
      "loss": 0.7042,
      "step": 130
    },
    {
      "epoch": 0.5226227921606581,
      "grad_norm": 6.1357340812683105,
      "learning_rate": 7.775510204081632e-06,
      "loss": 0.601,
      "step": 135
    },
    {
      "epoch": 0.5419791918703121,
      "grad_norm": 2.2827892303466797,
      "learning_rate": 7.673469387755102e-06,
      "loss": 0.5517,
      "step": 140
    },
    {
      "epoch": 0.5613355915799662,
      "grad_norm": 12.637822151184082,
      "learning_rate": 7.571428571428572e-06,
      "loss": 0.5195,
      "step": 145
    },
    {
      "epoch": 0.5806919912896201,
      "grad_norm": 11.605605125427246,
      "learning_rate": 7.469387755102041e-06,
      "loss": 0.5762,
      "step": 150
    },
    {
      "epoch": 0.6000483909992741,
      "grad_norm": 10.857634544372559,
      "learning_rate": 7.367346938775511e-06,
      "loss": 0.7404,
      "step": 155
    },
    {
      "epoch": 0.6194047907089282,
      "grad_norm": 3.4936256408691406,
      "learning_rate": 7.2653061224489805e-06,
      "loss": 0.5734,
      "step": 160
    },
    {
      "epoch": 0.6387611904185821,
      "grad_norm": 5.934628009796143,
      "learning_rate": 7.16326530612245e-06,
      "loss": 0.4472,
      "step": 165
    },
    {
      "epoch": 0.6581175901282361,
      "grad_norm": 6.569794178009033,
      "learning_rate": 7.061224489795919e-06,
      "loss": 0.5565,
      "step": 170
    },
    {
      "epoch": 0.6774739898378902,
      "grad_norm": 2.004188060760498,
      "learning_rate": 6.959183673469388e-06,
      "loss": 0.747,
      "step": 175
    },
    {
      "epoch": 0.6968303895475442,
      "grad_norm": 15.279809951782227,
      "learning_rate": 6.857142857142858e-06,
      "loss": 0.7158,
      "step": 180
    },
    {
      "epoch": 0.7161867892571981,
      "grad_norm": 10.226279258728027,
      "learning_rate": 6.755102040816327e-06,
      "loss": 0.6511,
      "step": 185
    },
    {
      "epoch": 0.7355431889668521,
      "grad_norm": 18.870132446289062,
      "learning_rate": 6.653061224489797e-06,
      "loss": 0.6767,
      "step": 190
    },
    {
      "epoch": 0.7548995886765062,
      "grad_norm": 21.00126075744629,
      "learning_rate": 6.5510204081632656e-06,
      "loss": 0.6051,
      "step": 195
    },
    {
      "epoch": 0.7742559883861602,
      "grad_norm": 43.422752380371094,
      "learning_rate": 6.4489795918367345e-06,
      "loss": 0.5288,
      "step": 200
    },
    {
      "epoch": 0.7742559883861602,
      "eval_loss": 0.6112865805625916,
      "eval_mse": 0.6112865930316091,
      "eval_runtime": 12.2861,
      "eval_samples_per_second": 35.406,
      "eval_steps_per_second": 17.744,
      "step": 200
    },
    {
      "epoch": 0.7936123880958141,
      "grad_norm": 3.7341082096099854,
      "learning_rate": 6.346938775510204e-06,
      "loss": 0.5249,
      "step": 205
    },
    {
      "epoch": 0.8129687878054682,
      "grad_norm": 31.00126075744629,
      "learning_rate": 6.244897959183675e-06,
      "loss": 0.6535,
      "step": 210
    },
    {
      "epoch": 0.8323251875151222,
      "grad_norm": 1.7273753881454468,
      "learning_rate": 6.142857142857144e-06,
      "loss": 0.5454,
      "step": 215
    },
    {
      "epoch": 0.8516815872247762,
      "grad_norm": 17.259763717651367,
      "learning_rate": 6.040816326530613e-06,
      "loss": 0.7058,
      "step": 220
    },
    {
      "epoch": 0.8710379869344302,
      "grad_norm": 6.889254570007324,
      "learning_rate": 5.9387755102040825e-06,
      "loss": 0.5654,
      "step": 225
    },
    {
      "epoch": 0.8903943866440842,
      "grad_norm": 19.396793365478516,
      "learning_rate": 5.8367346938775515e-06,
      "loss": 0.5629,
      "step": 230
    },
    {
      "epoch": 0.9097507863537382,
      "grad_norm": 17.010122299194336,
      "learning_rate": 5.73469387755102e-06,
      "loss": 0.7001,
      "step": 235
    },
    {
      "epoch": 0.9291071860633922,
      "grad_norm": 3.0937254428863525,
      "learning_rate": 5.63265306122449e-06,
      "loss": 0.6205,
      "step": 240
    },
    {
      "epoch": 0.9484635857730462,
      "grad_norm": 18.858959197998047,
      "learning_rate": 5.530612244897959e-06,
      "loss": 0.5545,
      "step": 245
    },
    {
      "epoch": 0.9678199854827002,
      "grad_norm": 0.07618504762649536,
      "learning_rate": 5.428571428571429e-06,
      "loss": 0.5103,
      "step": 250
    },
    {
      "epoch": 0.9871763851923542,
      "grad_norm": 9.257562637329102,
      "learning_rate": 5.326530612244898e-06,
      "loss": 0.6523,
      "step": 255
    },
    {
      "epoch": 1.0065327849020083,
      "grad_norm": 13.298598289489746,
      "learning_rate": 5.2244897959183684e-06,
      "loss": 0.5814,
      "step": 260
    },
    {
      "epoch": 1.0258891846116622,
      "grad_norm": 10.256103515625,
      "learning_rate": 5.122448979591837e-06,
      "loss": 0.5173,
      "step": 265
    },
    {
      "epoch": 1.0452455843213162,
      "grad_norm": 16.131662368774414,
      "learning_rate": 5.020408163265307e-06,
      "loss": 0.6716,
      "step": 270
    },
    {
      "epoch": 1.0646019840309702,
      "grad_norm": 1.7425230741500854,
      "learning_rate": 4.918367346938776e-06,
      "loss": 0.5767,
      "step": 275
    },
    {
      "epoch": 1.0839583837406241,
      "grad_norm": 4.797603130340576,
      "learning_rate": 4.816326530612245e-06,
      "loss": 0.5514,
      "step": 280
    },
    {
      "epoch": 1.1033147834502783,
      "grad_norm": 3.243138074874878,
      "learning_rate": 4.714285714285715e-06,
      "loss": 0.4869,
      "step": 285
    },
    {
      "epoch": 1.1226711831599323,
      "grad_norm": 1.337968349456787,
      "learning_rate": 4.612244897959184e-06,
      "loss": 0.6745,
      "step": 290
    },
    {
      "epoch": 1.1420275828695863,
      "grad_norm": 1.4539625644683838,
      "learning_rate": 4.5102040816326535e-06,
      "loss": 0.6467,
      "step": 295
    },
    {
      "epoch": 1.1613839825792402,
      "grad_norm": 4.222984313964844,
      "learning_rate": 4.408163265306123e-06,
      "loss": 0.5981,
      "step": 300
    },
    {
      "epoch": 1.1613839825792402,
      "eval_loss": 0.611698567867279,
      "eval_mse": 0.6116985452586207,
      "eval_runtime": 12.2661,
      "eval_samples_per_second": 35.463,
      "eval_steps_per_second": 17.772,
      "step": 300
    },
    {
      "epoch": 1.1807403822888942,
      "grad_norm": 10.752211570739746,
      "learning_rate": 4.306122448979592e-06,
      "loss": 0.7279,
      "step": 305
    },
    {
      "epoch": 1.2000967819985482,
      "grad_norm": 2.4483253955841064,
      "learning_rate": 4.204081632653061e-06,
      "loss": 0.4696,
      "step": 310
    },
    {
      "epoch": 1.2194531817082024,
      "grad_norm": 18.74379539489746,
      "learning_rate": 4.102040816326531e-06,
      "loss": 0.5732,
      "step": 315
    },
    {
      "epoch": 1.2388095814178564,
      "grad_norm": 1.103325605392456,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6505,
      "step": 320
    },
    {
      "epoch": 1.2581659811275103,
      "grad_norm": 10.703681945800781,
      "learning_rate": 3.89795918367347e-06,
      "loss": 0.6433,
      "step": 325
    },
    {
      "epoch": 1.2775223808371643,
      "grad_norm": 9.631330490112305,
      "learning_rate": 3.795918367346939e-06,
      "loss": 0.8211,
      "step": 330
    },
    {
      "epoch": 1.2968787805468183,
      "grad_norm": 16.350555419921875,
      "learning_rate": 3.6938775510204083e-06,
      "loss": 0.6267,
      "step": 335
    },
    {
      "epoch": 1.3162351802564722,
      "grad_norm": 7.614326000213623,
      "learning_rate": 3.5918367346938777e-06,
      "loss": 0.5665,
      "step": 340
    },
    {
      "epoch": 1.3355915799661262,
      "grad_norm": 7.319636821746826,
      "learning_rate": 3.4897959183673474e-06,
      "loss": 0.5397,
      "step": 345
    },
    {
      "epoch": 1.3549479796757802,
      "grad_norm": 7.513986110687256,
      "learning_rate": 3.3877551020408168e-06,
      "loss": 0.5152,
      "step": 350
    },
    {
      "epoch": 1.3743043793854344,
      "grad_norm": 0.7303381562232971,
      "learning_rate": 3.285714285714286e-06,
      "loss": 0.4511,
      "step": 355
    },
    {
      "epoch": 1.3936607790950883,
      "grad_norm": 6.5720930099487305,
      "learning_rate": 3.183673469387755e-06,
      "loss": 0.5241,
      "step": 360
    },
    {
      "epoch": 1.4130171788047423,
      "grad_norm": 4.096576690673828,
      "learning_rate": 3.0816326530612244e-06,
      "loss": 0.4544,
      "step": 365
    },
    {
      "epoch": 1.4323735785143963,
      "grad_norm": 8.602828979492188,
      "learning_rate": 2.979591836734694e-06,
      "loss": 0.6898,
      "step": 370
    },
    {
      "epoch": 1.4517299782240503,
      "grad_norm": 9.944686889648438,
      "learning_rate": 2.8775510204081636e-06,
      "loss": 0.6386,
      "step": 375
    },
    {
      "epoch": 1.4710863779337044,
      "grad_norm": 5.180520534515381,
      "learning_rate": 2.775510204081633e-06,
      "loss": 0.5729,
      "step": 380
    },
    {
      "epoch": 1.4904427776433584,
      "grad_norm": 7.07384729385376,
      "learning_rate": 2.6734693877551023e-06,
      "loss": 0.6033,
      "step": 385
    },
    {
      "epoch": 1.5097991773530124,
      "grad_norm": 3.9874448776245117,
      "learning_rate": 2.571428571428571e-06,
      "loss": 0.603,
      "step": 390
    },
    {
      "epoch": 1.5291555770626664,
      "grad_norm": 1.2320411205291748,
      "learning_rate": 2.469387755102041e-06,
      "loss": 0.6542,
      "step": 395
    },
    {
      "epoch": 1.5485119767723203,
      "grad_norm": 1.8463209867477417,
      "learning_rate": 2.3673469387755103e-06,
      "loss": 0.6077,
      "step": 400
    },
    {
      "epoch": 1.5485119767723203,
      "eval_loss": 0.6124882102012634,
      "eval_mse": 0.612488213900862,
      "eval_runtime": 12.2194,
      "eval_samples_per_second": 35.599,
      "eval_steps_per_second": 17.841,
      "step": 400
    },
    {
      "epoch": 1.5678683764819743,
      "grad_norm": 7.903787612915039,
      "learning_rate": 2.2653061224489797e-06,
      "loss": 0.5056,
      "step": 405
    },
    {
      "epoch": 1.5872247761916283,
      "grad_norm": 1.824765682220459,
      "learning_rate": 2.1632653061224495e-06,
      "loss": 0.5517,
      "step": 410
    },
    {
      "epoch": 1.6065811759012822,
      "grad_norm": 1.7653071880340576,
      "learning_rate": 2.0612244897959184e-06,
      "loss": 0.5645,
      "step": 415
    },
    {
      "epoch": 1.6259375756109362,
      "grad_norm": 8.513703346252441,
      "learning_rate": 1.9591836734693877e-06,
      "loss": 0.5903,
      "step": 420
    },
    {
      "epoch": 1.6452939753205904,
      "grad_norm": 0.14550276100635529,
      "learning_rate": 1.8571428571428573e-06,
      "loss": 0.5852,
      "step": 425
    },
    {
      "epoch": 1.6646503750302444,
      "grad_norm": 1.8322155475616455,
      "learning_rate": 1.7551020408163267e-06,
      "loss": 0.5202,
      "step": 430
    },
    {
      "epoch": 1.6840067747398983,
      "grad_norm": 8.522052764892578,
      "learning_rate": 1.6530612244897962e-06,
      "loss": 0.7683,
      "step": 435
    },
    {
      "epoch": 1.7033631744495525,
      "grad_norm": 9.164407730102539,
      "learning_rate": 1.5510204081632654e-06,
      "loss": 0.663,
      "step": 440
    },
    {
      "epoch": 1.7227195741592065,
      "grad_norm": 1.7836110591888428,
      "learning_rate": 1.4489795918367347e-06,
      "loss": 0.6314,
      "step": 445
    },
    {
      "epoch": 1.7420759738688605,
      "grad_norm": 1.4566117525100708,
      "learning_rate": 1.3469387755102043e-06,
      "loss": 0.6647,
      "step": 450
    },
    {
      "epoch": 1.7614323735785145,
      "grad_norm": 1.814237117767334,
      "learning_rate": 1.2448979591836734e-06,
      "loss": 0.5117,
      "step": 455
    },
    {
      "epoch": 1.7807887732881684,
      "grad_norm": 6.711891174316406,
      "learning_rate": 1.142857142857143e-06,
      "loss": 0.557,
      "step": 460
    },
    {
      "epoch": 1.8001451729978224,
      "grad_norm": 0.6150693297386169,
      "learning_rate": 1.0408163265306123e-06,
      "loss": 0.477,
      "step": 465
    },
    {
      "epoch": 1.8195015727074764,
      "grad_norm": 3.6564579010009766,
      "learning_rate": 9.387755102040817e-07,
      "loss": 0.5492,
      "step": 470
    },
    {
      "epoch": 1.8388579724171303,
      "grad_norm": 2.0056779384613037,
      "learning_rate": 8.367346938775512e-07,
      "loss": 0.6527,
      "step": 475
    },
    {
      "epoch": 1.8582143721267843,
      "grad_norm": 4.872880935668945,
      "learning_rate": 7.346938775510205e-07,
      "loss": 0.616,
      "step": 480
    },
    {
      "epoch": 1.8775707718364383,
      "grad_norm": 6.090467929840088,
      "learning_rate": 6.326530612244898e-07,
      "loss": 0.6453,
      "step": 485
    },
    {
      "epoch": 1.8969271715460925,
      "grad_norm": 6.719366073608398,
      "learning_rate": 5.306122448979592e-07,
      "loss": 0.5115,
      "step": 490
    },
    {
      "epoch": 1.9162835712557464,
      "grad_norm": 8.526107788085938,
      "learning_rate": 4.285714285714286e-07,
      "loss": 0.5886,
      "step": 495
    },
    {
      "epoch": 1.9356399709654004,
      "grad_norm": 6.093981742858887,
      "learning_rate": 3.2653061224489803e-07,
      "loss": 0.6943,
      "step": 500
    },
    {
      "epoch": 1.9356399709654004,
      "eval_loss": 0.611698567867279,
      "eval_mse": 0.6116985452586207,
      "eval_runtime": 12.5863,
      "eval_samples_per_second": 34.561,
      "eval_steps_per_second": 17.32,
      "step": 500
    },
    {
      "epoch": 1.9549963706750544,
      "grad_norm": 4.887479305267334,
      "learning_rate": 2.2448979591836735e-07,
      "loss": 0.7463,
      "step": 505
    },
    {
      "epoch": 1.9743527703847086,
      "grad_norm": 3.6627864837646484,
      "learning_rate": 1.2244897959183673e-07,
      "loss": 0.6146,
      "step": 510
    },
    {
      "epoch": 1.9937091700943625,
      "grad_norm": 2.4411888122558594,
      "learning_rate": 2.0408163265306127e-08,
      "loss": 0.71,
      "step": 515
    },
    {
      "epoch": 1.9975804500362933,
      "step": 516,
      "total_flos": 1.737675031707648e+16,
      "train_loss": 1.0921991518301557,
      "train_runtime": 835.9482,
      "train_samples_per_second": 19.774,
      "train_steps_per_second": 0.617
    }
  ],
  "logging_steps": 5,
  "max_steps": 516,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.737675031707648e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}