{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014284056314892022,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.5710140787230054e-05,
      "eval_loss": 3.6428475379943848,
      "eval_runtime": 937.0093,
      "eval_samples_per_second": 12.584,
      "eval_steps_per_second": 6.292,
      "step": 1
    },
    {
      "epoch": 0.00017855070393615026,
      "grad_norm": 38.791404724121094,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 11.968,
      "step": 5
    },
    {
      "epoch": 0.0003571014078723005,
      "grad_norm": 35.7210693359375,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 11.3643,
      "step": 10
    },
    {
      "epoch": 0.0005356521118084508,
      "grad_norm": 51.62553405761719,
      "learning_rate": 5e-05,
      "loss": 11.0627,
      "step": 15
    },
    {
      "epoch": 0.000714202815744601,
      "grad_norm": 33.5948486328125,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.9834,
      "step": 20
    },
    {
      "epoch": 0.0008927535196807514,
      "grad_norm": 26.09846305847168,
      "learning_rate": 8.333333333333334e-05,
      "loss": 9.9911,
      "step": 25
    },
    {
      "epoch": 0.0010713042236169016,
      "grad_norm": 25.926218032836914,
      "learning_rate": 0.0001,
      "loss": 8.5237,
      "step": 30
    },
    {
      "epoch": 0.0012498549275530518,
      "grad_norm": 28.499187469482422,
      "learning_rate": 9.995494831023409e-05,
      "loss": 8.7897,
      "step": 35
    },
    {
      "epoch": 0.001428405631489202,
      "grad_norm": 23.874563217163086,
      "learning_rate": 9.981987442712633e-05,
      "loss": 8.4972,
      "step": 40
    },
    {
      "epoch": 0.0016069563354253525,
      "grad_norm": 42.67042541503906,
      "learning_rate": 9.959502176294383e-05,
      "loss": 6.3415,
      "step": 45
    },
    {
      "epoch": 0.0017855070393615028,
      "grad_norm": 39.73894119262695,
      "learning_rate": 9.928079551738543e-05,
      "loss": 8.4446,
      "step": 50
    },
    {
      "epoch": 0.001964057743297653,
      "grad_norm": 12.979087829589844,
      "learning_rate": 9.887776194738432e-05,
      "loss": 8.0323,
      "step": 55
    },
    {
      "epoch": 0.002142608447233803,
      "grad_norm": 14.714144706726074,
      "learning_rate": 9.838664734667495e-05,
      "loss": 8.7265,
      "step": 60
    },
    {
      "epoch": 0.0023211591511699534,
      "grad_norm": 15.2055025100708,
      "learning_rate": 9.780833673696254e-05,
      "loss": 8.29,
      "step": 65
    },
    {
      "epoch": 0.0024997098551061037,
      "grad_norm": 13.198466300964355,
      "learning_rate": 9.714387227305422e-05,
      "loss": 7.7719,
      "step": 70
    },
    {
      "epoch": 0.002678260559042254,
      "grad_norm": 13.788397789001465,
      "learning_rate": 9.639445136482548e-05,
      "loss": 7.7218,
      "step": 75
    },
    {
      "epoch": 0.002856811262978404,
      "grad_norm": 13.282957077026367,
      "learning_rate": 9.55614245194068e-05,
      "loss": 7.6602,
      "step": 80
    },
    {
      "epoch": 0.0030353619669145544,
      "grad_norm": 25.1441650390625,
      "learning_rate": 9.464629290747842e-05,
      "loss": 7.1881,
      "step": 85
    },
    {
      "epoch": 0.003213912670850705,
      "grad_norm": 27.624034881591797,
      "learning_rate": 9.365070565805941e-05,
      "loss": 7.9707,
      "step": 90
    },
    {
      "epoch": 0.0033924633747868553,
      "grad_norm": 22.605091094970703,
      "learning_rate": 9.257645688666556e-05,
      "loss": 6.7703,
      "step": 95
    },
    {
      "epoch": 0.0035710140787230055,
      "grad_norm": 32.28632736206055,
      "learning_rate": 9.142548246219212e-05,
      "loss": 7.0126,
      "step": 100
    },
    {
      "epoch": 0.0035710140787230055,
      "eval_loss": 1.9531031847000122,
      "eval_runtime": 941.1342,
      "eval_samples_per_second": 12.529,
      "eval_steps_per_second": 6.265,
      "step": 100
    },
    {
      "epoch": 0.0037495647826591557,
      "grad_norm": 12.703049659729004,
      "learning_rate": 9.019985651834703e-05,
      "loss": 8.9811,
      "step": 105
    },
    {
      "epoch": 0.003928115486595306,
      "grad_norm": 11.499811172485352,
      "learning_rate": 8.890178771592199e-05,
      "loss": 8.2825,
      "step": 110
    },
    {
      "epoch": 0.004106666190531456,
      "grad_norm": 13.487603187561035,
      "learning_rate": 8.753361526263621e-05,
      "loss": 8.3682,
      "step": 115
    },
    {
      "epoch": 0.004285216894467606,
      "grad_norm": 11.988139152526855,
      "learning_rate": 8.609780469772623e-05,
      "loss": 7.4035,
      "step": 120
    },
    {
      "epoch": 0.004463767598403757,
      "grad_norm": 14.901617050170898,
      "learning_rate": 8.459694344887732e-05,
      "loss": 7.1697,
      "step": 125
    },
    {
      "epoch": 0.004642318302339907,
      "grad_norm": 18.64742088317871,
      "learning_rate": 8.303373616950408e-05,
      "loss": 7.3505,
      "step": 130
    },
    {
      "epoch": 0.004820869006276057,
      "grad_norm": 18.702434539794922,
      "learning_rate": 8.141099986478212e-05,
      "loss": 7.5959,
      "step": 135
    },
    {
      "epoch": 0.004999419710212207,
      "grad_norm": 18.720998764038086,
      "learning_rate": 7.973165881521434e-05,
      "loss": 7.286,
      "step": 140
    },
    {
      "epoch": 0.005177970414148358,
      "grad_norm": 28.588218688964844,
      "learning_rate": 7.799873930687978e-05,
      "loss": 7.4316,
      "step": 145
    },
    {
      "epoch": 0.005356521118084508,
      "grad_norm": 28.344491958618164,
      "learning_rate": 7.621536417786159e-05,
      "loss": 6.0416,
      "step": 150
    },
    {
      "epoch": 0.005535071822020658,
      "grad_norm": 10.961862564086914,
      "learning_rate": 7.438474719068173e-05,
      "loss": 8.0463,
      "step": 155
    },
    {
      "epoch": 0.005713622525956808,
      "grad_norm": 10.041893005371094,
      "learning_rate": 7.251018724088367e-05,
      "loss": 7.8733,
      "step": 160
    },
    {
      "epoch": 0.0058921732298929585,
      "grad_norm": 12.03637409210205,
      "learning_rate": 7.059506241219965e-05,
      "loss": 7.9375,
      "step": 165
    },
    {
      "epoch": 0.006070723933829109,
      "grad_norm": 10.636992454528809,
      "learning_rate": 6.864282388901544e-05,
      "loss": 6.9809,
      "step": 170
    },
    {
      "epoch": 0.006249274637765259,
      "grad_norm": 12.5416259765625,
      "learning_rate": 6.665698973710288e-05,
      "loss": 7.0759,
      "step": 175
    },
    {
      "epoch": 0.00642782534170141,
      "grad_norm": 12.943763732910156,
      "learning_rate": 6.464113856382752e-05,
      "loss": 8.2749,
      "step": 180
    },
    {
      "epoch": 0.00660637604563756,
      "grad_norm": 23.98349380493164,
      "learning_rate": 6.259890306925627e-05,
      "loss": 8.2475,
      "step": 185
    },
    {
      "epoch": 0.0067849267495737105,
      "grad_norm": 17.99372673034668,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 7.7457,
      "step": 190
    },
    {
      "epoch": 0.006963477453509861,
      "grad_norm": 138.98828125,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 6.9963,
      "step": 195
    },
    {
      "epoch": 0.007142028157446011,
      "grad_norm": 66.58040618896484,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 7.6597,
      "step": 200
    },
    {
      "epoch": 0.007142028157446011,
      "eval_loss": 1.931018352508545,
      "eval_runtime": 940.4445,
      "eval_samples_per_second": 12.538,
      "eval_steps_per_second": 6.269,
      "step": 200
    },
    {
      "epoch": 0.007320578861382161,
      "grad_norm": 10.602204322814941,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 8.5977,
      "step": 205
    },
    {
      "epoch": 0.0074991295653183115,
      "grad_norm": 9.361373901367188,
      "learning_rate": 5.212206015980742e-05,
      "loss": 8.1387,
      "step": 210
    },
    {
      "epoch": 0.007677680269254462,
      "grad_norm": 12.178308486938477,
      "learning_rate": 5e-05,
      "loss": 8.6586,
      "step": 215
    },
    {
      "epoch": 0.007856230973190612,
      "grad_norm": 11.601183891296387,
      "learning_rate": 4.78779398401926e-05,
      "loss": 7.8519,
      "step": 220
    },
    {
      "epoch": 0.008034781677126762,
      "grad_norm": 10.347457885742188,
      "learning_rate": 4.575970377622456e-05,
      "loss": 8.2135,
      "step": 225
    },
    {
      "epoch": 0.008213332381062912,
      "grad_norm": 20.473297119140625,
      "learning_rate": 4.364910901265606e-05,
      "loss": 7.7113,
      "step": 230
    },
    {
      "epoch": 0.008391883084999063,
      "grad_norm": 23.3872013092041,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 7.4215,
      "step": 235
    },
    {
      "epoch": 0.008570433788935213,
      "grad_norm": 14.155945777893066,
      "learning_rate": 3.94660365002137e-05,
      "loss": 7.2813,
      "step": 240
    },
    {
      "epoch": 0.008748984492871363,
      "grad_norm": 20.56569480895996,
      "learning_rate": 3.740109693074375e-05,
      "loss": 7.1628,
      "step": 245
    },
    {
      "epoch": 0.008927535196807513,
      "grad_norm": 39.14048767089844,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 6.7286,
      "step": 250
    },
    {
      "epoch": 0.009106085900743664,
      "grad_norm": 10.889725685119629,
      "learning_rate": 3.334301026289712e-05,
      "loss": 8.241,
      "step": 255
    },
    {
      "epoch": 0.009284636604679814,
      "grad_norm": 11.478461265563965,
      "learning_rate": 3.135717611098458e-05,
      "loss": 7.8557,
      "step": 260
    },
    {
      "epoch": 0.009463187308615964,
      "grad_norm": 10.177154541015625,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 7.7535,
      "step": 265
    },
    {
      "epoch": 0.009641738012552114,
      "grad_norm": 13.540087699890137,
      "learning_rate": 2.748981275911633e-05,
      "loss": 7.5926,
      "step": 270
    },
    {
      "epoch": 0.009820288716488264,
      "grad_norm": 14.206275939941406,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 7.7778,
      "step": 275
    },
    {
      "epoch": 0.009998839420424415,
      "grad_norm": 12.470731735229492,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 7.5519,
      "step": 280
    },
    {
      "epoch": 0.010177390124360565,
      "grad_norm": 12.996101379394531,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 7.4359,
      "step": 285
    },
    {
      "epoch": 0.010355940828296715,
      "grad_norm": 19.329702377319336,
      "learning_rate": 2.026834118478567e-05,
      "loss": 7.4877,
      "step": 290
    },
    {
      "epoch": 0.010534491532232865,
      "grad_norm": 20.063732147216797,
      "learning_rate": 1.858900013521788e-05,
      "loss": 6.4413,
      "step": 295
    },
    {
      "epoch": 0.010713042236169016,
      "grad_norm": 30.000850677490234,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 6.3928,
      "step": 300
    },
    {
      "epoch": 0.010713042236169016,
      "eval_loss": 1.8319700956344604,
      "eval_runtime": 940.4975,
      "eval_samples_per_second": 12.537,
      "eval_steps_per_second": 6.269,
      "step": 300
    },
    {
      "epoch": 0.010891592940105166,
      "grad_norm": 11.116142272949219,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 7.8649,
      "step": 305
    },
    {
      "epoch": 0.011070143644041316,
      "grad_norm": 10.031145095825195,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 7.8468,
      "step": 310
    },
    {
      "epoch": 0.011248694347977466,
      "grad_norm": 10.915895462036133,
      "learning_rate": 1.246638473736378e-05,
      "loss": 8.6783,
      "step": 315
    },
    {
      "epoch": 0.011427245051913617,
      "grad_norm": 12.510370254516602,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 7.5022,
      "step": 320
    },
    {
      "epoch": 0.011605795755849767,
      "grad_norm": 11.837886810302734,
      "learning_rate": 9.800143481652979e-06,
      "loss": 7.7391,
      "step": 325
    },
    {
      "epoch": 0.011784346459785917,
      "grad_norm": 17.98138427734375,
      "learning_rate": 8.574517537807897e-06,
      "loss": 7.7047,
      "step": 330
    },
    {
      "epoch": 0.011962897163722067,
      "grad_norm": 11.747542381286621,
      "learning_rate": 7.423543113334436e-06,
      "loss": 6.1822,
      "step": 335
    },
    {
      "epoch": 0.012141447867658217,
      "grad_norm": 20.17440414428711,
      "learning_rate": 6.349294341940593e-06,
      "loss": 7.4627,
      "step": 340
    },
    {
      "epoch": 0.012319998571594368,
      "grad_norm": 15.974550247192383,
      "learning_rate": 5.353707092521582e-06,
      "loss": 6.0153,
      "step": 345
    },
    {
      "epoch": 0.012498549275530518,
      "grad_norm": 17.395343780517578,
      "learning_rate": 4.43857548059321e-06,
      "loss": 5.7713,
      "step": 350
    },
    {
      "epoch": 0.012677099979466668,
      "grad_norm": 9.948678970336914,
      "learning_rate": 3.605548635174533e-06,
      "loss": 7.4623,
      "step": 355
    },
    {
      "epoch": 0.01285565068340282,
      "grad_norm": 12.097657203674316,
      "learning_rate": 2.85612772694579e-06,
      "loss": 8.4925,
      "step": 360
    },
    {
      "epoch": 0.01303420138733897,
      "grad_norm": 9.868169784545898,
      "learning_rate": 2.191663263037458e-06,
      "loss": 8.0455,
      "step": 365
    },
    {
      "epoch": 0.01321275209127512,
      "grad_norm": 10.206999778747559,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 7.8219,
      "step": 370
    },
    {
      "epoch": 0.01339130279521127,
      "grad_norm": 11.312124252319336,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 7.3541,
      "step": 375
    },
    {
      "epoch": 0.013569853499147421,
      "grad_norm": 17.35927963256836,
      "learning_rate": 7.192044826145771e-07,
      "loss": 6.85,
      "step": 380
    },
    {
      "epoch": 0.013748404203083571,
      "grad_norm": 13.923419952392578,
      "learning_rate": 4.049782370561583e-07,
      "loss": 7.0878,
      "step": 385
    },
    {
      "epoch": 0.013926954907019722,
      "grad_norm": 14.711668968200684,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 6.3097,
      "step": 390
    },
    {
      "epoch": 0.014105505610955872,
      "grad_norm": 13.454591751098633,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 5.6845,
      "step": 395
    },
    {
      "epoch": 0.014284056314892022,
      "grad_norm": 45.98155212402344,
      "learning_rate": 0.0,
      "loss": 7.6137,
      "step": 400
    },
    {
      "epoch": 0.014284056314892022,
      "eval_loss": 1.823633074760437,
      "eval_runtime": 941.154,
      "eval_samples_per_second": 12.528,
      "eval_steps_per_second": 6.265,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.402161598562304e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}