{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0541895278737384,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000135473819684346,
      "eval_loss": 3.3561253547668457,
      "eval_runtime": 356.7641,
      "eval_samples_per_second": 8.712,
      "eval_steps_per_second": 4.356,
      "step": 1
    },
    {
      "epoch": 0.00067736909842173,
      "grad_norm": 1.7185364961624146,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.9838,
      "step": 5
    },
    {
      "epoch": 0.00135473819684346,
      "grad_norm": 2.57662296295166,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.2297,
      "step": 10
    },
    {
      "epoch": 0.00203210729526519,
      "grad_norm": 2.434239387512207,
      "learning_rate": 5e-05,
      "loss": 2.1961,
      "step": 15
    },
    {
      "epoch": 0.00270947639368692,
      "grad_norm": 3.4190919399261475,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.0378,
      "step": 20
    },
    {
      "epoch": 0.00338684549210865,
      "grad_norm": 4.049190998077393,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.7562,
      "step": 25
    },
    {
      "epoch": 0.00406421459053038,
      "grad_norm": 3.6668996810913086,
      "learning_rate": 0.0001,
      "loss": 1.9335,
      "step": 30
    },
    {
      "epoch": 0.00474158368895211,
      "grad_norm": 5.728311061859131,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.9648,
      "step": 35
    },
    {
      "epoch": 0.00541895278737384,
      "grad_norm": 5.179512023925781,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.0792,
      "step": 40
    },
    {
      "epoch": 0.00609632188579557,
      "grad_norm": 7.390626430511475,
      "learning_rate": 9.959502176294383e-05,
      "loss": 2.3039,
      "step": 45
    },
    {
      "epoch": 0.0067736909842173,
      "grad_norm": 16.31654930114746,
      "learning_rate": 9.928079551738543e-05,
      "loss": 3.0051,
      "step": 50
    },
    {
      "epoch": 0.00745106008263903,
      "grad_norm": 2.098219871520996,
      "learning_rate": 9.887776194738432e-05,
      "loss": 1.4871,
      "step": 55
    },
    {
      "epoch": 0.00812842918106076,
      "grad_norm": 2.4226791858673096,
      "learning_rate": 9.838664734667495e-05,
      "loss": 1.392,
      "step": 60
    },
    {
      "epoch": 0.00880579827948249,
      "grad_norm": 2.593278408050537,
      "learning_rate": 9.780833673696254e-05,
      "loss": 1.6008,
      "step": 65
    },
    {
      "epoch": 0.00948316737790422,
      "grad_norm": 3.5855183601379395,
      "learning_rate": 9.714387227305422e-05,
      "loss": 1.643,
      "step": 70
    },
    {
      "epoch": 0.01016053647632595,
      "grad_norm": 3.1268999576568604,
      "learning_rate": 9.639445136482548e-05,
      "loss": 1.4779,
      "step": 75
    },
    {
      "epoch": 0.01083790557474768,
      "grad_norm": 4.07517671585083,
      "learning_rate": 9.55614245194068e-05,
      "loss": 1.7534,
      "step": 80
    },
    {
      "epoch": 0.01151527467316941,
      "grad_norm": 4.3191304206848145,
      "learning_rate": 9.464629290747842e-05,
      "loss": 1.8277,
      "step": 85
    },
    {
      "epoch": 0.01219264377159114,
      "grad_norm": 4.592923164367676,
      "learning_rate": 9.365070565805941e-05,
      "loss": 1.8091,
      "step": 90
    },
    {
      "epoch": 0.01287001287001287,
      "grad_norm": 6.058762073516846,
      "learning_rate": 9.257645688666556e-05,
      "loss": 2.0665,
      "step": 95
    },
    {
      "epoch": 0.0135473819684346,
      "grad_norm": 16.98031997680664,
      "learning_rate": 9.142548246219212e-05,
      "loss": 2.4085,
      "step": 100
    },
    {
      "epoch": 0.0135473819684346,
      "eval_loss": 1.714816689491272,
      "eval_runtime": 359.0961,
      "eval_samples_per_second": 8.655,
      "eval_steps_per_second": 4.328,
      "step": 100
    },
    {
      "epoch": 0.01422475106685633,
      "grad_norm": 2.266486883163452,
      "learning_rate": 9.019985651834703e-05,
      "loss": 1.4647,
      "step": 105
    },
    {
      "epoch": 0.01490212016527806,
      "grad_norm": 2.628476619720459,
      "learning_rate": 8.890178771592199e-05,
      "loss": 1.5253,
      "step": 110
    },
    {
      "epoch": 0.01557948926369979,
      "grad_norm": 2.8286502361297607,
      "learning_rate": 8.753361526263621e-05,
      "loss": 1.5114,
      "step": 115
    },
    {
      "epoch": 0.01625685836212152,
      "grad_norm": 2.6597888469696045,
      "learning_rate": 8.609780469772623e-05,
      "loss": 1.5533,
      "step": 120
    },
    {
      "epoch": 0.01693422746054325,
      "grad_norm": 3.285388946533203,
      "learning_rate": 8.459694344887732e-05,
      "loss": 1.6218,
      "step": 125
    },
    {
      "epoch": 0.01761159655896498,
      "grad_norm": 4.035200595855713,
      "learning_rate": 8.303373616950408e-05,
      "loss": 1.503,
      "step": 130
    },
    {
      "epoch": 0.01828896565738671,
      "grad_norm": 4.08750057220459,
      "learning_rate": 8.141099986478212e-05,
      "loss": 1.5611,
      "step": 135
    },
    {
      "epoch": 0.01896633475580844,
      "grad_norm": 4.282668113708496,
      "learning_rate": 7.973165881521434e-05,
      "loss": 1.5801,
      "step": 140
    },
    {
      "epoch": 0.01964370385423017,
      "grad_norm": 6.451112270355225,
      "learning_rate": 7.799873930687978e-05,
      "loss": 1.931,
      "step": 145
    },
    {
      "epoch": 0.0203210729526519,
      "grad_norm": 16.105079650878906,
      "learning_rate": 7.621536417786159e-05,
      "loss": 2.6923,
      "step": 150
    },
    {
      "epoch": 0.02099844205107363,
      "grad_norm": 2.3334879875183105,
      "learning_rate": 7.438474719068173e-05,
      "loss": 1.3757,
      "step": 155
    },
    {
      "epoch": 0.02167581114949536,
      "grad_norm": 2.7652111053466797,
      "learning_rate": 7.251018724088367e-05,
      "loss": 1.5446,
      "step": 160
    },
    {
      "epoch": 0.02235318024791709,
      "grad_norm": 2.606264114379883,
      "learning_rate": 7.059506241219965e-05,
      "loss": 1.5689,
      "step": 165
    },
    {
      "epoch": 0.02303054934633882,
      "grad_norm": 2.6986589431762695,
      "learning_rate": 6.864282388901544e-05,
      "loss": 1.444,
      "step": 170
    },
    {
      "epoch": 0.02370791844476055,
      "grad_norm": 3.537236452102661,
      "learning_rate": 6.665698973710288e-05,
      "loss": 1.435,
      "step": 175
    },
    {
      "epoch": 0.02438528754318228,
      "grad_norm": 3.0360429286956787,
      "learning_rate": 6.464113856382752e-05,
      "loss": 1.5123,
      "step": 180
    },
    {
      "epoch": 0.02506265664160401,
      "grad_norm": 4.179779529571533,
      "learning_rate": 6.259890306925627e-05,
      "loss": 1.6199,
      "step": 185
    },
    {
      "epoch": 0.02574002574002574,
      "grad_norm": 4.781707763671875,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 1.6176,
      "step": 190
    },
    {
      "epoch": 0.02641739483844747,
      "grad_norm": 6.485469818115234,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 2.0124,
      "step": 195
    },
    {
      "epoch": 0.0270947639368692,
      "grad_norm": 10.423331260681152,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 2.2729,
      "step": 200
    },
    {
      "epoch": 0.0270947639368692,
      "eval_loss": 1.5965768098831177,
      "eval_runtime": 359.2524,
      "eval_samples_per_second": 8.651,
      "eval_steps_per_second": 4.326,
      "step": 200
    },
    {
      "epoch": 0.02777213303529093,
      "grad_norm": 2.220208168029785,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 1.4705,
      "step": 205
    },
    {
      "epoch": 0.02844950213371266,
      "grad_norm": 2.292311906814575,
      "learning_rate": 5.212206015980742e-05,
      "loss": 1.1935,
      "step": 210
    },
    {
      "epoch": 0.02912687123213439,
      "grad_norm": 2.766972541809082,
      "learning_rate": 5e-05,
      "loss": 1.3662,
      "step": 215
    },
    {
      "epoch": 0.02980424033055612,
      "grad_norm": 2.6589162349700928,
      "learning_rate": 4.78779398401926e-05,
      "loss": 1.3131,
      "step": 220
    },
    {
      "epoch": 0.03048160942897785,
      "grad_norm": 2.739851951599121,
      "learning_rate": 4.575970377622456e-05,
      "loss": 1.4544,
      "step": 225
    },
    {
      "epoch": 0.03115897852739958,
      "grad_norm": 3.835242748260498,
      "learning_rate": 4.364910901265606e-05,
      "loss": 1.4068,
      "step": 230
    },
    {
      "epoch": 0.03183634762582131,
      "grad_norm": 4.4877753257751465,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 1.6459,
      "step": 235
    },
    {
      "epoch": 0.03251371672424304,
      "grad_norm": 5.761162757873535,
      "learning_rate": 3.94660365002137e-05,
      "loss": 1.3926,
      "step": 240
    },
    {
      "epoch": 0.03319108582266477,
      "grad_norm": 6.575611591339111,
      "learning_rate": 3.740109693074375e-05,
      "loss": 1.9598,
      "step": 245
    },
    {
      "epoch": 0.0338684549210865,
      "grad_norm": 10.984495162963867,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 2.4244,
      "step": 250
    },
    {
      "epoch": 0.03454582401950823,
      "grad_norm": 2.037391424179077,
      "learning_rate": 3.334301026289712e-05,
      "loss": 1.1748,
      "step": 255
    },
    {
      "epoch": 0.03522319311792996,
      "grad_norm": 2.154242515563965,
      "learning_rate": 3.135717611098458e-05,
      "loss": 1.4192,
      "step": 260
    },
    {
      "epoch": 0.03590056221635169,
      "grad_norm": 2.7775964736938477,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 1.4691,
      "step": 265
    },
    {
      "epoch": 0.03657793131477342,
      "grad_norm": 2.80249285697937,
      "learning_rate": 2.748981275911633e-05,
      "loss": 1.4816,
      "step": 270
    },
    {
      "epoch": 0.03725530041319515,
      "grad_norm": 3.063415765762329,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 1.3303,
      "step": 275
    },
    {
      "epoch": 0.03793266951161688,
      "grad_norm": 5.058098316192627,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 1.5817,
      "step": 280
    },
    {
      "epoch": 0.03861003861003861,
      "grad_norm": 3.6903367042541504,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 1.5363,
      "step": 285
    },
    {
      "epoch": 0.03928740770846034,
      "grad_norm": 5.226101875305176,
      "learning_rate": 2.026834118478567e-05,
      "loss": 1.8824,
      "step": 290
    },
    {
      "epoch": 0.03996477680688207,
      "grad_norm": 5.575075626373291,
      "learning_rate": 1.858900013521788e-05,
      "loss": 1.8689,
      "step": 295
    },
    {
      "epoch": 0.0406421459053038,
      "grad_norm": 8.714311599731445,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 2.0184,
      "step": 300
    },
    {
      "epoch": 0.0406421459053038,
      "eval_loss": 1.5472972393035889,
      "eval_runtime": 359.1071,
      "eval_samples_per_second": 8.655,
      "eval_steps_per_second": 4.327,
      "step": 300
    },
    {
      "epoch": 0.04131951500372553,
      "grad_norm": 2.0992095470428467,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 1.3814,
      "step": 305
    },
    {
      "epoch": 0.04199688410214726,
      "grad_norm": 2.3683693408966064,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 1.3649,
      "step": 310
    },
    {
      "epoch": 0.04267425320056899,
      "grad_norm": 2.8561010360717773,
      "learning_rate": 1.246638473736378e-05,
      "loss": 1.4736,
      "step": 315
    },
    {
      "epoch": 0.04335162229899072,
      "grad_norm": 3.205947160720825,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 1.4381,
      "step": 320
    },
    {
      "epoch": 0.04402899139741245,
      "grad_norm": 2.983264207839966,
      "learning_rate": 9.800143481652979e-06,
      "loss": 1.4195,
      "step": 325
    },
    {
      "epoch": 0.04470636049583418,
      "grad_norm": 4.009789943695068,
      "learning_rate": 8.574517537807897e-06,
      "loss": 1.6535,
      "step": 330
    },
    {
      "epoch": 0.04538372959425591,
      "grad_norm": 4.087887287139893,
      "learning_rate": 7.423543113334436e-06,
      "loss": 1.4596,
      "step": 335
    },
    {
      "epoch": 0.04606109869267764,
      "grad_norm": 5.446490287780762,
      "learning_rate": 6.349294341940593e-06,
      "loss": 1.9507,
      "step": 340
    },
    {
      "epoch": 0.04673846779109937,
      "grad_norm": 5.979248523712158,
      "learning_rate": 5.353707092521582e-06,
      "loss": 1.7338,
      "step": 345
    },
    {
      "epoch": 0.0474158368895211,
      "grad_norm": 12.100299835205078,
      "learning_rate": 4.43857548059321e-06,
      "loss": 2.5466,
      "step": 350
    },
    {
      "epoch": 0.04809320598794283,
      "grad_norm": 1.7918882369995117,
      "learning_rate": 3.605548635174533e-06,
      "loss": 1.3912,
      "step": 355
    },
    {
      "epoch": 0.04877057508636456,
      "grad_norm": 2.5956943035125732,
      "learning_rate": 2.85612772694579e-06,
      "loss": 1.198,
      "step": 360
    },
    {
      "epoch": 0.04944794418478629,
      "grad_norm": 2.834028720855713,
      "learning_rate": 2.191663263037458e-06,
      "loss": 1.4273,
      "step": 365
    },
    {
      "epoch": 0.05012531328320802,
      "grad_norm": 2.96675968170166,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 1.4331,
      "step": 370
    },
    {
      "epoch": 0.05080268238162975,
      "grad_norm": 3.480759859085083,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 1.4928,
      "step": 375
    },
    {
      "epoch": 0.05148005148005148,
      "grad_norm": 3.572807550430298,
      "learning_rate": 7.192044826145771e-07,
      "loss": 1.4602,
      "step": 380
    },
    {
      "epoch": 0.05215742057847321,
      "grad_norm": 4.694305896759033,
      "learning_rate": 4.049782370561583e-07,
      "loss": 1.563,
      "step": 385
    },
    {
      "epoch": 0.05283478967689494,
      "grad_norm": 4.593738079071045,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 1.6212,
      "step": 390
    },
    {
      "epoch": 0.05351215877531667,
      "grad_norm": 7.9974589347839355,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 1.7738,
      "step": 395
    },
    {
      "epoch": 0.0541895278737384,
      "grad_norm": 16.028162002563477,
      "learning_rate": 0.0,
      "loss": 2.1691,
      "step": 400
    },
    {
      "epoch": 0.0541895278737384,
      "eval_loss": 1.5395718812942505,
      "eval_runtime": 359.1048,
      "eval_samples_per_second": 8.655,
      "eval_steps_per_second": 4.327,
      "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": 1.642941090669527e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}