{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.34371643394199786,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 1.394996166229248,
      "eval_runtime": 40.2608,
      "eval_samples_per_second": 12.171,
      "eval_steps_per_second": 6.085,
      "step": 1
    },
    {
      "epoch": 0.004296455424274973,
      "grad_norm": 0.23794934153556824,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.1992,
      "step": 5
    },
    {
      "epoch": 0.008592910848549946,
      "grad_norm": 0.2756040394306183,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.231,
      "step": 10
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 0.356270432472229,
      "learning_rate": 5e-05,
      "loss": 1.2623,
      "step": 15
    },
    {
      "epoch": 0.017185821697099892,
      "grad_norm": 0.33776453137397766,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.2795,
      "step": 20
    },
    {
      "epoch": 0.021482277121374866,
      "grad_norm": 0.3778141140937805,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.2876,
      "step": 25
    },
    {
      "epoch": 0.02577873254564984,
      "grad_norm": 0.3612962067127228,
      "learning_rate": 0.0001,
      "loss": 1.3623,
      "step": 30
    },
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 0.4191547930240631,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.3004,
      "step": 35
    },
    {
      "epoch": 0.034371643394199784,
      "grad_norm": 0.46754342317581177,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.2625,
      "step": 40
    },
    {
      "epoch": 0.03866809881847476,
      "grad_norm": 0.5397198796272278,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.2879,
      "step": 45
    },
    {
      "epoch": 0.04296455424274973,
      "grad_norm": 0.7677071690559387,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.2999,
      "step": 50
    },
    {
      "epoch": 0.047261009667024706,
      "grad_norm": 0.4138832092285156,
      "learning_rate": 9.887776194738432e-05,
      "loss": 1.1668,
      "step": 55
    },
    {
      "epoch": 0.05155746509129968,
      "grad_norm": 0.2792375683784485,
      "learning_rate": 9.838664734667495e-05,
      "loss": 1.0441,
      "step": 60
    },
    {
      "epoch": 0.055853920515574654,
      "grad_norm": 0.24745427072048187,
      "learning_rate": 9.780833673696254e-05,
      "loss": 1.0572,
      "step": 65
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 0.2879851758480072,
      "learning_rate": 9.714387227305422e-05,
      "loss": 1.1503,
      "step": 70
    },
    {
      "epoch": 0.0644468313641246,
      "grad_norm": 0.28393059968948364,
      "learning_rate": 9.639445136482548e-05,
      "loss": 1.1686,
      "step": 75
    },
    {
      "epoch": 0.06874328678839957,
      "grad_norm": 0.31194278597831726,
      "learning_rate": 9.55614245194068e-05,
      "loss": 1.2062,
      "step": 80
    },
    {
      "epoch": 0.07303974221267455,
      "grad_norm": 0.3383505940437317,
      "learning_rate": 9.464629290747842e-05,
      "loss": 1.2357,
      "step": 85
    },
    {
      "epoch": 0.07733619763694952,
      "grad_norm": 0.4557180404663086,
      "learning_rate": 9.365070565805941e-05,
      "loss": 1.2134,
      "step": 90
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 0.49110710620880127,
      "learning_rate": 9.257645688666556e-05,
      "loss": 1.1879,
      "step": 95
    },
    {
      "epoch": 0.08592910848549946,
      "grad_norm": 0.7936285734176636,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.3171,
      "step": 100
    },
    {
      "epoch": 0.08592910848549946,
      "eval_loss": 1.165156602859497,
      "eval_runtime": 40.9421,
      "eval_samples_per_second": 11.968,
      "eval_steps_per_second": 5.984,
      "step": 100
    },
    {
      "epoch": 0.09022556390977443,
      "grad_norm": 0.262840211391449,
      "learning_rate": 9.019985651834703e-05,
      "loss": 1.0287,
      "step": 105
    },
    {
      "epoch": 0.09452201933404941,
      "grad_norm": 0.2776307165622711,
      "learning_rate": 8.890178771592199e-05,
      "loss": 1.0562,
      "step": 110
    },
    {
      "epoch": 0.09881847475832438,
      "grad_norm": 0.24230684340000153,
      "learning_rate": 8.753361526263621e-05,
      "loss": 1.0492,
      "step": 115
    },
    {
      "epoch": 0.10311493018259936,
      "grad_norm": 0.26593610644340515,
      "learning_rate": 8.609780469772623e-05,
      "loss": 1.1214,
      "step": 120
    },
    {
      "epoch": 0.10741138560687433,
      "grad_norm": 0.2664184868335724,
      "learning_rate": 8.459694344887732e-05,
      "loss": 1.0605,
      "step": 125
    },
    {
      "epoch": 0.11170784103114931,
      "grad_norm": 0.3584355115890503,
      "learning_rate": 8.303373616950408e-05,
      "loss": 1.1607,
      "step": 130
    },
    {
      "epoch": 0.11600429645542427,
      "grad_norm": 0.3514535129070282,
      "learning_rate": 8.141099986478212e-05,
      "loss": 1.1722,
      "step": 135
    },
    {
      "epoch": 0.12030075187969924,
      "grad_norm": 0.37866151332855225,
      "learning_rate": 7.973165881521434e-05,
      "loss": 1.1463,
      "step": 140
    },
    {
      "epoch": 0.12459720730397422,
      "grad_norm": 0.5098997354507446,
      "learning_rate": 7.799873930687978e-05,
      "loss": 1.1624,
      "step": 145
    },
    {
      "epoch": 0.1288936627282492,
      "grad_norm": 0.7254776954650879,
      "learning_rate": 7.621536417786159e-05,
      "loss": 1.2937,
      "step": 150
    },
    {
      "epoch": 0.13319011815252416,
      "grad_norm": 0.25712594389915466,
      "learning_rate": 7.438474719068173e-05,
      "loss": 1.0363,
      "step": 155
    },
    {
      "epoch": 0.13748657357679914,
      "grad_norm": 0.2931567430496216,
      "learning_rate": 7.251018724088367e-05,
      "loss": 1.0808,
      "step": 160
    },
    {
      "epoch": 0.14178302900107412,
      "grad_norm": 0.26306307315826416,
      "learning_rate": 7.059506241219965e-05,
      "loss": 1.0691,
      "step": 165
    },
    {
      "epoch": 0.1460794844253491,
      "grad_norm": 0.2805885970592499,
      "learning_rate": 6.864282388901544e-05,
      "loss": 1.1161,
      "step": 170
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 0.311975359916687,
      "learning_rate": 6.665698973710288e-05,
      "loss": 1.1258,
      "step": 175
    },
    {
      "epoch": 0.15467239527389903,
      "grad_norm": 0.36309123039245605,
      "learning_rate": 6.464113856382752e-05,
      "loss": 1.1442,
      "step": 180
    },
    {
      "epoch": 0.158968850698174,
      "grad_norm": 0.3787703514099121,
      "learning_rate": 6.259890306925627e-05,
      "loss": 1.1411,
      "step": 185
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 0.3751693069934845,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 1.169,
      "step": 190
    },
    {
      "epoch": 0.16756176154672395,
      "grad_norm": 0.4680764675140381,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 1.1813,
      "step": 195
    },
    {
      "epoch": 0.17185821697099893,
      "grad_norm": 0.7744162082672119,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 1.1581,
      "step": 200
    },
    {
      "epoch": 0.17185821697099893,
      "eval_loss": 1.1233917474746704,
      "eval_runtime": 40.9726,
      "eval_samples_per_second": 11.959,
      "eval_steps_per_second": 5.98,
      "step": 200
    },
    {
      "epoch": 0.1761546723952739,
      "grad_norm": 0.27927258610725403,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.9917,
      "step": 205
    },
    {
      "epoch": 0.18045112781954886,
      "grad_norm": 0.24128082394599915,
      "learning_rate": 5.212206015980742e-05,
      "loss": 1.0633,
      "step": 210
    },
    {
      "epoch": 0.18474758324382384,
      "grad_norm": 0.24835774302482605,
      "learning_rate": 5e-05,
      "loss": 1.0474,
      "step": 215
    },
    {
      "epoch": 0.18904403866809882,
      "grad_norm": 0.2867087423801422,
      "learning_rate": 4.78779398401926e-05,
      "loss": 1.0731,
      "step": 220
    },
    {
      "epoch": 0.1933404940923738,
      "grad_norm": 0.32365140318870544,
      "learning_rate": 4.575970377622456e-05,
      "loss": 1.1351,
      "step": 225
    },
    {
      "epoch": 0.19763694951664876,
      "grad_norm": 0.3021872341632843,
      "learning_rate": 4.364910901265606e-05,
      "loss": 1.1477,
      "step": 230
    },
    {
      "epoch": 0.20193340494092374,
      "grad_norm": 0.32880011200904846,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 1.0871,
      "step": 235
    },
    {
      "epoch": 0.20622986036519872,
      "grad_norm": 0.37060269713401794,
      "learning_rate": 3.94660365002137e-05,
      "loss": 1.1313,
      "step": 240
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.4778624176979065,
      "learning_rate": 3.740109693074375e-05,
      "loss": 1.1321,
      "step": 245
    },
    {
      "epoch": 0.21482277121374865,
      "grad_norm": 0.7110616564750671,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 1.1995,
      "step": 250
    },
    {
      "epoch": 0.21911922663802363,
      "grad_norm": 0.25710639357566833,
      "learning_rate": 3.334301026289712e-05,
      "loss": 1.032,
      "step": 255
    },
    {
      "epoch": 0.22341568206229862,
      "grad_norm": 0.2509933412075043,
      "learning_rate": 3.135717611098458e-05,
      "loss": 1.0843,
      "step": 260
    },
    {
      "epoch": 0.22771213748657357,
      "grad_norm": 0.3050920069217682,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 1.0497,
      "step": 265
    },
    {
      "epoch": 0.23200859291084855,
      "grad_norm": 0.3290669322013855,
      "learning_rate": 2.748981275911633e-05,
      "loss": 1.1028,
      "step": 270
    },
    {
      "epoch": 0.23630504833512353,
      "grad_norm": 0.3354766368865967,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 1.1204,
      "step": 275
    },
    {
      "epoch": 0.24060150375939848,
      "grad_norm": 0.3510461449623108,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 1.1427,
      "step": 280
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 0.34565868973731995,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 1.1692,
      "step": 285
    },
    {
      "epoch": 0.24919441460794844,
      "grad_norm": 0.45904621481895447,
      "learning_rate": 2.026834118478567e-05,
      "loss": 1.1149,
      "step": 290
    },
    {
      "epoch": 0.2534908700322234,
      "grad_norm": 0.5580776333808899,
      "learning_rate": 1.858900013521788e-05,
      "loss": 1.1701,
      "step": 295
    },
    {
      "epoch": 0.2577873254564984,
      "grad_norm": 0.6597335338592529,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 1.2856,
      "step": 300
    },
    {
      "epoch": 0.2577873254564984,
      "eval_loss": 1.1131397485733032,
      "eval_runtime": 40.9997,
      "eval_samples_per_second": 11.951,
      "eval_steps_per_second": 5.976,
      "step": 300
    },
    {
      "epoch": 0.2620837808807734,
      "grad_norm": 0.22676490247249603,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.9788,
      "step": 305
    },
    {
      "epoch": 0.2663802363050483,
      "grad_norm": 0.23795971274375916,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 1.0146,
      "step": 310
    },
    {
      "epoch": 0.2706766917293233,
      "grad_norm": 0.25049060583114624,
      "learning_rate": 1.246638473736378e-05,
      "loss": 1.0592,
      "step": 315
    },
    {
      "epoch": 0.2749731471535983,
      "grad_norm": 0.26915815472602844,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 1.1286,
      "step": 320
    },
    {
      "epoch": 0.27926960257787325,
      "grad_norm": 0.30342385172843933,
      "learning_rate": 9.800143481652979e-06,
      "loss": 1.0856,
      "step": 325
    },
    {
      "epoch": 0.28356605800214824,
      "grad_norm": 0.33587148785591125,
      "learning_rate": 8.574517537807897e-06,
      "loss": 1.127,
      "step": 330
    },
    {
      "epoch": 0.2878625134264232,
      "grad_norm": 0.34324607253074646,
      "learning_rate": 7.423543113334436e-06,
      "loss": 1.1454,
      "step": 335
    },
    {
      "epoch": 0.2921589688506982,
      "grad_norm": 0.3819216191768646,
      "learning_rate": 6.349294341940593e-06,
      "loss": 1.1508,
      "step": 340
    },
    {
      "epoch": 0.2964554242749731,
      "grad_norm": 0.48347216844558716,
      "learning_rate": 5.353707092521582e-06,
      "loss": 1.1406,
      "step": 345
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.7229000329971313,
      "learning_rate": 4.43857548059321e-06,
      "loss": 1.1203,
      "step": 350
    },
    {
      "epoch": 0.3050483351235231,
      "grad_norm": 0.24176344275474548,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.994,
      "step": 355
    },
    {
      "epoch": 0.30934479054779807,
      "grad_norm": 0.26498982310295105,
      "learning_rate": 2.85612772694579e-06,
      "loss": 1.0621,
      "step": 360
    },
    {
      "epoch": 0.31364124597207305,
      "grad_norm": 0.2522437572479248,
      "learning_rate": 2.191663263037458e-06,
      "loss": 1.0247,
      "step": 365
    },
    {
      "epoch": 0.317937701396348,
      "grad_norm": 0.2975510060787201,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 1.03,
      "step": 370
    },
    {
      "epoch": 0.322234156820623,
      "grad_norm": 0.287592351436615,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 1.0489,
      "step": 375
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.3139653205871582,
      "learning_rate": 7.192044826145771e-07,
      "loss": 1.0667,
      "step": 380
    },
    {
      "epoch": 0.3308270676691729,
      "grad_norm": 0.39107799530029297,
      "learning_rate": 4.049782370561583e-07,
      "loss": 1.1832,
      "step": 385
    },
    {
      "epoch": 0.3351235230934479,
      "grad_norm": 0.4092274606227875,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 1.1122,
      "step": 390
    },
    {
      "epoch": 0.3394199785177229,
      "grad_norm": 0.5057119131088257,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 1.0728,
      "step": 395
    },
    {
      "epoch": 0.34371643394199786,
      "grad_norm": 0.8013232946395874,
      "learning_rate": 0.0,
      "loss": 1.1565,
      "step": 400
    },
    {
      "epoch": 0.34371643394199786,
      "eval_loss": 1.1113475561141968,
      "eval_runtime": 40.9964,
      "eval_samples_per_second": 11.952,
      "eval_steps_per_second": 5.976,
      "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": 1.3974530306133197e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}