{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014361754647374042,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.590438661843511e-05,
      "eval_loss": 1.863739252090454,
      "eval_runtime": 296.2186,
      "eval_samples_per_second": 39.589,
      "eval_steps_per_second": 19.796,
      "step": 1
    },
    {
      "epoch": 0.00017952193309217552,
      "grad_norm": 3.3786585330963135,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.2882,
      "step": 5
    },
    {
      "epoch": 0.00035904386618435105,
      "grad_norm": 2.2973668575286865,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.9435,
      "step": 10
    },
    {
      "epoch": 0.0005385657992765267,
      "grad_norm": 3.7691123485565186,
      "learning_rate": 5e-05,
      "loss": 1.5858,
      "step": 15
    },
    {
      "epoch": 0.0007180877323687021,
      "grad_norm": 3.9693098068237305,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.3287,
      "step": 20
    },
    {
      "epoch": 0.0008976096654608777,
      "grad_norm": 3.8540399074554443,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.4156,
      "step": 25
    },
    {
      "epoch": 0.0010771315985530533,
      "grad_norm": 2.7623941898345947,
      "learning_rate": 0.0001,
      "loss": 1.057,
      "step": 30
    },
    {
      "epoch": 0.0012566535316452289,
      "grad_norm": 5.292708873748779,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.0241,
      "step": 35
    },
    {
      "epoch": 0.0014361754647374042,
      "grad_norm": 3.554041624069214,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.154,
      "step": 40
    },
    {
      "epoch": 0.0016156973978295797,
      "grad_norm": 3.4261510372161865,
      "learning_rate": 9.959502176294383e-05,
      "loss": 0.79,
      "step": 45
    },
    {
      "epoch": 0.0017952193309217553,
      "grad_norm": 2.8072378635406494,
      "learning_rate": 9.928079551738543e-05,
      "loss": 0.5961,
      "step": 50
    },
    {
      "epoch": 0.001974741264013931,
      "grad_norm": 3.4256656169891357,
      "learning_rate": 9.887776194738432e-05,
      "loss": 1.168,
      "step": 55
    },
    {
      "epoch": 0.0021542631971061066,
      "grad_norm": 2.899747610092163,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.7375,
      "step": 60
    },
    {
      "epoch": 0.002333785130198282,
      "grad_norm": 2.90761137008667,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.9732,
      "step": 65
    },
    {
      "epoch": 0.0025133070632904577,
      "grad_norm": 1.8555082082748413,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.3572,
      "step": 70
    },
    {
      "epoch": 0.002692828996382633,
      "grad_norm": 1.7630332708358765,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.9795,
      "step": 75
    },
    {
      "epoch": 0.0028723509294748084,
      "grad_norm": 3.8984899520874023,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.5745,
      "step": 80
    },
    {
      "epoch": 0.003051872862566984,
      "grad_norm": 2.8053131103515625,
      "learning_rate": 9.464629290747842e-05,
      "loss": 1.1649,
      "step": 85
    },
    {
      "epoch": 0.0032313947956591595,
      "grad_norm": 2.453521251678467,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.4999,
      "step": 90
    },
    {
      "epoch": 0.0034109167287513353,
      "grad_norm": 2.323896646499634,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.6508,
      "step": 95
    },
    {
      "epoch": 0.0035904386618435106,
      "grad_norm": 2.865272045135498,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.6108,
      "step": 100
    },
    {
      "epoch": 0.0035904386618435106,
      "eval_loss": 0.7927728891372681,
      "eval_runtime": 295.9288,
      "eval_samples_per_second": 39.628,
      "eval_steps_per_second": 19.816,
      "step": 100
    },
    {
      "epoch": 0.0037699605949356864,
      "grad_norm": 3.3485584259033203,
      "learning_rate": 9.019985651834703e-05,
      "loss": 1.5845,
      "step": 105
    },
    {
      "epoch": 0.003949482528027862,
      "grad_norm": 2.0757248401641846,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.3507,
      "step": 110
    },
    {
      "epoch": 0.0041290044611200375,
      "grad_norm": 5.261969089508057,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.8373,
      "step": 115
    },
    {
      "epoch": 0.004308526394212213,
      "grad_norm": 3.5156733989715576,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.6916,
      "step": 120
    },
    {
      "epoch": 0.004488048327304388,
      "grad_norm": 2.324287176132202,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.7903,
      "step": 125
    },
    {
      "epoch": 0.004667570260396564,
      "grad_norm": 3.4774346351623535,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.763,
      "step": 130
    },
    {
      "epoch": 0.00484709219348874,
      "grad_norm": 3.08046293258667,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.5603,
      "step": 135
    },
    {
      "epoch": 0.0050266141265809154,
      "grad_norm": 2.702235460281372,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.602,
      "step": 140
    },
    {
      "epoch": 0.00520613605967309,
      "grad_norm": 2.3828327655792236,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.7195,
      "step": 145
    },
    {
      "epoch": 0.005385657992765266,
      "grad_norm": 1.948315143585205,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.7553,
      "step": 150
    },
    {
      "epoch": 0.005565179925857442,
      "grad_norm": 2.2542800903320312,
      "learning_rate": 7.438474719068173e-05,
      "loss": 1.1293,
      "step": 155
    },
    {
      "epoch": 0.005744701858949617,
      "grad_norm": 1.8316344022750854,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.6391,
      "step": 160
    },
    {
      "epoch": 0.0059242237920417926,
      "grad_norm": 2.846313238143921,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.5962,
      "step": 165
    },
    {
      "epoch": 0.006103745725133968,
      "grad_norm": 2.2054855823516846,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.8706,
      "step": 170
    },
    {
      "epoch": 0.006283267658226144,
      "grad_norm": 2.6350550651550293,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.7453,
      "step": 175
    },
    {
      "epoch": 0.006462789591318319,
      "grad_norm": 2.7086055278778076,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.8613,
      "step": 180
    },
    {
      "epoch": 0.006642311524410495,
      "grad_norm": 1.7751556634902954,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.7272,
      "step": 185
    },
    {
      "epoch": 0.0068218334575026705,
      "grad_norm": 2.882451295852661,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 1.0168,
      "step": 190
    },
    {
      "epoch": 0.007001355390594846,
      "grad_norm": 1.646462321281433,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.4449,
      "step": 195
    },
    {
      "epoch": 0.007180877323687021,
      "grad_norm": 2.076798439025879,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.3385,
      "step": 200
    },
    {
      "epoch": 0.007180877323687021,
      "eval_loss": 0.7332786917686462,
      "eval_runtime": 297.6018,
      "eval_samples_per_second": 39.405,
      "eval_steps_per_second": 19.704,
      "step": 200
    },
    {
      "epoch": 0.007360399256779197,
      "grad_norm": 3.4360103607177734,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 1.0154,
      "step": 205
    },
    {
      "epoch": 0.007539921189871373,
      "grad_norm": 2.5292601585388184,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.7111,
      "step": 210
    },
    {
      "epoch": 0.007719443122963548,
      "grad_norm": 3.471696615219116,
      "learning_rate": 5e-05,
      "loss": 0.6379,
      "step": 215
    },
    {
      "epoch": 0.007898965056055723,
      "grad_norm": 1.6413151025772095,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.5324,
      "step": 220
    },
    {
      "epoch": 0.008078486989147898,
      "grad_norm": 3.4700419902801514,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.5782,
      "step": 225
    },
    {
      "epoch": 0.008258008922240075,
      "grad_norm": 0.9813743233680725,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.4875,
      "step": 230
    },
    {
      "epoch": 0.00843753085533225,
      "grad_norm": 2.0533673763275146,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.7237,
      "step": 235
    },
    {
      "epoch": 0.008617052788424426,
      "grad_norm": 2.0309364795684814,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.6707,
      "step": 240
    },
    {
      "epoch": 0.008796574721516601,
      "grad_norm": 1.6909382343292236,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.5498,
      "step": 245
    },
    {
      "epoch": 0.008976096654608776,
      "grad_norm": 2.379208564758301,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.5602,
      "step": 250
    },
    {
      "epoch": 0.009155618587700953,
      "grad_norm": 2.586571216583252,
      "learning_rate": 3.334301026289712e-05,
      "loss": 1.1834,
      "step": 255
    },
    {
      "epoch": 0.009335140520793128,
      "grad_norm": 2.466595411300659,
      "learning_rate": 3.135717611098458e-05,
      "loss": 1.0136,
      "step": 260
    },
    {
      "epoch": 0.009514662453885303,
      "grad_norm": 3.231771230697632,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.7171,
      "step": 265
    },
    {
      "epoch": 0.00969418438697748,
      "grad_norm": 3.0050177574157715,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.7772,
      "step": 270
    },
    {
      "epoch": 0.009873706320069654,
      "grad_norm": 1.6899439096450806,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.4259,
      "step": 275
    },
    {
      "epoch": 0.010053228253161831,
      "grad_norm": 3.8092710971832275,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.8559,
      "step": 280
    },
    {
      "epoch": 0.010232750186254006,
      "grad_norm": 3.3671493530273438,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 1.0261,
      "step": 285
    },
    {
      "epoch": 0.01041227211934618,
      "grad_norm": 1.5175124406814575,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.691,
      "step": 290
    },
    {
      "epoch": 0.010591794052438357,
      "grad_norm": 2.7138614654541016,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.6986,
      "step": 295
    },
    {
      "epoch": 0.010771315985530532,
      "grad_norm": 2.981684923171997,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.5018,
      "step": 300
    },
    {
      "epoch": 0.010771315985530532,
      "eval_loss": 0.702721118927002,
      "eval_runtime": 296.3371,
      "eval_samples_per_second": 39.573,
      "eval_steps_per_second": 19.788,
      "step": 300
    },
    {
      "epoch": 0.010950837918622707,
      "grad_norm": 2.8173673152923584,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.9842,
      "step": 305
    },
    {
      "epoch": 0.011130359851714884,
      "grad_norm": 2.158261775970459,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.8524,
      "step": 310
    },
    {
      "epoch": 0.011309881784807059,
      "grad_norm": 3.248124122619629,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.498,
      "step": 315
    },
    {
      "epoch": 0.011489403717899234,
      "grad_norm": 3.0474750995635986,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.8186,
      "step": 320
    },
    {
      "epoch": 0.01166892565099141,
      "grad_norm": 3.2479071617126465,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.547,
      "step": 325
    },
    {
      "epoch": 0.011848447584083585,
      "grad_norm": 3.9610724449157715,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.9603,
      "step": 330
    },
    {
      "epoch": 0.012027969517175762,
      "grad_norm": 1.994195580482483,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.6417,
      "step": 335
    },
    {
      "epoch": 0.012207491450267937,
      "grad_norm": 1.8411099910736084,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.6436,
      "step": 340
    },
    {
      "epoch": 0.012387013383360112,
      "grad_norm": 3.0507500171661377,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.7445,
      "step": 345
    },
    {
      "epoch": 0.012566535316452288,
      "grad_norm": 1.8591485023498535,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.437,
      "step": 350
    },
    {
      "epoch": 0.012746057249544463,
      "grad_norm": 3.04154896736145,
      "learning_rate": 3.605548635174533e-06,
      "loss": 1.2497,
      "step": 355
    },
    {
      "epoch": 0.012925579182636638,
      "grad_norm": 2.698528289794922,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.8649,
      "step": 360
    },
    {
      "epoch": 0.013105101115728815,
      "grad_norm": 3.410181999206543,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.5556,
      "step": 365
    },
    {
      "epoch": 0.01328462304882099,
      "grad_norm": 2.4212844371795654,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.4535,
      "step": 370
    },
    {
      "epoch": 0.013464144981913164,
      "grad_norm": 2.8054001331329346,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.7758,
      "step": 375
    },
    {
      "epoch": 0.013643666915005341,
      "grad_norm": 3.146541118621826,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.4744,
      "step": 380
    },
    {
      "epoch": 0.013823188848097516,
      "grad_norm": 2.158457040786743,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.9266,
      "step": 385
    },
    {
      "epoch": 0.014002710781189693,
      "grad_norm": 2.0651299953460693,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.6964,
      "step": 390
    },
    {
      "epoch": 0.014182232714281868,
      "grad_norm": 3.358060121536255,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.6306,
      "step": 395
    },
    {
      "epoch": 0.014361754647374042,
      "grad_norm": 2.789674997329712,
      "learning_rate": 0.0,
      "loss": 0.4816,
      "step": 400
    },
    {
      "epoch": 0.014361754647374042,
      "eval_loss": 0.6983225345611572,
      "eval_runtime": 297.2619,
      "eval_samples_per_second": 39.45,
      "eval_steps_per_second": 19.727,
      "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": 7519272933261312.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}