{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8864265927977839,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00221606648199446,
      "eval_loss": 3.0546226501464844,
      "eval_runtime": 28.6402,
      "eval_samples_per_second": 6.634,
      "eval_steps_per_second": 3.317,
      "step": 1
    },
    {
      "epoch": 0.0110803324099723,
      "grad_norm": 40.4317626953125,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 10.0604,
      "step": 5
    },
    {
      "epoch": 0.0221606648199446,
      "grad_norm": 41.771488189697266,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.0699,
      "step": 10
    },
    {
      "epoch": 0.0332409972299169,
      "grad_norm": 42.931514739990234,
      "learning_rate": 5e-05,
      "loss": 8.1899,
      "step": 15
    },
    {
      "epoch": 0.0443213296398892,
      "grad_norm": 22.341644287109375,
      "learning_rate": 6.666666666666667e-05,
      "loss": 5.8259,
      "step": 20
    },
    {
      "epoch": 0.055401662049861494,
      "grad_norm": 35.03843307495117,
      "learning_rate": 8.333333333333334e-05,
      "loss": 4.4083,
      "step": 25
    },
    {
      "epoch": 0.0664819944598338,
      "grad_norm": 44.581172943115234,
      "learning_rate": 0.0001,
      "loss": 2.615,
      "step": 30
    },
    {
      "epoch": 0.07756232686980609,
      "grad_norm": 20.425941467285156,
      "learning_rate": 9.995494831023409e-05,
      "loss": 2.357,
      "step": 35
    },
    {
      "epoch": 0.0886426592797784,
      "grad_norm": 49.352970123291016,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.5549,
      "step": 40
    },
    {
      "epoch": 0.0997229916897507,
      "grad_norm": 49.72975158691406,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.355,
      "step": 45
    },
    {
      "epoch": 0.11080332409972299,
      "grad_norm": 30.52098846435547,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.0371,
      "step": 50
    },
    {
      "epoch": 0.12188365650969529,
      "grad_norm": 32.97958755493164,
      "learning_rate": 9.887776194738432e-05,
      "loss": 2.4841,
      "step": 55
    },
    {
      "epoch": 0.1329639889196676,
      "grad_norm": 17.2390079498291,
      "learning_rate": 9.838664734667495e-05,
      "loss": 2.5226,
      "step": 60
    },
    {
      "epoch": 0.1440443213296399,
      "grad_norm": 14.520543098449707,
      "learning_rate": 9.780833673696254e-05,
      "loss": 1.9661,
      "step": 65
    },
    {
      "epoch": 0.15512465373961218,
      "grad_norm": 8.61408805847168,
      "learning_rate": 9.714387227305422e-05,
      "loss": 1.5782,
      "step": 70
    },
    {
      "epoch": 0.16620498614958448,
      "grad_norm": 37.85402297973633,
      "learning_rate": 9.639445136482548e-05,
      "loss": 1.5413,
      "step": 75
    },
    {
      "epoch": 0.1772853185595568,
      "grad_norm": 14.777547836303711,
      "learning_rate": 9.55614245194068e-05,
      "loss": 1.3084,
      "step": 80
    },
    {
      "epoch": 0.1883656509695291,
      "grad_norm": 15.355766296386719,
      "learning_rate": 9.464629290747842e-05,
      "loss": 2.0663,
      "step": 85
    },
    {
      "epoch": 0.1994459833795014,
      "grad_norm": 13.375919342041016,
      "learning_rate": 9.365070565805941e-05,
      "loss": 1.1714,
      "step": 90
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 19.361492156982422,
      "learning_rate": 9.257645688666556e-05,
      "loss": 1.2957,
      "step": 95
    },
    {
      "epoch": 0.22160664819944598,
      "grad_norm": 32.2000732421875,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.245,
      "step": 100
    },
    {
      "epoch": 0.22160664819944598,
      "eval_loss": 0.34181350469589233,
      "eval_runtime": 29.2512,
      "eval_samples_per_second": 6.495,
      "eval_steps_per_second": 3.248,
      "step": 100
    },
    {
      "epoch": 0.23268698060941828,
      "grad_norm": 17.071205139160156,
      "learning_rate": 9.019985651834703e-05,
      "loss": 2.5636,
      "step": 105
    },
    {
      "epoch": 0.24376731301939059,
      "grad_norm": 13.007355690002441,
      "learning_rate": 8.890178771592199e-05,
      "loss": 2.0721,
      "step": 110
    },
    {
      "epoch": 0.2548476454293629,
      "grad_norm": 9.219687461853027,
      "learning_rate": 8.753361526263621e-05,
      "loss": 1.2709,
      "step": 115
    },
    {
      "epoch": 0.2659279778393352,
      "grad_norm": 15.053553581237793,
      "learning_rate": 8.609780469772623e-05,
      "loss": 1.8663,
      "step": 120
    },
    {
      "epoch": 0.2770083102493075,
      "grad_norm": 16.7861328125,
      "learning_rate": 8.459694344887732e-05,
      "loss": 1.2774,
      "step": 125
    },
    {
      "epoch": 0.2880886426592798,
      "grad_norm": 15.787662506103516,
      "learning_rate": 8.303373616950408e-05,
      "loss": 1.4413,
      "step": 130
    },
    {
      "epoch": 0.29916897506925205,
      "grad_norm": 8.440824508666992,
      "learning_rate": 8.141099986478212e-05,
      "loss": 1.279,
      "step": 135
    },
    {
      "epoch": 0.31024930747922436,
      "grad_norm": 31.337549209594727,
      "learning_rate": 7.973165881521434e-05,
      "loss": 1.3324,
      "step": 140
    },
    {
      "epoch": 0.32132963988919666,
      "grad_norm": 5.685225963592529,
      "learning_rate": 7.799873930687978e-05,
      "loss": 1.1793,
      "step": 145
    },
    {
      "epoch": 0.33240997229916897,
      "grad_norm": 33.529388427734375,
      "learning_rate": 7.621536417786159e-05,
      "loss": 1.1855,
      "step": 150
    },
    {
      "epoch": 0.34349030470914127,
      "grad_norm": 13.9574556350708,
      "learning_rate": 7.438474719068173e-05,
      "loss": 2.081,
      "step": 155
    },
    {
      "epoch": 0.3545706371191136,
      "grad_norm": 21.573740005493164,
      "learning_rate": 7.251018724088367e-05,
      "loss": 1.3671,
      "step": 160
    },
    {
      "epoch": 0.3656509695290859,
      "grad_norm": 7.78122615814209,
      "learning_rate": 7.059506241219965e-05,
      "loss": 1.5839,
      "step": 165
    },
    {
      "epoch": 0.3767313019390582,
      "grad_norm": 11.617698669433594,
      "learning_rate": 6.864282388901544e-05,
      "loss": 1.0815,
      "step": 170
    },
    {
      "epoch": 0.3878116343490305,
      "grad_norm": 13.11463737487793,
      "learning_rate": 6.665698973710288e-05,
      "loss": 1.1565,
      "step": 175
    },
    {
      "epoch": 0.3988919667590028,
      "grad_norm": 13.981616973876953,
      "learning_rate": 6.464113856382752e-05,
      "loss": 1.3213,
      "step": 180
    },
    {
      "epoch": 0.4099722991689751,
      "grad_norm": 78.8832778930664,
      "learning_rate": 6.259890306925627e-05,
      "loss": 1.3421,
      "step": 185
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 10.022073745727539,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 1.5194,
      "step": 190
    },
    {
      "epoch": 0.43213296398891965,
      "grad_norm": 6.625938892364502,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 1.2761,
      "step": 195
    },
    {
      "epoch": 0.44321329639889195,
      "grad_norm": 37.585079193115234,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 1.3119,
      "step": 200
    },
    {
      "epoch": 0.44321329639889195,
      "eval_loss": 0.3075096905231476,
      "eval_runtime": 29.2699,
      "eval_samples_per_second": 6.491,
      "eval_steps_per_second": 3.246,
      "step": 200
    },
    {
      "epoch": 0.45429362880886426,
      "grad_norm": 9.12763500213623,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 1.9951,
      "step": 205
    },
    {
      "epoch": 0.46537396121883656,
      "grad_norm": 18.240190505981445,
      "learning_rate": 5.212206015980742e-05,
      "loss": 2.0906,
      "step": 210
    },
    {
      "epoch": 0.47645429362880887,
      "grad_norm": 25.478147506713867,
      "learning_rate": 5e-05,
      "loss": 2.0004,
      "step": 215
    },
    {
      "epoch": 0.48753462603878117,
      "grad_norm": 16.697818756103516,
      "learning_rate": 4.78779398401926e-05,
      "loss": 1.4445,
      "step": 220
    },
    {
      "epoch": 0.4986149584487535,
      "grad_norm": 10.243321418762207,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.9641,
      "step": 225
    },
    {
      "epoch": 0.5096952908587258,
      "grad_norm": 17.184789657592773,
      "learning_rate": 4.364910901265606e-05,
      "loss": 1.0775,
      "step": 230
    },
    {
      "epoch": 0.5207756232686981,
      "grad_norm": 8.637123107910156,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 1.0721,
      "step": 235
    },
    {
      "epoch": 0.5318559556786704,
      "grad_norm": 13.308157920837402,
      "learning_rate": 3.94660365002137e-05,
      "loss": 1.2811,
      "step": 240
    },
    {
      "epoch": 0.5429362880886427,
      "grad_norm": 15.352422714233398,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.9938,
      "step": 245
    },
    {
      "epoch": 0.554016620498615,
      "grad_norm": 18.489025115966797,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 1.4049,
      "step": 250
    },
    {
      "epoch": 0.5650969529085873,
      "grad_norm": 16.45484733581543,
      "learning_rate": 3.334301026289712e-05,
      "loss": 2.1442,
      "step": 255
    },
    {
      "epoch": 0.5761772853185596,
      "grad_norm": 7.563566207885742,
      "learning_rate": 3.135717611098458e-05,
      "loss": 1.4987,
      "step": 260
    },
    {
      "epoch": 0.5872576177285319,
      "grad_norm": 11.79305362701416,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 1.5674,
      "step": 265
    },
    {
      "epoch": 0.5983379501385041,
      "grad_norm": 6.213284492492676,
      "learning_rate": 2.748981275911633e-05,
      "loss": 1.0538,
      "step": 270
    },
    {
      "epoch": 0.6094182825484764,
      "grad_norm": 18.65719985961914,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.9036,
      "step": 275
    },
    {
      "epoch": 0.6204986149584487,
      "grad_norm": 15.78054428100586,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 1.08,
      "step": 280
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 3.284679651260376,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.6218,
      "step": 285
    },
    {
      "epoch": 0.6426592797783933,
      "grad_norm": 5.37770938873291,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.6554,
      "step": 290
    },
    {
      "epoch": 0.6537396121883656,
      "grad_norm": 24.48253059387207,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.727,
      "step": 295
    },
    {
      "epoch": 0.6648199445983379,
      "grad_norm": 12.94134521484375,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.7653,
      "step": 300
    },
    {
      "epoch": 0.6648199445983379,
      "eval_loss": 0.27097469568252563,
      "eval_runtime": 29.2785,
      "eval_samples_per_second": 6.489,
      "eval_steps_per_second": 3.245,
      "step": 300
    },
    {
      "epoch": 0.6759002770083102,
      "grad_norm": 15.39680004119873,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 1.7607,
      "step": 305
    },
    {
      "epoch": 0.6869806094182825,
      "grad_norm": 16.674484252929688,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 1.8385,
      "step": 310
    },
    {
      "epoch": 0.6980609418282548,
      "grad_norm": 10.502399444580078,
      "learning_rate": 1.246638473736378e-05,
      "loss": 1.2802,
      "step": 315
    },
    {
      "epoch": 0.7091412742382271,
      "grad_norm": 9.889562606811523,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 1.0546,
      "step": 320
    },
    {
      "epoch": 0.7202216066481995,
      "grad_norm": 5.083305835723877,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.3813,
      "step": 325
    },
    {
      "epoch": 0.7313019390581718,
      "grad_norm": 11.659056663513184,
      "learning_rate": 8.574517537807897e-06,
      "loss": 1.171,
      "step": 330
    },
    {
      "epoch": 0.7423822714681441,
      "grad_norm": 9.71153736114502,
      "learning_rate": 7.423543113334436e-06,
      "loss": 1.0335,
      "step": 335
    },
    {
      "epoch": 0.7534626038781164,
      "grad_norm": 12.402853965759277,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.6699,
      "step": 340
    },
    {
      "epoch": 0.7645429362880887,
      "grad_norm": 45.955116271972656,
      "learning_rate": 5.353707092521582e-06,
      "loss": 1.0712,
      "step": 345
    },
    {
      "epoch": 0.775623268698061,
      "grad_norm": 21.709836959838867,
      "learning_rate": 4.43857548059321e-06,
      "loss": 1.243,
      "step": 350
    },
    {
      "epoch": 0.7867036011080333,
      "grad_norm": 12.371013641357422,
      "learning_rate": 3.605548635174533e-06,
      "loss": 1.6315,
      "step": 355
    },
    {
      "epoch": 0.7977839335180056,
      "grad_norm": 15.897541999816895,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.9951,
      "step": 360
    },
    {
      "epoch": 0.8088642659279779,
      "grad_norm": 13.310140609741211,
      "learning_rate": 2.191663263037458e-06,
      "loss": 1.2105,
      "step": 365
    },
    {
      "epoch": 0.8199445983379502,
      "grad_norm": 4.561711311340332,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.7344,
      "step": 370
    },
    {
      "epoch": 0.8310249307479224,
      "grad_norm": 7.639242649078369,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.9416,
      "step": 375
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 9.151134490966797,
      "learning_rate": 7.192044826145771e-07,
      "loss": 1.2359,
      "step": 380
    },
    {
      "epoch": 0.853185595567867,
      "grad_norm": 8.265776634216309,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.7159,
      "step": 385
    },
    {
      "epoch": 0.8642659279778393,
      "grad_norm": 11.744566917419434,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.9993,
      "step": 390
    },
    {
      "epoch": 0.8753462603878116,
      "grad_norm": 22.258119583129883,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.9772,
      "step": 395
    },
    {
      "epoch": 0.8864265927977839,
      "grad_norm": 39.517921447753906,
      "learning_rate": 0.0,
      "loss": 1.3352,
      "step": 400
    },
    {
      "epoch": 0.8864265927977839,
      "eval_loss": 0.24912621080875397,
      "eval_runtime": 29.259,
      "eval_samples_per_second": 6.494,
      "eval_steps_per_second": 3.247,
      "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": 2.8007695351441e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}