{
  "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": 2.560588836669922,
      "eval_runtime": 5.6997,
      "eval_samples_per_second": 85.969,
      "eval_steps_per_second": 42.984,
      "step": 1
    },
    {
      "epoch": 0.004296455424274973,
      "grad_norm": 0.4264378845691681,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.5201,
      "step": 5
    },
    {
      "epoch": 0.008592910848549946,
      "grad_norm": 0.4207630455493927,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.384,
      "step": 10
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 0.471756249666214,
      "learning_rate": 5e-05,
      "loss": 2.4274,
      "step": 15
    },
    {
      "epoch": 0.017185821697099892,
      "grad_norm": 0.41662147641181946,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.3859,
      "step": 20
    },
    {
      "epoch": 0.021482277121374866,
      "grad_norm": 2.180488348007202,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.4303,
      "step": 25
    },
    {
      "epoch": 0.02577873254564984,
      "grad_norm": 0.6264692544937134,
      "learning_rate": 0.0001,
      "loss": 2.5621,
      "step": 30
    },
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 0.8322041034698486,
      "learning_rate": 9.995494831023409e-05,
      "loss": 2.5356,
      "step": 35
    },
    {
      "epoch": 0.034371643394199784,
      "grad_norm": 0.7277498245239258,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.4546,
      "step": 40
    },
    {
      "epoch": 0.03866809881847476,
      "grad_norm": 3.423780679702759,
      "learning_rate": 9.959502176294383e-05,
      "loss": 2.5419,
      "step": 45
    },
    {
      "epoch": 0.04296455424274973,
      "grad_norm": 1.0978513956069946,
      "learning_rate": 9.928079551738543e-05,
      "loss": 2.6394,
      "step": 50
    },
    {
      "epoch": 0.047261009667024706,
      "grad_norm": 0.6654792428016663,
      "learning_rate": 9.887776194738432e-05,
      "loss": 2.363,
      "step": 55
    },
    {
      "epoch": 0.05155746509129968,
      "grad_norm": 0.5801962018013,
      "learning_rate": 9.838664734667495e-05,
      "loss": 2.2459,
      "step": 60
    },
    {
      "epoch": 0.055853920515574654,
      "grad_norm": 0.4457996189594269,
      "learning_rate": 9.780833673696254e-05,
      "loss": 2.1574,
      "step": 65
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 0.6491867303848267,
      "learning_rate": 9.714387227305422e-05,
      "loss": 2.1884,
      "step": 70
    },
    {
      "epoch": 0.0644468313641246,
      "grad_norm": 0.5002301931381226,
      "learning_rate": 9.639445136482548e-05,
      "loss": 2.1838,
      "step": 75
    },
    {
      "epoch": 0.06874328678839957,
      "grad_norm": 0.9140828251838684,
      "learning_rate": 9.55614245194068e-05,
      "loss": 2.2511,
      "step": 80
    },
    {
      "epoch": 0.07303974221267455,
      "grad_norm": 0.5961155891418457,
      "learning_rate": 9.464629290747842e-05,
      "loss": 2.3192,
      "step": 85
    },
    {
      "epoch": 0.07733619763694952,
      "grad_norm": 0.8043453097343445,
      "learning_rate": 9.365070565805941e-05,
      "loss": 2.2701,
      "step": 90
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 0.7744258642196655,
      "learning_rate": 9.257645688666556e-05,
      "loss": 2.2571,
      "step": 95
    },
    {
      "epoch": 0.08592910848549946,
      "grad_norm": 1.2287739515304565,
      "learning_rate": 9.142548246219212e-05,
      "loss": 2.5016,
      "step": 100
    },
    {
      "epoch": 0.08592910848549946,
      "eval_loss": 2.225370168685913,
      "eval_runtime": 5.7053,
      "eval_samples_per_second": 85.885,
      "eval_steps_per_second": 42.942,
      "step": 100
    },
    {
      "epoch": 0.09022556390977443,
      "grad_norm": 0.8052483797073364,
      "learning_rate": 9.019985651834703e-05,
      "loss": 2.2847,
      "step": 105
    },
    {
      "epoch": 0.09452201933404941,
      "grad_norm": 0.49702775478363037,
      "learning_rate": 8.890178771592199e-05,
      "loss": 2.1225,
      "step": 110
    },
    {
      "epoch": 0.09881847475832438,
      "grad_norm": 0.4533235728740692,
      "learning_rate": 8.753361526263621e-05,
      "loss": 2.0419,
      "step": 115
    },
    {
      "epoch": 0.10311493018259936,
      "grad_norm": 0.4964291751384735,
      "learning_rate": 8.609780469772623e-05,
      "loss": 2.0997,
      "step": 120
    },
    {
      "epoch": 0.10741138560687433,
      "grad_norm": 0.5229367613792419,
      "learning_rate": 8.459694344887732e-05,
      "loss": 1.9925,
      "step": 125
    },
    {
      "epoch": 0.11170784103114931,
      "grad_norm": 0.5974547863006592,
      "learning_rate": 8.303373616950408e-05,
      "loss": 2.1483,
      "step": 130
    },
    {
      "epoch": 0.11600429645542427,
      "grad_norm": 0.5904881358146667,
      "learning_rate": 8.141099986478212e-05,
      "loss": 2.0385,
      "step": 135
    },
    {
      "epoch": 0.12030075187969924,
      "grad_norm": 0.8220380544662476,
      "learning_rate": 7.973165881521434e-05,
      "loss": 2.1609,
      "step": 140
    },
    {
      "epoch": 0.12459720730397422,
      "grad_norm": 0.7483985424041748,
      "learning_rate": 7.799873930687978e-05,
      "loss": 2.1462,
      "step": 145
    },
    {
      "epoch": 0.1288936627282492,
      "grad_norm": 1.0921134948730469,
      "learning_rate": 7.621536417786159e-05,
      "loss": 2.3785,
      "step": 150
    },
    {
      "epoch": 0.13319011815252416,
      "grad_norm": 0.8443463444709778,
      "learning_rate": 7.438474719068173e-05,
      "loss": 2.1076,
      "step": 155
    },
    {
      "epoch": 0.13748657357679914,
      "grad_norm": 0.6027088165283203,
      "learning_rate": 7.251018724088367e-05,
      "loss": 2.1111,
      "step": 160
    },
    {
      "epoch": 0.14178302900107412,
      "grad_norm": 0.5082783699035645,
      "learning_rate": 7.059506241219965e-05,
      "loss": 2.0684,
      "step": 165
    },
    {
      "epoch": 0.1460794844253491,
      "grad_norm": 0.4934474527835846,
      "learning_rate": 6.864282388901544e-05,
      "loss": 2.0674,
      "step": 170
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 0.5872422456741333,
      "learning_rate": 6.665698973710288e-05,
      "loss": 2.1015,
      "step": 175
    },
    {
      "epoch": 0.15467239527389903,
      "grad_norm": 0.5945985913276672,
      "learning_rate": 6.464113856382752e-05,
      "loss": 2.0898,
      "step": 180
    },
    {
      "epoch": 0.158968850698174,
      "grad_norm": 0.7060194611549377,
      "learning_rate": 6.259890306925627e-05,
      "loss": 2.0865,
      "step": 185
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 0.6977397203445435,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 2.1363,
      "step": 190
    },
    {
      "epoch": 0.16756176154672395,
      "grad_norm": 0.7754750847816467,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 2.1488,
      "step": 195
    },
    {
      "epoch": 0.17185821697099893,
      "grad_norm": 1.1881859302520752,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 2.2795,
      "step": 200
    },
    {
      "epoch": 0.17185821697099893,
      "eval_loss": 2.118762969970703,
      "eval_runtime": 5.7097,
      "eval_samples_per_second": 85.819,
      "eval_steps_per_second": 42.909,
      "step": 200
    },
    {
      "epoch": 0.1761546723952739,
      "grad_norm": 0.6017293334007263,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 2.1295,
      "step": 205
    },
    {
      "epoch": 0.18045112781954886,
      "grad_norm": 0.5341784954071045,
      "learning_rate": 5.212206015980742e-05,
      "loss": 2.067,
      "step": 210
    },
    {
      "epoch": 0.18474758324382384,
      "grad_norm": 0.5095373392105103,
      "learning_rate": 5e-05,
      "loss": 2.0527,
      "step": 215
    },
    {
      "epoch": 0.18904403866809882,
      "grad_norm": 0.48284170031547546,
      "learning_rate": 4.78779398401926e-05,
      "loss": 2.0631,
      "step": 220
    },
    {
      "epoch": 0.1933404940923738,
      "grad_norm": 0.5275474786758423,
      "learning_rate": 4.575970377622456e-05,
      "loss": 2.0624,
      "step": 225
    },
    {
      "epoch": 0.19763694951664876,
      "grad_norm": 0.5961275100708008,
      "learning_rate": 4.364910901265606e-05,
      "loss": 2.1405,
      "step": 230
    },
    {
      "epoch": 0.20193340494092374,
      "grad_norm": 0.7325344085693359,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 2.106,
      "step": 235
    },
    {
      "epoch": 0.20622986036519872,
      "grad_norm": 0.6524381637573242,
      "learning_rate": 3.94660365002137e-05,
      "loss": 2.0755,
      "step": 240
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.7961000204086304,
      "learning_rate": 3.740109693074375e-05,
      "loss": 2.1358,
      "step": 245
    },
    {
      "epoch": 0.21482277121374865,
      "grad_norm": 1.1256376504898071,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 2.2082,
      "step": 250
    },
    {
      "epoch": 0.21911922663802363,
      "grad_norm": 0.6478416919708252,
      "learning_rate": 3.334301026289712e-05,
      "loss": 2.057,
      "step": 255
    },
    {
      "epoch": 0.22341568206229862,
      "grad_norm": 0.5778697729110718,
      "learning_rate": 3.135717611098458e-05,
      "loss": 2.0913,
      "step": 260
    },
    {
      "epoch": 0.22771213748657357,
      "grad_norm": 0.5688227415084839,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 2.0437,
      "step": 265
    },
    {
      "epoch": 0.23200859291084855,
      "grad_norm": 0.5258074402809143,
      "learning_rate": 2.748981275911633e-05,
      "loss": 2.0344,
      "step": 270
    },
    {
      "epoch": 0.23630504833512353,
      "grad_norm": 0.6406161785125732,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 2.0797,
      "step": 275
    },
    {
      "epoch": 0.24060150375939848,
      "grad_norm": 0.6104590892791748,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 2.0336,
      "step": 280
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 0.6418982744216919,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 2.0997,
      "step": 285
    },
    {
      "epoch": 0.24919441460794844,
      "grad_norm": 0.7529294490814209,
      "learning_rate": 2.026834118478567e-05,
      "loss": 2.1008,
      "step": 290
    },
    {
      "epoch": 0.2534908700322234,
      "grad_norm": 0.9145365953445435,
      "learning_rate": 1.858900013521788e-05,
      "loss": 2.2217,
      "step": 295
    },
    {
      "epoch": 0.2577873254564984,
      "grad_norm": 1.3251687288284302,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 2.4646,
      "step": 300
    },
    {
      "epoch": 0.2577873254564984,
      "eval_loss": 2.0908751487731934,
      "eval_runtime": 5.7808,
      "eval_samples_per_second": 84.764,
      "eval_steps_per_second": 42.382,
      "step": 300
    },
    {
      "epoch": 0.2620837808807734,
      "grad_norm": 0.4574701189994812,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 1.9798,
      "step": 305
    },
    {
      "epoch": 0.2663802363050483,
      "grad_norm": 0.48488375544548035,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 1.9579,
      "step": 310
    },
    {
      "epoch": 0.2706766917293233,
      "grad_norm": 0.6625605225563049,
      "learning_rate": 1.246638473736378e-05,
      "loss": 2.0111,
      "step": 315
    },
    {
      "epoch": 0.2749731471535983,
      "grad_norm": 0.7432839274406433,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 2.0554,
      "step": 320
    },
    {
      "epoch": 0.27926960257787325,
      "grad_norm": 0.6828286051750183,
      "learning_rate": 9.800143481652979e-06,
      "loss": 2.0122,
      "step": 325
    },
    {
      "epoch": 0.28356605800214824,
      "grad_norm": 0.6228327751159668,
      "learning_rate": 8.574517537807897e-06,
      "loss": 2.1302,
      "step": 330
    },
    {
      "epoch": 0.2878625134264232,
      "grad_norm": 0.5838046669960022,
      "learning_rate": 7.423543113334436e-06,
      "loss": 2.092,
      "step": 335
    },
    {
      "epoch": 0.2921589688506982,
      "grad_norm": 0.7110097408294678,
      "learning_rate": 6.349294341940593e-06,
      "loss": 2.126,
      "step": 340
    },
    {
      "epoch": 0.2964554242749731,
      "grad_norm": 0.9247037172317505,
      "learning_rate": 5.353707092521582e-06,
      "loss": 2.2157,
      "step": 345
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 1.3924357891082764,
      "learning_rate": 4.43857548059321e-06,
      "loss": 2.1064,
      "step": 350
    },
    {
      "epoch": 0.3050483351235231,
      "grad_norm": 0.446307510137558,
      "learning_rate": 3.605548635174533e-06,
      "loss": 1.9835,
      "step": 355
    },
    {
      "epoch": 0.30934479054779807,
      "grad_norm": 0.5045768618583679,
      "learning_rate": 2.85612772694579e-06,
      "loss": 2.0543,
      "step": 360
    },
    {
      "epoch": 0.31364124597207305,
      "grad_norm": 0.5118470191955566,
      "learning_rate": 2.191663263037458e-06,
      "loss": 1.9604,
      "step": 365
    },
    {
      "epoch": 0.317937701396348,
      "grad_norm": 0.5900284051895142,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 1.9337,
      "step": 370
    },
    {
      "epoch": 0.322234156820623,
      "grad_norm": 0.5509868860244751,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 2.0001,
      "step": 375
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.6802031397819519,
      "learning_rate": 7.192044826145771e-07,
      "loss": 2.0305,
      "step": 380
    },
    {
      "epoch": 0.3308270676691729,
      "grad_norm": 0.6725232005119324,
      "learning_rate": 4.049782370561583e-07,
      "loss": 2.1426,
      "step": 385
    },
    {
      "epoch": 0.3351235230934479,
      "grad_norm": 0.7881231307983398,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 2.093,
      "step": 390
    },
    {
      "epoch": 0.3394199785177229,
      "grad_norm": 0.8408851027488708,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 2.1911,
      "step": 395
    },
    {
      "epoch": 0.34371643394199786,
      "grad_norm": 1.3322116136550903,
      "learning_rate": 0.0,
      "loss": 2.2042,
      "step": 400
    },
    {
      "epoch": 0.34371643394199786,
      "eval_loss": 2.0873777866363525,
      "eval_runtime": 5.6835,
      "eval_samples_per_second": 86.214,
      "eval_steps_per_second": 43.107,
      "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": 2942309410799616.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}