{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 385,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06493506493506493,
      "grad_norm": 2.600665284354585,
      "learning_rate": 1.25e-05,
      "loss": 1.6075,
      "step": 5
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 2.3704504908479493,
      "learning_rate": 2.5e-05,
      "loss": 1.4792,
      "step": 10
    },
    {
      "epoch": 0.19480519480519481,
      "grad_norm": 1.2779795738968422,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.4115,
      "step": 15
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 1.267787561996043,
      "learning_rate": 5e-05,
      "loss": 1.4018,
      "step": 20
    },
    {
      "epoch": 0.3246753246753247,
      "grad_norm": 0.9468473252185556,
      "learning_rate": 4.9979167589800175e-05,
      "loss": 1.3367,
      "step": 25
    },
    {
      "epoch": 0.38961038961038963,
      "grad_norm": 0.9893253972313399,
      "learning_rate": 4.991670893602868e-05,
      "loss": 1.3354,
      "step": 30
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 1.0881069970614872,
      "learning_rate": 4.9812739697734024e-05,
      "loss": 1.3007,
      "step": 35
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 1.0194980858529235,
      "learning_rate": 4.9667452402011365e-05,
      "loss": 1.2934,
      "step": 40
    },
    {
      "epoch": 0.5844155844155844,
      "grad_norm": 0.9223444885083613,
      "learning_rate": 4.94811160874866e-05,
      "loss": 1.3045,
      "step": 45
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 0.923065081102753,
      "learning_rate": 4.925407580611875e-05,
      "loss": 1.2753,
      "step": 50
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.0718722181581042,
      "learning_rate": 4.898675198424325e-05,
      "loss": 1.2756,
      "step": 55
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 1.052542976749598,
      "learning_rate": 4.867963964403906e-05,
      "loss": 1.2911,
      "step": 60
    },
    {
      "epoch": 0.8441558441558441,
      "grad_norm": 0.8128323214762116,
      "learning_rate": 4.833330748686162e-05,
      "loss": 1.2779,
      "step": 65
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.8676636174920215,
      "learning_rate": 4.794839684013882e-05,
      "loss": 1.2848,
      "step": 70
    },
    {
      "epoch": 0.974025974025974,
      "grad_norm": 1.042065531092415,
      "learning_rate": 4.7525620469780227e-05,
      "loss": 1.2567,
      "step": 75
    },
    {
      "epoch": 1.0389610389610389,
      "grad_norm": 0.972909624095194,
      "learning_rate": 4.7065761260298747e-05,
      "loss": 1.1721,
      "step": 80
    },
    {
      "epoch": 1.103896103896104,
      "grad_norm": 1.032654503817413,
      "learning_rate": 4.6569670765088703e-05,
      "loss": 1.0906,
      "step": 85
    },
    {
      "epoch": 1.1688311688311688,
      "grad_norm": 1.0351195035386815,
      "learning_rate": 4.603826762954497e-05,
      "loss": 1.1172,
      "step": 90
    },
    {
      "epoch": 1.2337662337662338,
      "grad_norm": 0.96162795934013,
      "learning_rate": 4.5472535889943214e-05,
      "loss": 1.0908,
      "step": 95
    },
    {
      "epoch": 1.2987012987012987,
      "grad_norm": 0.8351069694923322,
      "learning_rate": 4.487352315123119e-05,
      "loss": 1.1043,
      "step": 100
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 1.0009708201516048,
      "learning_rate": 4.424233864710562e-05,
      "loss": 1.0782,
      "step": 105
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.8512417675384085,
      "learning_rate": 4.3580151185966625e-05,
      "loss": 1.0982,
      "step": 110
    },
    {
      "epoch": 1.4935064935064934,
      "grad_norm": 1.0103004383513716,
      "learning_rate": 4.288818698655374e-05,
      "loss": 1.0942,
      "step": 115
    },
    {
      "epoch": 1.5584415584415585,
      "grad_norm": 0.8573478770737569,
      "learning_rate": 4.216772740727103e-05,
      "loss": 1.0897,
      "step": 120
    },
    {
      "epoch": 1.6233766233766234,
      "grad_norm": 0.781876249476916,
      "learning_rate": 4.142010657340632e-05,
      "loss": 1.0763,
      "step": 125
    },
    {
      "epoch": 1.6883116883116882,
      "grad_norm": 0.9579078710565259,
      "learning_rate": 4.064670890663829e-05,
      "loss": 1.1087,
      "step": 130
    },
    {
      "epoch": 1.7532467532467533,
      "grad_norm": 0.7939190983394226,
      "learning_rate": 3.9848966561406185e-05,
      "loss": 1.0746,
      "step": 135
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.0342389011696922,
      "learning_rate": 3.902835677288954e-05,
      "loss": 1.0677,
      "step": 140
    },
    {
      "epoch": 1.883116883116883,
      "grad_norm": 0.7587581170618278,
      "learning_rate": 3.818639912150864e-05,
      "loss": 1.0916,
      "step": 145
    },
    {
      "epoch": 1.948051948051948,
      "grad_norm": 0.7978087410640827,
      "learning_rate": 3.7324652719011446e-05,
      "loss": 1.0789,
      "step": 150
    },
    {
      "epoch": 2.012987012987013,
      "grad_norm": 1.1656631051781983,
      "learning_rate": 3.644471332135751e-05,
      "loss": 1.0629,
      "step": 155
    },
    {
      "epoch": 2.0779220779220777,
      "grad_norm": 1.0903515201097143,
      "learning_rate": 3.554821037374533e-05,
      "loss": 0.8856,
      "step": 160
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.7595990161921076,
      "learning_rate": 3.463680399325489e-05,
      "loss": 0.8855,
      "step": 165
    },
    {
      "epoch": 2.207792207792208,
      "grad_norm": 0.7774624026109681,
      "learning_rate": 3.371218189469306e-05,
      "loss": 0.8659,
      "step": 170
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.7461072755462708,
      "learning_rate": 3.277605626533422e-05,
      "loss": 0.8772,
      "step": 175
    },
    {
      "epoch": 2.3376623376623376,
      "grad_norm": 0.7432368434791046,
      "learning_rate": 3.183016059434367e-05,
      "loss": 0.8525,
      "step": 180
    },
    {
      "epoch": 2.4025974025974026,
      "grad_norm": 0.7590366429814798,
      "learning_rate": 3.0876246462754685e-05,
      "loss": 0.8742,
      "step": 185
    },
    {
      "epoch": 2.4675324675324677,
      "grad_norm": 0.7247155849317677,
      "learning_rate": 2.9916080299943672e-05,
      "loss": 0.9026,
      "step": 190
    },
    {
      "epoch": 2.5324675324675323,
      "grad_norm": 0.7310534548444702,
      "learning_rate": 2.8951440112609623e-05,
      "loss": 0.8883,
      "step": 195
    },
    {
      "epoch": 2.5974025974025974,
      "grad_norm": 0.7129005263727524,
      "learning_rate": 2.7984112192315004e-05,
      "loss": 0.8736,
      "step": 200
    },
    {
      "epoch": 2.6623376623376624,
      "grad_norm": 0.7437690616597665,
      "learning_rate": 2.7015887807685002e-05,
      "loss": 0.8981,
      "step": 205
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.7385255276801924,
      "learning_rate": 2.604855988739039e-05,
      "loss": 0.8895,
      "step": 210
    },
    {
      "epoch": 2.792207792207792,
      "grad_norm": 0.7144722424573203,
      "learning_rate": 2.5083919700056337e-05,
      "loss": 0.8744,
      "step": 215
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.7010146967901848,
      "learning_rate": 2.412375353724532e-05,
      "loss": 0.896,
      "step": 220
    },
    {
      "epoch": 2.9220779220779223,
      "grad_norm": 0.7504002323519033,
      "learning_rate": 2.316983940565633e-05,
      "loss": 0.8868,
      "step": 225
    },
    {
      "epoch": 2.987012987012987,
      "grad_norm": 0.7865383039242797,
      "learning_rate": 2.2223943734665787e-05,
      "loss": 0.8745,
      "step": 230
    },
    {
      "epoch": 3.051948051948052,
      "grad_norm": 1.0159335857839107,
      "learning_rate": 2.128781810530695e-05,
      "loss": 0.7511,
      "step": 235
    },
    {
      "epoch": 3.116883116883117,
      "grad_norm": 1.2002393858292175,
      "learning_rate": 2.0363196006745117e-05,
      "loss": 0.6809,
      "step": 240
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 0.7878609155092301,
      "learning_rate": 1.9451789626254672e-05,
      "loss": 0.6976,
      "step": 245
    },
    {
      "epoch": 3.2467532467532467,
      "grad_norm": 0.8016037192685418,
      "learning_rate": 1.8555286678642496e-05,
      "loss": 0.6747,
      "step": 250
    },
    {
      "epoch": 3.311688311688312,
      "grad_norm": 0.7587512144299318,
      "learning_rate": 1.7675347280988562e-05,
      "loss": 0.6964,
      "step": 255
    },
    {
      "epoch": 3.3766233766233764,
      "grad_norm": 0.7356037246911953,
      "learning_rate": 1.6813600878491376e-05,
      "loss": 0.6865,
      "step": 260
    },
    {
      "epoch": 3.4415584415584415,
      "grad_norm": 0.7631434364636613,
      "learning_rate": 1.597164322711047e-05,
      "loss": 0.6909,
      "step": 265
    },
    {
      "epoch": 3.5064935064935066,
      "grad_norm": 0.7131404046904652,
      "learning_rate": 1.5151033438593826e-05,
      "loss": 0.6934,
      "step": 270
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 0.711551265262125,
      "learning_rate": 1.4353291093361709e-05,
      "loss": 0.6973,
      "step": 275
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.705346898473505,
      "learning_rate": 1.3579893426593681e-05,
      "loss": 0.68,
      "step": 280
    },
    {
      "epoch": 3.7012987012987013,
      "grad_norm": 0.7118443145611075,
      "learning_rate": 1.2832272592728966e-05,
      "loss": 0.6904,
      "step": 285
    },
    {
      "epoch": 3.7662337662337664,
      "grad_norm": 0.7427739908839855,
      "learning_rate": 1.211181301344627e-05,
      "loss": 0.6793,
      "step": 290
    },
    {
      "epoch": 3.8311688311688314,
      "grad_norm": 0.6999298394629496,
      "learning_rate": 1.141984881403338e-05,
      "loss": 0.6876,
      "step": 295
    },
    {
      "epoch": 3.896103896103896,
      "grad_norm": 0.7120263608160156,
      "learning_rate": 1.0757661352894394e-05,
      "loss": 0.6893,
      "step": 300
    },
    {
      "epoch": 3.961038961038961,
      "grad_norm": 0.7144317661772965,
      "learning_rate": 1.0126476848768805e-05,
      "loss": 0.6789,
      "step": 305
    },
    {
      "epoch": 4.025974025974026,
      "grad_norm": 1.063865329311315,
      "learning_rate": 9.527464110056795e-06,
      "loss": 0.6269,
      "step": 310
    },
    {
      "epoch": 4.090909090909091,
      "grad_norm": 1.2451272279185113,
      "learning_rate": 8.961732370455032e-06,
      "loss": 0.5587,
      "step": 315
    },
    {
      "epoch": 4.1558441558441555,
      "grad_norm": 0.8874131926210624,
      "learning_rate": 8.430329234911305e-06,
      "loss": 0.5358,
      "step": 320
    },
    {
      "epoch": 4.220779220779221,
      "grad_norm": 0.8464865813880585,
      "learning_rate": 7.934238739701252e-06,
      "loss": 0.5414,
      "step": 325
    },
    {
      "epoch": 4.285714285714286,
      "grad_norm": 0.8425143948713799,
      "learning_rate": 7.4743795302197754e-06,
      "loss": 0.5494,
      "step": 330
    },
    {
      "epoch": 4.35064935064935,
      "grad_norm": 0.7956269077359945,
      "learning_rate": 7.051603159861185e-06,
      "loss": 0.5434,
      "step": 335
    },
    {
      "epoch": 4.415584415584416,
      "grad_norm": 0.7869754406789251,
      "learning_rate": 6.66669251313838e-06,
      "loss": 0.5545,
      "step": 340
    },
    {
      "epoch": 4.48051948051948,
      "grad_norm": 0.7360290448864131,
      "learning_rate": 6.320360355960941e-06,
      "loss": 0.5292,
      "step": 345
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.7623311010292727,
      "learning_rate": 6.013248015756759e-06,
      "loss": 0.547,
      "step": 350
    },
    {
      "epoch": 4.6103896103896105,
      "grad_norm": 0.7371275230206066,
      "learning_rate": 5.745924193881257e-06,
      "loss": 0.5501,
      "step": 355
    },
    {
      "epoch": 4.675324675324675,
      "grad_norm": 0.7480895176553981,
      "learning_rate": 5.518883912513413e-06,
      "loss": 0.5357,
      "step": 360
    },
    {
      "epoch": 4.740259740259741,
      "grad_norm": 0.7362818934957748,
      "learning_rate": 5.332547597988636e-06,
      "loss": 0.5451,
      "step": 365
    },
    {
      "epoch": 4.805194805194805,
      "grad_norm": 0.7678966619355423,
      "learning_rate": 5.1872603022659765e-06,
      "loss": 0.5297,
      "step": 370
    },
    {
      "epoch": 4.87012987012987,
      "grad_norm": 0.7535710804010259,
      "learning_rate": 5.083291063971324e-06,
      "loss": 0.5356,
      "step": 375
    },
    {
      "epoch": 4.935064935064935,
      "grad_norm": 0.7578922717450597,
      "learning_rate": 5.020832410199826e-06,
      "loss": 0.5347,
      "step": 380
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.7276287792812202,
      "learning_rate": 5e-06,
      "loss": 0.5505,
      "step": 385
    },
    {
      "epoch": 5.0,
      "step": 385,
      "total_flos": 43871077662720.0,
      "train_loss": 0.9090226414915803,
      "train_runtime": 2127.6426,
      "train_samples_per_second": 23.091,
      "train_steps_per_second": 0.181
    }
  ],
  "logging_steps": 5,
  "max_steps": 385,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 43871077662720.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}