{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 297,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016863406408094434,
      "grad_norm": 38.5,
      "learning_rate": 8.888888888888888e-06,
      "loss": 2.3417264938354494,
      "step": 5
    },
    {
      "epoch": 0.03372681281618887,
      "grad_norm": 9.875,
      "learning_rate": 2e-05,
      "loss": 1.7059539794921874,
      "step": 10
    },
    {
      "epoch": 0.050590219224283306,
      "grad_norm": 9.875,
      "learning_rate": 1.9985129789397633e-05,
      "loss": 1.7476335525512696,
      "step": 15
    },
    {
      "epoch": 0.06745362563237774,
      "grad_norm": 6.78125,
      "learning_rate": 1.9940563382223196e-05,
      "loss": 1.5680081367492675,
      "step": 20
    },
    {
      "epoch": 0.08431703204047218,
      "grad_norm": 8.375,
      "learning_rate": 1.9866433320848793e-05,
      "loss": 1.347496223449707,
      "step": 25
    },
    {
      "epoch": 0.10118043844856661,
      "grad_norm": 8.5625,
      "learning_rate": 1.9762960071199334e-05,
      "loss": 1.2069475173950195,
      "step": 30
    },
    {
      "epoch": 0.11804384485666104,
      "grad_norm": 5.8125,
      "learning_rate": 1.963045136707763e-05,
      "loss": 1.324411678314209,
      "step": 35
    },
    {
      "epoch": 0.13490725126475547,
      "grad_norm": 5.90625,
      "learning_rate": 1.946930129495106e-05,
      "loss": 1.165403175354004,
      "step": 40
    },
    {
      "epoch": 0.15177065767284992,
      "grad_norm": 5.96875,
      "learning_rate": 1.9279989121921846e-05,
      "loss": 1.2257371902465821,
      "step": 45
    },
    {
      "epoch": 0.16863406408094436,
      "grad_norm": 9.4375,
      "learning_rate": 1.9063077870366504e-05,
      "loss": 1.234571933746338,
      "step": 50
    },
    {
      "epoch": 0.18549747048903878,
      "grad_norm": 6.75,
      "learning_rate": 1.881921264348355e-05,
      "loss": 1.3958836555480958,
      "step": 55
    },
    {
      "epoch": 0.20236087689713322,
      "grad_norm": 6.5625,
      "learning_rate": 1.854911870672947e-05,
      "loss": 1.0263965606689454,
      "step": 60
    },
    {
      "epoch": 0.21922428330522767,
      "grad_norm": 4.15625,
      "learning_rate": 1.8253599330848638e-05,
      "loss": 1.228264617919922,
      "step": 65
    },
    {
      "epoch": 0.23608768971332209,
      "grad_norm": 7.21875,
      "learning_rate": 1.7933533402912354e-05,
      "loss": 1.250452423095703,
      "step": 70
    },
    {
      "epoch": 0.25295109612141653,
      "grad_norm": 5.5,
      "learning_rate": 1.758987281247162e-05,
      "loss": 1.2329339027404784,
      "step": 75
    },
    {
      "epoch": 0.26981450252951095,
      "grad_norm": 7.5,
      "learning_rate": 1.7223639620597556e-05,
      "loss": 1.2469540596008302,
      "step": 80
    },
    {
      "epoch": 0.2866779089376054,
      "grad_norm": 6.84375,
      "learning_rate": 1.6835923020228714e-05,
      "loss": 1.0711227416992188,
      "step": 85
    },
    {
      "epoch": 0.30354131534569984,
      "grad_norm": 6.8125,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 1.6063650131225586,
      "step": 90
    },
    {
      "epoch": 0.32040472175379425,
      "grad_norm": 6.75,
      "learning_rate": 1.6000712399244813e-05,
      "loss": 1.1470824241638184,
      "step": 95
    },
    {
      "epoch": 0.3372681281618887,
      "grad_norm": 6.3125,
      "learning_rate": 1.5555702330196024e-05,
      "loss": 1.255699348449707,
      "step": 100
    },
    {
      "epoch": 0.35413153456998314,
      "grad_norm": 6.09375,
      "learning_rate": 1.509416936840842e-05,
      "loss": 1.0055023193359376,
      "step": 105
    },
    {
      "epoch": 0.37099494097807756,
      "grad_norm": 2.96875,
      "learning_rate": 1.4617486132350343e-05,
      "loss": 1.4475191116333008,
      "step": 110
    },
    {
      "epoch": 0.38785834738617203,
      "grad_norm": 6.4375,
      "learning_rate": 1.4127070298043949e-05,
      "loss": 1.1591588973999023,
      "step": 115
    },
    {
      "epoch": 0.40472175379426645,
      "grad_norm": 7.65625,
      "learning_rate": 1.3624380382837017e-05,
      "loss": 1.1827627182006837,
      "step": 120
    },
    {
      "epoch": 0.42158516020236086,
      "grad_norm": 7.90625,
      "learning_rate": 1.3110911407710909e-05,
      "loss": 1.4125149726867676,
      "step": 125
    },
    {
      "epoch": 0.43844856661045534,
      "grad_norm": 6.3125,
      "learning_rate": 1.2588190451025209e-05,
      "loss": 1.1916536331176757,
      "step": 130
    },
    {
      "epoch": 0.45531197301854975,
      "grad_norm": 7.5625,
      "learning_rate": 1.205777210692235e-05,
      "loss": 1.049894142150879,
      "step": 135
    },
    {
      "epoch": 0.47217537942664417,
      "grad_norm": 6.4375,
      "learning_rate": 1.1521233861899168e-05,
      "loss": 1.4272873878479004,
      "step": 140
    },
    {
      "epoch": 0.48903878583473864,
      "grad_norm": 7.71875,
      "learning_rate": 1.098017140329561e-05,
      "loss": 1.1360230445861816,
      "step": 145
    },
    {
      "epoch": 0.5059021922428331,
      "grad_norm": 6.78125,
      "learning_rate": 1.0436193873653362e-05,
      "loss": 1.2251985549926758,
      "step": 150
    },
    {
      "epoch": 0.5227655986509275,
      "grad_norm": 8.5,
      "learning_rate": 9.890919085058179e-06,
      "loss": 1.2744477272033692,
      "step": 155
    },
    {
      "epoch": 0.5396290050590219,
      "grad_norm": 7.34375,
      "learning_rate": 9.34596870769857e-06,
      "loss": 1.2714393615722657,
      "step": 160
    },
    {
      "epoch": 0.5564924114671164,
      "grad_norm": 5.15625,
      "learning_rate": 8.802963446950378e-06,
      "loss": 1.019619846343994,
      "step": 165
    },
    {
      "epoch": 0.5733558178752108,
      "grad_norm": 6.4375,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.9829767227172852,
      "step": 170
    },
    {
      "epoch": 0.5902192242833052,
      "grad_norm": 6.9375,
      "learning_rate": 7.72923736965627e-06,
      "loss": 1.5283356666564942,
      "step": 175
    },
    {
      "epoch": 0.6070826306913997,
      "grad_norm": 7.0,
      "learning_rate": 7.201709859690081e-06,
      "loss": 1.0275829315185547,
      "step": 180
    },
    {
      "epoch": 0.6239460370994941,
      "grad_norm": 3.703125,
      "learning_rate": 6.682504582466482e-06,
      "loss": 1.1475248336791992,
      "step": 185
    },
    {
      "epoch": 0.6408094435075885,
      "grad_norm": 10.125,
      "learning_rate": 6.173165676349103e-06,
      "loss": 1.0172494888305663,
      "step": 190
    },
    {
      "epoch": 0.657672849915683,
      "grad_norm": 8.0625,
      "learning_rate": 5.675207936698337e-06,
      "loss": 1.176294994354248,
      "step": 195
    },
    {
      "epoch": 0.6745362563237775,
      "grad_norm": 6.8125,
      "learning_rate": 5.190112310806126e-06,
      "loss": 1.2884156227111816,
      "step": 200
    },
    {
      "epoch": 0.6913996627318718,
      "grad_norm": 7.375,
      "learning_rate": 4.7193214934963204e-06,
      "loss": 1.2367602348327638,
      "step": 205
    },
    {
      "epoch": 0.7082630691399663,
      "grad_norm": 5.8125,
      "learning_rate": 4.264235636489542e-06,
      "loss": 1.2425697326660157,
      "step": 210
    },
    {
      "epoch": 0.7251264755480608,
      "grad_norm": 5.5625,
      "learning_rate": 3.826208184292952e-06,
      "loss": 1.0178656578063965,
      "step": 215
    },
    {
      "epoch": 0.7419898819561551,
      "grad_norm": 4.125,
      "learning_rate": 3.4065418489993118e-06,
      "loss": 1.4105095863342285,
      "step": 220
    },
    {
      "epoch": 0.7588532883642496,
      "grad_norm": 3.625,
      "learning_rate": 3.0064847359663284e-06,
      "loss": 1.2955214500427246,
      "step": 225
    },
    {
      "epoch": 0.7757166947723441,
      "grad_norm": 6.5625,
      "learning_rate": 2.6272266318987606e-06,
      "loss": 1.0158836364746093,
      "step": 230
    },
    {
      "epoch": 0.7925801011804384,
      "grad_norm": 5.8125,
      "learning_rate": 2.26989546637263e-06,
      "loss": 1.2233789443969727,
      "step": 235
    },
    {
      "epoch": 0.8094435075885329,
      "grad_norm": 5.0625,
      "learning_rate": 1.9355539573251737e-06,
      "loss": 1.1834559440612793,
      "step": 240
    },
    {
      "epoch": 0.8263069139966274,
      "grad_norm": 7.4375,
      "learning_rate": 1.6251964504869221e-06,
      "loss": 1.0230623245239259,
      "step": 245
    },
    {
      "epoch": 0.8431703204047217,
      "grad_norm": 5.21875,
      "learning_rate": 1.339745962155613e-06,
      "loss": 1.103525447845459,
      "step": 250
    },
    {
      "epoch": 0.8600337268128162,
      "grad_norm": 5.03125,
      "learning_rate": 1.0800514341068592e-06,
      "loss": 0.9862545013427735,
      "step": 255
    },
    {
      "epoch": 0.8768971332209107,
      "grad_norm": 3.734375,
      "learning_rate": 8.468852088055291e-07,
      "loss": 1.7211034774780274,
      "step": 260
    },
    {
      "epoch": 0.893760539629005,
      "grad_norm": 8.0625,
      "learning_rate": 6.409407324267448e-07,
      "loss": 1.0896631240844727,
      "step": 265
    },
    {
      "epoch": 0.9106239460370995,
      "grad_norm": 5.8125,
      "learning_rate": 4.628304925177318e-07,
      "loss": 1.114693832397461,
      "step": 270
    },
    {
      "epoch": 0.927487352445194,
      "grad_norm": 7.8125,
      "learning_rate": 3.1308419643406915e-07,
      "loss": 1.1860212326049804,
      "step": 275
    },
    {
      "epoch": 0.9443507588532883,
      "grad_norm": 6.84375,
      "learning_rate": 1.921471959676957e-07,
      "loss": 1.1702337265014648,
      "step": 280
    },
    {
      "epoch": 0.9612141652613828,
      "grad_norm": 6.46875,
      "learning_rate": 1.0037916285192129e-07,
      "loss": 1.0407076835632325,
      "step": 285
    },
    {
      "epoch": 0.9780775716694773,
      "grad_norm": 7.40625,
      "learning_rate": 3.805301908254455e-08,
      "loss": 1.326705265045166,
      "step": 290
    },
    {
      "epoch": 0.9949409780775716,
      "grad_norm": 5.09375,
      "learning_rate": 5.354125236343155e-09,
      "loss": 1.308372402191162,
      "step": 295
    },
    {
      "epoch": 1.0,
      "step": 297,
      "total_flos": 1.4163205452745114e+17,
      "train_loss": 1.2549793832631224,
      "train_runtime": 2346.2604,
      "train_samples_per_second": 0.505,
      "train_steps_per_second": 0.127
    }
  ],
  "logging_steps": 5,
  "max_steps": 297,
  "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": 1.4163205452745114e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}