{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.01,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025,
      "grad_norm": 0.5332708954811096,
      "learning_rate": 0.0005,
      "loss": 1.3185,
      "step": 25
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.36998245120048523,
      "learning_rate": 0.001,
      "loss": 0.3227,
      "step": 50
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.31179681420326233,
      "learning_rate": 0.0009736842105263158,
      "loss": 0.2727,
      "step": 75
    },
    {
      "epoch": 1.001,
      "grad_norm": 0.24960194528102875,
      "learning_rate": 0.0009473684210526315,
      "loss": 0.2695,
      "step": 100
    },
    {
      "epoch": 1.026,
      "grad_norm": 0.277804434299469,
      "learning_rate": 0.0009210526315789473,
      "loss": 0.2295,
      "step": 125
    },
    {
      "epoch": 1.051,
      "grad_norm": 0.3241264224052429,
      "learning_rate": 0.0008947368421052632,
      "loss": 0.222,
      "step": 150
    },
    {
      "epoch": 1.076,
      "grad_norm": 0.2752802073955536,
      "learning_rate": 0.000868421052631579,
      "loss": 0.2296,
      "step": 175
    },
    {
      "epoch": 2.002,
      "grad_norm": 0.2725565433502197,
      "learning_rate": 0.0008421052631578947,
      "loss": 0.2251,
      "step": 200
    },
    {
      "epoch": 2.027,
      "grad_norm": 0.32025495171546936,
      "learning_rate": 0.0008157894736842105,
      "loss": 0.1499,
      "step": 225
    },
    {
      "epoch": 2.052,
      "grad_norm": 0.33148202300071716,
      "learning_rate": 0.0007894736842105263,
      "loss": 0.1523,
      "step": 250
    },
    {
      "epoch": 2.077,
      "grad_norm": 0.36358487606048584,
      "learning_rate": 0.0007631578947368421,
      "loss": 0.1582,
      "step": 275
    },
    {
      "epoch": 3.003,
      "grad_norm": 0.23482877016067505,
      "learning_rate": 0.0007368421052631579,
      "loss": 0.1592,
      "step": 300
    },
    {
      "epoch": 3.028,
      "grad_norm": 0.2773413062095642,
      "learning_rate": 0.0007105263157894737,
      "loss": 0.0931,
      "step": 325
    },
    {
      "epoch": 3.053,
      "grad_norm": 0.43919506669044495,
      "learning_rate": 0.0006842105263157895,
      "loss": 0.0944,
      "step": 350
    },
    {
      "epoch": 3.078,
      "grad_norm": 0.2814411222934723,
      "learning_rate": 0.0006578947368421054,
      "loss": 0.1019,
      "step": 375
    },
    {
      "epoch": 4.004,
      "grad_norm": 0.2654748260974884,
      "learning_rate": 0.0006315789473684211,
      "loss": 0.0984,
      "step": 400
    },
    {
      "epoch": 4.029,
      "grad_norm": 0.2132512629032135,
      "learning_rate": 0.0006052631578947369,
      "loss": 0.0506,
      "step": 425
    },
    {
      "epoch": 4.054,
      "grad_norm": 0.2793805003166199,
      "learning_rate": 0.0005789473684210527,
      "loss": 0.0549,
      "step": 450
    },
    {
      "epoch": 4.079,
      "grad_norm": 0.2352992296218872,
      "learning_rate": 0.0005526315789473685,
      "loss": 0.0638,
      "step": 475
    },
    {
      "epoch": 5.005,
      "grad_norm": 0.2415677160024643,
      "learning_rate": 0.0005263157894736842,
      "loss": 0.0581,
      "step": 500
    },
    {
      "epoch": 5.005,
      "eval_loss": 1.3403475284576416,
      "eval_runtime": 415.9648,
      "eval_samples_per_second": 7.811,
      "eval_steps_per_second": 0.978,
      "step": 500
    },
    {
      "epoch": 5.03,
      "grad_norm": 0.22632592916488647,
      "learning_rate": 0.0005,
      "loss": 0.0332,
      "step": 525
    },
    {
      "epoch": 5.055,
      "grad_norm": 0.2028239220380783,
      "learning_rate": 0.00047368421052631577,
      "loss": 0.0331,
      "step": 550
    },
    {
      "epoch": 5.08,
      "grad_norm": 0.3129159212112427,
      "learning_rate": 0.0004473684210526316,
      "loss": 0.0368,
      "step": 575
    },
    {
      "epoch": 6.006,
      "grad_norm": 0.18915531039237976,
      "learning_rate": 0.00042105263157894734,
      "loss": 0.0343,
      "step": 600
    },
    {
      "epoch": 6.031,
      "grad_norm": 0.16215360164642334,
      "learning_rate": 0.00039473684210526315,
      "loss": 0.0217,
      "step": 625
    },
    {
      "epoch": 6.056,
      "grad_norm": 0.3027922213077545,
      "learning_rate": 0.00036842105263157896,
      "loss": 0.0216,
      "step": 650
    },
    {
      "epoch": 6.081,
      "grad_norm": 0.20284023880958557,
      "learning_rate": 0.00034210526315789477,
      "loss": 0.0217,
      "step": 675
    },
    {
      "epoch": 7.007,
      "grad_norm": 0.10826993733644485,
      "learning_rate": 0.00031578947368421053,
      "loss": 0.0182,
      "step": 700
    },
    {
      "epoch": 7.032,
      "grad_norm": 0.08263543248176575,
      "learning_rate": 0.00028947368421052634,
      "loss": 0.0129,
      "step": 725
    },
    {
      "epoch": 7.057,
      "grad_norm": 0.09080210328102112,
      "learning_rate": 0.0002631578947368421,
      "loss": 0.0122,
      "step": 750
    },
    {
      "epoch": 7.082,
      "grad_norm": 0.12056039273738861,
      "learning_rate": 0.00023684210526315788,
      "loss": 0.0135,
      "step": 775
    },
    {
      "epoch": 8.008,
      "grad_norm": 0.042966585606336594,
      "learning_rate": 0.00021052631578947367,
      "loss": 0.0117,
      "step": 800
    },
    {
      "epoch": 8.033,
      "grad_norm": 0.09803847968578339,
      "learning_rate": 0.00018421052631578948,
      "loss": 0.0097,
      "step": 825
    },
    {
      "epoch": 8.058,
      "grad_norm": 0.05925946682691574,
      "learning_rate": 0.00015789473684210527,
      "loss": 0.0098,
      "step": 850
    },
    {
      "epoch": 8.083,
      "grad_norm": 0.06515707820653915,
      "learning_rate": 0.00013157894736842105,
      "loss": 0.0091,
      "step": 875
    },
    {
      "epoch": 9.009,
      "grad_norm": 0.051406506448984146,
      "learning_rate": 0.00010526315789473683,
      "loss": 0.0086,
      "step": 900
    },
    {
      "epoch": 9.034,
      "grad_norm": 0.03954557701945305,
      "learning_rate": 7.894736842105263e-05,
      "loss": 0.0078,
      "step": 925
    },
    {
      "epoch": 9.059,
      "grad_norm": 0.05422484129667282,
      "learning_rate": 5.263157894736842e-05,
      "loss": 0.0076,
      "step": 950
    },
    {
      "epoch": 9.084,
      "grad_norm": 0.04248082637786865,
      "learning_rate": 2.631578947368421e-05,
      "loss": 0.0081,
      "step": 975
    },
    {
      "epoch": 10.01,
      "grad_norm": 0.04863487556576729,
      "learning_rate": 0.0,
      "loss": 0.0075,
      "step": 1000
    },
    {
      "epoch": 10.01,
      "eval_loss": 1.5216612815856934,
      "eval_runtime": 357.9658,
      "eval_samples_per_second": 9.076,
      "eval_steps_per_second": 1.137,
      "step": 1000
    },
    {
      "epoch": 10.01,
      "step": 1000,
      "total_flos": 9.3113310633984e+18,
      "train_loss": 0.11658428072929382,
      "train_runtime": 5497.3683,
      "train_samples_per_second": 5.821,
      "train_steps_per_second": 0.182
    }
  ],
  "logging_steps": 25,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.3113310633984e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}