{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.018867924528302,
  "eval_steps": 50,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07547169811320754,
      "grad_norm": 3.1360068321228027,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 2.355,
      "step": 1
    },
    {
      "epoch": 0.07547169811320754,
      "eval_loss": 2.6891250610351562,
      "eval_runtime": 2.0759,
      "eval_samples_per_second": 85.265,
      "eval_steps_per_second": 2.89,
      "step": 1
    },
    {
      "epoch": 0.1509433962264151,
      "grad_norm": 2.098900079727173,
      "learning_rate": 2.0200000000000003e-05,
      "loss": 2.5605,
      "step": 2
    },
    {
      "epoch": 0.22641509433962265,
      "grad_norm": 1.1525990962982178,
      "learning_rate": 3.0299999999999998e-05,
      "loss": 2.824,
      "step": 3
    },
    {
      "epoch": 0.3018867924528302,
      "grad_norm": 3.684565305709839,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 2.294,
      "step": 4
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 1.9269472360610962,
      "learning_rate": 5.05e-05,
      "loss": 2.2797,
      "step": 5
    },
    {
      "epoch": 0.4528301886792453,
      "grad_norm": 1.8367829322814941,
      "learning_rate": 6.0599999999999996e-05,
      "loss": 2.5625,
      "step": 6
    },
    {
      "epoch": 0.5283018867924528,
      "grad_norm": 1.4874486923217773,
      "learning_rate": 7.07e-05,
      "loss": 2.0548,
      "step": 7
    },
    {
      "epoch": 0.6037735849056604,
      "grad_norm": 0.9860514402389526,
      "learning_rate": 8.080000000000001e-05,
      "loss": 1.9967,
      "step": 8
    },
    {
      "epoch": 0.6792452830188679,
      "grad_norm": 0.8753951191902161,
      "learning_rate": 9.09e-05,
      "loss": 2.2281,
      "step": 9
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.651441216468811,
      "learning_rate": 0.000101,
      "loss": 1.9075,
      "step": 10
    },
    {
      "epoch": 0.8301886792452831,
      "grad_norm": 0.5145401954650879,
      "learning_rate": 9.763333333333334e-05,
      "loss": 1.8424,
      "step": 11
    },
    {
      "epoch": 0.9056603773584906,
      "grad_norm": 0.44174325466156006,
      "learning_rate": 9.426666666666668e-05,
      "loss": 2.0169,
      "step": 12
    },
    {
      "epoch": 0.9811320754716981,
      "grad_norm": 0.7373551726341248,
      "learning_rate": 9.09e-05,
      "loss": 2.3326,
      "step": 13
    },
    {
      "epoch": 1.0566037735849056,
      "grad_norm": 0.7130667567253113,
      "learning_rate": 8.753333333333334e-05,
      "loss": 3.2117,
      "step": 14
    },
    {
      "epoch": 1.1320754716981132,
      "grad_norm": 0.34584125876426697,
      "learning_rate": 8.416666666666668e-05,
      "loss": 1.8345,
      "step": 15
    },
    {
      "epoch": 1.2075471698113207,
      "grad_norm": 0.48549094796180725,
      "learning_rate": 8.080000000000001e-05,
      "loss": 2.2408,
      "step": 16
    },
    {
      "epoch": 1.2830188679245282,
      "grad_norm": 0.2894538342952728,
      "learning_rate": 7.743333333333334e-05,
      "loss": 1.5507,
      "step": 17
    },
    {
      "epoch": 1.3584905660377358,
      "grad_norm": 0.27959537506103516,
      "learning_rate": 7.406666666666666e-05,
      "loss": 1.8387,
      "step": 18
    },
    {
      "epoch": 1.4339622641509435,
      "grad_norm": 0.30999821424484253,
      "learning_rate": 7.07e-05,
      "loss": 2.0469,
      "step": 19
    },
    {
      "epoch": 1.509433962264151,
      "grad_norm": 0.19885101914405823,
      "learning_rate": 6.733333333333333e-05,
      "loss": 1.3801,
      "step": 20
    },
    {
      "epoch": 1.5849056603773586,
      "grad_norm": 0.3023035228252411,
      "learning_rate": 6.396666666666666e-05,
      "loss": 2.0329,
      "step": 21
    },
    {
      "epoch": 1.6603773584905661,
      "grad_norm": 0.30719155073165894,
      "learning_rate": 6.0599999999999996e-05,
      "loss": 1.9123,
      "step": 22
    },
    {
      "epoch": 1.7358490566037736,
      "grad_norm": 0.15654319524765015,
      "learning_rate": 5.723333333333333e-05,
      "loss": 0.6971,
      "step": 23
    },
    {
      "epoch": 1.8113207547169812,
      "grad_norm": 0.3758471608161926,
      "learning_rate": 5.3866666666666664e-05,
      "loss": 2.6505,
      "step": 24
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": 0.22325968742370605,
      "learning_rate": 5.05e-05,
      "loss": 1.787,
      "step": 25
    },
    {
      "epoch": 1.9622641509433962,
      "grad_norm": 0.45555931329727173,
      "learning_rate": 4.713333333333334e-05,
      "loss": 2.3078,
      "step": 26
    },
    {
      "epoch": 2.0377358490566038,
      "grad_norm": 0.42708733677864075,
      "learning_rate": 4.376666666666667e-05,
      "loss": 2.6856,
      "step": 27
    },
    {
      "epoch": 2.1132075471698113,
      "grad_norm": 0.2096722275018692,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 1.5786,
      "step": 28
    },
    {
      "epoch": 2.188679245283019,
      "grad_norm": 0.32146334648132324,
      "learning_rate": 3.703333333333333e-05,
      "loss": 2.0501,
      "step": 29
    },
    {
      "epoch": 2.2641509433962264,
      "grad_norm": 0.2135702222585678,
      "learning_rate": 3.366666666666667e-05,
      "loss": 1.3575,
      "step": 30
    },
    {
      "epoch": 2.339622641509434,
      "grad_norm": 0.23232293128967285,
      "learning_rate": 3.0299999999999998e-05,
      "loss": 1.9002,
      "step": 31
    },
    {
      "epoch": 2.4150943396226414,
      "grad_norm": 0.2730821967124939,
      "learning_rate": 2.6933333333333332e-05,
      "loss": 1.8303,
      "step": 32
    },
    {
      "epoch": 2.490566037735849,
      "grad_norm": 0.16554129123687744,
      "learning_rate": 2.356666666666667e-05,
      "loss": 0.8436,
      "step": 33
    },
    {
      "epoch": 2.5660377358490565,
      "grad_norm": 0.2987569272518158,
      "learning_rate": 2.0200000000000003e-05,
      "loss": 2.4058,
      "step": 34
    },
    {
      "epoch": 2.641509433962264,
      "grad_norm": 0.2475874274969101,
      "learning_rate": 1.6833333333333334e-05,
      "loss": 1.7728,
      "step": 35
    },
    {
      "epoch": 2.7169811320754715,
      "grad_norm": 0.17108680307865143,
      "learning_rate": 1.3466666666666666e-05,
      "loss": 1.04,
      "step": 36
    },
    {
      "epoch": 2.7924528301886795,
      "grad_norm": 0.29829472303390503,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 2.2372,
      "step": 37
    },
    {
      "epoch": 2.867924528301887,
      "grad_norm": 0.2018345445394516,
      "learning_rate": 6.733333333333333e-06,
      "loss": 1.7036,
      "step": 38
    },
    {
      "epoch": 2.9433962264150946,
      "grad_norm": 0.34594178199768066,
      "learning_rate": 3.3666666666666665e-06,
      "loss": 2.1008,
      "step": 39
    },
    {
      "epoch": 3.018867924528302,
      "grad_norm": 0.37364983558654785,
      "learning_rate": 0.0,
      "loss": 2.603,
      "step": 40
    }
  ],
  "logging_steps": 1,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.4824157963996365e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}