{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 252,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11940298507462686,
      "grad_norm": 0.2085999995470047,
      "learning_rate": 3.461538461538462e-05,
      "loss": 0.5328742027282715,
      "step": 10
    },
    {
      "epoch": 0.23880597014925373,
      "grad_norm": 0.17245711386203766,
      "learning_rate": 7.307692307692307e-05,
      "loss": 0.28172030448913576,
      "step": 20
    },
    {
      "epoch": 0.3582089552238806,
      "grad_norm": 0.1451202780008316,
      "learning_rate": 9.995652871840006e-05,
      "loss": 0.22340788841247558,
      "step": 30
    },
    {
      "epoch": 0.47761194029850745,
      "grad_norm": 0.12613239884376526,
      "learning_rate": 9.918580696928205e-05,
      "loss": 0.19026432037353516,
      "step": 40
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.10020812600851059,
      "learning_rate": 9.746617916180905e-05,
      "loss": 0.1776690363883972,
      "step": 50
    },
    {
      "epoch": 0.7164179104477612,
      "grad_norm": 0.11177698522806168,
      "learning_rate": 9.483082082658983e-05,
      "loss": 0.16183719635009766,
      "step": 60
    },
    {
      "epoch": 0.835820895522388,
      "grad_norm": 0.11473167687654495,
      "learning_rate": 9.133057401836159e-05,
      "loss": 0.18729711771011354,
      "step": 70
    },
    {
      "epoch": 0.9552238805970149,
      "grad_norm": 0.09883058816194534,
      "learning_rate": 8.703296645714609e-05,
      "loss": 0.17510976791381835,
      "step": 80
    },
    {
      "epoch": 1.0716417910447762,
      "grad_norm": 0.09465258568525314,
      "learning_rate": 8.202090876498144e-05,
      "loss": 0.15757997035980226,
      "step": 90
    },
    {
      "epoch": 1.191044776119403,
      "grad_norm": 0.15254873037338257,
      "learning_rate": 7.639109493149537e-05,
      "loss": 0.14641659259796141,
      "step": 100
    },
    {
      "epoch": 1.191044776119403,
      "eval_loss": 0.1869809627532959,
      "eval_runtime": 13.646,
      "eval_samples_per_second": 1.099,
      "eval_steps_per_second": 0.586,
      "step": 100
    },
    {
      "epoch": 1.31044776119403,
      "grad_norm": 0.08413254469633102,
      "learning_rate": 7.02521368669762e-05,
      "loss": 0.11394469738006592,
      "step": 110
    },
    {
      "epoch": 1.4298507462686567,
      "grad_norm": 0.07326336950063705,
      "learning_rate": 6.372246903165446e-05,
      "loss": 0.11726579666137696,
      "step": 120
    },
    {
      "epoch": 1.5492537313432835,
      "grad_norm": 0.10139299929141998,
      "learning_rate": 5.692806356566095e-05,
      "loss": 0.12615565061569214,
      "step": 130
    },
    {
      "epoch": 1.6686567164179105,
      "grad_norm": 0.08335951715707779,
      "learning_rate": 5e-05,
      "loss": 0.11287055015563965,
      "step": 140
    },
    {
      "epoch": 1.7880597014925375,
      "grad_norm": 0.07054048031568527,
      "learning_rate": 4.307193643433907e-05,
      "loss": 0.10663604736328125,
      "step": 150
    },
    {
      "epoch": 1.9074626865671642,
      "grad_norm": 0.06786229461431503,
      "learning_rate": 3.627753096834555e-05,
      "loss": 0.107212233543396,
      "step": 160
    },
    {
      "epoch": 2.023880597014925,
      "grad_norm": 0.07071981579065323,
      "learning_rate": 2.9747863133023803e-05,
      "loss": 0.11782596111297608,
      "step": 170
    },
    {
      "epoch": 2.1432835820895524,
      "grad_norm": 0.09423048794269562,
      "learning_rate": 2.3608905068504637e-05,
      "loss": 0.0834022581577301,
      "step": 180
    },
    {
      "epoch": 2.262686567164179,
      "grad_norm": 0.09003670513629913,
      "learning_rate": 1.7979091235018565e-05,
      "loss": 0.08206533193588257,
      "step": 190
    },
    {
      "epoch": 2.382089552238806,
      "grad_norm": 0.09670283645391464,
      "learning_rate": 1.2967033542853917e-05,
      "loss": 0.08110529780387879,
      "step": 200
    },
    {
      "epoch": 2.382089552238806,
      "eval_loss": 0.1738630086183548,
      "eval_runtime": 13.5313,
      "eval_samples_per_second": 1.109,
      "eval_steps_per_second": 0.591,
      "step": 200
    },
    {
      "epoch": 2.5014925373134327,
      "grad_norm": 0.09121183305978775,
      "learning_rate": 8.669425981638413e-06,
      "loss": 0.08261927366256713,
      "step": 210
    },
    {
      "epoch": 2.62089552238806,
      "grad_norm": 0.09510096907615662,
      "learning_rate": 5.169179173410177e-06,
      "loss": 0.08233516216278076,
      "step": 220
    },
    {
      "epoch": 2.7402985074626867,
      "grad_norm": 0.07058050483465195,
      "learning_rate": 2.533820838190959e-06,
      "loss": 0.07825937271118164,
      "step": 230
    },
    {
      "epoch": 2.8597014925373134,
      "grad_norm": 0.09087616205215454,
      "learning_rate": 8.141930307179468e-07,
      "loss": 0.08194915056228638,
      "step": 240
    },
    {
      "epoch": 2.97910447761194,
      "grad_norm": 0.078521728515625,
      "learning_rate": 4.3471281599938295e-08,
      "loss": 0.08224834203720092,
      "step": 250
    },
    {
      "epoch": 3.0,
      "step": 252,
      "total_flos": 1.3584580095246336e+16,
      "train_loss": 0.14724678906892974,
      "train_runtime": 4599.332,
      "train_samples_per_second": 0.437,
      "train_steps_per_second": 0.055
    }
  ],
  "logging_steps": 10,
  "max_steps": 252,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.3584580095246336e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}