{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.19890601690701143,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000994530084535057,
      "eval_loss": 0.19087886810302734,
      "eval_runtime": 17.9988,
      "eval_samples_per_second": 23.557,
      "eval_steps_per_second": 11.779,
      "step": 1
    },
    {
      "epoch": 0.009945300845350571,
      "grad_norm": 0.09372030198574066,
      "learning_rate": 0.00019967573081342103,
      "loss": 0.4609,
      "step": 10
    },
    {
      "epoch": 0.019890601690701143,
      "grad_norm": 0.006174048408865929,
      "learning_rate": 0.0001970941817426052,
      "loss": 0.0019,
      "step": 20
    },
    {
      "epoch": 0.029835902536051714,
      "grad_norm": 0.015020099468529224,
      "learning_rate": 0.00019199794436588243,
      "loss": 0.0106,
      "step": 30
    },
    {
      "epoch": 0.039781203381402286,
      "grad_norm": 0.002900264458730817,
      "learning_rate": 0.0001845190085543795,
      "loss": 0.0104,
      "step": 40
    },
    {
      "epoch": 0.04972650422675286,
      "grad_norm": 0.09035145491361618,
      "learning_rate": 0.00017485107481711012,
      "loss": 0.0079,
      "step": 50
    },
    {
      "epoch": 0.04972650422675286,
      "eval_loss": 0.0004164431302342564,
      "eval_runtime": 16.9811,
      "eval_samples_per_second": 24.969,
      "eval_steps_per_second": 12.484,
      "step": 50
    },
    {
      "epoch": 0.05967180507210343,
      "grad_norm": 0.0004922051448374987,
      "learning_rate": 0.00016324453755953773,
      "loss": 0.0001,
      "step": 60
    },
    {
      "epoch": 0.069617105917454,
      "grad_norm": 0.0006716707139275968,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0029,
      "step": 70
    },
    {
      "epoch": 0.07956240676280457,
      "grad_norm": 0.0007786777568981051,
      "learning_rate": 0.00013546048870425356,
      "loss": 0.0056,
      "step": 80
    },
    {
      "epoch": 0.08950770760815514,
      "grad_norm": 0.0007724720053374767,
      "learning_rate": 0.00012000256937760445,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.09945300845350571,
      "grad_norm": 0.0005283428472466767,
      "learning_rate": 0.00010402659401094152,
      "loss": 0.0023,
      "step": 100
    },
    {
      "epoch": 0.09945300845350571,
      "eval_loss": 0.00019780758884735405,
      "eval_runtime": 17.0068,
      "eval_samples_per_second": 24.931,
      "eval_steps_per_second": 12.466,
      "step": 100
    },
    {
      "epoch": 0.10939830929885629,
      "grad_norm": 0.00031772072543390095,
      "learning_rate": 8.79463319744677e-05,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.11934361014420686,
      "grad_norm": 0.0003519990132190287,
      "learning_rate": 7.217825360835473e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.12928891098955744,
      "grad_norm": 0.00038776054861955345,
      "learning_rate": 5.713074385969457e-05,
      "loss": 0.0003,
      "step": 130
    },
    {
      "epoch": 0.139234211834908,
      "grad_norm": 0.0002530352503526956,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.14917951268025859,
      "grad_norm": 0.004385178443044424,
      "learning_rate": 3.072756464904006e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.14917951268025859,
      "eval_loss": 0.00019267982861492783,
      "eval_runtime": 16.9972,
      "eval_samples_per_second": 24.945,
      "eval_steps_per_second": 12.473,
      "step": 150
    },
    {
      "epoch": 0.15912481352560914,
      "grad_norm": 0.00029982332489453256,
      "learning_rate": 2.0055723659649904e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.16907011437095973,
      "grad_norm": 0.00021044349705334753,
      "learning_rate": 1.1454397434679021e-05,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.1790154152163103,
      "grad_norm": 0.006156627554446459,
      "learning_rate": 5.146355805285452e-06,
      "loss": 0.0039,
      "step": 180
    },
    {
      "epoch": 0.18896071606166087,
      "grad_norm": 0.00021411084162537009,
      "learning_rate": 1.2949737362087156e-06,
      "loss": 0.0021,
      "step": 190
    },
    {
      "epoch": 0.19890601690701143,
      "grad_norm": 0.000571880373172462,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.19890601690701143,
      "eval_loss": 0.00019206435536034405,
      "eval_runtime": 16.9819,
      "eval_samples_per_second": 24.968,
      "eval_steps_per_second": 12.484,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.494263021928448e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}