{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013392259274139548,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00026784518548279097,
      "eval_loss": 2.3582730293273926,
      "eval_runtime": 320.6997,
      "eval_samples_per_second": 19.607,
      "eval_steps_per_second": 2.451,
      "step": 1
    },
    {
      "epoch": 0.0008035355564483728,
      "grad_norm": 1.0472233295440674,
      "learning_rate": 3e-05,
      "loss": 2.3004,
      "step": 3
    },
    {
      "epoch": 0.0013392259274139548,
      "eval_loss": 2.1918420791625977,
      "eval_runtime": 321.9934,
      "eval_samples_per_second": 19.528,
      "eval_steps_per_second": 2.441,
      "step": 5
    },
    {
      "epoch": 0.0016070711128967456,
      "grad_norm": 0.8402730226516724,
      "learning_rate": 6e-05,
      "loss": 2.3754,
      "step": 6
    },
    {
      "epoch": 0.0024106066693451184,
      "grad_norm": 1.0472428798675537,
      "learning_rate": 9e-05,
      "loss": 1.9354,
      "step": 9
    },
    {
      "epoch": 0.0026784518548279095,
      "eval_loss": 1.8925467729568481,
      "eval_runtime": 321.919,
      "eval_samples_per_second": 19.533,
      "eval_steps_per_second": 2.442,
      "step": 10
    },
    {
      "epoch": 0.0032141422257934912,
      "grad_norm": 0.7915742993354797,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.644,
      "step": 12
    },
    {
      "epoch": 0.004017677782241864,
      "grad_norm": 0.7121199369430542,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.6447,
      "step": 15
    },
    {
      "epoch": 0.004017677782241864,
      "eval_loss": 1.6764249801635742,
      "eval_runtime": 321.5271,
      "eval_samples_per_second": 19.557,
      "eval_steps_per_second": 2.445,
      "step": 15
    },
    {
      "epoch": 0.004821213338690237,
      "grad_norm": 0.5832473039627075,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5461,
      "step": 18
    },
    {
      "epoch": 0.005356903709655819,
      "eval_loss": 1.5581156015396118,
      "eval_runtime": 321.5365,
      "eval_samples_per_second": 19.556,
      "eval_steps_per_second": 2.445,
      "step": 20
    },
    {
      "epoch": 0.00562474889513861,
      "grad_norm": 0.6032427549362183,
      "learning_rate": 8.247240241650918e-05,
      "loss": 1.6216,
      "step": 21
    },
    {
      "epoch": 0.0064282844515869825,
      "grad_norm": 0.5976678729057312,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.4342,
      "step": 24
    },
    {
      "epoch": 0.006696129637069774,
      "eval_loss": 1.4929274320602417,
      "eval_runtime": 321.5431,
      "eval_samples_per_second": 19.556,
      "eval_steps_per_second": 2.444,
      "step": 25
    },
    {
      "epoch": 0.007231820008035355,
      "grad_norm": 0.6036542654037476,
      "learning_rate": 6.167226819279528e-05,
      "loss": 1.4325,
      "step": 27
    },
    {
      "epoch": 0.008035355564483728,
      "grad_norm": 0.5827629566192627,
      "learning_rate": 5e-05,
      "loss": 1.5006,
      "step": 30
    },
    {
      "epoch": 0.008035355564483728,
      "eval_loss": 1.4570372104644775,
      "eval_runtime": 321.4599,
      "eval_samples_per_second": 19.561,
      "eval_steps_per_second": 2.445,
      "step": 30
    },
    {
      "epoch": 0.008838891120932101,
      "grad_norm": 0.6208497285842896,
      "learning_rate": 3.832773180720475e-05,
      "loss": 1.3604,
      "step": 33
    },
    {
      "epoch": 0.009374581491897684,
      "eval_loss": 1.4289625883102417,
      "eval_runtime": 321.2482,
      "eval_samples_per_second": 19.574,
      "eval_steps_per_second": 2.447,
      "step": 35
    },
    {
      "epoch": 0.009642426677380474,
      "grad_norm": 0.524007260799408,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 1.3218,
      "step": 36
    },
    {
      "epoch": 0.010445962233828847,
      "grad_norm": 0.5135562419891357,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 1.1962,
      "step": 39
    },
    {
      "epoch": 0.010713807419311638,
      "eval_loss": 1.4158045053482056,
      "eval_runtime": 321.2325,
      "eval_samples_per_second": 19.575,
      "eval_steps_per_second": 2.447,
      "step": 40
    },
    {
      "epoch": 0.01124949779027722,
      "grad_norm": 0.45847946405410767,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.3842,
      "step": 42
    },
    {
      "epoch": 0.012053033346725592,
      "grad_norm": 0.3463503122329712,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.4242,
      "step": 45
    },
    {
      "epoch": 0.012053033346725592,
      "eval_loss": 1.4100161790847778,
      "eval_runtime": 321.5851,
      "eval_samples_per_second": 19.553,
      "eval_steps_per_second": 2.444,
      "step": 45
    },
    {
      "epoch": 0.012856568903173965,
      "grad_norm": 0.48882532119750977,
      "learning_rate": 6.15582970243117e-07,
      "loss": 1.5511,
      "step": 48
    },
    {
      "epoch": 0.013392259274139548,
      "eval_loss": 1.4089781045913696,
      "eval_runtime": 321.5462,
      "eval_samples_per_second": 19.556,
      "eval_steps_per_second": 2.444,
      "step": 50
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.35690071687168e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}