{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003032749908069768,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.065499816139537e-05,
      "eval_loss": NaN,
      "eval_runtime": 21584.6915,
      "eval_samples_per_second": 2.716,
      "eval_steps_per_second": 2.716,
      "step": 1
    },
    {
      "epoch": 0.00030327499080697685,
      "grad_norm": 2.3457894325256348,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.3901,
      "step": 5
    },
    {
      "epoch": 0.0006065499816139537,
      "grad_norm": 3.1203553676605225,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.8744,
      "step": 10
    },
    {
      "epoch": 0.0009098249724209305,
      "grad_norm": 1.935280680656433,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.6605,
      "step": 15
    },
    {
      "epoch": 0.0012130999632279074,
      "grad_norm": 1.9517841339111328,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6743,
      "step": 20
    },
    {
      "epoch": 0.001516374954034884,
      "grad_norm": 1.675338625907898,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.6504,
      "step": 25
    },
    {
      "epoch": 0.001516374954034884,
      "eval_loss": NaN,
      "eval_runtime": 21488.9293,
      "eval_samples_per_second": 2.728,
      "eval_steps_per_second": 2.728,
      "step": 25
    },
    {
      "epoch": 0.001819649944841861,
      "grad_norm": 1.9589847326278687,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.6359,
      "step": 30
    },
    {
      "epoch": 0.002122924935648838,
      "grad_norm": 1.4695641994476318,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.6006,
      "step": 35
    },
    {
      "epoch": 0.002426199926455815,
      "grad_norm": 1.7299948930740356,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.6185,
      "step": 40
    },
    {
      "epoch": 0.0027294749172627917,
      "grad_norm": 1.8927239179611206,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.586,
      "step": 45
    },
    {
      "epoch": 0.003032749908069768,
      "grad_norm": 1.600250482559204,
      "learning_rate": 0.0,
      "loss": 1.4815,
      "step": 50
    },
    {
      "epoch": 0.003032749908069768,
      "eval_loss": NaN,
      "eval_runtime": 21453.8519,
      "eval_samples_per_second": 2.732,
      "eval_steps_per_second": 2.732,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.483774567120896e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}