{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5362229793889293,
  "eval_steps": 200,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08937049656482154,
      "grad_norm": 1.7896469831466675,
      "learning_rate": 5.9523809523809524e-05,
      "loss": 0.5113,
      "step": 200
    },
    {
      "epoch": 0.08937049656482154,
      "eval_loss": 0.2866540253162384,
      "eval_runtime": 106.9805,
      "eval_samples_per_second": 1.692,
      "eval_steps_per_second": 1.692,
      "step": 200
    },
    {
      "epoch": 0.1787409931296431,
      "grad_norm": 1.647935390472412,
      "learning_rate": 9.999141366451437e-05,
      "loss": 0.198,
      "step": 400
    },
    {
      "epoch": 0.1787409931296431,
      "eval_loss": 0.181967094540596,
      "eval_runtime": 106.8254,
      "eval_samples_per_second": 1.694,
      "eval_steps_per_second": 1.694,
      "step": 400
    },
    {
      "epoch": 0.26811148969446463,
      "grad_norm": 1.0844635963439941,
      "learning_rate": 9.98539650961911e-05,
      "loss": 0.1373,
      "step": 600
    },
    {
      "epoch": 0.26811148969446463,
      "eval_loss": 0.13569192588329315,
      "eval_runtime": 106.8311,
      "eval_samples_per_second": 1.694,
      "eval_steps_per_second": 1.694,
      "step": 600
    },
    {
      "epoch": 0.3574819862592862,
      "grad_norm": 1.2187799215316772,
      "learning_rate": 9.954934641715336e-05,
      "loss": 0.1143,
      "step": 800
    },
    {
      "epoch": 0.3574819862592862,
      "eval_loss": 0.11583366245031357,
      "eval_runtime": 106.7191,
      "eval_samples_per_second": 1.696,
      "eval_steps_per_second": 1.696,
      "step": 800
    },
    {
      "epoch": 0.44685248282410767,
      "grad_norm": 1.3064311742782593,
      "learning_rate": 9.907857907350287e-05,
      "loss": 0.104,
      "step": 1000
    },
    {
      "epoch": 0.44685248282410767,
      "eval_loss": 0.1101757362484932,
      "eval_runtime": 111.0182,
      "eval_samples_per_second": 1.63,
      "eval_steps_per_second": 1.63,
      "step": 1000
    },
    {
      "epoch": 0.5362229793889293,
      "grad_norm": 1.0463789701461792,
      "learning_rate": 9.844324164036011e-05,
      "loss": 0.1007,
      "step": 1200
    },
    {
      "epoch": 0.5362229793889293,
      "eval_loss": 0.10309936106204987,
      "eval_runtime": 110.4661,
      "eval_samples_per_second": 1.639,
      "eval_steps_per_second": 1.639,
      "step": 1200
    }
  ],
  "logging_steps": 200,
  "max_steps": 11185,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.271866477607834e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}