{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9976905311778291,
  "eval_steps": 500,
  "global_step": 243,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10264305876315115,
      "grad_norm": 0.47805914282798767,
      "learning_rate": 0.00018553191489361704,
      "loss": 1.2392,
      "step": 25
    },
    {
      "epoch": 0.2052861175263023,
      "grad_norm": 0.28673839569091797,
      "learning_rate": 0.00016425531914893618,
      "loss": 0.8265,
      "step": 50
    },
    {
      "epoch": 0.30792917628945343,
      "grad_norm": 0.268703818321228,
      "learning_rate": 0.00014297872340425532,
      "loss": 0.786,
      "step": 75
    },
    {
      "epoch": 0.4105722350526046,
      "grad_norm": 0.2763696014881134,
      "learning_rate": 0.00012170212765957448,
      "loss": 0.7836,
      "step": 100
    },
    {
      "epoch": 0.5132152938157557,
      "grad_norm": 0.30008208751678467,
      "learning_rate": 0.00010042553191489362,
      "loss": 0.7712,
      "step": 125
    },
    {
      "epoch": 0.6158583525789069,
      "grad_norm": 0.28837621212005615,
      "learning_rate": 7.914893617021277e-05,
      "loss": 0.7763,
      "step": 150
    },
    {
      "epoch": 0.718501411342058,
      "grad_norm": 0.28170982003211975,
      "learning_rate": 5.787234042553191e-05,
      "loss": 0.7512,
      "step": 175
    },
    {
      "epoch": 0.8211444701052092,
      "grad_norm": 0.298803448677063,
      "learning_rate": 3.6595744680851066e-05,
      "loss": 0.756,
      "step": 200
    },
    {
      "epoch": 0.9237875288683602,
      "grad_norm": 0.28528884053230286,
      "learning_rate": 1.5319148936170214e-05,
      "loss": 0.7626,
      "step": 225
    },
    {
      "epoch": 0.9976905311778291,
      "eval_loss": 0.7545520663261414,
      "eval_runtime": 432.6562,
      "eval_samples_per_second": 1.898,
      "eval_steps_per_second": 0.238,
      "step": 243
    }
  ],
  "logging_steps": 25,
  "max_steps": 243,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.549109544769618e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}