{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006907269901571404,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006907269901571404,
      "grad_norm": 1.8049594163894653,
      "learning_rate": 2e-05,
      "loss": 7.4193,
      "step": 1
    },
    {
      "epoch": 0.0013814539803142809,
      "grad_norm": 3.2862348556518555,
      "learning_rate": 4e-05,
      "loss": 7.9571,
      "step": 2
    },
    {
      "epoch": 0.002072180970471421,
      "grad_norm": 2.4154772758483887,
      "learning_rate": 6e-05,
      "loss": 8.2516,
      "step": 3
    },
    {
      "epoch": 0.002072180970471421,
      "eval_loss": 2.1313059329986572,
      "eval_runtime": 36.0262,
      "eval_samples_per_second": 16.932,
      "eval_steps_per_second": 8.466,
      "step": 3
    },
    {
      "epoch": 0.0027629079606285617,
      "grad_norm": 3.3950014114379883,
      "learning_rate": 8e-05,
      "loss": 9.8304,
      "step": 4
    },
    {
      "epoch": 0.003453634950785702,
      "grad_norm": 2.5431864261627197,
      "learning_rate": 0.0001,
      "loss": 8.5692,
      "step": 5
    },
    {
      "epoch": 0.004144361940942842,
      "grad_norm": 2.90328311920166,
      "learning_rate": 0.00012,
      "loss": 7.4297,
      "step": 6
    },
    {
      "epoch": 0.004144361940942842,
      "eval_loss": 2.0895447731018066,
      "eval_runtime": 28.5832,
      "eval_samples_per_second": 21.341,
      "eval_steps_per_second": 10.671,
      "step": 6
    },
    {
      "epoch": 0.004835088931099983,
      "grad_norm": 1.7622004747390747,
      "learning_rate": 0.00014,
      "loss": 7.1486,
      "step": 7
    },
    {
      "epoch": 0.005525815921257123,
      "grad_norm": 2.0755527019500732,
      "learning_rate": 0.00016,
      "loss": 7.5505,
      "step": 8
    },
    {
      "epoch": 0.006216542911414264,
      "grad_norm": 2.1994283199310303,
      "learning_rate": 0.00018,
      "loss": 7.3104,
      "step": 9
    },
    {
      "epoch": 0.006216542911414264,
      "eval_loss": 1.961014747619629,
      "eval_runtime": 30.8871,
      "eval_samples_per_second": 19.749,
      "eval_steps_per_second": 9.875,
      "step": 9
    },
    {
      "epoch": 0.006907269901571404,
      "grad_norm": 2.109363317489624,
      "learning_rate": 0.0002,
      "loss": 6.8207,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1032697549946880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}