{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007658759706414211,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.509733007126901e-05,
      "grad_norm": 1.3498567342758179,
      "learning_rate": 2e-05,
      "loss": 2.3186,
      "step": 1
    },
    {
      "epoch": 8.509733007126901e-05,
      "eval_loss": 2.56070876121521,
      "eval_runtime": 243.497,
      "eval_samples_per_second": 20.321,
      "eval_steps_per_second": 10.16,
      "step": 1
    },
    {
      "epoch": 0.00017019466014253802,
      "grad_norm": 1.514957070350647,
      "learning_rate": 4e-05,
      "loss": 2.3577,
      "step": 2
    },
    {
      "epoch": 0.00025529199021380705,
      "grad_norm": 1.549290657043457,
      "learning_rate": 6e-05,
      "loss": 2.5595,
      "step": 3
    },
    {
      "epoch": 0.00025529199021380705,
      "eval_loss": 2.550555944442749,
      "eval_runtime": 242.0581,
      "eval_samples_per_second": 20.441,
      "eval_steps_per_second": 10.221,
      "step": 3
    },
    {
      "epoch": 0.00034038932028507605,
      "grad_norm": 1.6015673875808716,
      "learning_rate": 8e-05,
      "loss": 2.3968,
      "step": 4
    },
    {
      "epoch": 0.00042548665035634504,
      "grad_norm": 1.0087080001831055,
      "learning_rate": 0.0001,
      "loss": 1.9501,
      "step": 5
    },
    {
      "epoch": 0.0005105839804276141,
      "grad_norm": 1.1886836290359497,
      "learning_rate": 0.00012,
      "loss": 1.9399,
      "step": 6
    },
    {
      "epoch": 0.0005105839804276141,
      "eval_loss": 2.40423846244812,
      "eval_runtime": 241.8495,
      "eval_samples_per_second": 20.459,
      "eval_steps_per_second": 10.23,
      "step": 6
    },
    {
      "epoch": 0.0005956813104988831,
      "grad_norm": 2.069767713546753,
      "learning_rate": 0.00014,
      "loss": 2.3984,
      "step": 7
    },
    {
      "epoch": 0.0006807786405701521,
      "grad_norm": 1.9127330780029297,
      "learning_rate": 0.00016,
      "loss": 2.1522,
      "step": 8
    },
    {
      "epoch": 0.0007658759706414211,
      "grad_norm": 1.5159175395965576,
      "learning_rate": 0.00018,
      "loss": 1.9218,
      "step": 9
    },
    {
      "epoch": 0.0007658759706414211,
      "eval_loss": 1.8095495700836182,
      "eval_runtime": 242.5412,
      "eval_samples_per_second": 20.401,
      "eval_steps_per_second": 10.2,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2849584887889920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}