{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004647560030983733,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005163955589981926,
      "grad_norm": 1.1969610452651978,
      "learning_rate": 2e-05,
      "loss": 2.0729,
      "step": 1
    },
    {
      "epoch": 0.0005163955589981926,
      "eval_loss": 2.127951145172119,
      "eval_runtime": 169.1999,
      "eval_samples_per_second": 4.823,
      "eval_steps_per_second": 2.411,
      "step": 1
    },
    {
      "epoch": 0.0010327911179963851,
      "grad_norm": 0.7818438410758972,
      "learning_rate": 4e-05,
      "loss": 1.9541,
      "step": 2
    },
    {
      "epoch": 0.001549186676994578,
      "grad_norm": 0.9892038702964783,
      "learning_rate": 6e-05,
      "loss": 2.0531,
      "step": 3
    },
    {
      "epoch": 0.001549186676994578,
      "eval_loss": 2.1219890117645264,
      "eval_runtime": 167.4596,
      "eval_samples_per_second": 4.873,
      "eval_steps_per_second": 2.436,
      "step": 3
    },
    {
      "epoch": 0.0020655822359927703,
      "grad_norm": 1.085023283958435,
      "learning_rate": 8e-05,
      "loss": 2.1749,
      "step": 4
    },
    {
      "epoch": 0.002581977794990963,
      "grad_norm": 0.8974502086639404,
      "learning_rate": 0.0001,
      "loss": 2.0413,
      "step": 5
    },
    {
      "epoch": 0.003098373353989156,
      "grad_norm": 0.92463219165802,
      "learning_rate": 0.00012,
      "loss": 2.163,
      "step": 6
    },
    {
      "epoch": 0.003098373353989156,
      "eval_loss": 2.0635273456573486,
      "eval_runtime": 167.8774,
      "eval_samples_per_second": 4.861,
      "eval_steps_per_second": 2.43,
      "step": 6
    },
    {
      "epoch": 0.0036147689129873485,
      "grad_norm": 0.864437997341156,
      "learning_rate": 0.00014,
      "loss": 1.8826,
      "step": 7
    },
    {
      "epoch": 0.004131164471985541,
      "grad_norm": 1.1451501846313477,
      "learning_rate": 0.00016,
      "loss": 1.9161,
      "step": 8
    },
    {
      "epoch": 0.004647560030983733,
      "grad_norm": 1.3628495931625366,
      "learning_rate": 0.00018,
      "loss": 2.1014,
      "step": 9
    },
    {
      "epoch": 0.004647560030983733,
      "eval_loss": 1.9846328496932983,
      "eval_runtime": 167.0451,
      "eval_samples_per_second": 4.885,
      "eval_steps_per_second": 2.442,
      "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": 648858870743040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}