{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002351696160856017,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00023516961608560175,
      "grad_norm": 0.005456574726849794,
      "learning_rate": 2e-05,
      "loss": 11.9364,
      "step": 1
    },
    {
      "epoch": 0.00023516961608560175,
      "eval_loss": 11.932561874389648,
      "eval_runtime": 26.0208,
      "eval_samples_per_second": 68.83,
      "eval_steps_per_second": 34.434,
      "step": 1
    },
    {
      "epoch": 0.0004703392321712035,
      "grad_norm": 0.005364065058529377,
      "learning_rate": 4e-05,
      "loss": 11.9332,
      "step": 2
    },
    {
      "epoch": 0.0007055088482568053,
      "grad_norm": 0.003814379684627056,
      "learning_rate": 6e-05,
      "loss": 11.9335,
      "step": 3
    },
    {
      "epoch": 0.0007055088482568053,
      "eval_loss": 11.932559967041016,
      "eval_runtime": 25.9813,
      "eval_samples_per_second": 68.934,
      "eval_steps_per_second": 34.486,
      "step": 3
    },
    {
      "epoch": 0.000940678464342407,
      "grad_norm": 0.007926777936518192,
      "learning_rate": 8e-05,
      "loss": 11.9325,
      "step": 4
    },
    {
      "epoch": 0.0011758480804280086,
      "grad_norm": 0.005247725639492273,
      "learning_rate": 0.0001,
      "loss": 11.9293,
      "step": 5
    },
    {
      "epoch": 0.0014110176965136105,
      "grad_norm": 0.006237534340471029,
      "learning_rate": 0.00012,
      "loss": 11.936,
      "step": 6
    },
    {
      "epoch": 0.0014110176965136105,
      "eval_loss": 11.932547569274902,
      "eval_runtime": 26.1045,
      "eval_samples_per_second": 68.609,
      "eval_steps_per_second": 34.324,
      "step": 6
    },
    {
      "epoch": 0.0016461873125992123,
      "grad_norm": 0.0062783206813037395,
      "learning_rate": 0.00014,
      "loss": 11.9318,
      "step": 7
    },
    {
      "epoch": 0.001881356928684814,
      "grad_norm": 0.005060715135186911,
      "learning_rate": 0.00016,
      "loss": 11.9324,
      "step": 8
    },
    {
      "epoch": 0.0021165265447704155,
      "grad_norm": 0.00466363737359643,
      "learning_rate": 0.00018,
      "loss": 11.9289,
      "step": 9
    },
    {
      "epoch": 0.0021165265447704155,
      "eval_loss": 11.93252944946289,
      "eval_runtime": 26.0435,
      "eval_samples_per_second": 68.77,
      "eval_steps_per_second": 34.404,
      "step": 9
    },
    {
      "epoch": 0.002351696160856017,
      "grad_norm": 0.004752365406602621,
      "learning_rate": 0.0002,
      "loss": 11.9335,
      "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": 2126905344.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}