{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007778317938745746,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.778317938745747e-05,
      "grad_norm": 1.6674002408981323,
      "learning_rate": 2e-05,
      "loss": 3.5142,
      "step": 1
    },
    {
      "epoch": 7.778317938745747e-05,
      "eval_loss": 3.8527331352233887,
      "eval_runtime": 168.9182,
      "eval_samples_per_second": 32.051,
      "eval_steps_per_second": 16.026,
      "step": 1
    },
    {
      "epoch": 0.00015556635877491494,
      "grad_norm": 2.234628200531006,
      "learning_rate": 4e-05,
      "loss": 4.0158,
      "step": 2
    },
    {
      "epoch": 0.00023334953816237238,
      "grad_norm": 1.700862169265747,
      "learning_rate": 6e-05,
      "loss": 3.743,
      "step": 3
    },
    {
      "epoch": 0.00023334953816237238,
      "eval_loss": 3.836986541748047,
      "eval_runtime": 171.301,
      "eval_samples_per_second": 31.605,
      "eval_steps_per_second": 15.803,
      "step": 3
    },
    {
      "epoch": 0.00031113271754982987,
      "grad_norm": 2.095756769180298,
      "learning_rate": 8e-05,
      "loss": 3.978,
      "step": 4
    },
    {
      "epoch": 0.0003889158969372873,
      "grad_norm": 1.9288415908813477,
      "learning_rate": 0.0001,
      "loss": 3.3931,
      "step": 5
    },
    {
      "epoch": 0.00046669907632474475,
      "grad_norm": 2.284522294998169,
      "learning_rate": 0.00012,
      "loss": 3.3418,
      "step": 6
    },
    {
      "epoch": 0.00046669907632474475,
      "eval_loss": 3.489284038543701,
      "eval_runtime": 171.2405,
      "eval_samples_per_second": 31.616,
      "eval_steps_per_second": 15.808,
      "step": 6
    },
    {
      "epoch": 0.0005444822557122023,
      "grad_norm": 2.6873786449432373,
      "learning_rate": 0.00014,
      "loss": 3.4227,
      "step": 7
    },
    {
      "epoch": 0.0006222654350996597,
      "grad_norm": 2.7271342277526855,
      "learning_rate": 0.00016,
      "loss": 3.119,
      "step": 8
    },
    {
      "epoch": 0.0007000486144871172,
      "grad_norm": 3.3658626079559326,
      "learning_rate": 0.00018,
      "loss": 2.8291,
      "step": 9
    },
    {
      "epoch": 0.0007000486144871172,
      "eval_loss": 2.613818883895874,
      "eval_runtime": 168.5825,
      "eval_samples_per_second": 32.115,
      "eval_steps_per_second": 16.057,
      "step": 9
    },
    {
      "epoch": 0.0007778317938745746,
      "grad_norm": 2.8640873432159424,
      "learning_rate": 0.0002,
      "loss": 2.6556,
      "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": 1849564248145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}