{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07225433526011561,
  "eval_steps": 4,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002890173410404624,
      "grad_norm": 2.2103090286254883,
      "learning_rate": 1e-05,
      "loss": 3.9098,
      "step": 1
    },
    {
      "epoch": 0.002890173410404624,
      "eval_loss": 3.771548271179199,
      "eval_runtime": 9.8911,
      "eval_samples_per_second": 29.522,
      "eval_steps_per_second": 3.741,
      "step": 1
    },
    {
      "epoch": 0.005780346820809248,
      "grad_norm": 2.5352649688720703,
      "learning_rate": 2e-05,
      "loss": 3.8253,
      "step": 2
    },
    {
      "epoch": 0.008670520231213872,
      "grad_norm": 2.2427029609680176,
      "learning_rate": 3e-05,
      "loss": 3.4456,
      "step": 3
    },
    {
      "epoch": 0.011560693641618497,
      "grad_norm": 2.1146886348724365,
      "learning_rate": 4e-05,
      "loss": 3.6371,
      "step": 4
    },
    {
      "epoch": 0.011560693641618497,
      "eval_loss": 3.7544989585876465,
      "eval_runtime": 8.9352,
      "eval_samples_per_second": 32.68,
      "eval_steps_per_second": 4.141,
      "step": 4
    },
    {
      "epoch": 0.014450867052023121,
      "grad_norm": 2.17097806930542,
      "learning_rate": 5e-05,
      "loss": 3.3359,
      "step": 5
    },
    {
      "epoch": 0.017341040462427744,
      "grad_norm": 2.1906416416168213,
      "learning_rate": 6e-05,
      "loss": 3.718,
      "step": 6
    },
    {
      "epoch": 0.02023121387283237,
      "grad_norm": 2.4084205627441406,
      "learning_rate": 7e-05,
      "loss": 3.6621,
      "step": 7
    },
    {
      "epoch": 0.023121387283236993,
      "grad_norm": 2.3436765670776367,
      "learning_rate": 8e-05,
      "loss": 3.977,
      "step": 8
    },
    {
      "epoch": 0.023121387283236993,
      "eval_loss": 3.5902154445648193,
      "eval_runtime": 8.9348,
      "eval_samples_per_second": 32.681,
      "eval_steps_per_second": 4.141,
      "step": 8
    },
    {
      "epoch": 0.02601156069364162,
      "grad_norm": 2.534742593765259,
      "learning_rate": 9e-05,
      "loss": 3.7168,
      "step": 9
    },
    {
      "epoch": 0.028901734104046242,
      "grad_norm": 2.017110586166382,
      "learning_rate": 0.0001,
      "loss": 3.1598,
      "step": 10
    },
    {
      "epoch": 0.031791907514450865,
      "grad_norm": 2.1366755962371826,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.9458,
      "step": 11
    },
    {
      "epoch": 0.03468208092485549,
      "grad_norm": 2.3269901275634766,
      "learning_rate": 9.567727288213005e-05,
      "loss": 3.5619,
      "step": 12
    },
    {
      "epoch": 0.03468208092485549,
      "eval_loss": 3.323472023010254,
      "eval_runtime": 8.9385,
      "eval_samples_per_second": 32.668,
      "eval_steps_per_second": 4.139,
      "step": 12
    },
    {
      "epoch": 0.03757225433526012,
      "grad_norm": 2.2002439498901367,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.4248,
      "step": 13
    },
    {
      "epoch": 0.04046242774566474,
      "grad_norm": 2.392763376235962,
      "learning_rate": 8.345653031794292e-05,
      "loss": 3.6027,
      "step": 14
    },
    {
      "epoch": 0.04335260115606936,
      "grad_norm": 2.200824022293091,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.246,
      "step": 15
    },
    {
      "epoch": 0.046242774566473986,
      "grad_norm": 2.8445470333099365,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.0348,
      "step": 16
    },
    {
      "epoch": 0.046242774566473986,
      "eval_loss": 3.19449782371521,
      "eval_runtime": 8.9358,
      "eval_samples_per_second": 32.677,
      "eval_steps_per_second": 4.141,
      "step": 16
    },
    {
      "epoch": 0.049132947976878616,
      "grad_norm": 2.7648165225982666,
      "learning_rate": 5.522642316338268e-05,
      "loss": 3.1899,
      "step": 17
    },
    {
      "epoch": 0.05202312138728324,
      "grad_norm": 2.2773354053497314,
      "learning_rate": 4.477357683661734e-05,
      "loss": 3.1442,
      "step": 18
    },
    {
      "epoch": 0.05491329479768786,
      "grad_norm": 2.5679569244384766,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.357,
      "step": 19
    },
    {
      "epoch": 0.057803468208092484,
      "grad_norm": 2.5891201496124268,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.1364,
      "step": 20
    },
    {
      "epoch": 0.057803468208092484,
      "eval_loss": 3.129070997238159,
      "eval_runtime": 8.9393,
      "eval_samples_per_second": 32.665,
      "eval_steps_per_second": 4.139,
      "step": 20
    },
    {
      "epoch": 0.06069364161849711,
      "grad_norm": 2.3856167793273926,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.9119,
      "step": 21
    },
    {
      "epoch": 0.06358381502890173,
      "grad_norm": 2.422062397003174,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.9894,
      "step": 22
    },
    {
      "epoch": 0.06647398843930635,
      "grad_norm": 2.790384292602539,
      "learning_rate": 4.322727117869951e-06,
      "loss": 3.1587,
      "step": 23
    },
    {
      "epoch": 0.06936416184971098,
      "grad_norm": 2.8436360359191895,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 3.1716,
      "step": 24
    },
    {
      "epoch": 0.06936416184971098,
      "eval_loss": 3.1090469360351562,
      "eval_runtime": 8.938,
      "eval_samples_per_second": 32.669,
      "eval_steps_per_second": 4.14,
      "step": 24
    },
    {
      "epoch": 0.07225433526011561,
      "grad_norm": 2.192410707473755,
      "learning_rate": 0.0,
      "loss": 3.0326,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2419306423910400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}