{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01192321449862883,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004769285799451532,
      "grad_norm": 0.425629585981369,
      "learning_rate": 2.5e-05,
      "loss": 1.5045,
      "step": 1
    },
    {
      "epoch": 0.0009538571598903064,
      "grad_norm": 0.5127414464950562,
      "learning_rate": 5e-05,
      "loss": 1.4964,
      "step": 2
    },
    {
      "epoch": 0.0014307857398354596,
      "grad_norm": 0.8226185441017151,
      "learning_rate": 4.994647308096509e-05,
      "loss": 1.6284,
      "step": 3
    },
    {
      "epoch": 0.0019077143197806128,
      "grad_norm": 0.7249281406402588,
      "learning_rate": 4.9786121534345265e-05,
      "loss": 1.5155,
      "step": 4
    },
    {
      "epoch": 0.002384642899725766,
      "grad_norm": 0.6889981627464294,
      "learning_rate": 4.951963201008076e-05,
      "loss": 1.3207,
      "step": 5
    },
    {
      "epoch": 0.002861571479670919,
      "grad_norm": 0.7409605383872986,
      "learning_rate": 4.914814565722671e-05,
      "loss": 1.5334,
      "step": 6
    },
    {
      "epoch": 0.0033385000596160724,
      "grad_norm": 0.8829396367073059,
      "learning_rate": 4.867325323737765e-05,
      "loss": 1.6189,
      "step": 7
    },
    {
      "epoch": 0.0038154286395612256,
      "grad_norm": 0.9240784049034119,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 1.2868,
      "step": 8
    },
    {
      "epoch": 0.004292357219506379,
      "grad_norm": 1.1313817501068115,
      "learning_rate": 4.742181853831721e-05,
      "loss": 1.7027,
      "step": 9
    },
    {
      "epoch": 0.004769285799451532,
      "grad_norm": 0.9213244318962097,
      "learning_rate": 4.665063509461097e-05,
      "loss": 1.2187,
      "step": 10
    },
    {
      "epoch": 0.005246214379396685,
      "grad_norm": 1.2456570863723755,
      "learning_rate": 4.5786740307563636e-05,
      "loss": 1.5233,
      "step": 11
    },
    {
      "epoch": 0.005723142959341838,
      "grad_norm": 1.2289069890975952,
      "learning_rate": 4.4833833507280884e-05,
      "loss": 1.4216,
      "step": 12
    },
    {
      "epoch": 0.0062000715392869915,
      "grad_norm": 1.204435110092163,
      "learning_rate": 4.379599518697444e-05,
      "loss": 1.4082,
      "step": 13
    },
    {
      "epoch": 0.006677000119232145,
      "grad_norm": 1.4659150838851929,
      "learning_rate": 4.267766952966369e-05,
      "loss": 1.3687,
      "step": 14
    },
    {
      "epoch": 0.007153928699177298,
      "grad_norm": 1.2851946353912354,
      "learning_rate": 4.148364537750172e-05,
      "loss": 1.0532,
      "step": 15
    },
    {
      "epoch": 0.007630857279122451,
      "grad_norm": 1.2946377992630005,
      "learning_rate": 4.021903572521802e-05,
      "loss": 1.8505,
      "step": 16
    },
    {
      "epoch": 0.008107785859067605,
      "grad_norm": 1.4644392728805542,
      "learning_rate": 3.888925582549006e-05,
      "loss": 1.5249,
      "step": 17
    },
    {
      "epoch": 0.008584714439012759,
      "grad_norm": 1.303274393081665,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.2641,
      "step": 18
    },
    {
      "epoch": 0.009061643018957911,
      "grad_norm": 1.5627962350845337,
      "learning_rate": 3.6057217255475034e-05,
      "loss": 1.4673,
      "step": 19
    },
    {
      "epoch": 0.009538571598903063,
      "grad_norm": 2.11969256401062,
      "learning_rate": 3.456708580912725e-05,
      "loss": 1.7425,
      "step": 20
    },
    {
      "epoch": 0.010015500178848218,
      "grad_norm": 1.8735617399215698,
      "learning_rate": 3.303598663257904e-05,
      "loss": 1.6553,
      "step": 21
    },
    {
      "epoch": 0.01049242875879337,
      "grad_norm": 2.941176176071167,
      "learning_rate": 3.147047612756302e-05,
      "loss": 2.1402,
      "step": 22
    },
    {
      "epoch": 0.010969357338738524,
      "grad_norm": 2.47955322265625,
      "learning_rate": 2.9877258050403212e-05,
      "loss": 1.5304,
      "step": 23
    },
    {
      "epoch": 0.011446285918683676,
      "grad_norm": 2.28279185295105,
      "learning_rate": 2.8263154805501297e-05,
      "loss": 1.7279,
      "step": 24
    },
    {
      "epoch": 0.01192321449862883,
      "grad_norm": 2.429161548614502,
      "learning_rate": 2.663507823075358e-05,
      "loss": 1.3317,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9023266530197504e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}