{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 148,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.033783783783783786,
      "grad_norm": 31.901745124039785,
      "learning_rate": 3.125e-05,
      "loss": 0.541,
      "step": 5
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 13.653650682209102,
      "learning_rate": 4.9977343997179584e-05,
      "loss": 0.685,
      "step": 10
    },
    {
      "epoch": 0.10135135135135136,
      "grad_norm": 6.695814046910074,
      "learning_rate": 4.97229876633906e-05,
      "loss": 0.5517,
      "step": 15
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 9.019348686103742,
      "learning_rate": 4.91891643656567e-05,
      "loss": 0.6,
      "step": 20
    },
    {
      "epoch": 0.16891891891891891,
      "grad_norm": 11.605485375911108,
      "learning_rate": 4.838258724167838e-05,
      "loss": 0.4496,
      "step": 25
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 3.265623806400331,
      "learning_rate": 4.731339946677661e-05,
      "loss": 0.3498,
      "step": 30
    },
    {
      "epoch": 0.23648648648648649,
      "grad_norm": 2.514181485694024,
      "learning_rate": 4.599504669757798e-05,
      "loss": 0.3176,
      "step": 35
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 2.2314102994695153,
      "learning_rate": 4.444410798508125e-05,
      "loss": 0.316,
      "step": 40
    },
    {
      "epoch": 0.30405405405405406,
      "grad_norm": 2.088879099787047,
      "learning_rate": 4.268008728347168e-05,
      "loss": 0.2625,
      "step": 45
    },
    {
      "epoch": 0.33783783783783783,
      "grad_norm": 2.5533655840080756,
      "learning_rate": 4.072516817658065e-05,
      "loss": 0.2568,
      "step": 50
    },
    {
      "epoch": 0.3716216216216216,
      "grad_norm": 1.8818068371173975,
      "learning_rate": 3.860393490644781e-05,
      "loss": 0.2943,
      "step": 55
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 2.10021137079353,
      "learning_rate": 3.634306321221328e-05,
      "loss": 0.2302,
      "step": 60
    },
    {
      "epoch": 0.4391891891891892,
      "grad_norm": 6.7894017770969874,
      "learning_rate": 3.397098486722039e-05,
      "loss": 0.2528,
      "step": 65
    },
    {
      "epoch": 0.47297297297297297,
      "grad_norm": 1.4680458694671086,
      "learning_rate": 3.1517530132969326e-05,
      "loss": 0.2323,
      "step": 70
    },
    {
      "epoch": 0.5067567567567568,
      "grad_norm": 2.2597597263228684,
      "learning_rate": 2.9013552626270894e-05,
      "loss": 0.268,
      "step": 75
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 1.3029591699374143,
      "learning_rate": 2.6490541317113427e-05,
      "loss": 0.2204,
      "step": 80
    },
    {
      "epoch": 0.5743243243243243,
      "grad_norm": 1.3879622094005373,
      "learning_rate": 2.3980224536594803e-05,
      "loss": 0.2324,
      "step": 85
    },
    {
      "epoch": 0.6081081081081081,
      "grad_norm": 1.9616136554142993,
      "learning_rate": 2.1514170974749814e-05,
      "loss": 0.2108,
      "step": 90
    },
    {
      "epoch": 0.6418918918918919,
      "grad_norm": 1.28503053544791,
      "learning_rate": 1.9123392685956238e-05,
      "loss": 0.2226,
      "step": 95
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 1.7365058283607635,
      "learning_rate": 1.6837955094357533e-05,
      "loss": 0.1812,
      "step": 100
    },
    {
      "epoch": 0.7094594594594594,
      "grad_norm": 1.4024460655941753,
      "learning_rate": 1.468659890370983e-05,
      "loss": 0.2198,
      "step": 105
    },
    {
      "epoch": 0.7432432432432432,
      "grad_norm": 1.6696419317520363,
      "learning_rate": 1.2696378666356468e-05,
      "loss": 0.1888,
      "step": 110
    },
    {
      "epoch": 0.777027027027027,
      "grad_norm": 1.1872751873854868,
      "learning_rate": 1.0892322556534839e-05,
      "loss": 0.162,
      "step": 115
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 1.4926247781952757,
      "learning_rate": 9.297117626563687e-06,
      "loss": 0.2288,
      "step": 120
    },
    {
      "epoch": 0.8445945945945946,
      "grad_norm": 1.2415630273207803,
      "learning_rate": 7.930824503996856e-06,
      "loss": 0.1909,
      "step": 125
    },
    {
      "epoch": 0.8783783783783784,
      "grad_norm": 1.2023085445773478,
      "learning_rate": 6.810625117592363e-06,
      "loss": 0.1806,
      "step": 130
    },
    {
      "epoch": 0.9121621621621622,
      "grad_norm": 1.4243483275853943,
      "learning_rate": 5.950606624589065e-06,
      "loss": 0.1621,
      "step": 135
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 0.9742887910332816,
      "learning_rate": 5.361584256530833e-06,
      "loss": 0.1855,
      "step": 140
    },
    {
      "epoch": 0.9797297297297297,
      "grad_norm": 0.8769764256105443,
      "learning_rate": 5.050965311454739e-06,
      "loss": 0.1646,
      "step": 145
    },
    {
      "epoch": 1.0,
      "step": 148,
      "total_flos": 103919835938816.0,
      "train_loss": 0.2840795581405227,
      "train_runtime": 2784.6561,
      "train_samples_per_second": 3.397,
      "train_steps_per_second": 0.053
    }
  ],
  "logging_steps": 5,
  "max_steps": 148,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 103919835938816.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}