{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6802721088435374,
  "eval_steps": 30,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.045351473922902494,
      "grad_norm": 0.5955151915550232,
      "learning_rate": 0.00019962469712828614,
      "loss": 0.4111457824707031,
      "step": 10
    },
    {
      "epoch": 0.09070294784580499,
      "grad_norm": 0.5896233320236206,
      "learning_rate": 0.00019543482507085482,
      "loss": 0.35993859767913816,
      "step": 20
    },
    {
      "epoch": 0.1360544217687075,
      "grad_norm": 0.48774707317352295,
      "learning_rate": 0.00018678252666130013,
      "loss": 0.38935122489929197,
      "step": 30
    },
    {
      "epoch": 0.1360544217687075,
      "eval_loss": 0.5217297077178955,
      "eval_runtime": 2.0775,
      "eval_samples_per_second": 34.657,
      "eval_steps_per_second": 8.664,
      "step": 30
    },
    {
      "epoch": 0.18140589569160998,
      "grad_norm": 0.4432049095630646,
      "learning_rate": 0.00017407237375691392,
      "loss": 0.3316951274871826,
      "step": 40
    },
    {
      "epoch": 0.22675736961451248,
      "grad_norm": 0.40836411714553833,
      "learning_rate": 0.0001578986789811849,
      "loss": 0.31510772705078127,
      "step": 50
    },
    {
      "epoch": 0.272108843537415,
      "grad_norm": 0.3234673738479614,
      "learning_rate": 0.00013901770632605547,
      "loss": 0.3653845310211182,
      "step": 60
    },
    {
      "epoch": 0.272108843537415,
      "eval_loss": 0.5070984363555908,
      "eval_runtime": 2.0635,
      "eval_samples_per_second": 34.891,
      "eval_steps_per_second": 8.723,
      "step": 60
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 0.28090140223503113,
      "learning_rate": 0.00011831230908818563,
      "loss": 0.2907076835632324,
      "step": 70
    },
    {
      "epoch": 0.36281179138321995,
      "grad_norm": 0.33969420194625854,
      "learning_rate": 9.675064863002196e-05,
      "loss": 0.3239952325820923,
      "step": 80
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 0.3883151113986969,
      "learning_rate": 7.534092423052381e-05,
      "loss": 0.39945359230041505,
      "step": 90
    },
    {
      "epoch": 0.40816326530612246,
      "eval_loss": 0.49975717067718506,
      "eval_runtime": 2.0811,
      "eval_samples_per_second": 34.597,
      "eval_steps_per_second": 8.649,
      "step": 90
    },
    {
      "epoch": 0.45351473922902497,
      "grad_norm": 0.37783923745155334,
      "learning_rate": 5.5084230807412126e-05,
      "loss": 0.33277587890625,
      "step": 100
    },
    {
      "epoch": 0.4988662131519274,
      "grad_norm": 0.44748321175575256,
      "learning_rate": 3.6927748831453836e-05,
      "loss": 0.3025733470916748,
      "step": 110
    },
    {
      "epoch": 0.54421768707483,
      "grad_norm": 0.39024776220321655,
      "learning_rate": 2.1720455220364444e-05,
      "loss": 0.30908067226409913,
      "step": 120
    },
    {
      "epoch": 0.54421768707483,
      "eval_loss": 0.4952836036682129,
      "eval_runtime": 2.0845,
      "eval_samples_per_second": 34.541,
      "eval_steps_per_second": 8.635,
      "step": 120
    },
    {
      "epoch": 0.5895691609977324,
      "grad_norm": 0.39623892307281494,
      "learning_rate": 1.0173426121705576e-05,
      "loss": 0.3232832193374634,
      "step": 130
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.3841199576854706,
      "learning_rate": 2.826587782529444e-06,
      "loss": 0.3398961782455444,
      "step": 140
    },
    {
      "epoch": 0.6802721088435374,
      "grad_norm": 0.4336070120334625,
      "learning_rate": 2.347019815158724e-08,
      "loss": 0.34069836139678955,
      "step": 150
    },
    {
      "epoch": 0.6802721088435374,
      "eval_loss": 0.49498093128204346,
      "eval_runtime": 2.0755,
      "eval_samples_per_second": 34.691,
      "eval_steps_per_second": 8.673,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "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": 4361616479379456.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}