{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9934640522875817,
  "eval_steps": 50,
  "global_step": 171,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17429193899782136,
      "grad_norm": 2.7665748596191406,
      "learning_rate": 0.0001,
      "loss": 3.3243,
      "step": 10
    },
    {
      "epoch": 0.3485838779956427,
      "grad_norm": 1.1791448593139648,
      "learning_rate": 0.00019997891995035912,
      "loss": 2.5147,
      "step": 20
    },
    {
      "epoch": 0.5228758169934641,
      "grad_norm": 1.3799898624420166,
      "learning_rate": 0.00019746005004415005,
      "loss": 2.0865,
      "step": 30
    },
    {
      "epoch": 0.6971677559912854,
      "grad_norm": 1.4944865703582764,
      "learning_rate": 0.00019084652718195238,
      "loss": 1.944,
      "step": 40
    },
    {
      "epoch": 0.8714596949891068,
      "grad_norm": 1.5263450145721436,
      "learning_rate": 0.00018041620963415417,
      "loss": 1.9216,
      "step": 50
    },
    {
      "epoch": 0.8714596949891068,
      "eval_loss": 1.7768996953964233,
      "eval_runtime": 50.8532,
      "eval_samples_per_second": 4.228,
      "eval_steps_per_second": 2.124,
      "step": 50
    },
    {
      "epoch": 1.0522875816993464,
      "grad_norm": 1.539164662361145,
      "learning_rate": 0.00016660731316772505,
      "loss": 1.8589,
      "step": 60
    },
    {
      "epoch": 1.2265795206971677,
      "grad_norm": 1.8095414638519287,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.4705,
      "step": 70
    },
    {
      "epoch": 1.4008714596949892,
      "grad_norm": 1.8503429889678955,
      "learning_rate": 0.00013129200406321545,
      "loss": 1.4052,
      "step": 80
    },
    {
      "epoch": 1.5751633986928104,
      "grad_norm": 2.2654404640197754,
      "learning_rate": 0.00011126931665153212,
      "loss": 1.3128,
      "step": 90
    },
    {
      "epoch": 1.7494553376906317,
      "grad_norm": 1.9233298301696777,
      "learning_rate": 9.077316405366981e-05,
      "loss": 1.2697,
      "step": 100
    },
    {
      "epoch": 1.7494553376906317,
      "eval_loss": 1.5438789129257202,
      "eval_runtime": 50.7985,
      "eval_samples_per_second": 4.232,
      "eval_steps_per_second": 2.126,
      "step": 100
    },
    {
      "epoch": 1.9237472766884531,
      "grad_norm": 2.314152956008911,
      "learning_rate": 7.066466456151541e-05,
      "loss": 1.2664,
      "step": 110
    },
    {
      "epoch": 2.104575163398693,
      "grad_norm": 1.8632112741470337,
      "learning_rate": 5.178864974296511e-05,
      "loss": 1.2569,
      "step": 120
    },
    {
      "epoch": 2.2788671023965144,
      "grad_norm": 2.1466894149780273,
      "learning_rate": 3.493816997957582e-05,
      "loss": 0.9429,
      "step": 130
    },
    {
      "epoch": 2.4531590413943354,
      "grad_norm": 2.1183736324310303,
      "learning_rate": 2.0821175521134207e-05,
      "loss": 0.8929,
      "step": 140
    },
    {
      "epoch": 2.627450980392157,
      "grad_norm": 1.9306416511535645,
      "learning_rate": 1.0030772907835483e-05,
      "loss": 0.9717,
      "step": 150
    },
    {
      "epoch": 2.627450980392157,
      "eval_loss": 1.5016634464263916,
      "eval_runtime": 50.922,
      "eval_samples_per_second": 4.222,
      "eval_steps_per_second": 2.121,
      "step": 150
    },
    {
      "epoch": 2.8017429193899783,
      "grad_norm": 2.1572751998901367,
      "learning_rate": 3.0203063964990617e-06,
      "loss": 0.9743,
      "step": 160
    },
    {
      "epoch": 2.9760348583877994,
      "grad_norm": 2.2213950157165527,
      "learning_rate": 8.43113111936189e-08,
      "loss": 0.9647,
      "step": 170
    },
    {
      "epoch": 2.9934640522875817,
      "step": 171,
      "total_flos": 9432701878665216.0,
      "train_loss": 1.5491869268361589,
      "train_runtime": 3331.8453,
      "train_samples_per_second": 1.651,
      "train_steps_per_second": 0.051
    }
  ],
  "logging_steps": 10,
  "max_steps": 171,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9432701878665216.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}