{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9997490589711417,
  "eval_steps": 500,
  "global_step": 996,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.050188205771643665,
      "grad_norm": 2.3202156020973708,
      "learning_rate": 9.989427142584392e-06,
      "loss": 1.5003,
      "step": 50
    },
    {
      "epoch": 0.10037641154328733,
      "grad_norm": 2.314291595101664,
      "learning_rate": 9.870995413367397e-06,
      "loss": 1.3883,
      "step": 100
    },
    {
      "epoch": 0.15056461731493098,
      "grad_norm": 2.314931158603531,
      "learning_rate": 9.624050979896533e-06,
      "loss": 1.3754,
      "step": 150
    },
    {
      "epoch": 0.20075282308657466,
      "grad_norm": 2.152003211136021,
      "learning_rate": 9.255109039631998e-06,
      "loss": 1.3628,
      "step": 200
    },
    {
      "epoch": 0.25094102885821834,
      "grad_norm": 2.1047973694759157,
      "learning_rate": 8.773903481118611e-06,
      "loss": 1.3543,
      "step": 250
    },
    {
      "epoch": 0.30112923462986196,
      "grad_norm": 2.1025984809300318,
      "learning_rate": 8.193130072341872e-06,
      "loss": 1.3515,
      "step": 300
    },
    {
      "epoch": 0.35131744040150564,
      "grad_norm": 2.2036136599303076,
      "learning_rate": 7.528111505069428e-06,
      "loss": 1.3419,
      "step": 350
    },
    {
      "epoch": 0.4015056461731493,
      "grad_norm": 2.1361038466937563,
      "learning_rate": 6.796393132397829e-06,
      "loss": 1.3361,
      "step": 400
    },
    {
      "epoch": 0.451693851944793,
      "grad_norm": 2.1253080705715175,
      "learning_rate": 6.0172800652631706e-06,
      "loss": 1.3336,
      "step": 450
    },
    {
      "epoch": 0.5018820577164367,
      "grad_norm": 2.094902290851612,
      "learning_rate": 5.211327840815459e-06,
      "loss": 1.321,
      "step": 500
    },
    {
      "epoch": 0.5520702634880803,
      "grad_norm": 2.086008706466924,
      "learning_rate": 4.399800100481858e-06,
      "loss": 1.3173,
      "step": 550
    },
    {
      "epoch": 0.6022584692597239,
      "grad_norm": 2.084376290248031,
      "learning_rate": 3.6041075859356383e-06,
      "loss": 1.3044,
      "step": 600
    },
    {
      "epoch": 0.6524466750313677,
      "grad_norm": 2.1873617946017525,
      "learning_rate": 2.845243254082134e-06,
      "loss": 1.3029,
      "step": 650
    },
    {
      "epoch": 0.7026348808030113,
      "grad_norm": 2.1539300794808733,
      "learning_rate": 2.1432284145659104e-06,
      "loss": 1.2977,
      "step": 700
    },
    {
      "epoch": 0.7528230865746549,
      "grad_norm": 2.100942527337154,
      "learning_rate": 1.5165845024934366e-06,
      "loss": 1.3072,
      "step": 750
    },
    {
      "epoch": 0.8030112923462986,
      "grad_norm": 2.2004509246977477,
      "learning_rate": 9.81844422725109e-07,
      "loss": 1.3014,
      "step": 800
    },
    {
      "epoch": 0.8531994981179423,
      "grad_norm": 2.148051612184209,
      "learning_rate": 5.531163580638483e-07,
      "loss": 1.2948,
      "step": 850
    },
    {
      "epoch": 0.903387703889586,
      "grad_norm": 2.0857628452747248,
      "learning_rate": 2.417115494991107e-07,
      "loss": 1.2925,
      "step": 900
    },
    {
      "epoch": 0.9535759096612296,
      "grad_norm": 2.1477939821041936,
      "learning_rate": 5.584586887435739e-08,
      "loss": 1.2951,
      "step": 950
    },
    {
      "epoch": 0.9997490589711417,
      "step": 996,
      "total_flos": 3245135674474496.0,
      "train_loss": 1.3331998112690018,
      "train_runtime": 34717.8895,
      "train_samples_per_second": 7.345,
      "train_steps_per_second": 0.029
    }
  ],
  "logging_steps": 50,
  "max_steps": 996,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 420,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3245135674474496.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}