{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 1.825063705444336,
      "learning_rate": 0.00019998287471579036,
      "loss": 5.5411,
      "step": 25
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 3.653587579727173,
      "learning_rate": 0.0001991011762655891,
      "loss": 4.573,
      "step": 50
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 2.3803489208221436,
      "learning_rate": 0.00019689503031247648,
      "loss": 4.196,
      "step": 75
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 3.465578317642212,
      "learning_rate": 0.00019339392111293425,
      "loss": 4.0655,
      "step": 100
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 2.49119234085083,
      "learning_rate": 0.00018864463958823596,
      "loss": 3.9363,
      "step": 125
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 2.9633536338806152,
      "learning_rate": 0.00018271065798253688,
      "loss": 3.8517,
      "step": 150
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.420480728149414,
      "learning_rate": 0.00017567128158176953,
      "loss": 3.8467,
      "step": 175
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 3.6492512226104736,
      "learning_rate": 0.0001676205888302812,
      "loss": 3.7944,
      "step": 200
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 2.560971975326538,
      "learning_rate": 0.00015866617401012994,
      "loss": 3.7162,
      "step": 225
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 4.758842468261719,
      "learning_rate": 0.00014892770928662697,
      "loss": 3.663,
      "step": 250
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 2.1538898944854736,
      "learning_rate": 0.0001385353453378093,
      "loss": 3.7238,
      "step": 275
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 3.301409959793091,
      "learning_rate": 0.00012762797194278984,
      "loss": 3.6179,
      "step": 300
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 2.6162853240966797,
      "learning_rate": 0.00011635136177552391,
      "loss": 3.6827,
      "step": 325
    },
    {
      "epoch": 0.5,
      "grad_norm": 3.1532206535339355,
      "learning_rate": 0.00010485622221144484,
      "loss": 3.6769,
      "step": 350
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 2.3506250381469727,
      "learning_rate": 9.329618118379187e-05,
      "loss": 3.5509,
      "step": 375
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.5581483840942383,
      "learning_rate": 8.182573400785367e-05,
      "loss": 3.5702,
      "step": 400
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 2.2614691257476807,
      "learning_rate": 7.05981786129982e-05,
      "loss": 3.6212,
      "step": 425
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 3.9808149337768555,
      "learning_rate": 5.9763566777285786e-05,
      "loss": 3.4905,
      "step": 450
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 2.6091268062591553,
      "learning_rate": 4.946669874559301e-05,
      "loss": 3.4592,
      "step": 475
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 2.98620867729187,
      "learning_rate": 3.9845188032373426e-05,
      "loss": 3.5303,
      "step": 500
    },
    {
      "epoch": 0.75,
      "grad_norm": 2.4898364543914795,
      "learning_rate": 3.102762227218957e-05,
      "loss": 3.4434,
      "step": 525
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 3.7425637245178223,
      "learning_rate": 2.313184469751265e-05,
      "loss": 3.5997,
      "step": 550
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 2.489025115966797,
      "learning_rate": 1.6263379211149732e-05,
      "loss": 3.5159,
      "step": 575
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 3.4107491970062256,
      "learning_rate": 1.0514020101574972e-05,
      "loss": 3.4185,
      "step": 600
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 2.2987284660339355,
      "learning_rate": 5.960605249053386e-06,
      "loss": 3.4054,
      "step": 625
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 3.6648387908935547,
      "learning_rate": 2.663989218166274e-06,
      "loss": 3.4479,
      "step": 650
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 2.634359121322632,
      "learning_rate": 6.682299609450993e-07,
      "loss": 3.5669,
      "step": 675
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.3128480911254883,
      "learning_rate": 0.0,
      "loss": 3.4478,
      "step": 700
    }
  ],
  "logging_steps": 25,
  "max_steps": 700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 464643034251264.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}