{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 8.3125,
      "learning_rate": 7.051012699706591e-06,
      "loss": 2.5154,
      "step": 5
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 6.3125,
      "learning_rate": 1.586477857433983e-05,
      "loss": 2.3465,
      "step": 10
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 4.0,
      "learning_rate": 2.467854444897307e-05,
      "loss": 2.1292,
      "step": 15
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 2.75,
      "learning_rate": 3.349231032360631e-05,
      "loss": 1.8541,
      "step": 20
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 2.515625,
      "learning_rate": 4.230607619823955e-05,
      "loss": 1.7741,
      "step": 25
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 2.515625,
      "learning_rate": 5.1119842072872785e-05,
      "loss": 1.7354,
      "step": 30
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.296875,
      "learning_rate": 5.993360794750602e-05,
      "loss": 1.664,
      "step": 35
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.328125,
      "learning_rate": 6.168403800651126e-05,
      "loss": 1.7135,
      "step": 40
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 2.046875,
      "learning_rate": 6.163399784593084e-05,
      "loss": 1.6611,
      "step": 45
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 2.15625,
      "learning_rate": 6.154555366874739e-05,
      "loss": 1.6437,
      "step": 50
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 1.953125,
      "learning_rate": 6.141885268156532e-05,
      "loss": 1.6746,
      "step": 55
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 2.015625,
      "learning_rate": 6.125410576567379e-05,
      "loss": 1.6045,
      "step": 60
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 2.03125,
      "learning_rate": 6.105158712605556e-05,
      "loss": 1.644,
      "step": 65
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.109375,
      "learning_rate": 6.0811633834999905e-05,
      "loss": 1.6435,
      "step": 70
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 2.046875,
      "learning_rate": 6.053464527107897e-05,
      "loss": 1.6181,
      "step": 75
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.9765625,
      "learning_rate": 6.0221082454421646e-05,
      "loss": 1.6064,
      "step": 80
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 2.109375,
      "learning_rate": 5.987146727939099e-05,
      "loss": 1.6007,
      "step": 85
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 2.046875,
      "learning_rate": 5.9486381645942624e-05,
      "loss": 1.59,
      "step": 90
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 2.109375,
      "learning_rate": 5.906646649110966e-05,
      "loss": 1.586,
      "step": 95
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 2.015625,
      "learning_rate": 5.861242072222619e-05,
      "loss": 1.6351,
      "step": 100
    },
    {
      "epoch": 0.75,
      "grad_norm": 2.0625,
      "learning_rate": 5.8125000053665165e-05,
      "loss": 1.5527,
      "step": 105
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 2.078125,
      "learning_rate": 5.760501574902626e-05,
      "loss": 1.5661,
      "step": 110
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 2.0625,
      "learning_rate": 5.705333327086771e-05,
      "loss": 1.5729,
      "step": 115
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 2.015625,
      "learning_rate": 5.647087084022936e-05,
      "loss": 1.5569,
      "step": 120
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 2.03125,
      "learning_rate": 5.585859790834425e-05,
      "loss": 1.559,
      "step": 125
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 1.8984375,
      "learning_rate": 5.521753354308279e-05,
      "loss": 1.5467,
      "step": 130
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 1.9609375,
      "learning_rate": 5.454874473281487e-05,
      "loss": 1.5725,
      "step": 135
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.90625,
      "learning_rate": 5.385334461051297e-05,
      "loss": 1.5524,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.5491536855697632,
      "eval_runtime": 0.5725,
      "eval_samples_per_second": 8.734,
      "eval_steps_per_second": 8.734,
      "step": 140
    }
  ],
  "logging_steps": 5,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0739329642921984e+17,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}