{
  "best_global_step": 150,
  "best_metric": 1.579034686088562,
  "best_model_checkpoint": "./models/t5-function-call-finetuned/checkpoint-150",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 64.5877914428711,
      "learning_rate": 0.0,
      "loss": 11.5084,
      "step": 1
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 3.7129411697387695,
      "learning_rate": 0.00019285714285714286,
      "loss": 7.3837,
      "step": 10
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.611706018447876,
      "eval_runtime": 5.5425,
      "eval_samples_per_second": 4.691,
      "eval_steps_per_second": 1.263,
      "step": 15
    },
    {
      "epoch": 1.3508771929824561,
      "grad_norm": 1.3122819662094116,
      "learning_rate": 0.00028897058823529407,
      "loss": 3.4848,
      "step": 20
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.599865198135376,
      "learning_rate": 0.0002669117647058823,
      "loss": 2.4457,
      "step": 30
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.8906079530715942,
      "eval_runtime": 4.8084,
      "eval_samples_per_second": 5.407,
      "eval_steps_per_second": 1.456,
      "step": 30
    },
    {
      "epoch": 2.7017543859649122,
      "grad_norm": 0.6903684139251709,
      "learning_rate": 0.0002448529411764706,
      "loss": 2.0901,
      "step": 40
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.754644513130188,
      "eval_runtime": 5.6357,
      "eval_samples_per_second": 4.613,
      "eval_steps_per_second": 1.242,
      "step": 45
    },
    {
      "epoch": 3.3508771929824563,
      "grad_norm": 0.39704379439353943,
      "learning_rate": 0.00022279411764705882,
      "loss": 1.9332,
      "step": 50
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.1494520902633667,
      "learning_rate": 0.00020073529411764702,
      "loss": 1.8694,
      "step": 60
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.6825193166732788,
      "eval_runtime": 5.5482,
      "eval_samples_per_second": 4.686,
      "eval_steps_per_second": 1.262,
      "step": 60
    },
    {
      "epoch": 4.701754385964913,
      "grad_norm": 0.37586721777915955,
      "learning_rate": 0.00017867647058823527,
      "loss": 1.8034,
      "step": 70
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.6308975219726562,
      "eval_runtime": 5.5437,
      "eval_samples_per_second": 4.69,
      "eval_steps_per_second": 1.263,
      "step": 75
    },
    {
      "epoch": 5.350877192982456,
      "grad_norm": 0.4155793786048889,
      "learning_rate": 0.00015661764705882352,
      "loss": 1.7805,
      "step": 80
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.2015619277954102,
      "learning_rate": 0.00013455882352941175,
      "loss": 1.7608,
      "step": 90
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.6127651929855347,
      "eval_runtime": 5.6533,
      "eval_samples_per_second": 4.599,
      "eval_steps_per_second": 1.238,
      "step": 90
    },
    {
      "epoch": 6.701754385964913,
      "grad_norm": 0.31167203187942505,
      "learning_rate": 0.0001125,
      "loss": 1.733,
      "step": 100
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.6017709970474243,
      "eval_runtime": 5.8448,
      "eval_samples_per_second": 4.448,
      "eval_steps_per_second": 1.198,
      "step": 105
    },
    {
      "epoch": 7.350877192982456,
      "grad_norm": 0.27257081866264343,
      "learning_rate": 9.044117647058822e-05,
      "loss": 1.7074,
      "step": 110
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.5978785157203674,
      "learning_rate": 6.838235294117646e-05,
      "loss": 1.7125,
      "step": 120
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.5895110368728638,
      "eval_runtime": 5.7894,
      "eval_samples_per_second": 4.491,
      "eval_steps_per_second": 1.209,
      "step": 120
    },
    {
      "epoch": 8.701754385964913,
      "grad_norm": 0.24433940649032593,
      "learning_rate": 4.63235294117647e-05,
      "loss": 1.6954,
      "step": 130
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.5858670473098755,
      "eval_runtime": 5.7488,
      "eval_samples_per_second": 4.523,
      "eval_steps_per_second": 1.218,
      "step": 135
    },
    {
      "epoch": 9.350877192982455,
      "grad_norm": 0.28507718443870544,
      "learning_rate": 2.426470588235294e-05,
      "loss": 1.6935,
      "step": 140
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.2023290395736694,
      "learning_rate": 2.2058823529411763e-06,
      "loss": 1.7175,
      "step": 150
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.579034686088562,
      "eval_runtime": 5.9112,
      "eval_samples_per_second": 4.398,
      "eval_steps_per_second": 1.184,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 380648816640000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}