{
  "best_metric": 0.47801119089126587,
  "best_model_checkpoint": "../../experiments_checkpoints/MAdAiLab/google_bert/bert_base_uncased_twitter/checkpoint-100",
  "epoch": 0.7352941176470589,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "grad_norm": 2.030212163925171,
      "learning_rate": 1.950980392156863e-05,
      "loss": 0.6218,
      "step": 10
    },
    {
      "epoch": 0.15,
      "grad_norm": 2.344938278198242,
      "learning_rate": 1.9019607843137255e-05,
      "loss": 0.5741,
      "step": 20
    },
    {
      "epoch": 0.22,
      "grad_norm": 5.662298679351807,
      "learning_rate": 1.8529411764705884e-05,
      "loss": 0.4956,
      "step": 30
    },
    {
      "epoch": 0.29,
      "grad_norm": 2.6259591579437256,
      "learning_rate": 1.8039215686274513e-05,
      "loss": 0.4936,
      "step": 40
    },
    {
      "epoch": 0.37,
      "grad_norm": 3.3229475021362305,
      "learning_rate": 1.7549019607843138e-05,
      "loss": 0.4689,
      "step": 50
    },
    {
      "epoch": 0.37,
      "eval_accuracy": 0.7582720588235294,
      "eval_f1_macro": 0.7184904910459111,
      "eval_f1_micro": 0.7582720588235294,
      "eval_loss": 0.48763757944107056,
      "eval_runtime": 1.0259,
      "eval_samples_per_second": 1060.508,
      "eval_steps_per_second": 16.57,
      "step": 50
    },
    {
      "epoch": 0.44,
      "grad_norm": 2.529259443283081,
      "learning_rate": 1.7058823529411767e-05,
      "loss": 0.4913,
      "step": 60
    },
    {
      "epoch": 0.51,
      "grad_norm": 3.275548219680786,
      "learning_rate": 1.6568627450980395e-05,
      "loss": 0.4695,
      "step": 70
    },
    {
      "epoch": 0.59,
      "grad_norm": 3.004589319229126,
      "learning_rate": 1.607843137254902e-05,
      "loss": 0.4803,
      "step": 80
    },
    {
      "epoch": 0.66,
      "grad_norm": 5.80615758895874,
      "learning_rate": 1.558823529411765e-05,
      "loss": 0.5044,
      "step": 90
    },
    {
      "epoch": 0.74,
      "grad_norm": 2.453000545501709,
      "learning_rate": 1.5098039215686276e-05,
      "loss": 0.4675,
      "step": 100
    },
    {
      "epoch": 0.74,
      "eval_accuracy": 0.7766544117647058,
      "eval_f1_macro": 0.7415457166235069,
      "eval_f1_micro": 0.7766544117647058,
      "eval_loss": 0.47801119089126587,
      "eval_runtime": 1.024,
      "eval_samples_per_second": 1062.456,
      "eval_steps_per_second": 16.601,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 408,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "total_flos": 420977678745600.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}