{
  "best_metric": 0.14659787714481354,
  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/mldoc/albeto_base_10/epochs_4_bs_32_lr_5e-5/checkpoint-700",
  "epoch": 4.0,
  "global_step": 1184,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.34,
      "eval_accuracy": 0.746999979019165,
      "eval_loss": 0.6933977007865906,
      "eval_runtime": 1.8687,
      "eval_samples_per_second": 535.118,
      "eval_steps_per_second": 17.124,
      "step": 100
    },
    {
      "epoch": 0.68,
      "eval_accuracy": 0.8700000047683716,
      "eval_loss": 0.4119150638580322,
      "eval_runtime": 1.8696,
      "eval_samples_per_second": 534.864,
      "eval_steps_per_second": 17.116,
      "step": 200
    },
    {
      "epoch": 1.01,
      "eval_accuracy": 0.9269999861717224,
      "eval_loss": 0.28070709109306335,
      "eval_runtime": 1.8707,
      "eval_samples_per_second": 534.572,
      "eval_steps_per_second": 17.106,
      "step": 300
    },
    {
      "epoch": 1.35,
      "eval_accuracy": 0.9279999732971191,
      "eval_loss": 0.25755012035369873,
      "eval_runtime": 1.8729,
      "eval_samples_per_second": 533.927,
      "eval_steps_per_second": 17.086,
      "step": 400
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.8927364864864863e-05,
      "loss": 0.1279,
      "step": 500
    },
    {
      "epoch": 1.69,
      "eval_accuracy": 0.9440000057220459,
      "eval_loss": 0.25176554918289185,
      "eval_runtime": 1.8715,
      "eval_samples_per_second": 534.323,
      "eval_steps_per_second": 17.098,
      "step": 500
    },
    {
      "epoch": 2.03,
      "eval_accuracy": 0.9620000123977661,
      "eval_loss": 0.1778251677751541,
      "eval_runtime": 1.8729,
      "eval_samples_per_second": 533.922,
      "eval_steps_per_second": 17.086,
      "step": 600
    },
    {
      "epoch": 2.36,
      "eval_accuracy": 0.9649999737739563,
      "eval_loss": 0.14659787714481354,
      "eval_runtime": 1.872,
      "eval_samples_per_second": 534.185,
      "eval_steps_per_second": 17.094,
      "step": 700
    },
    {
      "epoch": 2.7,
      "eval_accuracy": 0.9539999961853027,
      "eval_loss": 0.19388286769390106,
      "eval_runtime": 1.8707,
      "eval_samples_per_second": 534.552,
      "eval_steps_per_second": 17.106,
      "step": 800
    },
    {
      "epoch": 3.04,
      "eval_accuracy": 0.9620000123977661,
      "eval_loss": 0.16352728009223938,
      "eval_runtime": 1.8714,
      "eval_samples_per_second": 534.363,
      "eval_steps_per_second": 17.1,
      "step": 900
    },
    {
      "epoch": 3.38,
      "learning_rate": 7.8125e-06,
      "loss": 0.0377,
      "step": 1000
    },
    {
      "epoch": 3.38,
      "eval_accuracy": 0.9430000185966492,
      "eval_loss": 0.22912634909152985,
      "eval_runtime": 1.8706,
      "eval_samples_per_second": 534.593,
      "eval_steps_per_second": 17.107,
      "step": 1000
    },
    {
      "epoch": 3.72,
      "eval_accuracy": 0.953000009059906,
      "eval_loss": 0.1914745718240738,
      "eval_runtime": 1.8687,
      "eval_samples_per_second": 535.118,
      "eval_steps_per_second": 17.124,
      "step": 1100
    },
    {
      "epoch": 4.0,
      "step": 1184,
      "total_flos": 824085797689344.0,
      "train_loss": 0.07292293032278886,
      "train_runtime": 179.7572,
      "train_samples_per_second": 210.462,
      "train_steps_per_second": 6.587
    }
  ],
  "max_steps": 1184,
  "num_train_epochs": 4,
  "total_flos": 824085797689344.0,
  "trial_name": null,
  "trial_params": null
}