checkpoint-1200/trainer_state.json

{
  "best_metric": 0.6604133950171894,
  "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_paragraphs_ml512-v6/checkpoint-1200",
  "epoch": 0.6396588486140725,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "eval_accuracy": 0.8841533429944805,
      "eval_f1": 0.10664094791953704,
      "eval_loss": 0.4427741765975952,
      "eval_precision": 0.11536168521462639,
      "eval_recall": 0.09914602903501281,
      "eval_runtime": 348.7843,
      "eval_samples_per_second": 4.607,
      "eval_steps_per_second": 0.29,
      "step": 200
    },
    {
      "epoch": 0.21,
      "eval_accuracy": 0.9242655812394248,
      "eval_f1": 0.44395873404441333,
      "eval_loss": 0.30403900146484375,
      "eval_precision": 0.4547734193086154,
      "eval_recall": 0.4336464560204953,
      "eval_runtime": 350.1211,
      "eval_samples_per_second": 4.59,
      "eval_steps_per_second": 0.288,
      "step": 400
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.3209054593874834e-05,
      "loss": 0.7241,
      "step": 500
    },
    {
      "epoch": 0.32,
      "eval_accuracy": 0.9359434268564053,
      "eval_f1": 0.5543897040741045,
      "eval_loss": 0.22647875547409058,
      "eval_precision": 0.5330233291298865,
      "eval_recall": 0.5775405636208369,
      "eval_runtime": 342.3688,
      "eval_samples_per_second": 4.694,
      "eval_steps_per_second": 0.295,
      "step": 600
    },
    {
      "epoch": 0.43,
      "eval_accuracy": 0.947861481323102,
      "eval_f1": 0.6015281512784394,
      "eval_loss": 0.2140066921710968,
      "eval_precision": 0.6013484680378937,
      "eval_recall": 0.6017079419299743,
      "eval_runtime": 342.7133,
      "eval_samples_per_second": 4.689,
      "eval_steps_per_second": 0.295,
      "step": 800
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.927439656448986e-05,
      "loss": 0.2343,
      "step": 1000
    },
    {
      "epoch": 0.53,
      "eval_accuracy": 0.9402091136821377,
      "eval_f1": 0.6132131856006622,
      "eval_loss": 0.285193532705307,
      "eval_precision": 0.6641768748132656,
      "eval_recall": 0.5695132365499573,
      "eval_runtime": 341.4863,
      "eval_samples_per_second": 4.706,
      "eval_steps_per_second": 0.296,
      "step": 1000
    },
    {
      "epoch": 0.64,
      "eval_accuracy": 0.9539986854504707,
      "eval_f1": 0.6604133950171894,
      "eval_loss": 0.16944007575511932,
      "eval_precision": 0.6564846848367226,
      "eval_recall": 0.6643894107600341,
      "eval_runtime": 342.4627,
      "eval_samples_per_second": 4.692,
      "eval_steps_per_second": 0.295,
      "step": 1200
    }
  ],
  "max_steps": 7504,
  "num_train_epochs": 4,
  "total_flos": 5182741345075200.0,
  "trial_name": null,
  "trial_params": null
}