checkpoint-1000/trainer_state.json

{
  "best_metric": 0.8767404952738379,
  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-700",
  "epoch": 0.5330490405117271,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.053304904051172705,
      "eval_accuracy": 0.6321578647928374,
      "eval_f1": 0.6321578647928374,
      "eval_loss": 0.9594171643257141,
      "eval_precision": 0.6321578647928374,
      "eval_recall": 0.6321578647928374,
      "eval_runtime": 69.4219,
      "eval_samples_per_second": 23.148,
      "eval_steps_per_second": 0.735,
      "step": 100
    },
    {
      "epoch": 0.10660980810234541,
      "eval_accuracy": 0.8202860650583409,
      "eval_f1": 0.8202860650583409,
      "eval_loss": 0.6088714599609375,
      "eval_precision": 0.8202860650583409,
      "eval_recall": 0.8202860650583409,
      "eval_runtime": 69.0048,
      "eval_samples_per_second": 23.288,
      "eval_steps_per_second": 0.739,
      "step": 200
    },
    {
      "epoch": 0.15991471215351813,
      "eval_accuracy": 0.7378602014233383,
      "eval_f1": 0.7378602014233383,
      "eval_loss": 0.7009087800979614,
      "eval_precision": 0.7378602014233383,
      "eval_recall": 0.7378602014233383,
      "eval_runtime": 68.7975,
      "eval_samples_per_second": 23.358,
      "eval_steps_per_second": 0.741,
      "step": 300
    },
    {
      "epoch": 0.21321961620469082,
      "eval_accuracy": 0.7694710890634513,
      "eval_f1": 0.7694710890634513,
      "eval_loss": 0.5369378328323364,
      "eval_precision": 0.7694710890634513,
      "eval_recall": 0.7694710890634513,
      "eval_runtime": 69.0856,
      "eval_samples_per_second": 23.261,
      "eval_steps_per_second": 0.738,
      "step": 400
    },
    {
      "epoch": 0.26652452025586354,
      "grad_norm": 443972.875,
      "learning_rate": 1.4669509594882732e-05,
      "loss": 0.7136,
      "step": 500
    },
    {
      "epoch": 0.26652452025586354,
      "eval_accuracy": 0.8621777276492958,
      "eval_f1": 0.8621777276492958,
      "eval_loss": 0.4052257537841797,
      "eval_precision": 0.8621777276492958,
      "eval_recall": 0.8621777276492958,
      "eval_runtime": 68.528,
      "eval_samples_per_second": 23.45,
      "eval_steps_per_second": 0.744,
      "step": 500
    },
    {
      "epoch": 0.31982942430703626,
      "eval_accuracy": 0.8714304251050535,
      "eval_f1": 0.8714304251050535,
      "eval_loss": 0.40161609649658203,
      "eval_precision": 0.8714304251050535,
      "eval_recall": 0.8714304251050535,
      "eval_runtime": 68.104,
      "eval_samples_per_second": 23.596,
      "eval_steps_per_second": 0.749,
      "step": 600
    },
    {
      "epoch": 0.373134328358209,
      "eval_accuracy": 0.8767404952738379,
      "eval_f1": 0.8767404952738379,
      "eval_loss": 0.38839995861053467,
      "eval_precision": 0.8767404952738379,
      "eval_recall": 0.8767404952738379,
      "eval_runtime": 69.1004,
      "eval_samples_per_second": 23.256,
      "eval_steps_per_second": 0.738,
      "step": 700
    },
    {
      "epoch": 0.42643923240938164,
      "eval_accuracy": 0.866569515006937,
      "eval_f1": 0.866569515006937,
      "eval_loss": 0.4080258309841156,
      "eval_precision": 0.866569515006937,
      "eval_recall": 0.866569515006937,
      "eval_runtime": 68.4146,
      "eval_samples_per_second": 23.489,
      "eval_steps_per_second": 0.745,
      "step": 800
    },
    {
      "epoch": 0.47974413646055436,
      "eval_accuracy": 0.8303472506413008,
      "eval_f1": 0.8303472506413008,
      "eval_loss": 0.45843783020973206,
      "eval_precision": 0.8303472506413008,
      "eval_recall": 0.8303472506413008,
      "eval_runtime": 68.5359,
      "eval_samples_per_second": 23.448,
      "eval_steps_per_second": 0.744,
      "step": 900
    },
    {
      "epoch": 0.5330490405117271,
      "grad_norm": 97385.5703125,
      "learning_rate": 9.339019189765458e-06,
      "loss": 0.4387,
      "step": 1000
    },
    {
      "epoch": 0.5330490405117271,
      "eval_accuracy": 0.7901524149839799,
      "eval_f1": 0.7901524149839798,
      "eval_loss": 0.525492250919342,
      "eval_precision": 0.7901524149839799,
      "eval_recall": 0.7901524149839799,
      "eval_runtime": 69.1745,
      "eval_samples_per_second": 23.231,
      "eval_steps_per_second": 0.737,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1876,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2225377910784000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}