trainer_state.json

{
  "best_metric": 0.7635786873553013,
  "best_model_checkpoint": "model_checkpoint/fine-tuned_legalbert_multilabel_original_train/checkpoint-783",
  "epoch": 2.997129186602871,
  "eval_steps": 500,
  "global_step": 783,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.999043062200957,
      "eval_A_f1": 0.0,
      "eval_A_precision": 0.0,
      "eval_A_recall": 0.0,
      "eval_CH_f1": 0.0,
      "eval_CH_precision": 0.0,
      "eval_CH_recall": 0.0,
      "eval_CR_f1": 0.0,
      "eval_CR_precision": 0.0,
      "eval_CR_recall": 0.0,
      "eval_FAIR_f1": 0.9544351203273459,
      "eval_FAIR_precision": 0.9774147727272727,
      "eval_FAIR_recall": 0.9325111803767449,
      "eval_J_f1": 0.0,
      "eval_J_precision": 0.0,
      "eval_J_recall": 0.0,
      "eval_LAW_f1": 0.0,
      "eval_LAW_precision": 0.0,
      "eval_LAW_recall": 0.0,
      "eval_LTD_f1": 0.6153846153846154,
      "eval_LTD_precision": 0.7472527472527473,
      "eval_LTD_recall": 0.5230769230769231,
      "eval_TER_f1": 0.0,
      "eval_TER_precision": 0.0,
      "eval_TER_recall": 0.0,
      "eval_USE_f1": 0.017241379310344827,
      "eval_USE_precision": 1.0,
      "eval_USE_recall": 0.008695652173913044,
      "eval_accuracy": 0.8484116439183477,
      "eval_f1_macro": 0.17634012389136736,
      "eval_loss": 0.06019286438822746,
      "eval_precision_macro": 0.3027408355533356,
      "eval_recall_macro": 0.1626981950697312,
      "eval_runtime": 894.9212,
      "eval_samples_per_second": 9.251,
      "eval_steps_per_second": 0.579,
      "step": 261
    },
    {
      "epoch": 1.9138755980861244,
      "grad_norm": 0.9339248538017273,
      "learning_rate": 1.8135376756066413e-05,
      "loss": 0.0784,
      "step": 500
    },
    {
      "epoch": 1.998086124401914,
      "eval_A_f1": 0.5909090909090909,
      "eval_A_precision": 1.0,
      "eval_A_recall": 0.41935483870967744,
      "eval_CH_f1": 0.4873096446700508,
      "eval_CH_precision": 0.8571428571428571,
      "eval_CH_recall": 0.3404255319148936,
      "eval_CR_f1": 0.0,
      "eval_CR_precision": 0.0,
      "eval_CR_recall": 0.0,
      "eval_FAIR_f1": 0.9716993725804298,
      "eval_FAIR_precision": 0.9573852426673681,
      "eval_FAIR_recall": 0.9864480281881014,
      "eval_J_f1": 0.8623853211009175,
      "eval_J_precision": 0.9038461538461539,
      "eval_J_recall": 0.8245614035087719,
      "eval_LAW_f1": 0.7927927927927928,
      "eval_LAW_precision": 0.88,
      "eval_LAW_recall": 0.7213114754098361,
      "eval_LTD_f1": 0.6752688172043011,
      "eval_LTD_precision": 0.7658536585365854,
      "eval_LTD_recall": 0.6038461538461538,
      "eval_TER_f1": 0.6990881458966566,
      "eval_TER_precision": 0.7419354838709677,
      "eval_TER_recall": 0.6609195402298851,
      "eval_USE_f1": 0.6632124352331606,
      "eval_USE_precision": 0.8205128205128205,
      "eval_USE_recall": 0.5565217391304348,
      "eval_accuracy": 0.9299432298586786,
      "eval_f1_macro": 0.6380739578208222,
      "eval_loss": 0.04580436274409294,
      "eval_precision_macro": 0.7696306907307503,
      "eval_recall_macro": 0.568154301215306,
      "eval_runtime": 898.3262,
      "eval_samples_per_second": 9.216,
      "eval_steps_per_second": 0.577,
      "step": 522
    },
    {
      "epoch": 2.997129186602871,
      "eval_A_f1": 0.7,
      "eval_A_precision": 0.7241379310344828,
      "eval_A_recall": 0.6774193548387096,
      "eval_CH_f1": 0.72,
      "eval_CH_precision": 0.8256880733944955,
      "eval_CH_recall": 0.6382978723404256,
      "eval_CR_f1": 0.6301369863013698,
      "eval_CR_precision": 0.8214285714285714,
      "eval_CR_recall": 0.5111111111111111,
      "eval_FAIR_f1": 0.9708172523529014,
      "eval_FAIR_precision": 0.9700947225981056,
      "eval_FAIR_recall": 0.9715408591950129,
      "eval_J_f1": 0.9026548672566371,
      "eval_J_precision": 0.9107142857142857,
      "eval_J_recall": 0.8947368421052632,
      "eval_LAW_f1": 0.8035714285714286,
      "eval_LAW_precision": 0.8823529411764706,
      "eval_LAW_recall": 0.7377049180327869,
      "eval_LTD_f1": 0.7022900763358778,
      "eval_LTD_precision": 0.696969696969697,
      "eval_LTD_recall": 0.7076923076923077,
      "eval_TER_f1": 0.7440476190476191,
      "eval_TER_precision": 0.7716049382716049,
      "eval_TER_recall": 0.7183908045977011,
      "eval_USE_f1": 0.6986899563318777,
      "eval_USE_precision": 0.7017543859649122,
      "eval_USE_recall": 0.6956521739130435,
      "eval_accuracy": 0.9356202439908201,
      "eval_f1_macro": 0.7635786873553013,
      "eval_loss": 0.043075863271951675,
      "eval_precision_macro": 0.8116383940614028,
      "eval_recall_macro": 0.7280606937584846,
      "eval_runtime": 894.9343,
      "eval_samples_per_second": 9.251,
      "eval_steps_per_second": 0.579,
      "step": 783
    }
  ],
  "logging_steps": 500,
  "max_steps": 783,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.01
      },
      "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": 3294883706222592.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}