{
  "best_metric": 0.7924403183023873,
  "best_model_checkpoint": "logs/ecthr_b/MHGanainy/xmod-roberta-base-legal-multi/seed_1/checkpoint-1128",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 1974,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.18594583868980408,
      "eval_macro-f1": 0.6610565197291588,
      "eval_micro-f1": 0.7678571428571429,
      "eval_runtime": 9.434,
      "eval_samples_per_second": 105.999,
      "eval_steps_per_second": 3.392,
      "step": 282
    },
    {
      "epoch": 1.773049645390071,
      "grad_norm": 1.6924870014190674,
      "learning_rate": 2.7345744680851065e-05,
      "loss": 0.1734,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.204640731215477,
      "eval_macro-f1": 0.6510354952925879,
      "eval_micro-f1": 0.7552314521242867,
      "eval_runtime": 10.5166,
      "eval_samples_per_second": 95.088,
      "eval_steps_per_second": 3.043,
      "step": 564
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.17442859709262848,
      "eval_macro-f1": 0.7103393399151534,
      "eval_micro-f1": 0.7856437273625289,
      "eval_runtime": 9.5348,
      "eval_samples_per_second": 104.879,
      "eval_steps_per_second": 3.356,
      "step": 846
    },
    {
      "epoch": 3.546099290780142,
      "grad_norm": 0.9688987135887146,
      "learning_rate": 2.4686170212765958e-05,
      "loss": 0.1145,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.18016603589057922,
      "eval_macro-f1": 0.739214459676758,
      "eval_micro-f1": 0.7924403183023873,
      "eval_runtime": 10.4478,
      "eval_samples_per_second": 95.714,
      "eval_steps_per_second": 3.063,
      "step": 1128
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.19197727739810944,
      "eval_macro-f1": 0.721481034377041,
      "eval_micro-f1": 0.7874427730542839,
      "eval_runtime": 10.2803,
      "eval_samples_per_second": 97.273,
      "eval_steps_per_second": 3.113,
      "step": 1410
    },
    {
      "epoch": 5.319148936170213,
      "grad_norm": 0.9491854310035706,
      "learning_rate": 2.203191489361702e-05,
      "loss": 0.0906,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.19124138355255127,
      "eval_macro-f1": 0.7336639771212009,
      "eval_micro-f1": 0.7867017774851877,
      "eval_runtime": 13.0899,
      "eval_samples_per_second": 76.395,
      "eval_steps_per_second": 2.445,
      "step": 1692
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.1959591656923294,
      "eval_macro-f1": 0.7411436475174427,
      "eval_micro-f1": 0.7906208718626155,
      "eval_runtime": 9.3742,
      "eval_samples_per_second": 106.676,
      "eval_steps_per_second": 3.414,
      "step": 1974
    },
    {
      "epoch": 7.0,
      "step": 1974,
      "total_flos": 3.9803472298849075e+17,
      "train_loss": 0.11263628595385025,
      "train_runtime": 1312.5646,
      "train_samples_per_second": 137.136,
      "train_steps_per_second": 4.297
    }
  ],
  "logging_steps": 500,
  "max_steps": 5640,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "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": 3.9803472298849075e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}