trainer_state.json

{
  "best_metric": 0.7086017430845017,
  "best_model_checkpoint": "logs/ecthr_a/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": 0.18291330337524414,
      "eval_macro-f1": 0.5518037204425776,
      "eval_micro-f1": 0.677207867335133,
      "eval_runtime": 9.4627,
      "eval_samples_per_second": 105.679,
      "eval_steps_per_second": 3.382,
      "step": 282
    },
    {
      "epoch": 1.773049645390071,
      "grad_norm": 1.2761306762695312,
      "learning_rate": 2.7340425531914897e-05,
      "loss": 0.1547,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.1642679125070572,
      "eval_macro-f1": 0.5832870401688298,
      "eval_micro-f1": 0.6849209409949865,
      "eval_runtime": 10.2302,
      "eval_samples_per_second": 97.75,
      "eval_steps_per_second": 3.128,
      "step": 564
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.18205788731575012,
      "eval_macro-f1": 0.605599290957237,
      "eval_micro-f1": 0.6864124398370973,
      "eval_runtime": 9.5057,
      "eval_samples_per_second": 105.2,
      "eval_steps_per_second": 3.366,
      "step": 846
    },
    {
      "epoch": 3.546099290780142,
      "grad_norm": 1.2056403160095215,
      "learning_rate": 2.4680851063829786e-05,
      "loss": 0.1031,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.17138700187206268,
      "eval_macro-f1": 0.6431822683616067,
      "eval_micro-f1": 0.7086017430845017,
      "eval_runtime": 9.3996,
      "eval_samples_per_second": 106.388,
      "eval_steps_per_second": 3.404,
      "step": 1128
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.1661965399980545,
      "eval_macro-f1": 0.6357063441749147,
      "eval_micro-f1": 0.6957854406130268,
      "eval_runtime": 9.0902,
      "eval_samples_per_second": 110.009,
      "eval_steps_per_second": 3.52,
      "step": 1410
    },
    {
      "epoch": 5.319148936170213,
      "grad_norm": 1.897348403930664,
      "learning_rate": 2.2021276595744682e-05,
      "loss": 0.0836,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.18352459371089935,
      "eval_macro-f1": 0.6308890190522723,
      "eval_micro-f1": 0.6896046852122987,
      "eval_runtime": 10.0959,
      "eval_samples_per_second": 99.05,
      "eval_steps_per_second": 3.17,
      "step": 1692
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.22320151329040527,
      "eval_macro-f1": 0.6305744474515731,
      "eval_micro-f1": 0.6835172659309363,
      "eval_runtime": 9.9878,
      "eval_samples_per_second": 100.122,
      "eval_steps_per_second": 3.204,
      "step": 1974
    },
    {
      "epoch": 7.0,
      "step": 1974,
      "total_flos": 3.9803472298849075e+17,
      "train_loss": 0.10179799571708827,
      "train_runtime": 1296.3583,
      "train_samples_per_second": 138.851,
      "train_steps_per_second": 4.351
    }
  ],
  "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
}