trainer_state.json

{
  "best_global_step": 30816,
  "best_metric": 0.807234452615663,
  "best_model_checkpoint": "content/cross_encoder_distilroberta_base_all_data/checkpoint-30816",
  "epoch": 3.0,
  "eval_steps": 10272,
  "global_step": 30819,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.734254842791784e-05,
      "grad_norm": 5.287121772766113,
      "learning_rate": 0.0,
      "loss": 1.0174,
      "step": 1
    },
    {
      "epoch": 0.999902657451572,
      "grad_norm": 11.268630981445312,
      "learning_rate": 1.4816310343584383e-05,
      "loss": 0.6234,
      "step": 10272
    },
    {
      "epoch": 0.999902657451572,
      "eval_reranking-dev_base_map": 0.6214825536231217,
      "eval_reranking-dev_base_mrr@50": 0.7375349668670806,
      "eval_reranking-dev_base_ndcg@50": 0.725527756915131,
      "eval_reranking-dev_map": 0.6945674925725406,
      "eval_reranking-dev_mrr@50": 0.7747076964185934,
      "eval_reranking-dev_ndcg@50": 0.7913486180328326,
      "eval_runtime": 210.3713,
      "eval_samples_per_second": 0.0,
      "eval_steps_per_second": 0.0,
      "step": 10272
    },
    {
      "epoch": 1.9998053149031443,
      "grad_norm": 5.99316930770874,
      "learning_rate": 7.4095972888199885e-06,
      "loss": 0.3901,
      "step": 20544
    },
    {
      "epoch": 1.9998053149031443,
      "eval_reranking-dev_base_map": 0.6214825536231217,
      "eval_reranking-dev_base_mrr@50": 0.7375349668670806,
      "eval_reranking-dev_base_ndcg@50": 0.725527756915131,
      "eval_reranking-dev_map": 0.7153961592162474,
      "eval_reranking-dev_mrr@50": 0.7867533806941779,
      "eval_reranking-dev_ndcg@50": 0.8041280710955544,
      "eval_runtime": 206.6571,
      "eval_samples_per_second": 0.0,
      "eval_steps_per_second": 0.0,
      "step": 20544
    },
    {
      "epoch": 2.999707972354716,
      "grad_norm": 9.407133102416992,
      "learning_rate": 2.8842340555936117e-09,
      "loss": 0.2978,
      "step": 30816
    },
    {
      "epoch": 2.999707972354716,
      "eval_reranking-dev_base_map": 0.6214825536231217,
      "eval_reranking-dev_base_mrr@50": 0.7375349668670806,
      "eval_reranking-dev_base_ndcg@50": 0.725527756915131,
      "eval_reranking-dev_map": 0.7207063760806678,
      "eval_reranking-dev_mrr@50": 0.7903183680827569,
      "eval_reranking-dev_ndcg@50": 0.807234452615663,
      "eval_runtime": 204.5125,
      "eval_samples_per_second": 0.0,
      "eval_steps_per_second": 0.0,
      "step": 30816
    }
  ],
  "logging_steps": 10272,
  "max_steps": 30819,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10272,
  "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": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}