last-checkpoint/trainer_state.json

{
  "best_metric": 0.09005372226238251,
  "best_model_checkpoint": "doc-topic-model_eval-00_train-04/checkpoint-1000",
  "epoch": 0.4928536224741252,
  "eval_steps": 1000,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2464268112370626,
      "grad_norm": 0.36145079135894775,
      "learning_rate": 1.9950714637752587e-05,
      "loss": 0.1655,
      "step": 500
    },
    {
      "epoch": 0.4928536224741252,
      "grad_norm": 0.3764462471008301,
      "learning_rate": 1.990142927550518e-05,
      "loss": 0.0934,
      "step": 1000
    },
    {
      "epoch": 0.4928536224741252,
      "eval_accuracy": 0.9814660487265615,
      "eval_f1": 0.0,
      "eval_loss": 0.09005372226238251,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 11.9616,
      "eval_samples_per_second": 678.001,
      "eval_steps_per_second": 2.675,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 202900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 1000,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 22632134187960.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}