last-checkpoint/trainer_state.json

{
  "best_metric": 0.05613817274570465,
  "best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-3000",
  "epoch": 1.4792899408284024,
  "eval_steps": 1000,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2465483234714004,
      "grad_norm": 0.3822348415851593,
      "learning_rate": 1.9950690335305722e-05,
      "loss": 0.1664,
      "step": 500
    },
    {
      "epoch": 0.4930966469428008,
      "grad_norm": 0.40402480959892273,
      "learning_rate": 1.9901380670611442e-05,
      "loss": 0.0944,
      "step": 1000
    },
    {
      "epoch": 0.4930966469428008,
      "eval_accuracy": 0.981383845685049,
      "eval_f1": 0.0,
      "eval_loss": 0.089978888630867,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 11.9647,
      "eval_samples_per_second": 677.827,
      "eval_steps_per_second": 2.675,
      "step": 1000
    },
    {
      "epoch": 0.7396449704142012,
      "grad_norm": 0.385586678981781,
      "learning_rate": 1.9852071005917162e-05,
      "loss": 0.0863,
      "step": 1500
    },
    {
      "epoch": 0.9861932938856016,
      "grad_norm": 0.3922920525074005,
      "learning_rate": 1.980276134122288e-05,
      "loss": 0.0769,
      "step": 2000
    },
    {
      "epoch": 0.9861932938856016,
      "eval_accuracy": 0.9813966013294216,
      "eval_f1": 0.0015213753232922562,
      "eval_loss": 0.06878085434436798,
      "eval_precision": 0.9090909090909091,
      "eval_recall": 0.0007613247049866769,
      "eval_runtime": 14.1244,
      "eval_samples_per_second": 574.184,
      "eval_steps_per_second": 2.266,
      "step": 2000
    },
    {
      "epoch": 1.232741617357002,
      "grad_norm": 0.40515828132629395,
      "learning_rate": 1.9753451676528602e-05,
      "loss": 0.0677,
      "step": 2500
    },
    {
      "epoch": 1.4792899408284024,
      "grad_norm": 0.3946343958377838,
      "learning_rate": 1.9704142011834322e-05,
      "loss": 0.0607,
      "step": 3000
    },
    {
      "epoch": 1.4792899408284024,
      "eval_accuracy": 0.982203041512536,
      "eval_f1": 0.10543563439481371,
      "eval_loss": 0.05613817274570465,
      "eval_precision": 0.8203991130820399,
      "eval_recall": 0.056338028169014086,
      "eval_runtime": 14.2341,
      "eval_samples_per_second": 569.76,
      "eval_steps_per_second": 2.248,
      "step": 3000
    }
  ],
  "logging_steps": 500,
  "max_steps": 202800,
  "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": 67737816965952.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}