last-checkpoint/trainer_state.json

{
  "best_metric": 0.04988710954785347,
  "best_model_checkpoint": "doc-topic-model_eval-04_train-00/checkpoint-4000",
  "epoch": 1.972386587771203,
  "eval_steps": 1000,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2465483234714004,
      "grad_norm": 0.32839319109916687,
      "learning_rate": 1.9950690335305722e-05,
      "loss": 0.1668,
      "step": 500
    },
    {
      "epoch": 0.4930966469428008,
      "grad_norm": 0.4088590443134308,
      "learning_rate": 1.9901380670611442e-05,
      "loss": 0.0929,
      "step": 1000
    },
    {
      "epoch": 0.4930966469428008,
      "eval_accuracy": 0.981496987239155,
      "eval_f1": 0.0,
      "eval_loss": 0.09063737094402313,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 12.1099,
      "eval_samples_per_second": 669.945,
      "eval_steps_per_second": 2.642,
      "step": 1000
    },
    {
      "epoch": 0.7396449704142012,
      "grad_norm": 0.33391374349594116,
      "learning_rate": 1.9852071005917162e-05,
      "loss": 0.0874,
      "step": 1500
    },
    {
      "epoch": 0.9861932938856016,
      "grad_norm": 0.3162483870983124,
      "learning_rate": 1.980276134122288e-05,
      "loss": 0.0785,
      "step": 2000
    },
    {
      "epoch": 0.9861932938856016,
      "eval_accuracy": 0.981496987239155,
      "eval_f1": 0.0,
      "eval_loss": 0.0703761950135231,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 12.2009,
      "eval_samples_per_second": 664.948,
      "eval_steps_per_second": 2.623,
      "step": 2000
    },
    {
      "epoch": 1.232741617357002,
      "grad_norm": 0.31390729546546936,
      "learning_rate": 1.9753451676528602e-05,
      "loss": 0.0684,
      "step": 2500
    },
    {
      "epoch": 1.4792899408284024,
      "grad_norm": 0.40165144205093384,
      "learning_rate": 1.9704142011834322e-05,
      "loss": 0.0622,
      "step": 3000
    },
    {
      "epoch": 1.4792899408284024,
      "eval_accuracy": 0.982317296916684,
      "eval_f1": 0.10215092439392849,
      "eval_loss": 0.057249072939157486,
      "eval_precision": 0.8442330558858502,
      "eval_recall": 0.05436447166921899,
      "eval_runtime": 14.4254,
      "eval_samples_per_second": 562.413,
      "eval_steps_per_second": 2.218,
      "step": 3000
    },
    {
      "epoch": 1.725838264299803,
      "grad_norm": 0.4135937988758087,
      "learning_rate": 1.965483234714004e-05,
      "loss": 0.0584,
      "step": 3500
    },
    {
      "epoch": 1.972386587771203,
      "grad_norm": 0.324859082698822,
      "learning_rate": 1.9605522682445763e-05,
      "loss": 0.0542,
      "step": 4000
    },
    {
      "epoch": 1.972386587771203,
      "eval_accuracy": 0.9842951074690683,
      "eval_f1": 0.338958793010913,
      "eval_loss": 0.04988710954785347,
      "eval_precision": 0.7662442706929091,
      "eval_recall": 0.21761102603369065,
      "eval_runtime": 14.4271,
      "eval_samples_per_second": 562.343,
      "eval_steps_per_second": 2.218,
      "step": 4000
    }
  ],
  "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": 90534755794896.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}