checkpoint-1146/trainer_state.json

{
  "best_global_step": 1146,
  "best_metric": 0.3498033881187439,
  "best_model_checkpoint": "Traffic-Density-Classification/checkpoint-1146",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1146,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7838767819105358,
      "eval_loss": 0.5680652260780334,
      "eval_model_preparation_time": 0.0025,
      "eval_runtime": 107.6238,
      "eval_samples_per_second": 56.707,
      "eval_steps_per_second": 7.09,
      "step": 191
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.823037850237588,
      "eval_loss": 0.45864853262901306,
      "eval_model_preparation_time": 0.0025,
      "eval_runtime": 107.4221,
      "eval_samples_per_second": 56.813,
      "eval_steps_per_second": 7.103,
      "step": 382
    },
    {
      "epoch": 2.6178010471204187,
      "grad_norm": 23.99968910217285,
      "learning_rate": 2.947080291970803e-06,
      "loss": 0.6251,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.832541373095199,
      "eval_loss": 0.41261211037635803,
      "eval_model_preparation_time": 0.0025,
      "eval_runtime": 109.3365,
      "eval_samples_per_second": 55.818,
      "eval_steps_per_second": 6.978,
      "step": 573
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8341799115189251,
      "eval_loss": 0.41070693731307983,
      "eval_model_preparation_time": 0.0025,
      "eval_runtime": 108.0879,
      "eval_samples_per_second": 56.463,
      "eval_steps_per_second": 7.059,
      "step": 764
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8508930034409307,
      "eval_loss": 0.36471685767173767,
      "eval_model_preparation_time": 0.0025,
      "eval_runtime": 107.2228,
      "eval_samples_per_second": 56.919,
      "eval_steps_per_second": 7.116,
      "step": 955
    },
    {
      "epoch": 5.2356020942408374,
      "grad_norm": 29.588672637939453,
      "learning_rate": 6.66058394160584e-07,
      "loss": 0.3969,
      "step": 1000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8602326724561691,
      "eval_loss": 0.3498033881187439,
      "eval_model_preparation_time": 0.0025,
      "eval_runtime": 107.3052,
      "eval_samples_per_second": 56.875,
      "eval_steps_per_second": 7.111,
      "step": 1146
    }
  ],
  "logging_steps": 500,
  "max_steps": 1146,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.06700961103736e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}