trainer_state.json

{
  "best_metric": 0.9616724738675958,
  "best_model_checkpoint": "brain-tumor-classification/checkpoint-200",
  "epoch": 4.938271604938271,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 10.068439483642578,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.1888,
      "step": 40
    },
    {
      "epoch": 0.9876543209876543,
      "eval_accuracy": 0.9442508710801394,
      "eval_loss": 0.15003159642219543,
      "eval_runtime": 3.4689,
      "eval_samples_per_second": 82.736,
      "eval_steps_per_second": 5.189,
      "step": 40
    },
    {
      "epoch": 2.0,
      "grad_norm": 9.355758666992188,
      "learning_rate": 3.3055555555555553e-05,
      "loss": 0.1514,
      "step": 81
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9581881533101045,
      "eval_loss": 0.12207956612110138,
      "eval_runtime": 2.4115,
      "eval_samples_per_second": 119.012,
      "eval_steps_per_second": 7.464,
      "step": 81
    },
    {
      "epoch": 2.9876543209876543,
      "grad_norm": 11.253016471862793,
      "learning_rate": 2.1944444444444445e-05,
      "loss": 0.1189,
      "step": 121
    },
    {
      "epoch": 2.9876543209876543,
      "eval_accuracy": 0.9442508710801394,
      "eval_loss": 0.16469331085681915,
      "eval_runtime": 2.3749,
      "eval_samples_per_second": 120.849,
      "eval_steps_per_second": 7.579,
      "step": 121
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.731207847595215,
      "learning_rate": 1.0555555555555555e-05,
      "loss": 0.1042,
      "step": 162
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9581881533101045,
      "eval_loss": 0.12243915349245071,
      "eval_runtime": 2.571,
      "eval_samples_per_second": 111.632,
      "eval_steps_per_second": 7.001,
      "step": 162
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 7.372400283813477,
      "learning_rate": 0.0,
      "loss": 0.1055,
      "step": 200
    },
    {
      "epoch": 4.938271604938271,
      "eval_accuracy": 0.9616724738675958,
      "eval_loss": 0.11273417621850967,
      "eval_runtime": 2.687,
      "eval_samples_per_second": 106.809,
      "eval_steps_per_second": 6.699,
      "step": 200
    },
    {
      "epoch": 4.938271604938271,
      "step": 200,
      "total_flos": 3.1727957353537536e+17,
      "train_loss": 0.13397518873214723,
      "train_runtime": 259.5354,
      "train_samples_per_second": 49.762,
      "train_steps_per_second": 0.771
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 3.1727957353537536e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}