checkpoint-4098/trainer_state.json

{
  "best_metric": 2.96836519241333,
  "best_model_checkpoint": "military_aircraft_image_detection/checkpoint-4098",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 4098,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7320644216691069,
      "grad_norm": 1.73904550075531,
      "learning_rate": 1.7776679841897234e-07,
      "loss": 2.9196,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5273139558853844,
      "eval_loss": 2.9956250190734863,
      "eval_runtime": 433.4755,
      "eval_samples_per_second": 67.146,
      "eval_steps_per_second": 2.099,
      "step": 683
    },
    {
      "epoch": 1.4641288433382138,
      "grad_norm": 1.7973357439041138,
      "learning_rate": 1.5306324110671935e-07,
      "loss": 2.9104,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5284477427334571,
      "eval_loss": 2.985973596572876,
      "eval_runtime": 429.4589,
      "eval_samples_per_second": 67.774,
      "eval_steps_per_second": 2.119,
      "step": 1366
    },
    {
      "epoch": 2.1961932650073206,
      "grad_norm": 1.7381324768066406,
      "learning_rate": 1.283596837944664e-07,
      "loss": 2.9038,
      "step": 1500
    },
    {
      "epoch": 2.9282576866764276,
      "grad_norm": 1.8419060707092285,
      "learning_rate": 1.0365612648221343e-07,
      "loss": 2.8969,
      "step": 2000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5296158867587439,
      "eval_loss": 2.9781196117401123,
      "eval_runtime": 416.4739,
      "eval_samples_per_second": 69.887,
      "eval_steps_per_second": 2.185,
      "step": 2049
    },
    {
      "epoch": 3.660322108345534,
      "grad_norm": 1.8417006731033325,
      "learning_rate": 7.895256916996047e-08,
      "loss": 2.8889,
      "step": 2500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5304061018346733,
      "eval_loss": 2.972407341003418,
      "eval_runtime": 417.0986,
      "eval_samples_per_second": 69.782,
      "eval_steps_per_second": 2.182,
      "step": 2732
    },
    {
      "epoch": 4.392386530014641,
      "grad_norm": 2.0208425521850586,
      "learning_rate": 5.4249011857707506e-08,
      "loss": 2.8874,
      "step": 3000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5309901738473167,
      "eval_loss": 2.969489097595215,
      "eval_runtime": 410.5775,
      "eval_samples_per_second": 70.89,
      "eval_steps_per_second": 2.216,
      "step": 3415
    },
    {
      "epoch": 5.124450951683748,
      "grad_norm": 2.0944771766662598,
      "learning_rate": 2.9545454545454546e-08,
      "loss": 2.8839,
      "step": 3500
    },
    {
      "epoch": 5.856515373352855,
      "grad_norm": 2.000408172607422,
      "learning_rate": 4.8418972332015805e-09,
      "loss": 2.8841,
      "step": 4000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5313337456194599,
      "eval_loss": 2.96836519241333,
      "eval_runtime": 417.3097,
      "eval_samples_per_second": 69.747,
      "eval_steps_per_second": 2.181,
      "step": 4098
    }
  ],
  "logging_steps": 500,
  "max_steps": 4098,
  "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": 2.0307887664581878e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}