checkpoint-1302/trainer_state.json

{
  "best_metric": 2.27253794670105,
  "best_model_checkpoint": "traffic_sign_detection/checkpoint-1302",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1302,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9349329874621704,
      "eval_loss": 2.3095896244049072,
      "eval_runtime": 98.8393,
      "eval_samples_per_second": 93.607,
      "eval_steps_per_second": 11.706,
      "step": 434
    },
    {
      "epoch": 1.1520737327188941,
      "grad_norm": 1.8742210865020752,
      "learning_rate": 3.2028753993610226e-07,
      "loss": 2.1287,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9379593601383485,
      "eval_loss": 2.2814977169036865,
      "eval_runtime": 99.5751,
      "eval_samples_per_second": 92.915,
      "eval_steps_per_second": 11.619,
      "step": 868
    },
    {
      "epoch": 2.3041474654377883,
      "grad_norm": 1.7836453914642334,
      "learning_rate": 1.2060702875399362e-07,
      "loss": 2.0898,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9388240380458279,
      "eval_loss": 2.27253794670105,
      "eval_runtime": 98.7302,
      "eval_samples_per_second": 93.71,
      "eval_steps_per_second": 11.719,
      "step": 1302
    }
  ],
  "logging_steps": 500,
  "max_steps": 1302,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 3.2275448973660856e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}