checkpoint-522/trainer_state.json

{
  "best_metric": 0.08070622384548187,
  "best_model_checkpoint": "nike_image_classification/checkpoint-522",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 522,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8189655172413793,
      "eval_loss": 1.227477788925171,
      "eval_runtime": 2.9305,
      "eval_samples_per_second": 79.167,
      "eval_steps_per_second": 9.896,
      "step": 58
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9525862068965517,
      "eval_loss": 0.643058717250824,
      "eval_runtime": 3.0001,
      "eval_samples_per_second": 77.331,
      "eval_steps_per_second": 9.666,
      "step": 116
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9870689655172413,
      "eval_loss": 0.31094491481781006,
      "eval_runtime": 3.1342,
      "eval_samples_per_second": 74.021,
      "eval_steps_per_second": 9.253,
      "step": 174
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.16685688495635986,
      "eval_runtime": 3.1158,
      "eval_samples_per_second": 74.46,
      "eval_steps_per_second": 9.307,
      "step": 232
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.12485546618700027,
      "eval_runtime": 3.1368,
      "eval_samples_per_second": 73.961,
      "eval_steps_per_second": 9.245,
      "step": 290
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.10313940793275833,
      "eval_runtime": 3.1131,
      "eval_samples_per_second": 74.523,
      "eval_steps_per_second": 9.315,
      "step": 348
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.09054012596607208,
      "eval_runtime": 3.1083,
      "eval_samples_per_second": 74.638,
      "eval_steps_per_second": 9.33,
      "step": 406
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.08475273847579956,
      "eval_runtime": 3.1839,
      "eval_samples_per_second": 72.866,
      "eval_steps_per_second": 9.108,
      "step": 464
    },
    {
      "epoch": 8.620689655172415,
      "grad_norm": 0.3394070863723755,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.3935,
      "step": 500
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.08070622384548187,
      "eval_runtime": 3.1035,
      "eval_samples_per_second": 74.755,
      "eval_steps_per_second": 9.344,
      "step": 522
    }
  ],
  "logging_steps": 500,
  "max_steps": 580,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 6.472304995598991e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}