trainer_state.json

{
  "best_metric": 1.0,
  "best_model_checkpoint": "convnext-xlarge-224-22k-1k-v13/checkpoint-9",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.010405209846794605,
      "eval_recall": 1.0,
      "eval_runtime": 1.6504,
      "eval_samples_per_second": 76.95,
      "eval_steps_per_second": 2.424,
      "step": 9
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 12.378776550292969,
      "learning_rate": 4.375e-05,
      "loss": 0.0652,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.027809349820017815,
      "eval_recall": 0.9857142857142858,
      "eval_runtime": 1.6348,
      "eval_samples_per_second": 77.684,
      "eval_steps_per_second": 2.447,
      "step": 18
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 232.1143035888672,
      "learning_rate": 3.125e-05,
      "loss": 0.03,
      "step": 20
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.0006994050927460194,
      "eval_recall": 1.0,
      "eval_runtime": 1.6323,
      "eval_samples_per_second": 77.806,
      "eval_steps_per_second": 2.451,
      "step": 27
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 61.44147872924805,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.0156,
      "step": 30
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.00015087063366081566,
      "eval_recall": 1.0,
      "eval_runtime": 1.6426,
      "eval_samples_per_second": 77.318,
      "eval_steps_per_second": 2.435,
      "step": 36
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.5121456384658813,
      "learning_rate": 6.25e-06,
      "loss": 0.0042,
      "step": 40
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.00012451241491362453,
      "eval_recall": 1.0,
      "eval_runtime": 1.7523,
      "eval_samples_per_second": 72.476,
      "eval_steps_per_second": 2.283,
      "step": 45
    },
    {
      "epoch": 5.0,
      "step": 45,
      "total_flos": 1.7954512873784525e+18,
      "train_loss": 0.025862085550195642,
      "train_runtime": 258.3025,
      "train_samples_per_second": 22.106,
      "train_steps_per_second": 0.174
    }
  ],
  "logging_steps": 10,
  "max_steps": 45,
  "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": 1.7954512873784525e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}