trainer_state.json

{
  "best_metric": 0.9712643678160919,
  "best_model_checkpoint": "autotrain-chest-xray-demo-1677859324-finetuned-eurosat/checkpoint-108",
  "epoch": 2.979591836734694,
  "eval_steps": 500,
  "global_step": 108,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.272108843537415,
      "grad_norm": 16.689775466918945,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.4485,
      "step": 10
    },
    {
      "epoch": 0.54421768707483,
      "grad_norm": 10.187885284423828,
      "learning_rate": 4.536082474226804e-05,
      "loss": 0.2771,
      "step": 20
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 18.186771392822266,
      "learning_rate": 4.020618556701031e-05,
      "loss": 0.268,
      "step": 30
    },
    {
      "epoch": 0.9795918367346939,
      "eval_accuracy": 0.9616858237547893,
      "eval_loss": 0.08618783950805664,
      "eval_runtime": 179.5661,
      "eval_samples_per_second": 2.907,
      "eval_steps_per_second": 0.095,
      "step": 36
    },
    {
      "epoch": 1.1088435374149659,
      "grad_norm": 3.6211280822753906,
      "learning_rate": 3.5051546391752576e-05,
      "loss": 0.182,
      "step": 40
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 5.028314113616943,
      "learning_rate": 2.9896907216494846e-05,
      "loss": 0.1337,
      "step": 50
    },
    {
      "epoch": 1.6530612244897958,
      "grad_norm": 5.46250057220459,
      "learning_rate": 2.4742268041237116e-05,
      "loss": 0.1418,
      "step": 60
    },
    {
      "epoch": 1.925170068027211,
      "grad_norm": 6.8395280838012695,
      "learning_rate": 1.9587628865979382e-05,
      "loss": 0.1635,
      "step": 70
    },
    {
      "epoch": 1.9795918367346939,
      "eval_accuracy": 0.9674329501915708,
      "eval_loss": 0.07667217403650284,
      "eval_runtime": 15.7384,
      "eval_samples_per_second": 33.167,
      "eval_steps_per_second": 1.08,
      "step": 72
    },
    {
      "epoch": 2.2176870748299318,
      "grad_norm": 1.4188082218170166,
      "learning_rate": 1.4432989690721649e-05,
      "loss": 0.1132,
      "step": 80
    },
    {
      "epoch": 2.489795918367347,
      "grad_norm": 2.4192864894866943,
      "learning_rate": 9.278350515463918e-06,
      "loss": 0.1069,
      "step": 90
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 2.98118257522583,
      "learning_rate": 4.123711340206186e-06,
      "loss": 0.1039,
      "step": 100
    },
    {
      "epoch": 2.979591836734694,
      "eval_accuracy": 0.9712643678160919,
      "eval_loss": 0.07310493290424347,
      "eval_runtime": 16.8861,
      "eval_samples_per_second": 30.913,
      "eval_steps_per_second": 1.007,
      "step": 108
    },
    {
      "epoch": 2.979591836734694,
      "step": 108,
      "total_flos": 1.0930771921223025e+18,
      "train_loss": 0.1871028266571186,
      "train_runtime": 2653.3979,
      "train_samples_per_second": 5.307,
      "train_steps_per_second": 0.041
    }
  ],
  "logging_steps": 10,
  "max_steps": 108,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.0930771921223025e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}