trainer_state.json

{
  "best_metric": 0.31206899881362915,
  "best_model_checkpoint": "./drive/Shareddrives/CS198-Drones/training_output/vit-hybrid-base-bit-384_rice-leaf-disease-augmented-v2_fft/checkpoint-500",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 1750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 6.522961616516113,
      "learning_rate": 6.640000000000001e-06,
      "loss": 1.203,
      "step": 250
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8511904761904762,
      "eval_loss": 0.4458940923213959,
      "eval_runtime": 17.2925,
      "eval_samples_per_second": 19.43,
      "eval_steps_per_second": 0.636,
      "step": 250
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.191310882568359,
      "learning_rate": 9.703220280030607e-06,
      "loss": 0.1159,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9077380952380952,
      "eval_loss": 0.31206899881362915,
      "eval_runtime": 17.1167,
      "eval_samples_per_second": 19.63,
      "eval_steps_per_second": 0.643,
      "step": 500
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6064174175262451,
      "learning_rate": 7.512082232294491e-06,
      "loss": 0.0136,
      "step": 750
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9226190476190477,
      "eval_loss": 0.3433467745780945,
      "eval_runtime": 17.1077,
      "eval_samples_per_second": 19.64,
      "eval_steps_per_second": 0.643,
      "step": 750
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.01187341008335352,
      "learning_rate": 4.145512989383618e-06,
      "loss": 0.001,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9226190476190477,
      "eval_loss": 0.3376821279525757,
      "eval_runtime": 17.0783,
      "eval_samples_per_second": 19.674,
      "eval_steps_per_second": 0.644,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.026375439018011093,
      "learning_rate": 1.178767715305455e-06,
      "loss": 0.0003,
      "step": 1250
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9226190476190477,
      "eval_loss": 0.3365038335323334,
      "eval_runtime": 17.2601,
      "eval_samples_per_second": 19.467,
      "eval_steps_per_second": 0.637,
      "step": 1250
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0165720134973526,
      "learning_rate": 1.9495502197042214e-11,
      "loss": 0.0002,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9285714285714286,
      "eval_loss": 0.33658862113952637,
      "eval_runtime": 17.208,
      "eval_samples_per_second": 19.526,
      "eval_steps_per_second": 0.639,
      "step": 1500
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.004472899716347456,
      "learning_rate": 8.839182277652986e-06,
      "loss": 0.0002,
      "step": 1750
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9285714285714286,
      "eval_loss": 0.3431926965713501,
      "eval_runtime": 17.2537,
      "eval_samples_per_second": 19.474,
      "eval_steps_per_second": 0.638,
      "step": 1750
    }
  ],
  "logging_steps": 500,
  "max_steps": 3750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4594252463931392e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}