trainer_state.json

{
  "best_metric": 0.5642864108085632,
  "best_model_checkpoint": "vit-large-patch16-224-new-dungeon-geo-morphs-025/checkpoint-10",
  "epoch": 25.454545454545453,
  "eval_steps": 10,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.0011619372526183724,
      "learning_rate": 1.904761904761905e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 3.6363636363636362,
      "eval_accuracy": 0.9433962264150944,
      "eval_loss": 0.5642864108085632,
      "eval_runtime": 0.8676,
      "eval_samples_per_second": 61.091,
      "eval_steps_per_second": 8.069,
      "step": 10
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 0.0002521714777685702,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 7.2727272727272725,
      "eval_accuracy": 0.9433962264150944,
      "eval_loss": 0.6440225839614868,
      "eval_runtime": 0.8918,
      "eval_samples_per_second": 59.428,
      "eval_steps_per_second": 7.849,
      "step": 20
    },
    {
      "epoch": 10.909090909090908,
      "grad_norm": 9.973558189813048e-05,
      "learning_rate": 1.2698412698412699e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 10.909090909090908,
      "eval_accuracy": 0.9433962264150944,
      "eval_loss": 0.6484400033950806,
      "eval_runtime": 0.9598,
      "eval_samples_per_second": 55.222,
      "eval_steps_per_second": 7.294,
      "step": 30
    },
    {
      "epoch": 14.545454545454545,
      "grad_norm": 6.822261639172211e-05,
      "learning_rate": 9.523809523809525e-06,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 14.545454545454545,
      "eval_accuracy": 0.9433962264150944,
      "eval_loss": 0.6491027474403381,
      "eval_runtime": 0.8594,
      "eval_samples_per_second": 61.672,
      "eval_steps_per_second": 8.145,
      "step": 40
    },
    {
      "epoch": 18.181818181818183,
      "grad_norm": 5.878365846001543e-05,
      "learning_rate": 6.349206349206349e-06,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 18.181818181818183,
      "eval_accuracy": 0.9433962264150944,
      "eval_loss": 0.6514610648155212,
      "eval_runtime": 0.9922,
      "eval_samples_per_second": 53.419,
      "eval_steps_per_second": 7.055,
      "step": 50
    },
    {
      "epoch": 21.818181818181817,
      "grad_norm": 4.811874532606453e-05,
      "learning_rate": 3.1746031746031746e-06,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 21.818181818181817,
      "eval_accuracy": 0.9433962264150944,
      "eval_loss": 0.6538931727409363,
      "eval_runtime": 0.8796,
      "eval_samples_per_second": 60.251,
      "eval_steps_per_second": 7.958,
      "step": 60
    },
    {
      "epoch": 25.454545454545453,
      "grad_norm": 4.843185161007568e-05,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 25.454545454545453,
      "eval_accuracy": 0.9433962264150944,
      "eval_loss": 0.6547039151191711,
      "eval_runtime": 0.9121,
      "eval_samples_per_second": 58.106,
      "eval_steps_per_second": 7.674,
      "step": 70
    },
    {
      "epoch": 25.454545454545453,
      "step": 70,
      "total_flos": 5.862231071082086e+17,
      "train_loss": 6.2270888260432656e-06,
      "train_runtime": 354.1343,
      "train_samples_per_second": 8.302,
      "train_steps_per_second": 0.198
    }
  ],
  "logging_steps": 10,
  "max_steps": 70,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 35,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.862231071082086e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}