trainer_state.json

{
  "best_metric": 1.0,
  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/ViViT_lsa64_coR/checkpoint-864",
  "epoch": 7.1,
  "eval_steps": 500,
  "global_step": 2304,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 34.6246223449707,
      "learning_rate": 4.930555555555556e-05,
      "loss": 12.7049,
      "step": 288
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.84375,
      "eval_loss": 1.3316307067871094,
      "eval_runtime": 289.0213,
      "eval_samples_per_second": 0.886,
      "eval_steps_per_second": 0.443,
      "step": 288
    },
    {
      "epoch": 1.1,
      "grad_norm": 1.3600924015045166,
      "learning_rate": 4.4521604938271604e-05,
      "loss": 1.4335,
      "step": 576
    },
    {
      "epoch": 1.1,
      "eval_accuracy": 0.9921875,
      "eval_loss": 0.08541239798069,
      "eval_runtime": 353.5336,
      "eval_samples_per_second": 0.724,
      "eval_steps_per_second": 0.362,
      "step": 576
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.12772603332996368,
      "learning_rate": 3.8966049382716055e-05,
      "loss": 0.0869,
      "step": 864
    },
    {
      "epoch": 2.1,
      "eval_accuracy": 1.0,
      "eval_loss": 0.00544479675590992,
      "eval_runtime": 303.6919,
      "eval_samples_per_second": 0.843,
      "eval_steps_per_second": 0.421,
      "step": 864
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.10945271700620651,
      "learning_rate": 3.341049382716049e-05,
      "loss": 0.0225,
      "step": 1152
    },
    {
      "epoch": 3.1,
      "eval_accuracy": 1.0,
      "eval_loss": 0.002123473212122917,
      "eval_runtime": 394.5624,
      "eval_samples_per_second": 0.649,
      "eval_steps_per_second": 0.324,
      "step": 1152
    },
    {
      "epoch": 4.1,
      "grad_norm": 0.0422612763941288,
      "learning_rate": 2.785493827160494e-05,
      "loss": 0.0057,
      "step": 1440
    },
    {
      "epoch": 4.1,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0011819098144769669,
      "eval_runtime": 324.5781,
      "eval_samples_per_second": 0.789,
      "eval_steps_per_second": 0.394,
      "step": 1440
    },
    {
      "epoch": 5.1,
      "grad_norm": 0.026100359857082367,
      "learning_rate": 2.2299382716049384e-05,
      "loss": 0.0038,
      "step": 1728
    },
    {
      "epoch": 5.1,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0009726639837026596,
      "eval_runtime": 354.0444,
      "eval_samples_per_second": 0.723,
      "eval_steps_per_second": 0.362,
      "step": 1728
    },
    {
      "epoch": 6.1,
      "grad_norm": 0.02095157280564308,
      "learning_rate": 1.674382716049383e-05,
      "loss": 0.0024,
      "step": 2016
    },
    {
      "epoch": 6.1,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0008304659277200699,
      "eval_runtime": 359.9913,
      "eval_samples_per_second": 0.711,
      "eval_steps_per_second": 0.356,
      "step": 2016
    },
    {
      "epoch": 7.1,
      "grad_norm": 0.028533462435007095,
      "learning_rate": 1.1188271604938271e-05,
      "loss": 0.0016,
      "step": 2304
    },
    {
      "epoch": 7.1,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0007986431010067463,
      "eval_runtime": 294.083,
      "eval_samples_per_second": 0.871,
      "eval_steps_per_second": 0.435,
      "step": 2304
    },
    {
      "epoch": 7.1,
      "step": 2304,
      "total_flos": 4.72490560063663e+19,
      "train_loss": 1.7826555360419054,
      "train_runtime": 26105.5788,
      "train_samples_per_second": 0.883,
      "train_steps_per_second": 0.11
    }
  ],
  "logging_steps": 500,
  "max_steps": 2880,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.72490560063663e+19,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}