checkpoint-511/trainer_state.json

{
  "best_global_step": 511,
  "best_metric": 0.18303145468235016,
  "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-511",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 511,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9784735812133072,
      "grad_norm": 13.377490043640137,
      "learning_rate": 1.5496489468405215e-05,
      "loss": 0.3912,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.933435301315387,
      "eval_loss": 0.18303145468235016,
      "eval_model_preparation_time": 0.013,
      "eval_runtime": 81.9678,
      "eval_samples_per_second": 199.408,
      "eval_steps_per_second": 24.937,
      "step": 511
    }
  ],
  "logging_steps": 500,
  "max_steps": 2044,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 3.187576517078016e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}