checkpoint-200/trainer_state.json

{
  "best_global_step": 200,
  "best_metric": 0.0910862535238266,
  "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-200",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.94625,
      "eval_loss": 0.11963150650262833,
      "eval_model_preparation_time": 0.003,
      "eval_runtime": 169.7911,
      "eval_samples_per_second": 18.847,
      "eval_steps_per_second": 2.356,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.965625,
      "eval_loss": 0.0910862535238266,
      "eval_model_preparation_time": 0.003,
      "eval_runtime": 167.4063,
      "eval_samples_per_second": 19.115,
      "eval_steps_per_second": 2.389,
      "step": 200
    }
  ],
  "logging_steps": 500,
  "max_steps": 300,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.24802904489984e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}