checkpoint-1500/trainer_state.json

{
  "best_metric": 0.8726764917373657,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l57-l/checkpoint-1500",
  "epoch": 0.2763448784082535,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09211495946941783,
      "grad_norm": 3.0293657779693604,
      "learning_rate": 4.884856300663227e-07,
      "loss": 0.271,
      "step": 500
    },
    {
      "epoch": 0.09211495946941783,
      "eval_loss": 1.069305419921875,
      "eval_runtime": 75.1409,
      "eval_samples_per_second": 16.063,
      "eval_steps_per_second": 2.01,
      "step": 500
    },
    {
      "epoch": 0.18422991893883567,
      "grad_norm": 7.3040852546691895,
      "learning_rate": 4.769712601326456e-07,
      "loss": 0.2493,
      "step": 1000
    },
    {
      "epoch": 0.18422991893883567,
      "eval_loss": 0.9427077770233154,
      "eval_runtime": 74.8926,
      "eval_samples_per_second": 16.116,
      "eval_steps_per_second": 2.016,
      "step": 1000
    },
    {
      "epoch": 0.2763448784082535,
      "grad_norm": 0.020736657083034515,
      "learning_rate": 4.654568901989683e-07,
      "loss": 0.2348,
      "step": 1500
    },
    {
      "epoch": 0.2763448784082535,
      "eval_loss": 0.8726764917373657,
      "eval_runtime": 76.6621,
      "eval_samples_per_second": 15.744,
      "eval_steps_per_second": 1.97,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 21712,
  "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": 540357043592520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}