checkpoint-1500/trainer_state.json

{
  "best_metric": 1.5022265911102295,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e5l510-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": 21.660480499267578,
      "learning_rate": 4.907885040530583e-10,
      "loss": 0.3974,
      "step": 500
    },
    {
      "epoch": 0.09211495946941783,
      "eval_loss": 1.5028706789016724,
      "eval_runtime": 74.0662,
      "eval_samples_per_second": 16.296,
      "eval_steps_per_second": 2.039,
      "step": 500
    },
    {
      "epoch": 0.18422991893883567,
      "grad_norm": 60.26338577270508,
      "learning_rate": 4.815770081061165e-10,
      "loss": 0.462,
      "step": 1000
    },
    {
      "epoch": 0.18422991893883567,
      "eval_loss": 1.5025668144226074,
      "eval_runtime": 75.1835,
      "eval_samples_per_second": 16.054,
      "eval_steps_per_second": 2.008,
      "step": 1000
    },
    {
      "epoch": 0.2763448784082535,
      "grad_norm": 1.4199143648147583,
      "learning_rate": 4.723655121591747e-10,
      "loss": 0.5249,
      "step": 1500
    },
    {
      "epoch": 0.2763448784082535,
      "eval_loss": 1.5022265911102295,
      "eval_runtime": 76.3442,
      "eval_samples_per_second": 15.81,
      "eval_steps_per_second": 1.978,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 27140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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
}