checkpoint-1500/trainer_state.json

{
  "best_metric": 1.4757832288742065,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l59-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": 20.952665328979492,
      "learning_rate": 4.884856300663228e-09,
      "loss": 0.3952,
      "step": 500
    },
    {
      "epoch": 0.09211495946941783,
      "eval_loss": 1.4940427541732788,
      "eval_runtime": 73.9282,
      "eval_samples_per_second": 16.327,
      "eval_steps_per_second": 2.043,
      "step": 500
    },
    {
      "epoch": 0.18422991893883567,
      "grad_norm": 59.28666687011719,
      "learning_rate": 4.769712601326456e-09,
      "loss": 0.4562,
      "step": 1000
    },
    {
      "epoch": 0.18422991893883567,
      "eval_loss": 1.4853259325027466,
      "eval_runtime": 74.6533,
      "eval_samples_per_second": 16.168,
      "eval_steps_per_second": 2.023,
      "step": 1000
    },
    {
      "epoch": 0.2763448784082535,
      "grad_norm": 1.179814338684082,
      "learning_rate": 4.654568901989683e-09,
      "loss": 0.5131,
      "step": 1500
    },
    {
      "epoch": 0.2763448784082535,
      "eval_loss": 1.4757832288742065,
      "eval_runtime": 76.2866,
      "eval_samples_per_second": 15.822,
      "eval_steps_per_second": 1.979,
      "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
}