checkpoint-1500/trainer_state.json

{
  "best_metric": 1.2100127935409546,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l17-l/checkpoint-1500",
  "epoch": 0.1599829351535836,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05332764505119454,
      "grad_norm": 247.07174682617188,
      "learning_rate": 9.822241183162683e-08,
      "loss": 0.4515,
      "step": 500
    },
    {
      "epoch": 0.05332764505119454,
      "eval_loss": 1.38526451587677,
      "eval_runtime": 63.6956,
      "eval_samples_per_second": 15.496,
      "eval_steps_per_second": 1.947,
      "step": 500
    },
    {
      "epoch": 0.10665529010238908,
      "grad_norm": 72.11767578125,
      "learning_rate": 9.64448236632537e-08,
      "loss": 0.414,
      "step": 1000
    },
    {
      "epoch": 0.10665529010238908,
      "eval_loss": 1.284197211265564,
      "eval_runtime": 62.7418,
      "eval_samples_per_second": 15.731,
      "eval_steps_per_second": 1.976,
      "step": 1000
    },
    {
      "epoch": 0.1599829351535836,
      "grad_norm": 812.2269287109375,
      "learning_rate": 9.466723549488054e-08,
      "loss": 0.3279,
      "step": 1500
    },
    {
      "epoch": 0.1599829351535836,
      "eval_loss": 1.2100127935409546,
      "eval_runtime": 62.6215,
      "eval_samples_per_second": 15.761,
      "eval_steps_per_second": 1.98,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 28128,
  "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": 540357043592520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}