checkpoint-1500/trainer_state.json

{
  "best_metric": 2.061879873275757,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l55-l/checkpoint-1500",
  "epoch": 0.27629397679130596,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09209799226376865,
      "grad_norm": 0.24957604706287384,
      "learning_rate": 4.846503346227052e-05,
      "loss": 0.7314,
      "step": 500
    },
    {
      "epoch": 0.09209799226376865,
      "eval_loss": 2.0805552005767822,
      "eval_runtime": 77.1179,
      "eval_samples_per_second": 15.638,
      "eval_steps_per_second": 1.958,
      "step": 500
    },
    {
      "epoch": 0.1841959845275373,
      "grad_norm": 1.7965619564056396,
      "learning_rate": 4.693006692454105e-05,
      "loss": 0.706,
      "step": 1000
    },
    {
      "epoch": 0.1841959845275373,
      "eval_loss": 2.083494186401367,
      "eval_runtime": 77.6769,
      "eval_samples_per_second": 15.526,
      "eval_steps_per_second": 1.944,
      "step": 1000
    },
    {
      "epoch": 0.27629397679130596,
      "grad_norm": 2.3431804180145264,
      "learning_rate": 4.539510038681157e-05,
      "loss": 0.7413,
      "step": 1500
    },
    {
      "epoch": 0.27629397679130596,
      "eval_loss": 2.061879873275757,
      "eval_runtime": 78.7083,
      "eval_samples_per_second": 15.322,
      "eval_steps_per_second": 1.918,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 16287,
  "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
}