checkpoint-4688/trainer_state.json

{
  "best_metric": 1.233594298362732,
  "best_model_checkpoint": "fairface_age_image_detection/checkpoint-4688",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 4688,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21331058020477817,
      "grad_norm": 1.7164175510406494,
      "learning_rate": 2.2574385510996123e-06,
      "loss": 1.945,
      "step": 500
    },
    {
      "epoch": 0.42662116040955633,
      "grad_norm": 1.979918360710144,
      "learning_rate": 1.9879258300991807e-06,
      "loss": 1.5803,
      "step": 1000
    },
    {
      "epoch": 0.6399317406143344,
      "grad_norm": 2.0418295860290527,
      "learning_rate": 1.7184131090987496e-06,
      "loss": 1.4368,
      "step": 1500
    },
    {
      "epoch": 0.8532423208191127,
      "grad_norm": 2.872443199157715,
      "learning_rate": 1.4489003880983182e-06,
      "loss": 1.3531,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5275,
      "eval_loss": 1.3043227195739746,
      "eval_model_preparation_time": 0.0035,
      "eval_runtime": 894.9363,
      "eval_samples_per_second": 11.174,
      "eval_steps_per_second": 1.397,
      "step": 2344
    },
    {
      "epoch": 1.0665529010238908,
      "grad_norm": 4.807504177093506,
      "learning_rate": 1.179387667097887e-06,
      "loss": 1.3097,
      "step": 2500
    },
    {
      "epoch": 1.2798634812286689,
      "grad_norm": 6.204404830932617,
      "learning_rate": 9.098749460974558e-07,
      "loss": 1.2671,
      "step": 3000
    },
    {
      "epoch": 1.493174061433447,
      "grad_norm": 6.795459270477295,
      "learning_rate": 6.403622250970247e-07,
      "loss": 1.2428,
      "step": 3500
    },
    {
      "epoch": 1.7064846416382253,
      "grad_norm": 3.4942402839660645,
      "learning_rate": 3.708495040965934e-07,
      "loss": 1.2307,
      "step": 4000
    },
    {
      "epoch": 1.9197952218430034,
      "grad_norm": 3.384183406829834,
      "learning_rate": 1.0133678309616215e-07,
      "loss": 1.2214,
      "step": 4500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5385,
      "eval_loss": 1.233594298362732,
      "eval_model_preparation_time": 0.0035,
      "eval_runtime": 903.6391,
      "eval_samples_per_second": 11.066,
      "eval_steps_per_second": 1.383,
      "step": 4688
    }
  ],
  "logging_steps": 500,
  "max_steps": 4688,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.16245277051904e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}