checkpoint-1200/trainer_state.json

{
  "best_metric": 1.5165716409683228,
  "best_model_checkpoint": "facial_age_estimator/checkpoint-1200",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4476590753592024,
      "eval_loss": 1.694000482559204,
      "eval_runtime": 87.798,
      "eval_samples_per_second": 116.529,
      "eval_steps_per_second": 1.822,
      "step": 120
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4534258625745284,
      "eval_loss": 1.654381275177002,
      "eval_runtime": 87.4351,
      "eval_samples_per_second": 117.013,
      "eval_steps_per_second": 1.83,
      "step": 240
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4608542664451178,
      "eval_loss": 1.618933081626892,
      "eval_runtime": 87.806,
      "eval_samples_per_second": 116.518,
      "eval_steps_per_second": 1.822,
      "step": 360
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4673052487537875,
      "eval_loss": 1.6022893190383911,
      "eval_runtime": 87.7995,
      "eval_samples_per_second": 116.527,
      "eval_steps_per_second": 1.822,
      "step": 480
    },
    {
      "epoch": 4.166666666666667,
      "grad_norm": 3.601428747177124,
      "learning_rate": 6.086956521739132e-06,
      "loss": 1.5209,
      "step": 500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.47023751343954645,
      "eval_loss": 1.572880744934082,
      "eval_runtime": 88.2571,
      "eval_samples_per_second": 115.923,
      "eval_steps_per_second": 1.813,
      "step": 600
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4768839800606001,
      "eval_loss": 1.5591648817062378,
      "eval_runtime": 87.4224,
      "eval_samples_per_second": 117.03,
      "eval_steps_per_second": 1.83,
      "step": 720
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4815756035578145,
      "eval_loss": 1.5406521558761597,
      "eval_runtime": 87.5838,
      "eval_samples_per_second": 116.814,
      "eval_steps_per_second": 1.827,
      "step": 840
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.48138011924543056,
      "eval_loss": 1.5303517580032349,
      "eval_runtime": 87.3649,
      "eval_samples_per_second": 117.107,
      "eval_steps_per_second": 1.831,
      "step": 960
    },
    {
      "epoch": 8.333333333333334,
      "grad_norm": 4.306453227996826,
      "learning_rate": 1.7391304347826088e-06,
      "loss": 1.369,
      "step": 1000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.4878311015541003,
      "eval_loss": 1.51864492893219,
      "eval_runtime": 88.2907,
      "eval_samples_per_second": 115.879,
      "eval_steps_per_second": 1.812,
      "step": 1080
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.49086110839605124,
      "eval_loss": 1.5165716409683228,
      "eval_runtime": 87.8471,
      "eval_samples_per_second": 116.464,
      "eval_steps_per_second": 1.821,
      "step": 1200
    }
  ],
  "logging_steps": 500,
  "max_steps": 1200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 1.2071959063022186e+19,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}