trainer_state.json

{
  "best_metric": 0.30833333333333335,
  "best_model_checkpoint": "resnet-18-please-work/checkpoint-25",
  "epoch": 2.9411764705882355,
  "eval_steps": 500,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.39215686274509803,
      "grad_norm": NaN,
      "learning_rate": 4.850746268656717e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": NaN,
      "learning_rate": 4.104477611940299e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.9803921568627451,
      "eval_accuracy": 0.30833333333333335,
      "eval_loss": NaN,
      "eval_runtime": 2.1345,
      "eval_samples_per_second": 168.656,
      "eval_steps_per_second": 5.622,
      "step": 25
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": NaN,
      "learning_rate": 3.358208955223881e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": NaN,
      "learning_rate": 2.6119402985074626e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 1.9607843137254903,
      "grad_norm": NaN,
      "learning_rate": 1.865671641791045e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.30833333333333335,
      "eval_loss": NaN,
      "eval_runtime": 1.8559,
      "eval_samples_per_second": 193.978,
      "eval_steps_per_second": 6.466,
      "step": 51
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": NaN,
      "learning_rate": 1.119402985074627e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 2.7450980392156863,
      "grad_norm": NaN,
      "learning_rate": 3.7313432835820893e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 2.9411764705882355,
      "eval_accuracy": 0.30833333333333335,
      "eval_loss": NaN,
      "eval_runtime": 1.403,
      "eval_samples_per_second": 256.584,
      "eval_steps_per_second": 8.553,
      "step": 75
    },
    {
      "epoch": 2.9411764705882355,
      "step": 75,
      "total_flos": 9.643372488710554e+16,
      "train_loss": 0.0,
      "train_runtime": 96.2766,
      "train_samples_per_second": 100.959,
      "train_steps_per_second": 0.779
    }
  ],
  "logging_steps": 10,
  "max_steps": 75,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.643372488710554e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}