trainer_state.json

{
  "best_metric": 0.8408,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0119/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 84.44805145263672,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.228,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6064,
      "eval_loss": 1.6652494668960571,
      "eval_runtime": 7.4575,
      "eval_samples_per_second": 502.851,
      "eval_steps_per_second": 7.912,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 98.2839126586914,
      "learning_rate": 6e-05,
      "loss": 1.0412,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7728,
      "eval_loss": 0.7656798362731934,
      "eval_runtime": 7.5098,
      "eval_samples_per_second": 499.35,
      "eval_steps_per_second": 7.856,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 92.2596206665039,
      "learning_rate": 4.5e-05,
      "loss": 0.6409,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.816,
      "eval_loss": 0.5897997617721558,
      "eval_runtime": 7.4893,
      "eval_samples_per_second": 500.717,
      "eval_steps_per_second": 7.878,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 82.87971496582031,
      "learning_rate": 3e-05,
      "loss": 0.507,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8293333333333334,
      "eval_loss": 0.5527738332748413,
      "eval_runtime": 7.4817,
      "eval_samples_per_second": 501.225,
      "eval_steps_per_second": 7.886,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 100.02799224853516,
      "learning_rate": 1.5e-05,
      "loss": 0.4411,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8408,
      "eval_loss": 0.5221856236457825,
      "eval_runtime": 7.5016,
      "eval_samples_per_second": 499.891,
      "eval_steps_per_second": 7.865,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}