trainer_state.json

{
  "best_metric": 0.7021333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0187/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 159.78395080566406,
      "learning_rate": 2.5e-05,
      "loss": 3.8671,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.33413333333333334,
      "eval_loss": 3.798372507095337,
      "eval_runtime": 9.2066,
      "eval_samples_per_second": 407.315,
      "eval_steps_per_second": 6.408,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 141.2098388671875,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 3.4515,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5197333333333334,
      "eval_loss": 3.05800461769104,
      "eval_runtime": 7.643,
      "eval_samples_per_second": 490.646,
      "eval_steps_per_second": 7.719,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 260.08026123046875,
      "learning_rate": 1.5e-05,
      "loss": 2.5539,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6024,
      "eval_loss": 2.041151285171509,
      "eval_runtime": 7.6541,
      "eval_samples_per_second": 489.936,
      "eval_steps_per_second": 7.708,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 223.23348999023438,
      "learning_rate": 9.999999999999999e-06,
      "loss": 1.7582,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6626666666666666,
      "eval_loss": 1.5822703838348389,
      "eval_runtime": 8.0396,
      "eval_samples_per_second": 466.442,
      "eval_steps_per_second": 7.339,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 241.17361450195312,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 1.4264,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7008,
      "eval_loss": 1.338184118270874,
      "eval_runtime": 7.9284,
      "eval_samples_per_second": 472.985,
      "eval_steps_per_second": 7.442,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 241.77935791015625,
      "learning_rate": 0.0,
      "loss": 1.2918,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7021333333333334,
      "eval_loss": 1.2734109163284302,
      "eval_runtime": 8.0215,
      "eval_samples_per_second": 467.495,
      "eval_steps_per_second": 7.355,
      "step": 1998
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.9058575437312e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}