trainer_state.json

{
  "best_metric": 0.8285718560218811,
  "best_model_checkpoint": "./results/resnet/tumour/checkpoint-975",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 975,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 4.508346080780029,
      "eval_runtime": 77.3249,
      "eval_samples_per_second": 10.475,
      "eval_steps_per_second": 0.66,
      "step": 195
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.457480549812317,
      "eval_runtime": 77.608,
      "eval_samples_per_second": 10.437,
      "eval_steps_per_second": 0.657,
      "step": 390
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 205.6478729248047,
      "learning_rate": 9.743589743589744e-06,
      "loss": 3.0791,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.9050098657608032,
      "eval_runtime": 78.6283,
      "eval_samples_per_second": 10.302,
      "eval_steps_per_second": 0.649,
      "step": 585
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.8538194298744202,
      "eval_runtime": 79.9143,
      "eval_samples_per_second": 10.136,
      "eval_steps_per_second": 0.638,
      "step": 780
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.8285718560218811,
      "eval_runtime": 79.1036,
      "eval_samples_per_second": 10.24,
      "eval_steps_per_second": 0.645,
      "step": 975
    },
    {
      "epoch": 5.0,
      "step": 975,
      "total_flos": 3.588142521058099e+17,
      "train_loss": 1.746917755909455,
      "train_runtime": 2049.8226,
      "train_samples_per_second": 7.584,
      "train_steps_per_second": 0.476
    }
  ],
  "logging_steps": 500,
  "max_steps": 975,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 3.588142521058099e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}