trainer_state.json

{
  "best_metric": 0.39,
  "best_model_checkpoint": "/data/data2/azhar/mine/testing_chamber/bpn-mining-model/swin-transformer/checkpoint-6",
  "epoch": 2.1818181818181817,
  "eval_steps": 500,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7272727272727273,
      "eval_accuracy": 0.3,
      "eval_f1": 0.21609904935862845,
      "eval_loss": 2.076603651046753,
      "eval_runtime": 0.7765,
      "eval_samples_per_second": 128.784,
      "eval_steps_per_second": 2.576,
      "step": 2
    },
    {
      "epoch": 1.8181818181818183,
      "eval_accuracy": 0.37,
      "eval_f1": 0.2461453180965376,
      "eval_loss": 1.768675684928894,
      "eval_runtime": 0.7757,
      "eval_samples_per_second": 128.909,
      "eval_steps_per_second": 2.578,
      "step": 5
    },
    {
      "epoch": 2.1818181818181817,
      "eval_accuracy": 0.39,
      "eval_f1": 0.27527716186252765,
      "eval_loss": 1.73661208152771,
      "eval_runtime": 0.7746,
      "eval_samples_per_second": 129.092,
      "eval_steps_per_second": 2.582,
      "step": 6
    },
    {
      "epoch": 2.1818181818181817,
      "step": 6,
      "total_flos": 5.44949848203264e+16,
      "train_loss": 2.0223546028137207,
      "train_runtime": 26.4538,
      "train_samples_per_second": 113.405,
      "train_steps_per_second": 0.227
    }
  ],
  "logging_steps": 10,
  "max_steps": 6,
  "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": 5.44949848203264e+16,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}