trainer_state.json

{
  "best_metric": 1.0,
  "best_model_checkpoint": "segformer-class-classWeights-augmentation/checkpoint-6",
  "epoch": 8.88888888888889,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.89,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.04543434828519821,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.9849,
      "eval_samples_per_second": 29.446,
      "eval_steps_per_second": 3.046,
      "step": 6
    },
    {
      "epoch": 1.48,
      "learning_rate": 1.992337164750958e-05,
      "loss": 0.1558,
      "step": 10
    },
    {
      "epoch": 1.93,
      "eval_accuracy": 0.9655172413793104,
      "eval_f1": 0.964683592269799,
      "eval_loss": 0.08155026286840439,
      "eval_precision": 0.9674329501915708,
      "eval_recall": 0.9655172413793104,
      "eval_runtime": 0.7233,
      "eval_samples_per_second": 40.093,
      "eval_steps_per_second": 4.148,
      "step": 13
    },
    {
      "epoch": 2.96,
      "learning_rate": 1.9846743295019158e-05,
      "loss": 0.1727,
      "step": 20
    },
    {
      "epoch": 2.96,
      "eval_accuracy": 0.9655172413793104,
      "eval_f1": 0.964683592269799,
      "eval_loss": 0.07752516865730286,
      "eval_precision": 0.9674329501915708,
      "eval_recall": 0.9655172413793104,
      "eval_runtime": 0.9304,
      "eval_samples_per_second": 31.17,
      "eval_steps_per_second": 3.225,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9655172413793104,
      "eval_f1": 0.964683592269799,
      "eval_loss": 0.04428544268012047,
      "eval_precision": 0.9674329501915708,
      "eval_recall": 0.9655172413793104,
      "eval_runtime": 0.7055,
      "eval_samples_per_second": 41.107,
      "eval_steps_per_second": 4.252,
      "step": 27
    },
    {
      "epoch": 4.44,
      "learning_rate": 1.9770114942528737e-05,
      "loss": 0.1299,
      "step": 30
    },
    {
      "epoch": 4.89,
      "eval_accuracy": 0.9655172413793104,
      "eval_f1": 0.964683592269799,
      "eval_loss": 0.053459376096725464,
      "eval_precision": 0.9674329501915708,
      "eval_recall": 0.9655172413793104,
      "eval_runtime": 0.7107,
      "eval_samples_per_second": 40.805,
      "eval_steps_per_second": 4.221,
      "step": 33
    },
    {
      "epoch": 5.93,
      "learning_rate": 1.9693486590038315e-05,
      "loss": 0.1808,
      "step": 40
    },
    {
      "epoch": 5.93,
      "eval_accuracy": 0.9655172413793104,
      "eval_f1": 0.964683592269799,
      "eval_loss": 0.029818205162882805,
      "eval_precision": 0.9674329501915708,
      "eval_recall": 0.9655172413793104,
      "eval_runtime": 0.932,
      "eval_samples_per_second": 31.115,
      "eval_steps_per_second": 3.219,
      "step": 40
    },
    {
      "epoch": 6.96,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.019522428512573242,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.699,
      "eval_samples_per_second": 41.486,
      "eval_steps_per_second": 4.292,
      "step": 47
    },
    {
      "epoch": 7.41,
      "learning_rate": 1.9616858237547893e-05,
      "loss": 0.1406,
      "step": 50
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9655172413793104,
      "eval_f1": 0.964683592269799,
      "eval_loss": 0.05264897271990776,
      "eval_precision": 0.9674329501915708,
      "eval_recall": 0.9655172413793104,
      "eval_runtime": 0.6927,
      "eval_samples_per_second": 41.863,
      "eval_steps_per_second": 4.331,
      "step": 54
    },
    {
      "epoch": 8.89,
      "learning_rate": 1.9540229885057475e-05,
      "loss": 0.1193,
      "step": 60
    },
    {
      "epoch": 8.89,
      "eval_accuracy": 0.9655172413793104,
      "eval_f1": 0.964683592269799,
      "eval_loss": 0.14525191485881805,
      "eval_precision": 0.9674329501915708,
      "eval_recall": 0.9655172413793104,
      "eval_runtime": 0.9816,
      "eval_samples_per_second": 29.543,
      "eval_steps_per_second": 3.056,
      "step": 60
    },
    {
      "epoch": 8.89,
      "step": 60,
      "total_flos": 5.786635923932774e+16,
      "train_loss": 0.14985284606615704,
      "train_runtime": 220.5615,
      "train_samples_per_second": 11.833,
      "train_steps_per_second": 0.272
    }
  ],
  "max_steps": 60,
  "num_train_epochs": 10,
  "total_flos": 5.786635923932774e+16,
  "trial_name": null,
  "trial_params": null
}