trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 2157,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7,
      "learning_rate": 4.027710257656782e-05,
      "loss": 0.8673,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy_Flower": 0.0,
      "eval_accuracy_Fruit": 0.6187969917205768,
      "eval_accuracy_Leaf": 0.027110182813683492,
      "eval_accuracy_Stem": 0.00984884036851335,
      "eval_accuracy_void": NaN,
      "eval_iou_Flower": 0.0,
      "eval_iou_Fruit": 0.6135452082676719,
      "eval_iou_Leaf": 0.02710993329044417,
      "eval_iou_Stem": 0.009847838626079469,
      "eval_iou_void": 0.0,
      "eval_loss": 0.4826911985874176,
      "eval_mean_accuracy": 0.1639390037256934,
      "eval_mean_iou": 0.13010059603683913,
      "eval_overall_accuracy": 0.22269417401620872,
      "eval_runtime": 629.1507,
      "eval_samples_per_second": 2.284,
      "eval_steps_per_second": 0.286,
      "step": 719
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.812348079727759e-05,
      "loss": 0.4457,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy_Flower": 0.0,
      "eval_accuracy_Fruit": 0.5224305614109305,
      "eval_accuracy_Leaf": 0.030497162112158364,
      "eval_accuracy_Stem": 0.01345547780335815,
      "eval_accuracy_void": NaN,
      "eval_iou_Flower": 0.0,
      "eval_iou_Fruit": 0.5208764218356096,
      "eval_iou_Leaf": 0.03049613008799236,
      "eval_iou_Stem": 0.013451725440891977,
      "eval_iou_void": 0.0,
      "eval_loss": 0.5555266737937927,
      "eval_mean_accuracy": 0.14159580033161173,
      "eval_mean_iou": 0.11296485547289878,
      "eval_overall_accuracy": 0.19273811257470955,
      "eval_runtime": 608.2307,
      "eval_samples_per_second": 2.363,
      "eval_steps_per_second": 0.296,
      "step": 1438
    },
    {
      "epoch": 2.09,
      "learning_rate": 1.596985901798736e-05,
      "loss": 0.3611,
      "step": 1500
    },
    {
      "epoch": 2.78,
      "learning_rate": 3.816237238697132e-06,
      "loss": 0.3272,
      "step": 2000
    },
    {
      "epoch": 3.0,
      "eval_accuracy_Flower": 0.0,
      "eval_accuracy_Fruit": 0.5207503711922854,
      "eval_accuracy_Leaf": 0.019658400128824395,
      "eval_accuracy_Stem": 0.008740514065810164,
      "eval_accuracy_void": NaN,
      "eval_iou_Flower": 0.0,
      "eval_iou_Fruit": 0.5192388236213553,
      "eval_iou_Leaf": 0.019658382089666124,
      "eval_iou_Stem": 0.008740514065810164,
      "eval_iou_void": 0.0,
      "eval_loss": 0.563906192779541,
      "eval_mean_accuracy": 0.13728732134672997,
      "eval_mean_iou": 0.1095275439553663,
      "eval_overall_accuracy": 0.18580018135979884,
      "eval_runtime": 598.0982,
      "eval_samples_per_second": 2.403,
      "eval_steps_per_second": 0.301,
      "step": 2157
    },
    {
      "epoch": 3.0,
      "step": 2157,
      "total_flos": 3.021570149371085e+17,
      "train_loss": 0.48755044808916104,
      "train_runtime": 3369.8837,
      "train_samples_per_second": 5.114,
      "train_steps_per_second": 0.64
    }
  ],
  "logging_steps": 500,
  "max_steps": 2157,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 3.021570149371085e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}