trainer_state.json

{
  "best_metric": 0.7359368938316306,
  "best_model_checkpoint": "./models/baseline-LMkor_emo_model/checkpoint-952",
  "epoch": 4.0,
  "global_step": 952,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9746434231378764,
      "eval_f1": 0.5608345902463551,
      "eval_loss": 0.8029250502586365,
      "eval_runtime": 3.237,
      "eval_samples_per_second": 194.934,
      "eval_steps_per_second": 3.398,
      "step": 238
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9778129952456418,
      "eval_f1": 0.6028032770703781,
      "eval_loss": 1.027860164642334,
      "eval_runtime": 3.2318,
      "eval_samples_per_second": 195.244,
      "eval_steps_per_second": 3.404,
      "step": 476
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.3479345947435582e-05,
      "loss": 0.8248,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9730586370839936,
      "eval_f1": 0.5595050367831943,
      "eval_loss": 1.371740698814392,
      "eval_runtime": 3.2428,
      "eval_samples_per_second": 194.587,
      "eval_steps_per_second": 3.392,
      "step": 714
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9746434231378764,
      "eval_f1": 0.7359368938316306,
      "eval_loss": 0.8928404450416565,
      "eval_runtime": 3.9611,
      "eval_samples_per_second": 159.299,
      "eval_steps_per_second": 2.777,
      "step": 952
    }
  ],
  "max_steps": 2380,
  "num_train_epochs": 10,
  "total_flos": 494489293335954.0,
  "trial_name": null,
  "trial_params": null
}