baseline_bs4_top2/checkpoint-20000/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01705516920859751,
  "eval_steps": 500,
  "global_step": 20000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.6449,
      "step": 500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5651,
      "step": 1000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5875,
      "step": 1500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5539,
      "step": 2000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5524,
      "step": 2500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5449,
      "step": 3000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.549,
      "step": 3500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5671,
      "step": 4000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5251,
      "step": 4500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5532,
      "step": 5000
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.01,
      "loss": 1.5262,
      "step": 5500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5306,
      "step": 6000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5273,
      "step": 6500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.519,
      "step": 7000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5305,
      "step": 7500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.507,
      "step": 8000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5255,
      "step": 8500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5106,
      "step": 9000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5224,
      "step": 9500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5241,
      "step": 10000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5311,
      "step": 10500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5202,
      "step": 11000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5247,
      "step": 11500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5305,
      "step": 12000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5179,
      "step": 12500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.4874,
      "step": 13000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5302,
      "step": 13500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5048,
      "step": 14000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.4812,
      "step": 14500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5259,
      "step": 15000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5175,
      "step": 15500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5104,
      "step": 16000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5367,
      "step": 16500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5121,
      "step": 17000
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.01,
      "loss": 1.5041,
      "step": 17500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.5155,
      "step": 18000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.5012,
      "step": 18500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.5193,
      "step": 19000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.521,
      "step": 19500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.01,
      "loss": 1.5138,
      "step": 20000
    }
  ],
  "logging_steps": 500,
  "max_steps": 20000,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "total_flos": 9.652535293088563e+16,
  "trial_name": null,
  "trial_params": null
}