trainer_state.json

{
  "best_metric": 0.49658698950399305,
  "best_model_checkpoint": "checkpoints/msim-mt5-luat",
  "epoch": 0.9943079086586755,
  "global_step": 116,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14,
      "learning_rate": 1.7241379310344828e-05,
      "loss": 0.3263,
      "step": 16
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.4482758620689657e-05,
      "loss": 0.0284,
      "step": 32
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.1724137931034483e-05,
      "loss": 0.0238,
      "step": 48
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.965517241379312e-06,
      "loss": 0.0209,
      "step": 64
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.206896551724138e-06,
      "loss": 0.021,
      "step": 80
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.448275862068966e-06,
      "loss": 0.0178,
      "step": 96
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.896551724137931e-07,
      "loss": 0.0175,
      "step": 112
    },
    {
      "epoch": 0.99,
      "eval_avg_sts": 0.5005058891033085,
      "eval_sickr_spearman": 0.504424788702624,
      "eval_stsb_spearman": 0.49658698950399305,
      "step": 116
    },
    {
      "epoch": 0.99,
      "step": 116,
      "total_flos": 149561804549339136,
      "train_runtime": 4919.3719,
      "train_samples_per_second": 0.024
    }
  ],
  "max_steps": 116,
  "num_train_epochs": 1,
  "total_flos": 149561804549339136,
  "trial_name": null,
  "trial_params": null
}