trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "global_step": 2192,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 3e-05,
      "loss": 1.4992,
      "step": 274
    },
    {
      "epoch": 1.0,
      "eval_exact_match": 72.37961991372275,
      "eval_f1": 75.86711958969134,
      "eval_runtime": 3.8163,
      "eval_samples_per_second": 2247.45,
      "eval_steps_per_second": 7.075,
      "step": 274
    },
    {
      "epoch": 2.0,
      "learning_rate": 3e-05,
      "loss": 0.7954,
      "step": 548
    },
    {
      "epoch": 2.0,
      "eval_exact_match": 72.6477789436866,
      "eval_f1": 75.94557382966855,
      "eval_runtime": 3.0701,
      "eval_samples_per_second": 2793.752,
      "eval_steps_per_second": 8.795,
      "step": 548
    },
    {
      "epoch": 3.0,
      "learning_rate": 3e-05,
      "loss": 0.6424,
      "step": 822
    },
    {
      "epoch": 3.0,
      "eval_exact_match": 72.0531654424624,
      "eval_f1": 75.83772268943578,
      "eval_runtime": 3.0693,
      "eval_samples_per_second": 2794.477,
      "eval_steps_per_second": 8.797,
      "step": 822
    },
    {
      "epoch": 4.0,
      "learning_rate": 3e-05,
      "loss": 0.5303,
      "step": 1096
    },
    {
      "epoch": 4.0,
      "eval_exact_match": 72.22805176635187,
      "eval_f1": 75.9153997406021,
      "eval_runtime": 3.0469,
      "eval_samples_per_second": 2814.976,
      "eval_steps_per_second": 8.861,
      "step": 1096
    },
    {
      "epoch": 5.0,
      "learning_rate": 3e-05,
      "loss": 0.4455,
      "step": 1370
    },
    {
      "epoch": 5.0,
      "eval_exact_match": 72.6477789436866,
      "eval_f1": 75.75701909023866,
      "eval_runtime": 3.072,
      "eval_samples_per_second": 2791.953,
      "eval_steps_per_second": 8.789,
      "step": 1370
    },
    {
      "epoch": 6.0,
      "learning_rate": 3e-05,
      "loss": 0.3811,
      "step": 1644
    },
    {
      "epoch": 6.0,
      "eval_exact_match": 72.6827562084645,
      "eval_f1": 75.97434781831825,
      "eval_runtime": 3.0795,
      "eval_samples_per_second": 2785.228,
      "eval_steps_per_second": 8.768,
      "step": 1644
    },
    {
      "epoch": 7.0,
      "learning_rate": 3e-05,
      "loss": 0.3304,
      "step": 1918
    },
    {
      "epoch": 7.0,
      "eval_exact_match": 72.85764253235396,
      "eval_f1": 75.94136333360241,
      "eval_runtime": 3.0675,
      "eval_samples_per_second": 2796.077,
      "eval_steps_per_second": 8.802,
      "step": 1918
    },
    {
      "epoch": 8.0,
      "learning_rate": 3e-05,
      "loss": 0.2894,
      "step": 2192
    },
    {
      "epoch": 8.0,
      "eval_exact_match": 72.6594380319459,
      "eval_f1": 76.13961062883962,
      "eval_runtime": 3.0768,
      "eval_samples_per_second": 2787.62,
      "eval_steps_per_second": 8.775,
      "step": 2192
    }
  ],
  "max_steps": 2740,
  "num_train_epochs": 10,
  "total_flos": 264668247490560.0,
  "trial_name": null,
  "trial_params": null
}