trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9323671497584543,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24,
      "eval_loss": 1.0984270572662354,
      "eval_runtime": 21.1382,
      "eval_samples_per_second": 7.664,
      "eval_steps_per_second": 0.993,
      "step": 50
    },
    {
      "epoch": 0.48,
      "eval_loss": 1.0866656303405762,
      "eval_runtime": 21.1298,
      "eval_samples_per_second": 7.667,
      "eval_steps_per_second": 0.994,
      "step": 100
    },
    {
      "epoch": 0.72,
      "eval_loss": 1.0614020824432373,
      "eval_runtime": 21.1356,
      "eval_samples_per_second": 7.665,
      "eval_steps_per_second": 0.994,
      "step": 150
    },
    {
      "epoch": 0.97,
      "eval_loss": 1.0404683351516724,
      "eval_runtime": 21.1305,
      "eval_samples_per_second": 7.667,
      "eval_steps_per_second": 0.994,
      "step": 200
    },
    {
      "epoch": 1.21,
      "eval_loss": 1.062158465385437,
      "eval_runtime": 21.14,
      "eval_samples_per_second": 7.663,
      "eval_steps_per_second": 0.993,
      "step": 250
    },
    {
      "epoch": 1.45,
      "eval_loss": 1.0509228706359863,
      "eval_runtime": 21.1314,
      "eval_samples_per_second": 7.666,
      "eval_steps_per_second": 0.994,
      "step": 300
    },
    {
      "epoch": 1.69,
      "eval_loss": 1.03497314453125,
      "eval_runtime": 21.1338,
      "eval_samples_per_second": 7.665,
      "eval_steps_per_second": 0.994,
      "step": 350
    },
    {
      "epoch": 1.93,
      "eval_loss": 1.0270304679870605,
      "eval_runtime": 21.1332,
      "eval_samples_per_second": 7.666,
      "eval_steps_per_second": 0.994,
      "step": 400
    }
  ],
  "logging_steps": 500,
  "max_steps": 2000,
  "num_train_epochs": 10,
  "save_steps": 100,
  "total_flos": 1.2821409870336e+17,
  "trial_name": null,
  "trial_params": null
}