checkpoint-2000/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.329004329004329,
  "eval_steps": 1000,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.65,
      "learning_rate": 6.493506493506493e-07,
      "loss": 2.3458,
      "step": 300
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.2987012987012986e-06,
      "loss": 2.3309,
      "step": 600
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.9480519480519483e-06,
      "loss": 2.2872,
      "step": 900
    },
    {
      "epoch": 2.16,
      "eval_loss": 2.2653801441192627,
      "eval_runtime": 40.5821,
      "eval_samples_per_second": 64.166,
      "eval_steps_per_second": 4.017,
      "step": 1000
    },
    {
      "epoch": 2.6,
      "learning_rate": 2.597402597402597e-06,
      "loss": 2.2593,
      "step": 1200
    },
    {
      "epoch": 3.25,
      "learning_rate": 3.246753246753247e-06,
      "loss": 2.2332,
      "step": 1500
    },
    {
      "epoch": 3.9,
      "learning_rate": 3.896103896103897e-06,
      "loss": 2.1927,
      "step": 1800
    },
    {
      "epoch": 4.33,
      "eval_loss": 2.181955575942993,
      "eval_runtime": 40.5637,
      "eval_samples_per_second": 64.195,
      "eval_steps_per_second": 4.018,
      "step": 2000
    }
  ],
  "logging_steps": 300,
  "max_steps": 9240,
  "num_train_epochs": 20,
  "save_steps": 1000,
  "total_flos": 1.3907025982557389e+17,
  "trial_name": null,
  "trial_params": null
}