trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.930524428507396,
  "eval_steps": 500,
  "global_step": 11000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.22,
      "grad_norm": 0.0,
      "learning_rate": 4.775885253249664e-05,
      "loss": 0.0,
      "step": 500
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.0,
      "learning_rate": 4.551770506499328e-05,
      "loss": 0.0,
      "step": 1000
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.0,
      "learning_rate": 4.327655759748992e-05,
      "loss": 0.0,
      "step": 1500
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.0,
      "learning_rate": 4.1035410129986554e-05,
      "loss": 0.0,
      "step": 2000
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.0,
      "learning_rate": 3.8794262662483196e-05,
      "loss": 0.0,
      "step": 2500
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.0,
      "learning_rate": 3.655311519497983e-05,
      "loss": 0.0,
      "step": 3000
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.0,
      "learning_rate": 3.4311967727476465e-05,
      "loss": 0.0,
      "step": 3500
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.0,
      "learning_rate": 3.2070820259973107e-05,
      "loss": 0.0,
      "step": 4000
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.0,
      "learning_rate": 2.9829672792469748e-05,
      "loss": 0.0,
      "step": 4500
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.0,
      "learning_rate": 2.7588525324966386e-05,
      "loss": 0.0,
      "step": 5000
    },
    {
      "epoch": 2.47,
      "grad_norm": 0.0,
      "learning_rate": 2.5347377857463024e-05,
      "loss": 0.0,
      "step": 5500
    },
    {
      "epoch": 2.69,
      "grad_norm": 0.0,
      "learning_rate": 2.310623038995966e-05,
      "loss": 0.0,
      "step": 6000
    },
    {
      "epoch": 2.91,
      "grad_norm": 0.0,
      "learning_rate": 2.08650829224563e-05,
      "loss": 0.0,
      "step": 6500
    },
    {
      "epoch": 3.14,
      "grad_norm": 0.0,
      "learning_rate": 1.8623935454952938e-05,
      "loss": 0.0,
      "step": 7000
    },
    {
      "epoch": 3.36,
      "grad_norm": 0.0,
      "learning_rate": 1.6382787987449573e-05,
      "loss": 0.0,
      "step": 7500
    },
    {
      "epoch": 3.59,
      "grad_norm": 0.0,
      "learning_rate": 1.4141640519946214e-05,
      "loss": 0.0,
      "step": 8000
    },
    {
      "epoch": 3.81,
      "grad_norm": 0.0,
      "learning_rate": 1.1900493052442852e-05,
      "loss": 0.0,
      "step": 8500
    },
    {
      "epoch": 4.03,
      "grad_norm": 0.0,
      "learning_rate": 9.65934558493949e-06,
      "loss": 0.0,
      "step": 9000
    },
    {
      "epoch": 4.26,
      "grad_norm": 0.0,
      "learning_rate": 7.418198117436127e-06,
      "loss": 0.0,
      "step": 9500
    },
    {
      "epoch": 4.48,
      "grad_norm": 0.0,
      "learning_rate": 5.177050649932766e-06,
      "loss": 0.0,
      "step": 10000
    },
    {
      "epoch": 4.71,
      "grad_norm": 0.0,
      "learning_rate": 2.9359031824294042e-06,
      "loss": 0.0,
      "step": 10500
    },
    {
      "epoch": 4.93,
      "grad_norm": 0.0,
      "learning_rate": 6.947557149260422e-07,
      "loss": 0.0,
      "step": 11000
    }
  ],
  "logging_steps": 500,
  "max_steps": 11155,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.781601348825047e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}