trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1823985408116735,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022799817601459188,
      "grad_norm": 4.15625,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.7819,
      "step": 50
    },
    {
      "epoch": 0.045599635202918376,
      "grad_norm": 2.28125,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.6693,
      "step": 100
    },
    {
      "epoch": 0.06839945280437756,
      "grad_norm": 0.021484375,
      "learning_rate": 0.0001,
      "loss": 0.0543,
      "step": 150
    },
    {
      "epoch": 0.09119927040583675,
      "grad_norm": 0.02978515625,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.0068,
      "step": 200
    },
    {
      "epoch": 0.11399908800729594,
      "grad_norm": 0.072265625,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.003,
      "step": 250
    },
    {
      "epoch": 0.13679890560875513,
      "grad_norm": 0.007110595703125,
      "learning_rate": 0.0002,
      "loss": 0.0028,
      "step": 300
    },
    {
      "epoch": 0.15959872321021432,
      "grad_norm": 0.012939453125,
      "learning_rate": 0.00019840738971173754,
      "loss": 0.001,
      "step": 350
    },
    {
      "epoch": 0.1823985408116735,
      "grad_norm": 0.00201416015625,
      "learning_rate": 0.00019681477942347508,
      "loss": 0.0009,
      "step": 400
    }
  ],
  "logging_steps": 50,
  "max_steps": 6579,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}