checkpoint-1270/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.980353634577604,
  "eval_steps": 500,
  "global_step": 1270,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.79,
      "learning_rate": 7.952755905511812e-05,
      "loss": 1.7536,
      "step": 101
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.343832020997377e-05,
      "loss": 0.7,
      "step": 202
    },
    {
      "epoch": 2.38,
      "learning_rate": 8.460192475940508e-05,
      "loss": 0.537,
      "step": 303
    },
    {
      "epoch": 3.17,
      "learning_rate": 7.57655293088364e-05,
      "loss": 0.4869,
      "step": 404
    },
    {
      "epoch": 3.97,
      "learning_rate": 6.692913385826773e-05,
      "loss": 0.4598,
      "step": 505
    },
    {
      "epoch": 4.76,
      "learning_rate": 5.8092738407699046e-05,
      "loss": 0.4427,
      "step": 606
    },
    {
      "epoch": 5.56,
      "learning_rate": 4.9256342957130364e-05,
      "loss": 0.4289,
      "step": 707
    },
    {
      "epoch": 6.35,
      "learning_rate": 4.041994750656168e-05,
      "loss": 0.423,
      "step": 808
    },
    {
      "epoch": 7.14,
      "learning_rate": 3.158355205599301e-05,
      "loss": 0.414,
      "step": 909
    },
    {
      "epoch": 7.94,
      "learning_rate": 2.274715660542432e-05,
      "loss": 0.4079,
      "step": 1010
    },
    {
      "epoch": 8.73,
      "learning_rate": 1.3910761154855645e-05,
      "loss": 0.4032,
      "step": 1111
    },
    {
      "epoch": 9.52,
      "learning_rate": 5.074365704286965e-06,
      "loss": 0.4013,
      "step": 1212
    }
  ],
  "logging_steps": 101,
  "max_steps": 1270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.0186295745134592e+18,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}