trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.236671362215321e-05,
  "eval_steps": 10,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.236671362215321e-06,
      "grad_norm": 0.75390625,
      "learning_rate": 3.3333333333333337e-06,
      "loss": 2.9563,
      "step": 1
    },
    {
      "epoch": 1.0473342724430642e-05,
      "grad_norm": 0.74609375,
      "learning_rate": 6.6666666666666675e-06,
      "loss": 2.5902,
      "step": 2
    },
    {
      "epoch": 1.5710014086645963e-05,
      "grad_norm": 0.7421875,
      "learning_rate": 1e-05,
      "loss": 3.0025,
      "step": 3
    },
    {
      "epoch": 2.0946685448861285e-05,
      "grad_norm": 0.69921875,
      "learning_rate": 1.3333333333333335e-05,
      "loss": 3.2071,
      "step": 4
    },
    {
      "epoch": 2.6183356811076606e-05,
      "grad_norm": 0.7109375,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.8776,
      "step": 5
    },
    {
      "epoch": 3.142002817329193e-05,
      "grad_norm": 0.87109375,
      "learning_rate": 2e-05,
      "loss": 2.6961,
      "step": 6
    },
    {
      "epoch": 3.665669953550725e-05,
      "grad_norm": 0.7265625,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 3.0848,
      "step": 7
    },
    {
      "epoch": 4.189337089772257e-05,
      "grad_norm": 0.69140625,
      "learning_rate": 2.666666666666667e-05,
      "loss": 2.2647,
      "step": 8
    },
    {
      "epoch": 4.713004225993789e-05,
      "grad_norm": 0.73828125,
      "learning_rate": 3e-05,
      "loss": 3.293,
      "step": 9
    },
    {
      "epoch": 5.236671362215321e-05,
      "grad_norm": 0.87890625,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.6686,
      "step": 10
    },
    {
      "epoch": 5.236671362215321e-05,
      "eval_runtime": 70.4378,
      "eval_samples_per_second": 14.538,
      "eval_steps_per_second": 0.454,
      "step": 10
    },
    {
      "epoch": 5.236671362215321e-05,
      "eval/hellaswag_acc": 0.37621987651862177,
      "eval/hellaswag_acc_norm": 0.4691296554471221,
      "eval_hellaswag_elapsed_time": 235.1232237815857,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 190961,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 646101577236480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}