trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 11,
  "global_step": 11,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.3511991500854492,
      "learning_rate": 1e-05,
      "loss": 2.5901,
      "step": 1
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 1.3428705930709839,
      "learning_rate": 9.090909090909091e-06,
      "loss": 2.607,
      "step": 2
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 1.299910068511963,
      "learning_rate": 8.181818181818183e-06,
      "loss": 2.5676,
      "step": 3
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.2755225896835327,
      "learning_rate": 7.272727272727273e-06,
      "loss": 2.5746,
      "step": 4
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 1.185289740562439,
      "learning_rate": 6.363636363636364e-06,
      "loss": 2.4739,
      "step": 5
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.1727769374847412,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 2.4603,
      "step": 6
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 1.1834678649902344,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 2.5204,
      "step": 7
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.1182799339294434,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 2.4285,
      "step": 8
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 1.0836458206176758,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 2.404,
      "step": 9
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.1250439882278442,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 2.5184,
      "step": 10
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.0879329442977905,
      "learning_rate": 9.090909090909091e-07,
      "loss": 2.4612,
      "step": 11
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.5195209980010986,
      "eval_runtime": 1.1688,
      "eval_samples_per_second": 2.567,
      "eval_steps_per_second": 0.856,
      "step": 11
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 11,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8757710040334336.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}