trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08456659619450317,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.272727272727273e-05,
      "loss": 0.5525,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.0202020202020203e-05,
      "loss": 0.1094,
      "step": 100
    },
    {
      "epoch": 0.03,
      "eval_loss": 0.08147025853395462,
      "eval_runtime": 380.9782,
      "eval_samples_per_second": 3.921,
      "eval_steps_per_second": 0.491,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.7676767676767676e-05,
      "loss": 0.078,
      "step": 150
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 0.0661,
      "step": 200
    },
    {
      "epoch": 0.06,
      "eval_loss": 0.0661635473370552,
      "eval_runtime": 381.0472,
      "eval_samples_per_second": 3.921,
      "eval_steps_per_second": 0.491,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.2626262626262628e-05,
      "loss": 0.0645,
      "step": 250
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.0101010101010101e-05,
      "loss": 0.0632,
      "step": 300
    },
    {
      "epoch": 0.08,
      "eval_loss": 0.06215110421180725,
      "eval_runtime": 381.0085,
      "eval_samples_per_second": 3.921,
      "eval_steps_per_second": 0.491,
      "step": 300
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 1.054779409170432e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}