{
  "best_metric": 0.8730660676956177,
  "best_model_checkpoint": "/tmp/model/checkpoint-10",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "learning_rate": 0.00016666666666666666,
      "loss": 1.0986,
      "step": 1
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003333333333333333,
      "loss": 1.0986,
      "step": 2
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.25,
      "eval_f1_macro": 0.13333333333333333,
      "eval_f1_micro": 0.25,
      "eval_f1_weighted": 0.1,
      "eval_loss": 1.0986123085021973,
      "eval_precision_macro": 0.08333333333333333,
      "eval_precision_micro": 0.25,
      "eval_precision_weighted": 0.0625,
      "eval_recall_macro": 0.3333333333333333,
      "eval_recall_micro": 0.25,
      "eval_recall_weighted": 0.25,
      "eval_runtime": 1.2304,
      "eval_samples_per_second": 3.251,
      "eval_steps_per_second": 0.813,
      "step": 2
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0005,
      "loss": 1.0961,
      "step": 3
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00042857142857142855,
      "loss": 1.1095,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.25,
      "eval_f1_macro": 0.13333333333333333,
      "eval_f1_micro": 0.25,
      "eval_f1_weighted": 0.1,
      "eval_loss": 1.0986123085021973,
      "eval_precision_macro": 0.08333333333333333,
      "eval_precision_micro": 0.25,
      "eval_precision_weighted": 0.0625,
      "eval_recall_macro": 0.3333333333333333,
      "eval_recall_micro": 0.25,
      "eval_recall_weighted": 0.25,
      "eval_runtime": 1.2033,
      "eval_samples_per_second": 3.324,
      "eval_steps_per_second": 0.831,
      "step": 4
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00035714285714285714,
      "loss": 1.0834,
      "step": 5
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0002857142857142857,
      "loss": 1.0603,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5,
      "eval_f1_macro": 0.38888888888888884,
      "eval_f1_micro": 0.5,
      "eval_f1_weighted": 0.4583333333333333,
      "eval_loss": 1.0029972791671753,
      "eval_precision_macro": 0.4444444444444444,
      "eval_precision_micro": 0.5,
      "eval_precision_weighted": 0.5833333333333334,
      "eval_recall_macro": 0.5,
      "eval_recall_micro": 0.5,
      "eval_recall_weighted": 0.5,
      "eval_runtime": 1.2155,
      "eval_samples_per_second": 3.291,
      "eval_steps_per_second": 0.823,
      "step": 6
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.00021428571428571427,
      "loss": 1.0027,
      "step": 7
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00014285714285714284,
      "loss": 1.012,
      "step": 8
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.75,
      "eval_f1_macro": 0.5555555555555555,
      "eval_f1_micro": 0.75,
      "eval_f1_weighted": 0.6666666666666666,
      "eval_loss": 0.93815678358078,
      "eval_precision_macro": 0.5,
      "eval_precision_micro": 0.75,
      "eval_precision_weighted": 0.625,
      "eval_recall_macro": 0.6666666666666666,
      "eval_recall_micro": 0.75,
      "eval_recall_weighted": 0.75,
      "eval_runtime": 1.2096,
      "eval_samples_per_second": 3.307,
      "eval_steps_per_second": 0.827,
      "step": 8
    },
    {
      "epoch": 4.5,
      "learning_rate": 7.142857142857142e-05,
      "loss": 0.9143,
      "step": 9
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.9452,
      "step": 10
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 1.0,
      "eval_f1_macro": 1.0,
      "eval_f1_micro": 1.0,
      "eval_f1_weighted": 1.0,
      "eval_loss": 0.8730660676956177,
      "eval_precision_macro": 1.0,
      "eval_precision_micro": 1.0,
      "eval_precision_weighted": 1.0,
      "eval_recall_macro": 1.0,
      "eval_recall_micro": 1.0,
      "eval_recall_weighted": 1.0,
      "eval_runtime": 1.2396,
      "eval_samples_per_second": 3.227,
      "eval_steps_per_second": 0.807,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 4649561049047040.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}