{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 0.6251392960548401,
      "learning_rate": 5e-05,
      "loss": 2.427,
      "step": 100
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6590011715888977,
      "learning_rate": 5e-05,
      "loss": 2.2748,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5142539682539683,
      "eval_loss": 2.336690902709961,
      "eval_runtime": 5.4733,
      "eval_samples_per_second": 91.353,
      "eval_steps_per_second": 11.51,
      "step": 250
    },
    {
      "epoch": 1.0,
      "eval_exact_match": 16.8,
      "eval_f1": 24.850246583481884,
      "step": 250
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.8194239139556885,
      "learning_rate": 5e-05,
      "loss": 2.2322,
      "step": 300
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.9867294430732727,
      "learning_rate": 5e-05,
      "loss": 2.1904,
      "step": 400
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9660400152206421,
      "learning_rate": 5e-05,
      "loss": 2.1657,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5168253968253969,
      "eval_loss": 2.323688507080078,
      "eval_runtime": 5.1683,
      "eval_samples_per_second": 96.744,
      "eval_steps_per_second": 12.19,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_exact_match": 17.2,
      "eval_f1": 24.620036075036083,
      "step": 500
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.281128168106079,
      "learning_rate": 5e-05,
      "loss": 2.0251,
      "step": 600
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.3365116119384766,
      "learning_rate": 5e-05,
      "loss": 2.0158,
      "step": 700
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5156507936507937,
      "eval_loss": 2.3560824394226074,
      "eval_runtime": 5.4675,
      "eval_samples_per_second": 91.449,
      "eval_steps_per_second": 11.523,
      "step": 750
    },
    {
      "epoch": 3.0,
      "eval_exact_match": 19.0,
      "eval_f1": 27.242790688843332,
      "step": 750
    }
  ],
  "logging_steps": 100,
  "max_steps": 12500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.940307860835533e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}