{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.998535871156662,
  "eval_steps": 500,
  "global_step": 1024,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.29,
      "learning_rate": 0.0001,
      "loss": 1.4842,
      "step": 100
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 1.4016,
      "step": 200
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001,
      "loss": 1.3892,
      "step": 300
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4543589743589744,
      "eval_loss": 3.4055869579315186,
      "eval_runtime": 4.1688,
      "eval_samples_per_second": 119.938,
      "eval_steps_per_second": 15.112,
      "step": 341
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.09711501224106496,
      "eval_exact_match": 0.0,
      "eval_prefix_exact_match": 0.054,
      "step": 341
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001,
      "loss": 1.3608,
      "step": 400
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001,
      "loss": 1.3456,
      "step": 500
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001,
      "loss": 1.3499,
      "step": 600
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4576923076923077,
      "eval_loss": 3.453113317489624,
      "eval_runtime": 4.4031,
      "eval_samples_per_second": 113.556,
      "eval_steps_per_second": 14.308,
      "step": 683
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.1225593574040313,
      "eval_exact_match": 0.0,
      "eval_prefix_exact_match": 0.056,
      "step": 683
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001,
      "loss": 1.3238,
      "step": 700
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0001,
      "loss": 1.2486,
      "step": 800
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0001,
      "loss": 1.2452,
      "step": 900
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0001,
      "loss": 1.2427,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4584102564102564,
      "eval_loss": 3.671137809753418,
      "eval_runtime": 4.4094,
      "eval_samples_per_second": 113.393,
      "eval_steps_per_second": 14.288,
      "step": 1024
    },
    {
      "epoch": 3.0,
      "eval_bleu": 0.13165889774889974,
      "eval_exact_match": 0.0,
      "eval_prefix_exact_match": 0.056,
      "step": 1024
    }
  ],
  "logging_steps": 100,
  "max_steps": 17050,
  "num_train_epochs": 50,
  "save_steps": 500,
  "total_flos": 2.0298630319151514e+17,
  "trial_name": null,
  "trial_params": null
}