{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1366,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.29,
      "learning_rate": 3e-05,
      "loss": 1.574,
      "step": 100
    },
    {
      "epoch": 0.59,
      "learning_rate": 3e-05,
      "loss": 1.474,
      "step": 200
    },
    {
      "epoch": 0.88,
      "learning_rate": 3e-05,
      "loss": 1.4104,
      "step": 300
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4536923076923077,
      "eval_loss": 3.3574578762054443,
      "eval_runtime": 4.4299,
      "eval_samples_per_second": 112.869,
      "eval_steps_per_second": 14.221,
      "step": 341
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.08840557310176213,
      "eval_exact_match": 0.0,
      "eval_prefix_exact_match": 0.058,
      "step": 341
    },
    {
      "epoch": 1.17,
      "learning_rate": 3e-05,
      "loss": 1.3889,
      "step": 400
    },
    {
      "epoch": 1.46,
      "learning_rate": 3e-05,
      "loss": 1.387,
      "step": 500
    },
    {
      "epoch": 1.76,
      "learning_rate": 3e-05,
      "loss": 1.389,
      "step": 600
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4543589743589744,
      "eval_loss": 3.4179794788360596,
      "eval_runtime": 4.1997,
      "eval_samples_per_second": 119.055,
      "eval_steps_per_second": 15.001,
      "step": 683
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.09820569565497561,
      "eval_exact_match": 0.0,
      "eval_prefix_exact_match": 0.056,
      "step": 683
    },
    {
      "epoch": 2.05,
      "learning_rate": 3e-05,
      "loss": 1.3725,
      "step": 700
    },
    {
      "epoch": 2.34,
      "learning_rate": 3e-05,
      "loss": 1.3588,
      "step": 800
    },
    {
      "epoch": 2.64,
      "learning_rate": 3e-05,
      "loss": 1.348,
      "step": 900
    },
    {
      "epoch": 2.93,
      "learning_rate": 3e-05,
      "loss": 1.3414,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.45476923076923076,
      "eval_loss": 3.511923313140869,
      "eval_runtime": 4.1985,
      "eval_samples_per_second": 119.089,
      "eval_steps_per_second": 15.005,
      "step": 1024
    },
    {
      "epoch": 3.0,
      "eval_bleu": 0.09889831624589397,
      "eval_exact_match": 0.0,
      "eval_prefix_exact_match": 0.056,
      "step": 1024
    },
    {
      "epoch": 3.22,
      "learning_rate": 3e-05,
      "loss": 1.3166,
      "step": 1100
    },
    {
      "epoch": 3.51,
      "learning_rate": 3e-05,
      "loss": 1.3035,
      "step": 1200
    },
    {
      "epoch": 3.81,
      "learning_rate": 3e-05,
      "loss": 1.3002,
      "step": 1300
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.45543589743589746,
      "eval_loss": 3.5288071632385254,
      "eval_runtime": 4.4066,
      "eval_samples_per_second": 113.466,
      "eval_steps_per_second": 14.297,
      "step": 1366
    },
    {
      "epoch": 4.0,
      "eval_bleu": 0.11209345982903633,
      "eval_exact_match": 0.0,
      "eval_prefix_exact_match": 0.054,
      "step": 1366
    }
  ],
  "logging_steps": 100,
  "max_steps": 17050,
  "num_train_epochs": 50,
  "save_steps": 500,
  "total_flos": 2.706556325063557e+17,
  "trial_name": null,
  "trial_params": null
}