{
  "best_metric": 0.682648401826484,
  "best_model_checkpoint": "tmp/tst-translation353/checkpoint-840",
  "epoch": 10.0,
  "global_step": 1050,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2990867579908676,
      "eval_loss": 0.3042815625667572,
      "eval_runtime": 6.3082,
      "eval_samples_per_second": 69.434,
      "eval_steps_per_second": 5.865,
      "step": 105
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3310502283105023,
      "eval_loss": 0.2653220593929291,
      "eval_runtime": 6.6274,
      "eval_samples_per_second": 66.089,
      "eval_steps_per_second": 5.583,
      "step": 210
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4726027397260274,
      "eval_loss": 0.24747495353221893,
      "eval_runtime": 6.6413,
      "eval_samples_per_second": 65.951,
      "eval_steps_per_second": 5.571,
      "step": 315
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6095890410958904,
      "eval_loss": 0.17373643815517426,
      "eval_runtime": 10.6832,
      "eval_samples_per_second": 40.999,
      "eval_steps_per_second": 3.463,
      "step": 420
    },
    {
      "epoch": 4.76,
      "learning_rate": 2.6190476190476192e-05,
      "loss": 0.5112,
      "step": 500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6255707762557078,
      "eval_loss": 0.16598360240459442,
      "eval_runtime": 6.8539,
      "eval_samples_per_second": 63.906,
      "eval_steps_per_second": 5.398,
      "step": 525
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6575342465753424,
      "eval_loss": 0.1499105989933014,
      "eval_runtime": 7.0098,
      "eval_samples_per_second": 62.484,
      "eval_steps_per_second": 5.278,
      "step": 630
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6438356164383562,
      "eval_loss": 0.14968065917491913,
      "eval_runtime": 7.4429,
      "eval_samples_per_second": 58.848,
      "eval_steps_per_second": 4.971,
      "step": 735
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.682648401826484,
      "eval_loss": 0.14565615355968475,
      "eval_runtime": 6.9321,
      "eval_samples_per_second": 63.184,
      "eval_steps_per_second": 5.337,
      "step": 840
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.678082191780822,
      "eval_loss": 0.14702993631362915,
      "eval_runtime": 8.9981,
      "eval_samples_per_second": 48.677,
      "eval_steps_per_second": 4.112,
      "step": 945
    },
    {
      "epoch": 9.52,
      "learning_rate": 2.3809523809523808e-06,
      "loss": 0.151,
      "step": 1000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.678082191780822,
      "eval_loss": 0.14281360805034637,
      "eval_runtime": 7.0161,
      "eval_samples_per_second": 62.428,
      "eval_steps_per_second": 5.274,
      "step": 1050
    },
    {
      "epoch": 10.0,
      "step": 1050,
      "total_flos": 2385811380510720.0,
      "train_loss": 0.32115679332188196,
      "train_runtime": 336.3145,
      "train_samples_per_second": 37.287,
      "train_steps_per_second": 3.122
    }
  ],
  "max_steps": 1050,
  "num_train_epochs": 10,
  "total_flos": 2385811380510720.0,
  "trial_name": null,
  "trial_params": null
}