{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "global_step": 3970,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_bleu": 0.0222,
      "eval_gen_len": 19.0,
      "eval_loss": 1.032914400100708,
      "eval_runtime": 38.8818,
      "eval_samples_per_second": 20.395,
      "eval_steps_per_second": 1.286,
      "step": 397
    },
    {
      "epoch": 1.26,
      "learning_rate": 4.370277078085643e-05,
      "loss": 1.5198,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.0395,
      "eval_gen_len": 19.0,
      "eval_loss": 0.9034101963043213,
      "eval_runtime": 38.8135,
      "eval_samples_per_second": 20.431,
      "eval_steps_per_second": 1.288,
      "step": 794
    },
    {
      "epoch": 2.52,
      "learning_rate": 3.7405541561712845e-05,
      "loss": 1.0351,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_bleu": 0.0686,
      "eval_gen_len": 19.0,
      "eval_loss": 0.8492476344108582,
      "eval_runtime": 38.98,
      "eval_samples_per_second": 20.344,
      "eval_steps_per_second": 1.283,
      "step": 1191
    },
    {
      "epoch": 3.78,
      "learning_rate": 3.1108312342569276e-05,
      "loss": 0.9326,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_bleu": 0.0832,
      "eval_gen_len": 19.0,
      "eval_loss": 0.8076524138450623,
      "eval_runtime": 38.884,
      "eval_samples_per_second": 20.394,
      "eval_steps_per_second": 1.286,
      "step": 1588
    },
    {
      "epoch": 5.0,
      "eval_bleu": 0.0983,
      "eval_gen_len": 19.0,
      "eval_loss": 0.7785636782646179,
      "eval_runtime": 38.9036,
      "eval_samples_per_second": 20.384,
      "eval_steps_per_second": 1.285,
      "step": 1985
    },
    {
      "epoch": 5.04,
      "learning_rate": 2.4811083123425694e-05,
      "loss": 0.8785,
      "step": 2000
    },
    {
      "epoch": 6.0,
      "eval_bleu": 0.0606,
      "eval_gen_len": 19.0,
      "eval_loss": 0.7609861493110657,
      "eval_runtime": 39.0721,
      "eval_samples_per_second": 20.296,
      "eval_steps_per_second": 1.28,
      "step": 2382
    },
    {
      "epoch": 6.3,
      "learning_rate": 1.8513853904282116e-05,
      "loss": 0.8436,
      "step": 2500
    },
    {
      "epoch": 7.0,
      "eval_bleu": 0.065,
      "eval_gen_len": 19.0,
      "eval_loss": 0.7446194291114807,
      "eval_runtime": 39.2241,
      "eval_samples_per_second": 20.217,
      "eval_steps_per_second": 1.275,
      "step": 2779
    },
    {
      "epoch": 7.56,
      "learning_rate": 1.2216624685138539e-05,
      "loss": 0.8153,
      "step": 3000
    },
    {
      "epoch": 8.0,
      "eval_bleu": 0.0618,
      "eval_gen_len": 19.0,
      "eval_loss": 0.7361475825309753,
      "eval_runtime": 38.8407,
      "eval_samples_per_second": 20.417,
      "eval_steps_per_second": 1.287,
      "step": 3176
    },
    {
      "epoch": 8.82,
      "learning_rate": 5.919395465994963e-06,
      "loss": 0.7987,
      "step": 3500
    },
    {
      "epoch": 9.0,
      "eval_bleu": 0.068,
      "eval_gen_len": 19.0,
      "eval_loss": 0.7305701971054077,
      "eval_runtime": 38.7216,
      "eval_samples_per_second": 20.48,
      "eval_steps_per_second": 1.291,
      "step": 3573
    },
    {
      "epoch": 10.0,
      "eval_bleu": 0.0616,
      "eval_gen_len": 19.0,
      "eval_loss": 0.7289602160453796,
      "eval_runtime": 38.8065,
      "eval_samples_per_second": 20.435,
      "eval_steps_per_second": 1.288,
      "step": 3970
    },
    {
      "epoch": 10.0,
      "step": 3970,
      "total_flos": 2.255280810983424e+16,
      "train_loss": 0.9529764708703952,
      "train_runtime": 2099.0683,
      "train_samples_per_second": 30.213,
      "train_steps_per_second": 1.891
    }
  ],
  "max_steps": 3970,
  "num_train_epochs": 10,
  "total_flos": 2.255280810983424e+16,
  "trial_name": null,
  "trial_params": null
}