{
  "best_metric": 0.5348,
  "best_model_checkpoint": "outputs/checkpoint-29586",
  "epoch": 8.0,
  "global_step": 236688,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.0004469415766030179,
      "loss": 3.6106,
      "step": 29586
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 15.296,
      "eval_loss": 2.7799501419067383,
      "eval_runtime": 368.7401,
      "eval_sacrebleu": 0.5348,
      "eval_samples_per_second": 6.175,
      "eval_steps_per_second": 3.089,
      "step": 29586
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00038309277994544387,
      "loss": 2.7653,
      "step": 59172
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 14.7356,
      "eval_loss": 2.742591619491577,
      "eval_runtime": 368.9941,
      "eval_sacrebleu": 0.4271,
      "eval_samples_per_second": 6.171,
      "eval_steps_per_second": 3.087,
      "step": 59172
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0003192439832878699,
      "loss": 2.7302,
      "step": 88758
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 14.7444,
      "eval_loss": 2.7364578247070312,
      "eval_runtime": 357.3278,
      "eval_sacrebleu": 0.4211,
      "eval_samples_per_second": 6.372,
      "eval_steps_per_second": 3.188,
      "step": 88758
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0002553951866302959,
      "loss": 2.705,
      "step": 118344
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 14.8669,
      "eval_loss": 2.7070209980010986,
      "eval_runtime": 365.3611,
      "eval_sacrebleu": 0.4635,
      "eval_samples_per_second": 6.232,
      "eval_steps_per_second": 3.117,
      "step": 118344
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.00019154638997272193,
      "loss": 2.6613,
      "step": 147930
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 13.9183,
      "eval_loss": 2.6642842292785645,
      "eval_runtime": 363.1965,
      "eval_sacrebleu": 0.3438,
      "eval_samples_per_second": 6.269,
      "eval_steps_per_second": 3.136,
      "step": 147930
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00012769759331514796,
      "loss": 2.6045,
      "step": 177516
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 14.9087,
      "eval_loss": 2.614426374435425,
      "eval_runtime": 359.5255,
      "eval_sacrebleu": 0.4651,
      "eval_samples_per_second": 6.333,
      "eval_steps_per_second": 3.168,
      "step": 177516
    },
    {
      "epoch": 7.0,
      "learning_rate": 6.384879665757398e-05,
      "loss": 2.5271,
      "step": 207102
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 14.6271,
      "eval_loss": 2.5494837760925293,
      "eval_runtime": 358.1093,
      "eval_sacrebleu": 0.468,
      "eval_samples_per_second": 6.358,
      "eval_steps_per_second": 3.181,
      "step": 207102
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.0,
      "loss": 2.4325,
      "step": 236688
    },
    {
      "epoch": 8.0,
      "eval_gen_len": 14.7071,
      "eval_loss": 2.4964401721954346,
      "eval_runtime": 362.2324,
      "eval_sacrebleu": 0.484,
      "eval_samples_per_second": 6.286,
      "eval_steps_per_second": 3.144,
      "step": 236688
    },
    {
      "epoch": 8.0,
      "step": 236688,
      "total_flos": 3.211579566884874e+18,
      "train_loss": 2.7545470263067835,
      "train_runtime": 376582.9978,
      "train_samples_per_second": 20.112,
      "train_steps_per_second": 0.629
    }
  ],
  "max_steps": 236688,
  "num_train_epochs": 8,
  "total_flos": 3.211579566884874e+18,
  "trial_name": null,
  "trial_params": null
}