{
  "best_metric": 64.0,
  "best_model_checkpoint": "pubmedqa_unifiedqa/checkpoint-1100",
  "epoch": 39.283185840707965,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.0,
      "loss": 5.2557,
      "step": 1
    },
    {
      "epoch": 3.57,
      "learning_rate": 1.44e-06,
      "loss": 5.5451,
      "step": 100
    },
    {
      "epoch": 3.57,
      "eval_bleu": 3.515852791538636,
      "eval_gen_len": 2.44,
      "eval_loss": 5.634477615356445,
      "eval_meteor": 0.25,
      "eval_rouge1": 50.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 50.0,
      "eval_rougeLsum": 50.0,
      "eval_runtime": 3.8236,
      "eval_samples_per_second": 13.077,
      "eval_steps_per_second": 1.831,
      "step": 100
    },
    {
      "epoch": 7.14,
      "learning_rate": 2.925e-06,
      "loss": 4.9008,
      "step": 200
    },
    {
      "epoch": 7.14,
      "eval_bleu": 3.4801542313344793,
      "eval_gen_len": 2.44,
      "eval_loss": 4.566105842590332,
      "eval_meteor": 0.24,
      "eval_rouge1": 48.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 48.0,
      "eval_rougeLsum": 48.0,
      "eval_runtime": 1.6121,
      "eval_samples_per_second": 31.016,
      "eval_steps_per_second": 4.342,
      "step": 200
    },
    {
      "epoch": 10.71,
      "learning_rate": 2.9425e-06,
      "loss": 3.9884,
      "step": 300
    },
    {
      "epoch": 10.71,
      "eval_bleu": 5.48568366540206,
      "eval_gen_len": 2.24,
      "eval_loss": 3.5699760913848877,
      "eval_meteor": 0.28,
      "eval_rouge1": 56.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 56.0,
      "eval_rougeLsum": 56.0,
      "eval_runtime": 1.5002,
      "eval_samples_per_second": 33.328,
      "eval_steps_per_second": 4.666,
      "step": 300
    },
    {
      "epoch": 14.28,
      "learning_rate": 2.88125e-06,
      "loss": 3.2254,
      "step": 400
    },
    {
      "epoch": 14.28,
      "eval_bleu": 0.0,
      "eval_gen_len": 2.0,
      "eval_loss": 2.9374730587005615,
      "eval_meteor": 0.3,
      "eval_rouge1": 60.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 60.0,
      "eval_rougeLsum": 60.0,
      "eval_runtime": 1.3736,
      "eval_samples_per_second": 36.402,
      "eval_steps_per_second": 5.096,
      "step": 400
    },
    {
      "epoch": 17.85,
      "learning_rate": 2.81875e-06,
      "loss": 2.6924,
      "step": 500
    },
    {
      "epoch": 17.85,
      "eval_bleu": 0.0,
      "eval_gen_len": 2.0,
      "eval_loss": 2.5620052814483643,
      "eval_meteor": 0.29,
      "eval_rouge1": 58.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 58.0,
      "eval_rougeLsum": 58.0,
      "eval_runtime": 1.3734,
      "eval_samples_per_second": 36.405,
      "eval_steps_per_second": 5.097,
      "step": 500
    },
    {
      "epoch": 21.42,
      "learning_rate": 2.75625e-06,
      "loss": 2.4122,
      "step": 600
    },
    {
      "epoch": 21.42,
      "eval_bleu": 0.0,
      "eval_gen_len": 2.0,
      "eval_loss": 2.3537566661834717,
      "eval_meteor": 0.28,
      "eval_rouge1": 56.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 56.0,
      "eval_rougeLsum": 56.0,
      "eval_runtime": 1.3768,
      "eval_samples_per_second": 36.317,
      "eval_steps_per_second": 5.084,
      "step": 600
    },
    {
      "epoch": 24.99,
      "learning_rate": 2.695e-06,
      "loss": 2.2719,
      "step": 700
    },
    {
      "epoch": 24.99,
      "eval_bleu": 0.0,
      "eval_gen_len": 2.0,
      "eval_loss": 2.212905168533325,
      "eval_meteor": 0.29,
      "eval_rouge1": 58.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 58.0,
      "eval_rougeLsum": 58.0,
      "eval_runtime": 1.3724,
      "eval_samples_per_second": 36.432,
      "eval_steps_per_second": 5.101,
      "step": 700
    },
    {
      "epoch": 28.57,
      "learning_rate": 2.6324999999999998e-06,
      "loss": 2.1539,
      "step": 800
    },
    {
      "epoch": 28.57,
      "eval_bleu": 0.0,
      "eval_gen_len": 2.0,
      "eval_loss": 2.123441219329834,
      "eval_meteor": 0.29,
      "eval_rouge1": 58.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 58.0,
      "eval_rougeLsum": 58.0,
      "eval_runtime": 1.3738,
      "eval_samples_per_second": 36.397,
      "eval_steps_per_second": 5.096,
      "step": 800
    },
    {
      "epoch": 32.14,
      "learning_rate": 2.57125e-06,
      "loss": 2.1149,
      "step": 900
    },
    {
      "epoch": 32.14,
      "eval_bleu": 0.0,
      "eval_gen_len": 2.0,
      "eval_loss": 2.0748918056488037,
      "eval_meteor": 0.29,
      "eval_rouge1": 58.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 58.0,
      "eval_rougeLsum": 58.0,
      "eval_runtime": 1.3748,
      "eval_samples_per_second": 36.37,
      "eval_steps_per_second": 5.092,
      "step": 900
    },
    {
      "epoch": 35.71,
      "learning_rate": 2.509375e-06,
      "loss": 2.0404,
      "step": 1000
    },
    {
      "epoch": 35.71,
      "eval_bleu": 0.0,
      "eval_gen_len": 2.0,
      "eval_loss": 2.0326242446899414,
      "eval_meteor": 0.31,
      "eval_rouge1": 62.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 62.0,
      "eval_rougeLsum": 62.0,
      "eval_runtime": 1.3725,
      "eval_samples_per_second": 36.429,
      "eval_steps_per_second": 5.1,
      "step": 1000
    },
    {
      "epoch": 39.28,
      "learning_rate": 2.446875e-06,
      "loss": 1.9918,
      "step": 1100
    },
    {
      "epoch": 39.28,
      "eval_bleu": 0.0,
      "eval_gen_len": 2.0,
      "eval_loss": 2.012605667114258,
      "eval_meteor": 0.32,
      "eval_rouge1": 64.0,
      "eval_rouge2": 0.0,
      "eval_rougeL": 64.0,
      "eval_rougeLsum": 64.0,
      "eval_runtime": 1.3788,
      "eval_samples_per_second": 36.265,
      "eval_steps_per_second": 5.077,
      "step": 1100
    }
  ],
  "max_steps": 5000,
  "num_train_epochs": 179,
  "total_flos": 2.153031549530931e+16,
  "trial_name": null,
  "trial_params": null
}