{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.994152046783626,
  "global_step": 850,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.99,
      "eval_bleu": 11.266686519347816,
      "eval_exact_match": 0.14903129657228018,
      "eval_f1": 30.21710322109275,
      "eval_gen_len": 14.8927,
      "eval_loss": 1.8995920419692993,
      "eval_meteor": 0.23408756851747575,
      "eval_rouge1": 33.9195,
      "eval_rouge2": 15.2888,
      "eval_rougeL": 29.791,
      "eval_rougeLsum": 29.7773,
      "eval_runtime": 28.2982,
      "eval_samples_per_second": 23.712,
      "eval_steps_per_second": 1.484,
      "step": 85
    },
    {
      "epoch": 1.18,
      "learning_rate": 5.5147058823529414e-05,
      "loss": 2.1513,
      "step": 100
    },
    {
      "epoch": 1.99,
      "eval_bleu": 11.335423199007373,
      "eval_exact_match": 0.29806259314456035,
      "eval_f1": 30.027654721126762,
      "eval_gen_len": 15.3145,
      "eval_loss": 1.8702094554901123,
      "eval_meteor": 0.235594520111885,
      "eval_rouge1": 33.7784,
      "eval_rouge2": 14.8738,
      "eval_rougeL": 29.2696,
      "eval_rougeLsum": 29.2779,
      "eval_runtime": 27.3102,
      "eval_samples_per_second": 24.57,
      "eval_steps_per_second": 1.538,
      "step": 170
    },
    {
      "epoch": 2.35,
      "learning_rate": 4.779411764705882e-05,
      "loss": 1.8467,
      "step": 200
    },
    {
      "epoch": 2.99,
      "eval_bleu": 10.970390071816464,
      "eval_exact_match": 0.29806259314456035,
      "eval_f1": 29.342625862434428,
      "eval_gen_len": 14.8092,
      "eval_loss": 1.8641228675842285,
      "eval_meteor": 0.22682614068845547,
      "eval_rouge1": 33.0427,
      "eval_rouge2": 14.7078,
      "eval_rougeL": 28.6661,
      "eval_rougeLsum": 28.6581,
      "eval_runtime": 27.4789,
      "eval_samples_per_second": 24.419,
      "eval_steps_per_second": 1.528,
      "step": 255
    },
    {
      "epoch": 3.53,
      "learning_rate": 4.044117647058824e-05,
      "loss": 1.7299,
      "step": 300
    },
    {
      "epoch": 3.99,
      "eval_bleu": 11.298951356985155,
      "eval_exact_match": 0.29806259314456035,
      "eval_f1": 29.69224049966665,
      "eval_gen_len": 15.4411,
      "eval_loss": 1.8667548894882202,
      "eval_meteor": 0.2335660625586558,
      "eval_rouge1": 33.4131,
      "eval_rouge2": 14.7452,
      "eval_rougeL": 29.2171,
      "eval_rougeLsum": 29.1971,
      "eval_runtime": 27.5069,
      "eval_samples_per_second": 24.394,
      "eval_steps_per_second": 1.527,
      "step": 340
    },
    {
      "epoch": 4.7,
      "learning_rate": 3.308823529411765e-05,
      "loss": 1.6344,
      "step": 400
    },
    {
      "epoch": 4.99,
      "eval_bleu": 11.128887020318073,
      "eval_exact_match": 0.29806259314456035,
      "eval_f1": 29.70405153408973,
      "eval_gen_len": 15.4322,
      "eval_loss": 1.873842477798462,
      "eval_meteor": 0.23505921804881705,
      "eval_rouge1": 33.4428,
      "eval_rouge2": 14.6654,
      "eval_rougeL": 28.9946,
      "eval_rougeLsum": 28.9659,
      "eval_runtime": 27.689,
      "eval_samples_per_second": 24.233,
      "eval_steps_per_second": 1.517,
      "step": 425
    },
    {
      "epoch": 5.88,
      "learning_rate": 2.5735294117647057e-05,
      "loss": 1.5525,
      "step": 500
    },
    {
      "epoch": 5.99,
      "eval_bleu": 11.095344184995806,
      "eval_exact_match": 0.29806259314456035,
      "eval_f1": 29.75051837804376,
      "eval_gen_len": 15.2459,
      "eval_loss": 1.8811864852905273,
      "eval_meteor": 0.23266595904228066,
      "eval_rouge1": 33.4515,
      "eval_rouge2": 14.6207,
      "eval_rougeL": 28.9941,
      "eval_rougeLsum": 28.9538,
      "eval_runtime": 27.5396,
      "eval_samples_per_second": 24.365,
      "eval_steps_per_second": 1.525,
      "step": 510
    },
    {
      "epoch": 6.99,
      "eval_bleu": 10.852000849244718,
      "eval_exact_match": 0.44709388971684055,
      "eval_f1": 29.511040845778247,
      "eval_gen_len": 15.1043,
      "eval_loss": 1.890497088432312,
      "eval_meteor": 0.2288281311870586,
      "eval_rouge1": 33.1936,
      "eval_rouge2": 14.4288,
      "eval_rougeL": 28.7935,
      "eval_rougeLsum": 28.7517,
      "eval_runtime": 27.4742,
      "eval_samples_per_second": 24.423,
      "eval_steps_per_second": 1.529,
      "step": 595
    },
    {
      "epoch": 7.06,
      "learning_rate": 1.8382352941176472e-05,
      "loss": 1.5055,
      "step": 600
    },
    {
      "epoch": 7.99,
      "eval_bleu": 10.761708424546821,
      "eval_exact_match": 0.44709388971684055,
      "eval_f1": 29.313362686890127,
      "eval_gen_len": 15.1162,
      "eval_loss": 1.8992335796356201,
      "eval_meteor": 0.22928378485119694,
      "eval_rouge1": 33.0224,
      "eval_rouge2": 14.3064,
      "eval_rougeL": 28.7414,
      "eval_rougeLsum": 28.6691,
      "eval_runtime": 27.7431,
      "eval_samples_per_second": 24.186,
      "eval_steps_per_second": 1.514,
      "step": 680
    },
    {
      "epoch": 8.23,
      "learning_rate": 1.1029411764705883e-05,
      "loss": 1.4639,
      "step": 700
    },
    {
      "epoch": 8.99,
      "eval_bleu": 10.525652007565263,
      "eval_exact_match": 0.29806259314456035,
      "eval_f1": 29.146996985420294,
      "eval_gen_len": 15.1893,
      "eval_loss": 1.9027963876724243,
      "eval_meteor": 0.22646903254562226,
      "eval_rouge1": 32.8329,
      "eval_rouge2": 14.0255,
      "eval_rougeL": 28.4605,
      "eval_rougeLsum": 28.413,
      "eval_runtime": 27.8054,
      "eval_samples_per_second": 24.132,
      "eval_steps_per_second": 1.51,
      "step": 765
    },
    {
      "epoch": 9.41,
      "learning_rate": 3.6764705882352942e-06,
      "loss": 1.4222,
      "step": 800
    },
    {
      "epoch": 9.99,
      "eval_bleu": 10.701165268155146,
      "eval_exact_match": 0.44709388971684055,
      "eval_f1": 29.233906743341034,
      "eval_gen_len": 15.2235,
      "eval_loss": 1.9045032262802124,
      "eval_meteor": 0.2286663107294665,
      "eval_rouge1": 32.9054,
      "eval_rouge2": 14.207,
      "eval_rougeL": 28.5796,
      "eval_rougeLsum": 28.5103,
      "eval_runtime": 27.6458,
      "eval_samples_per_second": 24.271,
      "eval_steps_per_second": 1.519,
      "step": 850
    },
    {
      "epoch": 9.99,
      "step": 850,
      "total_flos": 1.60086109146624e+16,
      "train_loss": 1.6479782463522519,
      "train_runtime": 1663.4222,
      "train_samples_per_second": 16.388,
      "train_steps_per_second": 0.511
    }
  ],
  "max_steps": 850,
  "num_train_epochs": 10,
  "total_flos": 1.60086109146624e+16,
  "trial_name": null,
  "trial_params": null
}