{
  "best_metric": 3.359348773956299,
  "best_model_checkpoint": "BASH-Coder-Flan-T5-base/checkpoint-5614",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 8020,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.556818181818182e-05,
      "loss": 4.3554,
      "step": 802
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 15.2363,
      "eval_loss": 3.59275484085083,
      "eval_rouge1": 22.7234,
      "eval_rouge2": 6.7951,
      "eval_rougeL": 22.0647,
      "eval_rougeLsum": 22.0744,
      "eval_runtime": 190.6891,
      "eval_samples_per_second": 9.675,
      "eval_steps_per_second": 0.608,
      "step": 802
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.0505050505050506e-05,
      "loss": 3.5335,
      "step": 1604
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 15.168,
      "eval_loss": 3.4654388427734375,
      "eval_rouge1": 25.7842,
      "eval_rouge2": 8.5847,
      "eval_rougeL": 24.8207,
      "eval_rougeLsum": 24.8808,
      "eval_runtime": 187.8163,
      "eval_samples_per_second": 9.823,
      "eval_steps_per_second": 0.618,
      "step": 1604
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.5441919191919196e-05,
      "loss": 3.3341,
      "step": 2406
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 15.6472,
      "eval_loss": 3.4077794551849365,
      "eval_rouge1": 25.5756,
      "eval_rouge2": 8.4456,
      "eval_rougeL": 24.706,
      "eval_rougeLsum": 24.7207,
      "eval_runtime": 187.2408,
      "eval_samples_per_second": 9.854,
      "eval_steps_per_second": 0.62,
      "step": 2406
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.037878787878788e-05,
      "loss": 3.2011,
      "step": 3208
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 16.2748,
      "eval_loss": 3.3789384365081787,
      "eval_rouge1": 26.0638,
      "eval_rouge2": 8.6853,
      "eval_rougeL": 25.0862,
      "eval_rougeLsum": 25.1223,
      "eval_runtime": 221.9787,
      "eval_samples_per_second": 8.312,
      "eval_steps_per_second": 0.523,
      "step": 3208
    },
    {
      "epoch": 5.0,
      "learning_rate": 2.5315656565656566e-05,
      "loss": 3.1059,
      "step": 4010
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 15.7366,
      "eval_loss": 3.362180709838867,
      "eval_rouge1": 26.7254,
      "eval_rouge2": 9.1138,
      "eval_rougeL": 25.7985,
      "eval_rougeLsum": 25.8521,
      "eval_runtime": 195.6438,
      "eval_samples_per_second": 9.43,
      "eval_steps_per_second": 0.593,
      "step": 4010
    },
    {
      "epoch": 6.0,
      "learning_rate": 2.0252525252525253e-05,
      "loss": 3.0336,
      "step": 4812
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 16.548,
      "eval_loss": 3.366245746612549,
      "eval_rouge1": 26.4655,
      "eval_rouge2": 9.1283,
      "eval_rougeL": 25.4587,
      "eval_rougeLsum": 25.5112,
      "eval_runtime": 221.12,
      "eval_samples_per_second": 8.344,
      "eval_steps_per_second": 0.525,
      "step": 4812
    },
    {
      "epoch": 7.0,
      "learning_rate": 1.518939393939394e-05,
      "loss": 2.9727,
      "step": 5614
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 15.5431,
      "eval_loss": 3.359348773956299,
      "eval_rouge1": 26.8211,
      "eval_rouge2": 9.3045,
      "eval_rougeL": 25.8497,
      "eval_rougeLsum": 25.8772,
      "eval_runtime": 192.8568,
      "eval_samples_per_second": 9.567,
      "eval_steps_per_second": 0.601,
      "step": 5614
    },
    {
      "epoch": 8.0,
      "learning_rate": 1.0126262626262626e-05,
      "loss": 2.9298,
      "step": 6416
    },
    {
      "epoch": 8.0,
      "eval_gen_len": 15.916,
      "eval_loss": 3.364309549331665,
      "eval_rouge1": 26.8932,
      "eval_rouge2": 9.3537,
      "eval_rougeL": 25.9444,
      "eval_rougeLsum": 26.0088,
      "eval_runtime": 199.9625,
      "eval_samples_per_second": 9.227,
      "eval_steps_per_second": 0.58,
      "step": 6416
    },
    {
      "epoch": 9.0,
      "learning_rate": 5.063131313131313e-06,
      "loss": 2.9005,
      "step": 7218
    },
    {
      "epoch": 9.0,
      "eval_gen_len": 15.71,
      "eval_loss": 3.3606483936309814,
      "eval_rouge1": 27.1732,
      "eval_rouge2": 9.5661,
      "eval_rougeL": 26.1198,
      "eval_rougeLsum": 26.1515,
      "eval_runtime": 186.8674,
      "eval_samples_per_second": 9.873,
      "eval_steps_per_second": 0.621,
      "step": 7218
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 2.8846,
      "step": 8020
    },
    {
      "epoch": 10.0,
      "eval_gen_len": 15.5767,
      "eval_loss": 3.3608038425445557,
      "eval_rouge1": 27.0741,
      "eval_rouge2": 9.3824,
      "eval_rougeL": 26.133,
      "eval_rougeLsum": 26.1559,
      "eval_runtime": 189.991,
      "eval_samples_per_second": 9.711,
      "eval_steps_per_second": 0.611,
      "step": 8020
    },
    {
      "epoch": 10.0,
      "step": 8020,
      "total_flos": 2.196016829300736e+16,
      "train_loss": 3.2251040794011065,
      "train_runtime": 10442.016,
      "train_samples_per_second": 6.142,
      "train_steps_per_second": 0.768
    }
  ],
  "logging_steps": 500,
  "max_steps": 8020,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 2.196016829300736e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}