{
  "best_metric": 0.6162260174751282,
  "best_model_checkpoint": "flan_t5_summarization/checkpoint-2720",
  "epoch": 10.0,
  "global_step": 2720,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 19.0,
      "eval_loss": 1.120025634765625,
      "eval_rouge1": 9.2565,
      "eval_rouge2": 1.2805,
      "eval_rougeL": 9.2358,
      "eval_rougeLsum": 9.284,
      "eval_runtime": 4.0606,
      "eval_samples_per_second": 16.5,
      "eval_steps_per_second": 1.478,
      "step": 272
    },
    {
      "epoch": 1.84,
      "learning_rate": 4.0808823529411765e-05,
      "loss": 1.5343,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 19.0,
      "eval_loss": 0.8922988772392273,
      "eval_rouge1": 10.9045,
      "eval_rouge2": 2.9468,
      "eval_rougeL": 10.9112,
      "eval_rougeLsum": 10.8827,
      "eval_runtime": 4.0719,
      "eval_samples_per_second": 16.454,
      "eval_steps_per_second": 1.474,
      "step": 544
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 19.0,
      "eval_loss": 0.7884227633476257,
      "eval_rouge1": 13.637,
      "eval_rouge2": 4.8447,
      "eval_rougeL": 13.3594,
      "eval_rougeLsum": 13.3459,
      "eval_runtime": 4.0204,
      "eval_samples_per_second": 16.665,
      "eval_steps_per_second": 1.492,
      "step": 816
    },
    {
      "epoch": 3.68,
      "learning_rate": 3.161764705882353e-05,
      "loss": 0.9949,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 18.91044776119403,
      "eval_loss": 0.7256659269332886,
      "eval_rouge1": 15.2005,
      "eval_rouge2": 6.3919,
      "eval_rougeL": 14.781,
      "eval_rougeLsum": 14.7204,
      "eval_runtime": 4.0736,
      "eval_samples_per_second": 16.447,
      "eval_steps_per_second": 1.473,
      "step": 1088
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 18.73134328358209,
      "eval_loss": 0.6852018237113953,
      "eval_rouge1": 15.1627,
      "eval_rouge2": 6.3116,
      "eval_rougeL": 14.7187,
      "eval_rougeLsum": 14.6983,
      "eval_runtime": 4.0455,
      "eval_samples_per_second": 16.561,
      "eval_steps_per_second": 1.483,
      "step": 1360
    },
    {
      "epoch": 5.51,
      "learning_rate": 2.2426470588235296e-05,
      "loss": 0.8504,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 18.73134328358209,
      "eval_loss": 0.6580936312675476,
      "eval_rouge1": 16.0795,
      "eval_rouge2": 6.9284,
      "eval_rougeL": 15.3516,
      "eval_rougeLsum": 15.3571,
      "eval_runtime": 4.0423,
      "eval_samples_per_second": 16.575,
      "eval_steps_per_second": 1.484,
      "step": 1632
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 18.91044776119403,
      "eval_loss": 0.6391794681549072,
      "eval_rouge1": 16.0518,
      "eval_rouge2": 6.9377,
      "eval_rougeL": 15.3914,
      "eval_rougeLsum": 15.3748,
      "eval_runtime": 4.0453,
      "eval_samples_per_second": 16.562,
      "eval_steps_per_second": 1.483,
      "step": 1904
    },
    {
      "epoch": 7.35,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.7841,
      "step": 2000
    },
    {
      "epoch": 8.0,
      "eval_gen_len": 18.82089552238806,
      "eval_loss": 0.6258341073989868,
      "eval_rouge1": 16.1307,
      "eval_rouge2": 7.6286,
      "eval_rougeL": 15.7398,
      "eval_rougeLsum": 15.7627,
      "eval_runtime": 4.0536,
      "eval_samples_per_second": 16.529,
      "eval_steps_per_second": 1.48,
      "step": 2176
    },
    {
      "epoch": 9.0,
      "eval_gen_len": 18.73134328358209,
      "eval_loss": 0.6200478672981262,
      "eval_rouge1": 15.9488,
      "eval_rouge2": 7.4447,
      "eval_rougeL": 15.5654,
      "eval_rougeLsum": 15.583,
      "eval_runtime": 4.042,
      "eval_samples_per_second": 16.576,
      "eval_steps_per_second": 1.484,
      "step": 2448
    },
    {
      "epoch": 9.19,
      "learning_rate": 4.044117647058824e-06,
      "loss": 0.7599,
      "step": 2500
    },
    {
      "epoch": 10.0,
      "eval_gen_len": 18.73134328358209,
      "eval_loss": 0.6162260174751282,
      "eval_rouge1": 15.9418,
      "eval_rouge2": 7.4447,
      "eval_rougeL": 15.5655,
      "eval_rougeLsum": 15.5835,
      "eval_runtime": 4.0403,
      "eval_samples_per_second": 16.583,
      "eval_steps_per_second": 1.485,
      "step": 2720
    },
    {
      "epoch": 10.0,
      "step": 2720,
      "total_flos": 1177555285370880.0,
      "train_loss": 0.9648406533633962,
      "train_runtime": 1843.1414,
      "train_samples_per_second": 17.693,
      "train_steps_per_second": 1.476
    }
  ],
  "max_steps": 2720,
  "num_train_epochs": 10,
  "total_flos": 1177555285370880.0,
  "trial_name": null,
  "trial_params": null
}