{
  "best_metric": 17.3273,
  "best_model_checkpoint": "models/mt0-xl_russian_natprompt_adafactor_updated/checkpoint-6150",
  "epoch": 14.999024390243903,
  "eval_steps": 500,
  "global_step": 7687,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.75e-05,
      "loss": 2.0388,
      "step": 512
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 16.58484100877193,
      "eval_loss": 1.6734575033187866,
      "eval_rouge1": 14.1367,
      "eval_rouge2": 7.0437,
      "eval_rougeL": 14.0625,
      "eval_rougeLsum": 14.0916,
      "eval_runtime": 270.6111,
      "eval_samples_per_second": 26.932,
      "eval_steps_per_second": 0.843,
      "step": 512
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.4995117187500005e-05,
      "loss": 1.7098,
      "step": 1025
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 16.68050986842105,
      "eval_loss": 1.6203718185424805,
      "eval_rouge1": 15.2619,
      "eval_rouge2": 7.8124,
      "eval_rougeL": 15.159,
      "eval_rougeLsum": 15.2078,
      "eval_runtime": 276.6842,
      "eval_samples_per_second": 26.341,
      "eval_steps_per_second": 0.824,
      "step": 1025
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.24951171875e-05,
      "loss": 1.539,
      "step": 1537
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 16.61417214912281,
      "eval_loss": 1.6058766841888428,
      "eval_rouge1": 15.9942,
      "eval_rouge2": 8.1827,
      "eval_rougeL": 15.872,
      "eval_rougeLsum": 15.9105,
      "eval_runtime": 263.8074,
      "eval_samples_per_second": 27.626,
      "eval_steps_per_second": 0.864,
      "step": 1537
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.9990234375e-05,
      "loss": 1.403,
      "step": 2050
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 16.26343201754386,
      "eval_loss": 1.6041721105575562,
      "eval_rouge1": 16.6383,
      "eval_rouge2": 8.4603,
      "eval_rougeL": 16.5096,
      "eval_rougeLsum": 16.5635,
      "eval_runtime": 251.4581,
      "eval_samples_per_second": 28.983,
      "eval_steps_per_second": 0.907,
      "step": 2050
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.7490234375e-05,
      "loss": 1.295,
      "step": 2562
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 15.741365131578947,
      "eval_loss": 1.6226089000701904,
      "eval_rouge1": 16.9189,
      "eval_rouge2": 8.8384,
      "eval_rougeL": 16.7799,
      "eval_rougeLsum": 16.8258,
      "eval_runtime": 169.6881,
      "eval_samples_per_second": 42.949,
      "eval_steps_per_second": 1.344,
      "step": 2562
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.49853515625e-05,
      "loss": 1.1984,
      "step": 3075
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 15.888157894736842,
      "eval_loss": 1.6289030313491821,
      "eval_rouge1": 16.9788,
      "eval_rouge2": 8.7272,
      "eval_rougeL": 16.8238,
      "eval_rougeLsum": 16.8765,
      "eval_runtime": 175.0677,
      "eval_samples_per_second": 41.63,
      "eval_steps_per_second": 1.302,
      "step": 3075
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.2485351562499996e-05,
      "loss": 1.1195,
      "step": 3587
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 16.23519736842105,
      "eval_loss": 1.6697918176651,
      "eval_rouge1": 17.0912,
      "eval_rouge2": 8.7061,
      "eval_rougeL": 16.9084,
      "eval_rougeLsum": 16.9633,
      "eval_runtime": 171.9395,
      "eval_samples_per_second": 42.387,
      "eval_steps_per_second": 1.326,
      "step": 3587
    },
    {
      "epoch": 8.0,
      "learning_rate": 2.998046875e-05,
      "loss": 1.0463,
      "step": 4100
    },
    {
      "epoch": 8.0,
      "eval_gen_len": 16.14761513157895,
      "eval_loss": 1.6845269203186035,
      "eval_rouge1": 17.201,
      "eval_rouge2": 8.7395,
      "eval_rougeL": 17.003,
      "eval_rougeLsum": 17.052,
      "eval_runtime": 252.7052,
      "eval_samples_per_second": 28.84,
      "eval_steps_per_second": 0.902,
      "step": 4100
    },
    {
      "epoch": 9.0,
      "learning_rate": 2.748046875e-05,
      "loss": 0.9866,
      "step": 4612
    },
    {
      "epoch": 9.0,
      "eval_gen_len": 15.878837719298245,
      "eval_loss": 1.726230502128601,
      "eval_rouge1": 17.3223,
      "eval_rouge2": 8.8289,
      "eval_rougeL": 17.1413,
      "eval_rougeLsum": 17.1756,
      "eval_runtime": 182.5703,
      "eval_samples_per_second": 39.919,
      "eval_steps_per_second": 1.249,
      "step": 4612
    },
    {
      "epoch": 10.0,
      "learning_rate": 2.49755859375e-05,
      "loss": 0.9326,
      "step": 5125
    },
    {
      "epoch": 10.0,
      "eval_gen_len": 15.797149122807017,
      "eval_loss": 1.7532711029052734,
      "eval_rouge1": 17.2655,
      "eval_rouge2": 8.7512,
      "eval_rougeL": 17.0508,
      "eval_rougeLsum": 17.1055,
      "eval_runtime": 168.7949,
      "eval_samples_per_second": 43.177,
      "eval_steps_per_second": 1.351,
      "step": 5125
    },
    {
      "epoch": 11.0,
      "learning_rate": 2.24755859375e-05,
      "loss": 0.8844,
      "step": 5637
    },
    {
      "epoch": 11.0,
      "eval_gen_len": 16.32360197368421,
      "eval_loss": 1.7794246673583984,
      "eval_rouge1": 17.008,
      "eval_rouge2": 8.5404,
      "eval_rougeL": 16.8044,
      "eval_rougeLsum": 16.848,
      "eval_runtime": 168.6102,
      "eval_samples_per_second": 43.224,
      "eval_steps_per_second": 1.352,
      "step": 5637
    },
    {
      "epoch": 12.0,
      "learning_rate": 1.9970703125e-05,
      "loss": 0.8393,
      "step": 6150
    },
    {
      "epoch": 12.0,
      "eval_gen_len": 16.143092105263158,
      "eval_loss": 1.7995822429656982,
      "eval_rouge1": 17.3273,
      "eval_rouge2": 8.7829,
      "eval_rougeL": 17.097,
      "eval_rougeLsum": 17.1644,
      "eval_runtime": 171.5723,
      "eval_samples_per_second": 42.478,
      "eval_steps_per_second": 1.329,
      "step": 6150
    },
    {
      "epoch": 13.0,
      "learning_rate": 1.7470703125000003e-05,
      "loss": 0.8046,
      "step": 6662
    },
    {
      "epoch": 13.0,
      "eval_gen_len": 16.090597587719298,
      "eval_loss": 1.8266295194625854,
      "eval_rouge1": 17.1859,
      "eval_rouge2": 8.6524,
      "eval_rougeL": 16.9605,
      "eval_rougeLsum": 17.0118,
      "eval_runtime": 259.1646,
      "eval_samples_per_second": 28.121,
      "eval_steps_per_second": 0.88,
      "step": 6662
    },
    {
      "epoch": 14.0,
      "learning_rate": 1.49658203125e-05,
      "loss": 0.7682,
      "step": 7175
    },
    {
      "epoch": 14.0,
      "eval_gen_len": 16.11239035087719,
      "eval_loss": 1.8624775409698486,
      "eval_rouge1": 17.0184,
      "eval_rouge2": 8.5314,
      "eval_rougeL": 16.8019,
      "eval_rougeLsum": 16.847,
      "eval_runtime": 170.9938,
      "eval_samples_per_second": 42.621,
      "eval_steps_per_second": 1.333,
      "step": 7175
    },
    {
      "epoch": 15.0,
      "learning_rate": 1.2465820312500002e-05,
      "loss": 0.7419,
      "step": 7687
    },
    {
      "epoch": 15.0,
      "eval_gen_len": 15.95751096491228,
      "eval_loss": 1.8779526948928833,
      "eval_rouge1": 17.2742,
      "eval_rouge2": 8.6795,
      "eval_rougeL": 17.0699,
      "eval_rougeLsum": 17.1118,
      "eval_runtime": 177.9916,
      "eval_samples_per_second": 40.946,
      "eval_steps_per_second": 1.281,
      "step": 7687
    },
    {
      "epoch": 15.0,
      "step": 7687,
      "total_flos": 1.7085595424946913e+18,
      "train_loss": 1.153788715837463,
      "train_runtime": 20083.7121,
      "train_samples_per_second": 65.311,
      "train_steps_per_second": 0.51
    }
  ],
  "logging_steps": 500,
  "max_steps": 10240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "total_flos": 1.7085595424946913e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}