{
  "best_metric": 0.8322489857673645,
  "best_model_checkpoint": "./Zeroshot/01-12-23-mistralai-Mistral-7B-v0.1_multilang-dataset-3.0.3-portuguese-2_epochs-10_batch_3/checkpoints/checkpoint-13546",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 13546,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "learning_rate": 5.835794447725931e-05,
      "loss": 1.4468,
      "step": 500
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00011742468989958655,
      "loss": 0.9754,
      "step": 1000
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017649143532191377,
      "loss": 0.9429,
      "step": 1500
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000235558180744241,
      "loss": 0.9147,
      "step": 2000
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00029462492616656825,
      "loss": 0.9067,
      "step": 2500
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00035369167158889544,
      "loss": 0.8978,
      "step": 3000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8805813789367676,
      "eval_runtime": 88.2945,
      "eval_samples_per_second": 17.057,
      "eval_steps_per_second": 2.141,
      "step": 3386
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00039998760393503537,
      "loss": 0.895,
      "step": 3500
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003996072594095129,
      "loss": 0.8687,
      "step": 4000
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00039869668890858337,
      "loss": 0.8884,
      "step": 4500
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00039725831122269285,
      "loss": 0.8715,
      "step": 5000
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00039529594718087214,
      "loss": 0.8645,
      "step": 5500
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0003928148095012922,
      "loss": 0.8666,
      "step": 6000
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0003898214889444803,
      "loss": 0.8719,
      "step": 6500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8552550673484802,
      "eval_runtime": 88.3232,
      "eval_samples_per_second": 17.051,
      "eval_steps_per_second": 2.14,
      "step": 6773
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00038632393680597854,
      "loss": 0.8438,
      "step": 7000
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0003823314437949511,
      "loss": 0.8308,
      "step": 7500
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00037785461535484375,
      "loss": 0.8259,
      "step": 8000
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0003729053434916558,
      "loss": 0.8324,
      "step": 8500
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0003674967751846552,
      "loss": 0.8413,
      "step": 9000
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.0003616554183563445,
      "loss": 0.8322,
      "step": 9500
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.00035537338261496887,
      "loss": 0.8368,
      "step": 10000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.8443310260772705,
      "eval_runtime": 88.3102,
      "eval_samples_per_second": 17.054,
      "eval_steps_per_second": 2.14,
      "step": 10159
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.0003486786213865893,
      "loss": 0.8088,
      "step": 10500
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0003415889182744321,
      "loss": 0.8003,
      "step": 11000
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0003341231059840768,
      "loss": 0.805,
      "step": 11500
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.0003263010162972709,
      "loss": 0.8061,
      "step": 12000
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.00031814342739185336,
      "loss": 0.8008,
      "step": 12500
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.000309672008647721,
      "loss": 0.8029,
      "step": 13000
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.00030090926308545536,
      "loss": 0.8056,
      "step": 13500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.8322489857673645,
      "eval_runtime": 88.3294,
      "eval_samples_per_second": 17.05,
      "eval_steps_per_second": 2.14,
      "step": 13546
    }
  ],
  "logging_steps": 500,
  "max_steps": 33860,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 6.802174422960538e+17,
  "trial_name": null,
  "trial_params": null
}