{
  "best_metric": 3.8772294521331787,
  "best_model_checkpoint": "/content/drive/MyDrive/Azari/Models/AzerBert_v2/checkpoint-11630",
  "epoch": 10.0,
  "global_step": 11630,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.5e-05,
      "loss": 6.7343,
      "step": 1163
    },
    {
      "epoch": 1.0,
      "eval_loss": 6.081459045410156,
      "eval_runtime": 503.0003,
      "eval_samples_per_second": 263.048,
      "eval_steps_per_second": 2.056,
      "step": 1163
    },
    {
      "epoch": 2.0,
      "learning_rate": 4e-05,
      "loss": 5.7511,
      "step": 2326
    },
    {
      "epoch": 2.0,
      "eval_loss": 5.344614028930664,
      "eval_runtime": 516.7667,
      "eval_samples_per_second": 256.04,
      "eval_steps_per_second": 2.001,
      "step": 2326
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.5e-05,
      "loss": 5.2027,
      "step": 3489
    },
    {
      "epoch": 3.0,
      "eval_loss": 4.8805670738220215,
      "eval_runtime": 513.7912,
      "eval_samples_per_second": 257.523,
      "eval_steps_per_second": 2.012,
      "step": 3489
    },
    {
      "epoch": 4.0,
      "learning_rate": 3e-05,
      "loss": 4.8194,
      "step": 4652
    },
    {
      "epoch": 4.0,
      "eval_loss": 4.549716472625732,
      "eval_runtime": 489.7556,
      "eval_samples_per_second": 270.161,
      "eval_steps_per_second": 2.111,
      "step": 4652
    },
    {
      "epoch": 5.0,
      "learning_rate": 2.5e-05,
      "loss": 4.5507,
      "step": 5815
    },
    {
      "epoch": 5.0,
      "eval_loss": 4.3259382247924805,
      "eval_runtime": 475.757,
      "eval_samples_per_second": 278.11,
      "eval_steps_per_second": 2.173,
      "step": 5815
    },
    {
      "epoch": 6.0,
      "learning_rate": 2e-05,
      "loss": 4.3528,
      "step": 6978
    },
    {
      "epoch": 6.0,
      "eval_loss": 4.155429363250732,
      "eval_runtime": 485.1031,
      "eval_samples_per_second": 272.752,
      "eval_steps_per_second": 2.132,
      "step": 6978
    },
    {
      "epoch": 7.0,
      "learning_rate": 1.5e-05,
      "loss": 4.2138,
      "step": 8141
    },
    {
      "epoch": 7.0,
      "eval_loss": 4.037585258483887,
      "eval_runtime": 549.6833,
      "eval_samples_per_second": 240.708,
      "eval_steps_per_second": 1.881,
      "step": 8141
    },
    {
      "epoch": 8.0,
      "learning_rate": 1e-05,
      "loss": 4.1146,
      "step": 9304
    },
    {
      "epoch": 8.0,
      "eval_loss": 3.954880714416504,
      "eval_runtime": 527.3306,
      "eval_samples_per_second": 250.911,
      "eval_steps_per_second": 1.961,
      "step": 9304
    },
    {
      "epoch": 9.0,
      "learning_rate": 5e-06,
      "loss": 4.0459,
      "step": 10467
    },
    {
      "epoch": 9.0,
      "eval_loss": 3.9045631885528564,
      "eval_runtime": 520.0259,
      "eval_samples_per_second": 254.435,
      "eval_steps_per_second": 1.988,
      "step": 10467
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 4.0144,
      "step": 11630
    },
    {
      "epoch": 10.0,
      "eval_loss": 3.8772294521331787,
      "eval_runtime": 540.0798,
      "eval_samples_per_second": 244.988,
      "eval_steps_per_second": 1.915,
      "step": 11630
    }
  ],
  "max_steps": 11630,
  "num_train_epochs": 10,
  "total_flos": 3.9169211524061184e+17,
  "trial_name": null,
  "trial_params": null
}