{
  "best_global_step": 120,
  "best_metric": 2.2681305408477783,
  "best_model_checkpoint": "/content/drive/MyDrive/lyrics_model_results-2/checkpoint-120",
  "epoch": 4.45,
  "eval_steps": 20,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1875,
      "grad_norm": 1.8194600343704224,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 2.8542,
      "step": 5
    },
    {
      "epoch": 0.375,
      "grad_norm": 1.4292370080947876,
      "learning_rate": 3e-06,
      "loss": 3.0358,
      "step": 10
    },
    {
      "epoch": 0.5625,
      "grad_norm": 1.117842674255371,
      "learning_rate": 4.666666666666667e-06,
      "loss": 3.0467,
      "step": 15
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.8387831449508667,
      "learning_rate": 6.333333333333334e-06,
      "loss": 3.0155,
      "step": 20
    },
    {
      "epoch": 0.75,
      "eval_loss": 2.9648935794830322,
      "eval_runtime": 8.2439,
      "eval_samples_per_second": 14.678,
      "eval_steps_per_second": 3.76,
      "step": 20
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.8464245796203613,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.9769,
      "step": 25
    },
    {
      "epoch": 1.1125,
      "grad_norm": 0.8221689462661743,
      "learning_rate": 9.666666666666667e-06,
      "loss": 2.8774,
      "step": 30
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.5932669639587402,
      "learning_rate": 1.1333333333333334e-05,
      "loss": 2.7237,
      "step": 35
    },
    {
      "epoch": 1.4875,
      "grad_norm": 0.4320496618747711,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 2.5494,
      "step": 40
    },
    {
      "epoch": 1.4875,
      "eval_loss": 2.601949691772461,
      "eval_runtime": 7.1177,
      "eval_samples_per_second": 17.0,
      "eval_steps_per_second": 4.355,
      "step": 40
    },
    {
      "epoch": 1.675,
      "grad_norm": 1.2623802423477173,
      "learning_rate": 1.4666666666666668e-05,
      "loss": 2.5653,
      "step": 45
    },
    {
      "epoch": 1.8625,
      "grad_norm": 0.7509922981262207,
      "learning_rate": 1.6333333333333335e-05,
      "loss": 2.5052,
      "step": 50
    },
    {
      "epoch": 2.0375,
      "grad_norm": 0.400310218334198,
      "learning_rate": 1.8e-05,
      "loss": 2.5921,
      "step": 55
    },
    {
      "epoch": 2.225,
      "grad_norm": 0.6286957859992981,
      "learning_rate": 1.9666666666666666e-05,
      "loss": 2.2916,
      "step": 60
    },
    {
      "epoch": 2.225,
      "eval_loss": 2.3243348598480225,
      "eval_runtime": 6.2585,
      "eval_samples_per_second": 19.334,
      "eval_steps_per_second": 4.953,
      "step": 60
    },
    {
      "epoch": 2.4125,
      "grad_norm": 0.49130329489707947,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 2.3263,
      "step": 65
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.409078985452652,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 2.367,
      "step": 70
    },
    {
      "epoch": 2.7875,
      "grad_norm": 0.40927085280418396,
      "learning_rate": 2.466666666666667e-05,
      "loss": 2.2767,
      "step": 75
    },
    {
      "epoch": 2.975,
      "grad_norm": 0.43190890550613403,
      "learning_rate": 2.633333333333333e-05,
      "loss": 2.2449,
      "step": 80
    },
    {
      "epoch": 2.975,
      "eval_loss": 2.287776231765747,
      "eval_runtime": 7.165,
      "eval_samples_per_second": 16.888,
      "eval_steps_per_second": 4.327,
      "step": 80
    },
    {
      "epoch": 3.15,
      "grad_norm": 0.42665043473243713,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.3112,
      "step": 85
    },
    {
      "epoch": 3.3375,
      "grad_norm": 0.4464608132839203,
      "learning_rate": 2.9666666666666672e-05,
      "loss": 2.2996,
      "step": 90
    },
    {
      "epoch": 3.525,
      "grad_norm": 0.355787992477417,
      "learning_rate": 3.1333333333333334e-05,
      "loss": 2.3476,
      "step": 95
    },
    {
      "epoch": 3.7125,
      "grad_norm": 0.3554602861404419,
      "learning_rate": 3.3e-05,
      "loss": 2.1772,
      "step": 100
    },
    {
      "epoch": 3.7125,
      "eval_loss": 2.2873313426971436,
      "eval_runtime": 6.3162,
      "eval_samples_per_second": 19.157,
      "eval_steps_per_second": 4.908,
      "step": 100
    },
    {
      "epoch": 3.9,
      "grad_norm": 0.7602716684341431,
      "learning_rate": 3.466666666666667e-05,
      "loss": 2.2508,
      "step": 105
    },
    {
      "epoch": 4.075,
      "grad_norm": 0.4771987497806549,
      "learning_rate": 3.633333333333333e-05,
      "loss": 2.3496,
      "step": 110
    },
    {
      "epoch": 4.2625,
      "grad_norm": 0.440900593996048,
      "learning_rate": 3.8e-05,
      "loss": 2.2687,
      "step": 115
    },
    {
      "epoch": 4.45,
      "grad_norm": 1.545401692390442,
      "learning_rate": 3.966666666666667e-05,
      "loss": 2.1467,
      "step": 120
    },
    {
      "epoch": 4.45,
      "eval_loss": 2.2681305408477783,
      "eval_runtime": 6.1902,
      "eval_samples_per_second": 19.547,
      "eval_steps_per_second": 5.008,
      "step": 120
    }
  ],
  "logging_steps": 5,
  "max_steps": 405,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 60,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5930172639789056e+16,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}