{
  "best_metric": 0.899099588394165,
  "best_model_checkpoint": "FuturixAI-hate-speech-2/checkpoint-300",
  "epoch": 13.714285714285714,
  "eval_steps": 50,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.46,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 3.3626,
      "step": 10
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 3.2143,
      "step": 20
    },
    {
      "epoch": 1.37,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.778,
      "step": 30
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00011999999999999999,
      "loss": 2.1442,
      "step": 40
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00015,
      "loss": 1.4083,
      "step": 50
    },
    {
      "epoch": 2.29,
      "eval_loss": 1.2041112184524536,
      "eval_runtime": 31.844,
      "eval_samples_per_second": 6.281,
      "eval_steps_per_second": 0.785,
      "step": 50
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.1391,
      "step": 60
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.00020999999999999998,
      "loss": 1.061,
      "step": 70
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.0083,
      "step": 80
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.00027,
      "loss": 0.9991,
      "step": 90
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.0003,
      "loss": 0.9615,
      "step": 100
    },
    {
      "epoch": 4.57,
      "eval_loss": 0.9786862134933472,
      "eval_runtime": 31.7381,
      "eval_samples_per_second": 6.302,
      "eval_steps_per_second": 0.788,
      "step": 100
    },
    {
      "epoch": 5.03,
      "learning_rate": 0.000285,
      "loss": 0.953,
      "step": 110
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.00027,
      "loss": 0.9031,
      "step": 120
    },
    {
      "epoch": 5.94,
      "learning_rate": 0.00025499999999999996,
      "loss": 0.8762,
      "step": 130
    },
    {
      "epoch": 6.4,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.8833,
      "step": 140
    },
    {
      "epoch": 6.86,
      "learning_rate": 0.000225,
      "loss": 0.875,
      "step": 150
    },
    {
      "epoch": 6.86,
      "eval_loss": 0.904224693775177,
      "eval_runtime": 32.9474,
      "eval_samples_per_second": 6.07,
      "eval_steps_per_second": 0.759,
      "step": 150
    },
    {
      "epoch": 7.31,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.8946,
      "step": 160
    },
    {
      "epoch": 7.77,
      "learning_rate": 0.000195,
      "loss": 0.8751,
      "step": 170
    },
    {
      "epoch": 8.23,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.8854,
      "step": 180
    },
    {
      "epoch": 8.69,
      "learning_rate": 0.000165,
      "loss": 0.8708,
      "step": 190
    },
    {
      "epoch": 9.14,
      "learning_rate": 0.00015,
      "loss": 0.8683,
      "step": 200
    },
    {
      "epoch": 9.14,
      "eval_loss": 0.8998382091522217,
      "eval_runtime": 31.7282,
      "eval_samples_per_second": 6.304,
      "eval_steps_per_second": 0.788,
      "step": 200
    },
    {
      "epoch": 9.6,
      "learning_rate": 0.000135,
      "loss": 0.8628,
      "step": 210
    },
    {
      "epoch": 10.06,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.857,
      "step": 220
    },
    {
      "epoch": 10.51,
      "learning_rate": 0.00010499999999999999,
      "loss": 0.8688,
      "step": 230
    },
    {
      "epoch": 10.97,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.8527,
      "step": 240
    },
    {
      "epoch": 11.43,
      "learning_rate": 7.5e-05,
      "loss": 0.8495,
      "step": 250
    },
    {
      "epoch": 11.43,
      "eval_loss": 0.8998110890388489,
      "eval_runtime": 32.1816,
      "eval_samples_per_second": 6.215,
      "eval_steps_per_second": 0.777,
      "step": 250
    },
    {
      "epoch": 11.89,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.8639,
      "step": 260
    },
    {
      "epoch": 12.34,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 0.8696,
      "step": 270
    },
    {
      "epoch": 12.8,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.8524,
      "step": 280
    },
    {
      "epoch": 13.26,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 0.83,
      "step": 290
    },
    {
      "epoch": 13.71,
      "learning_rate": 0.0,
      "loss": 0.8545,
      "step": 300
    },
    {
      "epoch": 13.71,
      "eval_loss": 0.899099588394165,
      "eval_runtime": 32.5062,
      "eval_samples_per_second": 6.153,
      "eval_steps_per_second": 0.769,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 300,
  "num_train_epochs": 15,
  "save_steps": 50,
  "total_flos": 2.6513261434503168e+17,
  "trial_name": null,
  "trial_params": null
}