{
  "best_global_step": 30,
  "best_metric": 0.9119236177929095,
  "best_model_checkpoint": "./models/indic_toxicity_v2\\checkpoint-30",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 4.22359037399292,
      "learning_rate": 1.8e-05,
      "loss": 0.4506,
      "step": 10
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 8.100936889648438,
      "learning_rate": 1.577777777777778e-05,
      "loss": 0.2223,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.663024663925171,
      "learning_rate": 1.3555555555555557e-05,
      "loss": 0.2156,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.940677966101695,
      "eval_f1": 0.9119236177929095,
      "eval_loss": 0.23991811275482178,
      "eval_runtime": 1.7613,
      "eval_samples_per_second": 66.996,
      "eval_steps_per_second": 4.542,
      "step": 30
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 2.3720521926879883,
      "learning_rate": 1.1333333333333334e-05,
      "loss": 0.2807,
      "step": 40
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.536311388015747,
      "learning_rate": 9.111111111111112e-06,
      "loss": 0.1254,
      "step": 50
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5451638102531433,
      "learning_rate": 6.88888888888889e-06,
      "loss": 0.2193,
      "step": 60
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.940677966101695,
      "eval_f1": 0.9119236177929095,
      "eval_loss": 0.2537901699542999,
      "eval_runtime": 1.5809,
      "eval_samples_per_second": 74.643,
      "eval_steps_per_second": 5.061,
      "step": 60
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 2.8201632499694824,
      "learning_rate": 4.666666666666667e-06,
      "loss": 0.1388,
      "step": 70
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 13.822385787963867,
      "learning_rate": 2.4444444444444447e-06,
      "loss": 0.1893,
      "step": 80
    },
    {
      "epoch": 3.0,
      "grad_norm": 17.247787475585938,
      "learning_rate": 2.2222222222222224e-07,
      "loss": 0.3219,
      "step": 90
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.940677966101695,
      "eval_f1": 0.9119236177929095,
      "eval_loss": 0.26261603832244873,
      "eval_runtime": 1.5458,
      "eval_samples_per_second": 76.334,
      "eval_steps_per_second": 5.175,
      "step": 90
    }
  ],
  "logging_steps": 10,
  "max_steps": 90,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5085443366880.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}