{
  "best_metric": 0.05,
  "best_model_checkpoint": "model14-finetuned-SLT-subset/checkpoint-59",
  "epoch": 2.3333333333333335,
  "eval_steps": 500,
  "global_step": 177,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05649717514124294,
      "grad_norm": 15.659302711486816,
      "learning_rate": 2.777777777777778e-05,
      "loss": 3.8577,
      "step": 10
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 13.975533485412598,
      "learning_rate": 4.937106918238994e-05,
      "loss": 3.6714,
      "step": 20
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 13.702733039855957,
      "learning_rate": 4.6226415094339625e-05,
      "loss": 3.996,
      "step": 30
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 13.188166618347168,
      "learning_rate": 4.308176100628931e-05,
      "loss": 4.017,
      "step": 40
    },
    {
      "epoch": 0.2824858757062147,
      "grad_norm": 12.505217552185059,
      "learning_rate": 3.9937106918239e-05,
      "loss": 3.9073,
      "step": 50
    },
    {
      "epoch": 0.3333333333333333,
      "eval_accuracy": 0.05,
      "eval_loss": 3.707028865814209,
      "eval_runtime": 86.3138,
      "eval_samples_per_second": 0.463,
      "eval_steps_per_second": 0.232,
      "step": 59
    },
    {
      "epoch": 1.0056497175141244,
      "grad_norm": 12.231797218322754,
      "learning_rate": 3.679245283018868e-05,
      "loss": 3.906,
      "step": 60
    },
    {
      "epoch": 1.0621468926553672,
      "grad_norm": 11.97706413269043,
      "learning_rate": 3.364779874213837e-05,
      "loss": 3.8198,
      "step": 70
    },
    {
      "epoch": 1.11864406779661,
      "grad_norm": 11.600285530090332,
      "learning_rate": 3.050314465408805e-05,
      "loss": 3.7922,
      "step": 80
    },
    {
      "epoch": 1.1751412429378532,
      "grad_norm": 11.922569274902344,
      "learning_rate": 2.7358490566037738e-05,
      "loss": 3.8627,
      "step": 90
    },
    {
      "epoch": 1.231638418079096,
      "grad_norm": 11.862650871276855,
      "learning_rate": 2.421383647798742e-05,
      "loss": 3.7829,
      "step": 100
    },
    {
      "epoch": 1.288135593220339,
      "grad_norm": 12.290817260742188,
      "learning_rate": 2.106918238993711e-05,
      "loss": 3.8434,
      "step": 110
    },
    {
      "epoch": 1.3333333333333333,
      "eval_accuracy": 0.05,
      "eval_loss": 3.654296875,
      "eval_runtime": 86.7853,
      "eval_samples_per_second": 0.461,
      "eval_steps_per_second": 0.23,
      "step": 118
    },
    {
      "epoch": 2.0112994350282487,
      "grad_norm": 11.525404930114746,
      "learning_rate": 1.7924528301886792e-05,
      "loss": 3.8266,
      "step": 120
    },
    {
      "epoch": 2.0677966101694913,
      "grad_norm": 11.840191841125488,
      "learning_rate": 1.4779874213836479e-05,
      "loss": 3.6656,
      "step": 130
    },
    {
      "epoch": 2.1242937853107344,
      "grad_norm": 11.563905715942383,
      "learning_rate": 1.1635220125786164e-05,
      "loss": 3.6074,
      "step": 140
    },
    {
      "epoch": 2.1807909604519775,
      "grad_norm": 11.315864562988281,
      "learning_rate": 8.49056603773585e-06,
      "loss": 3.7573,
      "step": 150
    },
    {
      "epoch": 2.23728813559322,
      "grad_norm": 11.722553253173828,
      "learning_rate": 5.345911949685535e-06,
      "loss": 3.7128,
      "step": 160
    },
    {
      "epoch": 2.2937853107344632,
      "grad_norm": 11.536542892456055,
      "learning_rate": 2.20125786163522e-06,
      "loss": 3.6998,
      "step": 170
    },
    {
      "epoch": 2.3333333333333335,
      "eval_accuracy": 0.05,
      "eval_loss": 3.643190860748291,
      "eval_runtime": 87.9928,
      "eval_samples_per_second": 0.455,
      "eval_steps_per_second": 0.227,
      "step": 177
    },
    {
      "epoch": 2.3333333333333335,
      "step": 177,
      "total_flos": 4.412563510866739e+17,
      "train_loss": 3.8058138055316473,
      "train_runtime": 1305.8999,
      "train_samples_per_second": 0.271,
      "train_steps_per_second": 0.136
    },
    {
      "epoch": 2.3333333333333335,
      "eval_accuracy": 0.0,
      "eval_loss": 3.5820634365081787,
      "eval_runtime": 2.7763,
      "eval_samples_per_second": 0.36,
      "eval_steps_per_second": 0.36,
      "step": 177
    }
  ],
  "logging_steps": 10,
  "max_steps": 177,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 4.412563510866739e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}