{
  "best_metric": 5.475988388061523,
  "best_model_checkpoint": "autotrain-g10wr-ryb7t/checkpoint-64",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 64,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.046875,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 3.8675,
      "step": 3
    },
    {
      "epoch": 0.09375,
      "grad_norm": 26.64595603942871,
      "learning_rate": 7.8125e-07,
      "loss": 3.8727,
      "step": 6
    },
    {
      "epoch": 0.140625,
      "grad_norm": 28.351032257080078,
      "learning_rate": 3.125e-06,
      "loss": 3.8738,
      "step": 9
    },
    {
      "epoch": 0.1875,
      "grad_norm": 30.790821075439453,
      "learning_rate": 5.46875e-06,
      "loss": 3.6174,
      "step": 12
    },
    {
      "epoch": 0.234375,
      "grad_norm": 30.02513885498047,
      "learning_rate": 7.8125e-06,
      "loss": 2.5911,
      "step": 15
    },
    {
      "epoch": 0.28125,
      "grad_norm": 16.17921257019043,
      "learning_rate": 1.0156250000000001e-05,
      "loss": 1.8417,
      "step": 18
    },
    {
      "epoch": 0.328125,
      "grad_norm": 20.254079818725586,
      "learning_rate": 1.25e-05,
      "loss": 1.5405,
      "step": 21
    },
    {
      "epoch": 0.375,
      "grad_norm": 6.887765884399414,
      "learning_rate": 1.484375e-05,
      "loss": 1.5088,
      "step": 24
    },
    {
      "epoch": 0.421875,
      "grad_norm": 10.511013984680176,
      "learning_rate": 1.71875e-05,
      "loss": 1.3341,
      "step": 27
    },
    {
      "epoch": 0.46875,
      "grad_norm": 12.581910133361816,
      "learning_rate": 1.953125e-05,
      "loss": 1.4883,
      "step": 30
    },
    {
      "epoch": 0.515625,
      "grad_norm": 5.822439670562744,
      "learning_rate": 2.1875e-05,
      "loss": 1.5237,
      "step": 33
    },
    {
      "epoch": 0.5625,
      "grad_norm": 9.540604591369629,
      "learning_rate": 2.4218750000000003e-05,
      "loss": 1.4182,
      "step": 36
    },
    {
      "epoch": 0.609375,
      "grad_norm": 3.624293804168701,
      "learning_rate": 2.6562500000000002e-05,
      "loss": 1.5184,
      "step": 39
    },
    {
      "epoch": 0.65625,
      "grad_norm": 6.4345221519470215,
      "learning_rate": 2.890625e-05,
      "loss": 1.3708,
      "step": 42
    },
    {
      "epoch": 0.703125,
      "grad_norm": 4.039494514465332,
      "learning_rate": 3.125e-05,
      "loss": 1.5398,
      "step": 45
    },
    {
      "epoch": 0.75,
      "grad_norm": 8.686318397521973,
      "learning_rate": 3.359375e-05,
      "loss": 1.3794,
      "step": 48
    },
    {
      "epoch": 0.796875,
      "grad_norm": 5.242523193359375,
      "learning_rate": 3.59375e-05,
      "loss": 1.3477,
      "step": 51
    },
    {
      "epoch": 0.84375,
      "grad_norm": 2.8347246646881104,
      "learning_rate": 3.828125e-05,
      "loss": 1.4509,
      "step": 54
    },
    {
      "epoch": 0.890625,
      "grad_norm": 3.3037731647491455,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 1.4429,
      "step": 57
    },
    {
      "epoch": 0.9375,
      "grad_norm": 3.0450754165649414,
      "learning_rate": 4.2968750000000004e-05,
      "loss": 1.5172,
      "step": 60
    },
    {
      "epoch": 0.984375,
      "grad_norm": 3.5716280937194824,
      "learning_rate": 4.5312500000000004e-05,
      "loss": 1.3965,
      "step": 63
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.0026870229007633587,
      "eval_f1": 0.0,
      "eval_loss": 5.475988388061523,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.7114,
      "eval_samples_per_second": 195.393,
      "eval_steps_per_second": 12.651,
      "step": 64
    }
  ],
  "logging_steps": 3,
  "max_steps": 640,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 118191988716288.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}