{
  "best_metric": 0.5942,
  "best_model_checkpoint": "save_model/flan-t5-small-amazon-reviews-multi-zero-shot/checkpoint-31250",
  "epoch": 5.0,
  "global_step": 31250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 4.92e-05,
      "loss": 0.7233,
      "step": 500
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.8400000000000004e-05,
      "loss": 0.5502,
      "step": 1000
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.76e-05,
      "loss": 0.53,
      "step": 1500
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.6800000000000006e-05,
      "loss": 0.5205,
      "step": 2000
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.5167,
      "step": 2500
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.52e-05,
      "loss": 0.5169,
      "step": 3000
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.44e-05,
      "loss": 0.5075,
      "step": 3500
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.36e-05,
      "loss": 0.5072,
      "step": 4000
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.2800000000000004e-05,
      "loss": 0.5038,
      "step": 4500
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.2e-05,
      "loss": 0.4952,
      "step": 5000
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.12e-05,
      "loss": 0.5005,
      "step": 5500
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 0.4927,
      "step": 6000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5824,
      "eval_loss": 0.4850093126296997,
      "eval_runtime": 9.725,
      "eval_samples_per_second": 514.137,
      "eval_steps_per_second": 16.144,
      "step": 6250
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.960000000000001e-05,
      "loss": 0.4896,
      "step": 6500
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.88e-05,
      "loss": 0.4845,
      "step": 7000
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.8e-05,
      "loss": 0.4827,
      "step": 7500
    },
    {
      "epoch": 1.28,
      "learning_rate": 3.72e-05,
      "loss": 0.4795,
      "step": 8000
    },
    {
      "epoch": 1.36,
      "learning_rate": 3.6400000000000004e-05,
      "loss": 0.4804,
      "step": 8500
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.56e-05,
      "loss": 0.4822,
      "step": 9000
    },
    {
      "epoch": 1.52,
      "learning_rate": 3.48e-05,
      "loss": 0.4804,
      "step": 9500
    },
    {
      "epoch": 1.6,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.4803,
      "step": 10000
    },
    {
      "epoch": 1.68,
      "learning_rate": 3.32e-05,
      "loss": 0.482,
      "step": 10500
    },
    {
      "epoch": 1.76,
      "learning_rate": 3.24e-05,
      "loss": 0.4791,
      "step": 11000
    },
    {
      "epoch": 1.84,
      "learning_rate": 3.16e-05,
      "loss": 0.4803,
      "step": 11500
    },
    {
      "epoch": 1.92,
      "learning_rate": 3.08e-05,
      "loss": 0.476,
      "step": 12000
    },
    {
      "epoch": 2.0,
      "learning_rate": 3e-05,
      "loss": 0.4756,
      "step": 12500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5892,
      "eval_loss": 0.4798971712589264,
      "eval_runtime": 9.5745,
      "eval_samples_per_second": 522.222,
      "eval_steps_per_second": 16.398,
      "step": 12500
    },
    {
      "epoch": 2.08,
      "learning_rate": 2.9199999999999998e-05,
      "loss": 0.4657,
      "step": 13000
    },
    {
      "epoch": 2.16,
      "learning_rate": 2.84e-05,
      "loss": 0.469,
      "step": 13500
    },
    {
      "epoch": 2.24,
      "learning_rate": 2.7600000000000003e-05,
      "loss": 0.4719,
      "step": 14000
    },
    {
      "epoch": 2.32,
      "learning_rate": 2.6800000000000004e-05,
      "loss": 0.4698,
      "step": 14500
    },
    {
      "epoch": 2.4,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.4718,
      "step": 15000
    },
    {
      "epoch": 2.48,
      "learning_rate": 2.5200000000000003e-05,
      "loss": 0.4693,
      "step": 15500
    },
    {
      "epoch": 2.56,
      "learning_rate": 2.44e-05,
      "loss": 0.4659,
      "step": 16000
    },
    {
      "epoch": 2.64,
      "learning_rate": 2.36e-05,
      "loss": 0.4665,
      "step": 16500
    },
    {
      "epoch": 2.72,
      "learning_rate": 2.2800000000000002e-05,
      "loss": 0.4654,
      "step": 17000
    },
    {
      "epoch": 2.8,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.4634,
      "step": 17500
    },
    {
      "epoch": 2.88,
      "learning_rate": 2.12e-05,
      "loss": 0.466,
      "step": 18000
    },
    {
      "epoch": 2.96,
      "learning_rate": 2.04e-05,
      "loss": 0.4679,
      "step": 18500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.591,
      "eval_loss": 0.475551575422287,
      "eval_runtime": 9.5718,
      "eval_samples_per_second": 522.366,
      "eval_steps_per_second": 16.402,
      "step": 18750
    },
    {
      "epoch": 3.04,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.4569,
      "step": 19000
    },
    {
      "epoch": 3.12,
      "learning_rate": 1.88e-05,
      "loss": 0.4539,
      "step": 19500
    },
    {
      "epoch": 3.2,
      "learning_rate": 1.8e-05,
      "loss": 0.4567,
      "step": 20000
    },
    {
      "epoch": 3.28,
      "learning_rate": 1.7199999999999998e-05,
      "loss": 0.4573,
      "step": 20500
    },
    {
      "epoch": 3.36,
      "learning_rate": 1.6400000000000002e-05,
      "loss": 0.4575,
      "step": 21000
    },
    {
      "epoch": 3.44,
      "learning_rate": 1.56e-05,
      "loss": 0.4651,
      "step": 21500
    },
    {
      "epoch": 3.52,
      "learning_rate": 1.48e-05,
      "loss": 0.4602,
      "step": 22000
    },
    {
      "epoch": 3.6,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.4562,
      "step": 22500
    },
    {
      "epoch": 3.68,
      "learning_rate": 1.32e-05,
      "loss": 0.4605,
      "step": 23000
    },
    {
      "epoch": 3.76,
      "learning_rate": 1.24e-05,
      "loss": 0.4621,
      "step": 23500
    },
    {
      "epoch": 3.84,
      "learning_rate": 1.16e-05,
      "loss": 0.4614,
      "step": 24000
    },
    {
      "epoch": 3.92,
      "learning_rate": 1.08e-05,
      "loss": 0.4589,
      "step": 24500
    },
    {
      "epoch": 4.0,
      "learning_rate": 1e-05,
      "loss": 0.4568,
      "step": 25000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.594,
      "eval_loss": 0.4779850244522095,
      "eval_runtime": 9.6408,
      "eval_samples_per_second": 518.631,
      "eval_steps_per_second": 16.285,
      "step": 25000
    },
    {
      "epoch": 4.08,
      "learning_rate": 9.2e-06,
      "loss": 0.4567,
      "step": 25500
    },
    {
      "epoch": 4.16,
      "learning_rate": 8.400000000000001e-06,
      "loss": 0.4577,
      "step": 26000
    },
    {
      "epoch": 4.24,
      "learning_rate": 7.6e-06,
      "loss": 0.4592,
      "step": 26500
    },
    {
      "epoch": 4.32,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.4595,
      "step": 27000
    },
    {
      "epoch": 4.4,
      "learning_rate": 6e-06,
      "loss": 0.4534,
      "step": 27500
    },
    {
      "epoch": 4.48,
      "learning_rate": 5.2e-06,
      "loss": 0.4535,
      "step": 28000
    },
    {
      "epoch": 4.56,
      "learning_rate": 4.4e-06,
      "loss": 0.4534,
      "step": 28500
    },
    {
      "epoch": 4.64,
      "learning_rate": 3.6e-06,
      "loss": 0.4559,
      "step": 29000
    },
    {
      "epoch": 4.72,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.4527,
      "step": 29500
    },
    {
      "epoch": 4.8,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.4491,
      "step": 30000
    },
    {
      "epoch": 4.88,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.4515,
      "step": 30500
    },
    {
      "epoch": 4.96,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.4586,
      "step": 31000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5942,
      "eval_loss": 0.4768580198287964,
      "eval_runtime": 9.7269,
      "eval_samples_per_second": 514.04,
      "eval_steps_per_second": 16.141,
      "step": 31250
    },
    {
      "epoch": 5.0,
      "step": 31250,
      "total_flos": 4.6472626176e+16,
      "train_loss": 0.4780897451171875,
      "train_runtime": 2648.3755,
      "train_samples_per_second": 377.59,
      "train_steps_per_second": 11.8
    }
  ],
  "max_steps": 31250,
  "num_train_epochs": 5,
  "total_flos": 4.6472626176e+16,
  "trial_name": null,
  "trial_params": null
}