{
  "best_metric": 1.4858289957046509,
  "best_model_checkpoint": "./results/checkpoint-6250",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 12500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "grad_norm": 3.800455331802368,
      "learning_rate": 4.92e-05,
      "loss": 1.8865,
      "step": 500
    },
    {
      "epoch": 0.32,
      "grad_norm": 3.2938010692596436,
      "learning_rate": 4.8400000000000004e-05,
      "loss": 1.8249,
      "step": 1000
    },
    {
      "epoch": 0.48,
      "grad_norm": 3.251399517059326,
      "learning_rate": 4.76e-05,
      "loss": 1.7717,
      "step": 1500
    },
    {
      "epoch": 0.64,
      "grad_norm": 3.223798990249634,
      "learning_rate": 4.6800000000000006e-05,
      "loss": 1.7477,
      "step": 2000
    },
    {
      "epoch": 0.8,
      "grad_norm": 3.1936862468719482,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.7458,
      "step": 2500
    },
    {
      "epoch": 0.96,
      "grad_norm": 3.4300343990325928,
      "learning_rate": 4.52e-05,
      "loss": 1.7226,
      "step": 3000
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.5059889554977417,
      "eval_runtime": 13.9307,
      "eval_samples_per_second": 335.876,
      "eval_steps_per_second": 10.552,
      "step": 3125
    },
    {
      "epoch": 1.12,
      "grad_norm": 3.277369737625122,
      "learning_rate": 4.44e-05,
      "loss": 1.5592,
      "step": 3500
    },
    {
      "epoch": 1.28,
      "grad_norm": 2.9364540576934814,
      "learning_rate": 4.36e-05,
      "loss": 1.5109,
      "step": 4000
    },
    {
      "epoch": 1.44,
      "grad_norm": 2.9026784896850586,
      "learning_rate": 4.2800000000000004e-05,
      "loss": 1.5117,
      "step": 4500
    },
    {
      "epoch": 1.6,
      "grad_norm": 3.0175607204437256,
      "learning_rate": 4.2e-05,
      "loss": 1.5143,
      "step": 5000
    },
    {
      "epoch": 1.76,
      "grad_norm": 3.0337491035461426,
      "learning_rate": 4.12e-05,
      "loss": 1.5219,
      "step": 5500
    },
    {
      "epoch": 1.92,
      "grad_norm": 2.8166635036468506,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 1.5017,
      "step": 6000
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.4858289957046509,
      "eval_runtime": 14.2343,
      "eval_samples_per_second": 328.713,
      "eval_steps_per_second": 10.327,
      "step": 6250
    },
    {
      "epoch": 2.08,
      "grad_norm": 2.935457706451416,
      "learning_rate": 3.960000000000001e-05,
      "loss": 1.4048,
      "step": 6500
    },
    {
      "epoch": 2.24,
      "grad_norm": 3.244539499282837,
      "learning_rate": 3.88e-05,
      "loss": 1.3372,
      "step": 7000
    },
    {
      "epoch": 2.4,
      "grad_norm": 3.7380311489105225,
      "learning_rate": 3.8e-05,
      "loss": 1.3405,
      "step": 7500
    },
    {
      "epoch": 2.56,
      "grad_norm": 3.5527069568634033,
      "learning_rate": 3.72e-05,
      "loss": 1.3517,
      "step": 8000
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 2.839742422103882,
      "learning_rate": 3.6400000000000004e-05,
      "loss": 1.3515,
      "step": 8500
    },
    {
      "epoch": 2.88,
      "grad_norm": 3.501607894897461,
      "learning_rate": 3.56e-05,
      "loss": 1.3555,
      "step": 9000
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.4895309209823608,
      "eval_runtime": 13.9356,
      "eval_samples_per_second": 335.759,
      "eval_steps_per_second": 10.549,
      "step": 9375
    },
    {
      "epoch": 3.04,
      "grad_norm": 2.6918106079101562,
      "learning_rate": 3.48e-05,
      "loss": 1.3244,
      "step": 9500
    },
    {
      "epoch": 3.2,
      "grad_norm": 3.5866470336914062,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.2057,
      "step": 10000
    },
    {
      "epoch": 3.36,
      "grad_norm": 3.242699384689331,
      "learning_rate": 3.32e-05,
      "loss": 1.21,
      "step": 10500
    },
    {
      "epoch": 3.52,
      "grad_norm": 2.8729286193847656,
      "learning_rate": 3.24e-05,
      "loss": 1.2239,
      "step": 11000
    },
    {
      "epoch": 3.68,
      "grad_norm": 3.33542799949646,
      "learning_rate": 3.16e-05,
      "loss": 1.2178,
      "step": 11500
    },
    {
      "epoch": 3.84,
      "grad_norm": 3.3703885078430176,
      "learning_rate": 3.08e-05,
      "loss": 1.2281,
      "step": 12000
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.5465049743652344,
      "learning_rate": 3e-05,
      "loss": 1.238,
      "step": 12500
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.4973833560943604,
      "eval_runtime": 13.8641,
      "eval_samples_per_second": 337.491,
      "eval_steps_per_second": 10.603,
      "step": 12500
    }
  ],
  "logging_steps": 500,
  "max_steps": 31250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6779672985600000.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}