{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9984235417761429,
  "global_step": 475,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.994534068046937e-05,
      "loss": 1.8599,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.980286753286195e-05,
      "loss": 1.6162,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.965903258506806e-05,
      "loss": 1.5187,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.95415555523494e-05,
      "loss": 1.4685,
      "step": 40
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.929469844930753e-05,
      "loss": 1.3233,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.885188413200075e-05,
      "loss": 1.1081,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.830477159419966e-05,
      "loss": 0.9364,
      "step": 70
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.7655753219826114e-05,
      "loss": 0.7434,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.690766700109659e-05,
      "loss": 0.5053,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.6063784128704367e-05,
      "loss": 0.2824,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.512779468773494e-05,
      "loss": 0.1312,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.4103791521862784e-05,
      "loss": 0.0681,
      "step": 120
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.2996252336387414e-05,
      "loss": 0.0496,
      "step": 130
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.181002011836737e-05,
      "loss": 0.0482,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.0550281959470023e-05,
      "loss": 0.0497,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.9222546374139533e-05,
      "loss": 0.0523,
      "step": 160
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.783261921226479e-05,
      "loss": 0.0561,
      "step": 170
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.6386578271674984e-05,
      "loss": 0.0606,
      "step": 180
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.489074672147621e-05,
      "loss": 0.0664,
      "step": 190
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.335166545244178e-05,
      "loss": 0.0742,
      "step": 200
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.1776064475361114e-05,
      "loss": 0.0799,
      "step": 210
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.017083349241492e-05,
      "loss": 0.0873,
      "step": 220
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.8542991770260608e-05,
      "loss": 0.0952,
      "step": 230
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.689965744656508e-05,
      "loss": 0.1036,
      "step": 240
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.5248016404199908e-05,
      "loss": 0.1103,
      "step": 250
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.3595290849203862e-05,
      "loss": 0.1207,
      "step": 260
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.19487077299135e-05,
      "loss": 0.1254,
      "step": 270
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.031546713535688e-05,
      "loss": 0.1387,
      "step": 280
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.87027108110963e-05,
      "loss": 0.1402,
      "step": 290
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.7117490930191965e-05,
      "loss": 0.1518,
      "step": 300
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.5566739255843606e-05,
      "loss": 0.1563,
      "step": 310
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.4057236830553704e-05,
      "loss": 0.1663,
      "step": 320
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.2595584324353943e-05,
      "loss": 0.17,
      "step": 330
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.118817317175467e-05,
      "loss": 0.1744,
      "step": 340
    },
    {
      "epoch": 0.74,
      "learning_rate": 9.841157623627947e-06,
      "loss": 0.181,
      "step": 350
    },
    {
      "epoch": 0.76,
      "learning_rate": 8.56042783623439e-06,
      "loss": 0.185,
      "step": 360
    },
    {
      "epoch": 0.78,
      "learning_rate": 7.351584115068535e-06,
      "loss": 0.1898,
      "step": 370
    },
    {
      "epoch": 0.8,
      "learning_rate": 6.219912426147795e-06,
      "loss": 0.1973,
      "step": 380
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.170361281828054e-06,
      "loss": 0.1962,
      "step": 390
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.207520102218213e-06,
      "loss": 0.1991,
      "step": 400
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.3355991468137394e-06,
      "loss": 0.2005,
      "step": 410
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.558411104103198e-06,
      "loss": 0.2046,
      "step": 420
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.87935441965153e-06,
      "loss": 0.2059,
      "step": 430
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.3013984355623315e-06,
      "loss": 0.2045,
      "step": 440
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.270704063003232e-07,
      "loss": 0.2049,
      "step": 450
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.5844444765059945e-07,
      "loss": 0.2027,
      "step": 460
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.9713246713805588e-07,
      "loss": 0.2072,
      "step": 470
    },
    {
      "epoch": 1.0,
      "step": 475,
      "total_flos": 9.056996286686822e+17,
      "train_loss": 0.3478317604566875,
      "train_runtime": 4641.6132,
      "train_samples_per_second": 13.114,
      "train_steps_per_second": 0.102
    }
  ],
  "max_steps": 475,
  "num_train_epochs": 1,
  "total_flos": 9.056996286686822e+17,
  "trial_name": null,
  "trial_params": null
}