{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 670,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 1.9701492537313435e-05,
      "loss": 1.1334,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9402985074626868e-05,
      "loss": 1.1003,
      "step": 20
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9104477611940298e-05,
      "loss": 1.0769,
      "step": 30
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.8805970149253735e-05,
      "loss": 1.0546,
      "step": 40
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.8507462686567165e-05,
      "loss": 1.0465,
      "step": 50
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.8208955223880598e-05,
      "loss": 0.9684,
      "step": 60
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.791044776119403e-05,
      "loss": 0.9276,
      "step": 70
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.7611940298507464e-05,
      "loss": 0.8279,
      "step": 80
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.7313432835820894e-05,
      "loss": 0.816,
      "step": 90
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.701492537313433e-05,
      "loss": 0.7778,
      "step": 100
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.671641791044776e-05,
      "loss": 0.7261,
      "step": 110
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.6417910447761197e-05,
      "loss": 0.7208,
      "step": 120
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.6119402985074627e-05,
      "loss": 0.6404,
      "step": 130
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.582089552238806e-05,
      "loss": 0.6556,
      "step": 140
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.5522388059701494e-05,
      "loss": 0.6484,
      "step": 150
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.5223880597014925e-05,
      "loss": 0.6387,
      "step": 160
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.492537313432836e-05,
      "loss": 0.545,
      "step": 170
    },
    {
      "epoch": 1.34,
      "learning_rate": 1.4626865671641792e-05,
      "loss": 0.5693,
      "step": 180
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.4328358208955224e-05,
      "loss": 0.4667,
      "step": 190
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.4029850746268658e-05,
      "loss": 0.5243,
      "step": 200
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.373134328358209e-05,
      "loss": 0.4737,
      "step": 210
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.3432835820895525e-05,
      "loss": 0.4586,
      "step": 220
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.3134328358208957e-05,
      "loss": 0.4561,
      "step": 230
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.2835820895522388e-05,
      "loss": 0.5476,
      "step": 240
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.2537313432835823e-05,
      "loss": 0.4314,
      "step": 250
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.2238805970149255e-05,
      "loss": 0.4875,
      "step": 260
    },
    {
      "epoch": 2.01,
      "learning_rate": 1.1940298507462686e-05,
      "loss": 0.5459,
      "step": 270
    },
    {
      "epoch": 2.09,
      "learning_rate": 1.1641791044776121e-05,
      "loss": 0.4429,
      "step": 280
    },
    {
      "epoch": 2.16,
      "learning_rate": 1.1343283582089553e-05,
      "loss": 0.3935,
      "step": 290
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.1044776119402986e-05,
      "loss": 0.4531,
      "step": 300
    },
    {
      "epoch": 2.31,
      "learning_rate": 1.074626865671642e-05,
      "loss": 0.3705,
      "step": 310
    },
    {
      "epoch": 2.39,
      "learning_rate": 1.0447761194029851e-05,
      "loss": 0.3925,
      "step": 320
    },
    {
      "epoch": 2.46,
      "learning_rate": 1.0149253731343284e-05,
      "loss": 0.4739,
      "step": 330
    },
    {
      "epoch": 2.54,
      "learning_rate": 9.850746268656717e-06,
      "loss": 0.3975,
      "step": 340
    },
    {
      "epoch": 2.61,
      "learning_rate": 9.552238805970149e-06,
      "loss": 0.4335,
      "step": 350
    },
    {
      "epoch": 2.69,
      "learning_rate": 9.253731343283582e-06,
      "loss": 0.443,
      "step": 360
    },
    {
      "epoch": 2.76,
      "learning_rate": 8.955223880597016e-06,
      "loss": 0.3843,
      "step": 370
    },
    {
      "epoch": 2.84,
      "learning_rate": 8.656716417910447e-06,
      "loss": 0.333,
      "step": 380
    },
    {
      "epoch": 2.91,
      "learning_rate": 8.35820895522388e-06,
      "loss": 0.3555,
      "step": 390
    },
    {
      "epoch": 2.99,
      "learning_rate": 8.059701492537314e-06,
      "loss": 0.39,
      "step": 400
    },
    {
      "epoch": 3.06,
      "learning_rate": 7.761194029850747e-06,
      "loss": 0.3848,
      "step": 410
    },
    {
      "epoch": 3.13,
      "learning_rate": 7.46268656716418e-06,
      "loss": 0.3658,
      "step": 420
    },
    {
      "epoch": 3.21,
      "learning_rate": 7.164179104477612e-06,
      "loss": 0.3329,
      "step": 430
    },
    {
      "epoch": 3.28,
      "learning_rate": 6.865671641791045e-06,
      "loss": 0.4015,
      "step": 440
    },
    {
      "epoch": 3.36,
      "learning_rate": 6.567164179104478e-06,
      "loss": 0.3598,
      "step": 450
    },
    {
      "epoch": 3.43,
      "learning_rate": 6.2686567164179116e-06,
      "loss": 0.3306,
      "step": 460
    },
    {
      "epoch": 3.51,
      "learning_rate": 5.970149253731343e-06,
      "loss": 0.3427,
      "step": 470
    },
    {
      "epoch": 3.58,
      "learning_rate": 5.671641791044776e-06,
      "loss": 0.2763,
      "step": 480
    },
    {
      "epoch": 3.66,
      "learning_rate": 5.37313432835821e-06,
      "loss": 0.3242,
      "step": 490
    },
    {
      "epoch": 3.73,
      "learning_rate": 5.074626865671642e-06,
      "loss": 0.3514,
      "step": 500
    },
    {
      "epoch": 3.81,
      "learning_rate": 4.7761194029850745e-06,
      "loss": 0.3407,
      "step": 510
    },
    {
      "epoch": 3.88,
      "learning_rate": 4.477611940298508e-06,
      "loss": 0.3108,
      "step": 520
    },
    {
      "epoch": 3.96,
      "learning_rate": 4.17910447761194e-06,
      "loss": 0.3061,
      "step": 530
    },
    {
      "epoch": 4.03,
      "learning_rate": 3.8805970149253735e-06,
      "loss": 0.3153,
      "step": 540
    },
    {
      "epoch": 4.1,
      "learning_rate": 3.582089552238806e-06,
      "loss": 0.2951,
      "step": 550
    },
    {
      "epoch": 4.18,
      "learning_rate": 3.283582089552239e-06,
      "loss": 0.3297,
      "step": 560
    },
    {
      "epoch": 4.25,
      "learning_rate": 2.9850746268656716e-06,
      "loss": 0.339,
      "step": 570
    },
    {
      "epoch": 4.33,
      "learning_rate": 2.686567164179105e-06,
      "loss": 0.3228,
      "step": 580
    },
    {
      "epoch": 4.4,
      "learning_rate": 2.3880597014925373e-06,
      "loss": 0.2971,
      "step": 590
    },
    {
      "epoch": 4.48,
      "learning_rate": 2.08955223880597e-06,
      "loss": 0.3168,
      "step": 600
    },
    {
      "epoch": 4.55,
      "learning_rate": 1.791044776119403e-06,
      "loss": 0.2814,
      "step": 610
    },
    {
      "epoch": 4.63,
      "learning_rate": 1.4925373134328358e-06,
      "loss": 0.276,
      "step": 620
    },
    {
      "epoch": 4.7,
      "learning_rate": 1.1940298507462686e-06,
      "loss": 0.2376,
      "step": 630
    },
    {
      "epoch": 4.78,
      "learning_rate": 8.955223880597015e-07,
      "loss": 0.2764,
      "step": 640
    },
    {
      "epoch": 4.85,
      "learning_rate": 5.970149253731343e-07,
      "loss": 0.2799,
      "step": 650
    },
    {
      "epoch": 4.93,
      "learning_rate": 2.9850746268656716e-07,
      "loss": 0.3265,
      "step": 660
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.4295,
      "step": 670
    },
    {
      "epoch": 5.0,
      "step": 670,
      "total_flos": 1400421165857280.0,
      "train_loss": 0.49670425315401445,
      "train_runtime": 261.2142,
      "train_samples_per_second": 81.504,
      "train_steps_per_second": 2.565
    }
  ],
  "max_steps": 670,
  "num_train_epochs": 5,
  "total_flos": 1400421165857280.0,
  "trial_name": null,
  "trial_params": null
}