{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.569593147751606,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 9.856938483547926e-05,
      "loss": 3.6649,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.713876967095852e-05,
      "loss": 2.813,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.570815450643778e-05,
      "loss": 2.7133,
      "step": 30
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.427753934191703e-05,
      "loss": 2.3768,
      "step": 40
    },
    {
      "epoch": 0.21,
      "learning_rate": 9.284692417739628e-05,
      "loss": 2.3128,
      "step": 50
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.141630901287554e-05,
      "loss": 2.2792,
      "step": 60
    },
    {
      "epoch": 0.3,
      "learning_rate": 8.99856938483548e-05,
      "loss": 2.2207,
      "step": 70
    },
    {
      "epoch": 0.34,
      "learning_rate": 8.855507868383405e-05,
      "loss": 2.2776,
      "step": 80
    },
    {
      "epoch": 0.39,
      "learning_rate": 8.71244635193133e-05,
      "loss": 2.3522,
      "step": 90
    },
    {
      "epoch": 0.43,
      "learning_rate": 8.569384835479256e-05,
      "loss": 2.201,
      "step": 100
    },
    {
      "epoch": 0.47,
      "learning_rate": 8.426323319027182e-05,
      "loss": 2.2058,
      "step": 110
    },
    {
      "epoch": 0.51,
      "learning_rate": 8.283261802575107e-05,
      "loss": 2.2312,
      "step": 120
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.140200286123033e-05,
      "loss": 2.2807,
      "step": 130
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.997138769670959e-05,
      "loss": 2.339,
      "step": 140
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.854077253218884e-05,
      "loss": 2.1615,
      "step": 150
    },
    {
      "epoch": 0.69,
      "learning_rate": 7.71101573676681e-05,
      "loss": 2.1912,
      "step": 160
    },
    {
      "epoch": 0.73,
      "learning_rate": 7.567954220314736e-05,
      "loss": 2.1207,
      "step": 170
    },
    {
      "epoch": 0.77,
      "learning_rate": 7.424892703862662e-05,
      "loss": 2.2326,
      "step": 180
    },
    {
      "epoch": 0.81,
      "learning_rate": 7.281831187410587e-05,
      "loss": 2.2286,
      "step": 190
    },
    {
      "epoch": 0.86,
      "learning_rate": 7.138769670958512e-05,
      "loss": 2.03,
      "step": 200
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.995708154506438e-05,
      "loss": 2.2001,
      "step": 210
    },
    {
      "epoch": 0.94,
      "learning_rate": 6.852646638054364e-05,
      "loss": 2.2102,
      "step": 220
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.70958512160229e-05,
      "loss": 2.1974,
      "step": 230
    },
    {
      "epoch": 1.03,
      "learning_rate": 6.566523605150215e-05,
      "loss": 2.046,
      "step": 240
    },
    {
      "epoch": 1.07,
      "learning_rate": 6.42346208869814e-05,
      "loss": 1.9384,
      "step": 250
    },
    {
      "epoch": 1.11,
      "learning_rate": 6.280400572246066e-05,
      "loss": 2.1286,
      "step": 260
    },
    {
      "epoch": 1.16,
      "learning_rate": 6.137339055793991e-05,
      "loss": 2.0289,
      "step": 270
    },
    {
      "epoch": 1.2,
      "learning_rate": 5.9942775393419173e-05,
      "loss": 2.0393,
      "step": 280
    },
    {
      "epoch": 1.24,
      "learning_rate": 5.8512160228898425e-05,
      "loss": 2.0035,
      "step": 290
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.7081545064377684e-05,
      "loss": 2.0714,
      "step": 300
    },
    {
      "epoch": 1.33,
      "learning_rate": 5.565092989985694e-05,
      "loss": 2.0226,
      "step": 310
    },
    {
      "epoch": 1.37,
      "learning_rate": 5.4220314735336195e-05,
      "loss": 2.0695,
      "step": 320
    },
    {
      "epoch": 1.41,
      "learning_rate": 5.278969957081545e-05,
      "loss": 1.989,
      "step": 330
    },
    {
      "epoch": 1.46,
      "learning_rate": 5.135908440629471e-05,
      "loss": 2.0688,
      "step": 340
    },
    {
      "epoch": 1.5,
      "learning_rate": 4.992846924177397e-05,
      "loss": 1.8838,
      "step": 350
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.8497854077253216e-05,
      "loss": 2.0109,
      "step": 360
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.7067238912732475e-05,
      "loss": 2.0371,
      "step": 370
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.563662374821173e-05,
      "loss": 2.0012,
      "step": 380
    },
    {
      "epoch": 1.67,
      "learning_rate": 4.420600858369099e-05,
      "loss": 2.0461,
      "step": 390
    },
    {
      "epoch": 1.71,
      "learning_rate": 4.2775393419170244e-05,
      "loss": 1.9601,
      "step": 400
    },
    {
      "epoch": 1.76,
      "learning_rate": 4.13447782546495e-05,
      "loss": 1.9282,
      "step": 410
    },
    {
      "epoch": 1.8,
      "learning_rate": 3.991416309012876e-05,
      "loss": 2.0841,
      "step": 420
    },
    {
      "epoch": 1.84,
      "learning_rate": 3.848354792560801e-05,
      "loss": 2.0851,
      "step": 430
    },
    {
      "epoch": 1.88,
      "learning_rate": 3.7052932761087265e-05,
      "loss": 2.039,
      "step": 440
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.5622317596566524e-05,
      "loss": 1.9102,
      "step": 450
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.419170243204578e-05,
      "loss": 2.0091,
      "step": 460
    },
    {
      "epoch": 2.01,
      "learning_rate": 3.2761087267525034e-05,
      "loss": 2.0263,
      "step": 470
    },
    {
      "epoch": 2.06,
      "learning_rate": 3.133047210300429e-05,
      "loss": 1.7926,
      "step": 480
    },
    {
      "epoch": 2.1,
      "learning_rate": 2.9899856938483552e-05,
      "loss": 1.8643,
      "step": 490
    },
    {
      "epoch": 2.14,
      "learning_rate": 2.8469241773962807e-05,
      "loss": 1.7537,
      "step": 500
    },
    {
      "epoch": 2.18,
      "learning_rate": 2.7038626609442062e-05,
      "loss": 1.8578,
      "step": 510
    },
    {
      "epoch": 2.23,
      "learning_rate": 2.5608011444921314e-05,
      "loss": 1.7847,
      "step": 520
    },
    {
      "epoch": 2.27,
      "learning_rate": 2.4177396280400573e-05,
      "loss": 1.7704,
      "step": 530
    },
    {
      "epoch": 2.31,
      "learning_rate": 2.2746781115879828e-05,
      "loss": 1.864,
      "step": 540
    },
    {
      "epoch": 2.36,
      "learning_rate": 2.1316165951359084e-05,
      "loss": 1.7659,
      "step": 550
    },
    {
      "epoch": 2.4,
      "learning_rate": 1.9885550786838342e-05,
      "loss": 1.6955,
      "step": 560
    },
    {
      "epoch": 2.44,
      "learning_rate": 1.8454935622317597e-05,
      "loss": 1.7299,
      "step": 570
    },
    {
      "epoch": 2.48,
      "learning_rate": 1.7024320457796853e-05,
      "loss": 1.7581,
      "step": 580
    },
    {
      "epoch": 2.53,
      "learning_rate": 1.5593705293276108e-05,
      "loss": 1.8381,
      "step": 590
    },
    {
      "epoch": 2.57,
      "learning_rate": 1.4163090128755365e-05,
      "loss": 1.731,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 699,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 3.739811903756698e+16,
  "trial_name": null,
  "trial_params": null
}