{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.114571746384872,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 5e-05,
      "loss": 3.0439,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 3.1296,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00015000000000000001,
      "loss": 2.6415,
      "step": 30
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 2.2394,
      "step": 40
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001999145758387301,
      "loss": 2.1922,
      "step": 50
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000199658449300667,
      "loss": 2.1356,
      "step": 60
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001992320579737045,
      "loss": 2.1113,
      "step": 70
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019863613034027224,
      "loss": 2.0595,
      "step": 80
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019787168453273544,
      "loss": 2.176,
      "step": 90
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019694002659393305,
      "loss": 1.9658,
      "step": 100
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001958427482458253,
      "loss": 2.054,
      "step": 110
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019458172417006347,
      "loss": 1.9974,
      "step": 120
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001931591088051279,
      "loss": 2.08,
      "step": 130
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019157733266550575,
      "loss": 2.0511,
      "step": 140
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001898390981891979,
      "loss": 2.0537,
      "step": 150
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001879473751206489,
      "loss": 2.0272,
      "step": 160
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00018590539543698854,
      "loss": 1.814,
      "step": 170
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00018371664782625287,
      "loss": 1.9998,
      "step": 180
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001813848717270195,
      "loss": 2.0532,
      "step": 190
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00017891405093963938,
      "loss": 1.9846,
      "step": 200
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00017630840681998066,
      "loss": 2.0036,
      "step": 210
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00017357239106731317,
      "loss": 1.9404,
      "step": 220
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.0365,
      "step": 230
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00016772815716257412,
      "loss": 1.899,
      "step": 240
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00016462992378609407,
      "loss": 1.8882,
      "step": 250
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001614212712689668,
      "loss": 1.8806,
      "step": 260
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00015810768154019385,
      "loss": 1.8318,
      "step": 270
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00015469481581224272,
      "loss": 1.8892,
      "step": 280
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00015118850490896012,
      "loss": 1.8362,
      "step": 290
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00014759473930370736,
      "loss": 1.9268,
      "step": 300
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00014391965888473703,
      "loss": 1.8581,
      "step": 310
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00014016954246529696,
      "loss": 1.928,
      "step": 320
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00013635079705638298,
      "loss": 1.8851,
      "step": 330
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00013246994692046836,
      "loss": 1.8826,
      "step": 340
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00012853362242491053,
      "loss": 1.9504,
      "step": 350
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00012454854871407994,
      "loss": 1.93,
      "step": 360
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00012052153421956342,
      "loss": 1.8744,
      "step": 370
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00011645945902807341,
      "loss": 1.9418,
      "step": 380
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00011236926312693479,
      "loss": 1.9751,
      "step": 390
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00010825793454723325,
      "loss": 1.7895,
      "step": 400
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00010413249742488131,
      "loss": 2.0188,
      "step": 410
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0001,
      "loss": 1.9481,
      "step": 420
    },
    {
      "epoch": 1.91,
      "learning_rate": 9.586750257511867e-05,
      "loss": 1.9162,
      "step": 430
    },
    {
      "epoch": 1.96,
      "learning_rate": 9.174206545276677e-05,
      "loss": 1.8781,
      "step": 440
    },
    {
      "epoch": 2.0,
      "learning_rate": 8.763073687306524e-05,
      "loss": 1.8272,
      "step": 450
    },
    {
      "epoch": 2.05,
      "learning_rate": 8.35405409719266e-05,
      "loss": 1.7678,
      "step": 460
    },
    {
      "epoch": 2.09,
      "learning_rate": 7.947846578043659e-05,
      "loss": 1.7603,
      "step": 470
    },
    {
      "epoch": 2.14,
      "learning_rate": 7.54514512859201e-05,
      "loss": 1.812,
      "step": 480
    },
    {
      "epoch": 2.18,
      "learning_rate": 7.146637757508949e-05,
      "loss": 1.7061,
      "step": 490
    },
    {
      "epoch": 2.22,
      "learning_rate": 6.753005307953167e-05,
      "loss": 1.749,
      "step": 500
    },
    {
      "epoch": 2.27,
      "learning_rate": 6.3649202943617e-05,
      "loss": 1.8795,
      "step": 510
    },
    {
      "epoch": 2.31,
      "learning_rate": 5.983045753470308e-05,
      "loss": 1.7342,
      "step": 520
    },
    {
      "epoch": 2.36,
      "learning_rate": 5.608034111526298e-05,
      "loss": 1.8323,
      "step": 530
    },
    {
      "epoch": 2.4,
      "learning_rate": 5.240526069629265e-05,
      "loss": 1.7113,
      "step": 540
    },
    {
      "epoch": 2.45,
      "learning_rate": 4.8811495091039926e-05,
      "loss": 1.6987,
      "step": 550
    },
    {
      "epoch": 2.49,
      "learning_rate": 4.530518418775733e-05,
      "loss": 1.7021,
      "step": 560
    },
    {
      "epoch": 2.54,
      "learning_rate": 4.189231845980618e-05,
      "loss": 1.7919,
      "step": 570
    },
    {
      "epoch": 2.58,
      "learning_rate": 3.857872873103322e-05,
      "loss": 1.8427,
      "step": 580
    },
    {
      "epoch": 2.63,
      "learning_rate": 3.53700762139059e-05,
      "loss": 1.7832,
      "step": 590
    },
    {
      "epoch": 2.67,
      "learning_rate": 3.227184283742591e-05,
      "loss": 1.5746,
      "step": 600
    },
    {
      "epoch": 2.71,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 1.7318,
      "step": 610
    },
    {
      "epoch": 2.76,
      "learning_rate": 2.6427608932686843e-05,
      "loss": 1.7361,
      "step": 620
    },
    {
      "epoch": 2.8,
      "learning_rate": 2.3691593180019366e-05,
      "loss": 1.7565,
      "step": 630
    },
    {
      "epoch": 2.85,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 1.6935,
      "step": 640
    },
    {
      "epoch": 2.89,
      "learning_rate": 1.861512827298051e-05,
      "loss": 1.6684,
      "step": 650
    },
    {
      "epoch": 2.94,
      "learning_rate": 1.6283352173747145e-05,
      "loss": 1.665,
      "step": 660
    },
    {
      "epoch": 2.98,
      "learning_rate": 1.4094604563011472e-05,
      "loss": 1.7024,
      "step": 670
    },
    {
      "epoch": 3.03,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 1.6249,
      "step": 680
    },
    {
      "epoch": 3.07,
      "learning_rate": 1.0160901810802115e-05,
      "loss": 1.6777,
      "step": 690
    },
    {
      "epoch": 3.11,
      "learning_rate": 8.422667334494249e-06,
      "loss": 1.7344,
      "step": 700
    }
  ],
  "max_steps": 800,
  "num_train_epochs": 4,
  "total_flos": 2.2824821692897536e+16,
  "trial_name": null,
  "trial_params": null
}