{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 3000,
  "global_step": 556,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.00019640287769784174,
      "loss": 2.1468,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019280575539568347,
      "loss": 1.9709,
      "step": 20
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00018920863309352518,
      "loss": 1.8468,
      "step": 30
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001856115107913669,
      "loss": 1.6942,
      "step": 40
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018201438848920864,
      "loss": 1.4989,
      "step": 50
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00017841726618705037,
      "loss": 1.3514,
      "step": 60
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001748201438848921,
      "loss": 1.3165,
      "step": 70
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017122302158273383,
      "loss": 1.2268,
      "step": 80
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016762589928057554,
      "loss": 1.3164,
      "step": 90
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016402877697841727,
      "loss": 1.3179,
      "step": 100
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000160431654676259,
      "loss": 1.2648,
      "step": 110
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00015683453237410073,
      "loss": 1.178,
      "step": 120
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00015323741007194246,
      "loss": 1.1558,
      "step": 130
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001496402877697842,
      "loss": 1.0114,
      "step": 140
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001460431654676259,
      "loss": 0.8844,
      "step": 150
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00014244604316546763,
      "loss": 0.9118,
      "step": 160
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00013884892086330936,
      "loss": 1.0269,
      "step": 170
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001352517985611511,
      "loss": 0.9542,
      "step": 180
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00013165467625899283,
      "loss": 0.8281,
      "step": 190
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00012805755395683453,
      "loss": 0.8024,
      "step": 200
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00012446043165467626,
      "loss": 0.8185,
      "step": 210
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00012086330935251799,
      "loss": 1.099,
      "step": 220
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00011726618705035972,
      "loss": 0.8726,
      "step": 230
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00011366906474820144,
      "loss": 0.7907,
      "step": 240
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00011007194244604317,
      "loss": 0.9099,
      "step": 250
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001064748201438849,
      "loss": 0.7301,
      "step": 260
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00010287769784172662,
      "loss": 0.772,
      "step": 270
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.928057553956835e-05,
      "loss": 0.7936,
      "step": 280
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.568345323741009e-05,
      "loss": 0.6623,
      "step": 290
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.20863309352518e-05,
      "loss": 0.5091,
      "step": 300
    },
    {
      "epoch": 1.12,
      "learning_rate": 8.848920863309353e-05,
      "loss": 0.4996,
      "step": 310
    },
    {
      "epoch": 1.15,
      "learning_rate": 8.489208633093527e-05,
      "loss": 0.5529,
      "step": 320
    },
    {
      "epoch": 1.19,
      "learning_rate": 8.129496402877698e-05,
      "loss": 0.6094,
      "step": 330
    },
    {
      "epoch": 1.22,
      "learning_rate": 7.769784172661872e-05,
      "loss": 0.4422,
      "step": 340
    },
    {
      "epoch": 1.26,
      "learning_rate": 7.410071942446043e-05,
      "loss": 0.4468,
      "step": 350
    },
    {
      "epoch": 1.29,
      "learning_rate": 7.050359712230215e-05,
      "loss": 0.4673,
      "step": 360
    },
    {
      "epoch": 1.33,
      "learning_rate": 6.690647482014388e-05,
      "loss": 0.4746,
      "step": 370
    },
    {
      "epoch": 1.37,
      "learning_rate": 6.366906474820145e-05,
      "loss": 0.4601,
      "step": 380
    },
    {
      "epoch": 1.4,
      "learning_rate": 6.007194244604317e-05,
      "loss": 0.4793,
      "step": 390
    },
    {
      "epoch": 1.44,
      "learning_rate": 5.64748201438849e-05,
      "loss": 0.5919,
      "step": 400
    },
    {
      "epoch": 1.47,
      "learning_rate": 5.287769784172663e-05,
      "loss": 0.4313,
      "step": 410
    },
    {
      "epoch": 1.51,
      "learning_rate": 4.9280575539568345e-05,
      "loss": 0.4715,
      "step": 420
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.5683453237410076e-05,
      "loss": 0.3263,
      "step": 430
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.20863309352518e-05,
      "loss": 0.4526,
      "step": 440
    },
    {
      "epoch": 1.62,
      "learning_rate": 3.8489208633093525e-05,
      "loss": 0.4379,
      "step": 450
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.489208633093525e-05,
      "loss": 0.5083,
      "step": 460
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.129496402877698e-05,
      "loss": 0.5373,
      "step": 470
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.7697841726618706e-05,
      "loss": 0.3303,
      "step": 480
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.4100719424460434e-05,
      "loss": 0.3214,
      "step": 490
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.050359712230216e-05,
      "loss": 0.4343,
      "step": 500
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.6906474820143887e-05,
      "loss": 0.314,
      "step": 510
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.3309352517985613e-05,
      "loss": 0.3727,
      "step": 520
    },
    {
      "epoch": 1.91,
      "learning_rate": 9.71223021582734e-06,
      "loss": 0.2798,
      "step": 530
    },
    {
      "epoch": 1.94,
      "learning_rate": 6.115107913669065e-06,
      "loss": 0.4031,
      "step": 540
    },
    {
      "epoch": 1.98,
      "learning_rate": 2.5179856115107916e-06,
      "loss": 0.3542,
      "step": 550
    },
    {
      "epoch": 2.0,
      "step": 556,
      "total_flos": 6.887981879958897e+17,
      "train_loss": 0.8073481788738168,
      "train_runtime": 211.1785,
      "train_samples_per_second": 42.088,
      "train_steps_per_second": 2.633
    }
  ],
  "logging_steps": 10,
  "max_steps": 556,
  "num_train_epochs": 2,
  "save_steps": 3000,
  "total_flos": 6.887981879958897e+17,
  "trial_name": null,
  "trial_params": null
}