{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5435801312089972,
  "eval_steps": 500,
  "global_step": 290,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 3.7037037037037036e-07,
      "loss": 1.7019,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 1.5901,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 1.3226,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.555555555555557e-06,
      "loss": 1.1733,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 1.0978,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.25925925925926e-06,
      "loss": 1.0591,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 1.0304,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.2962962962962964e-05,
      "loss": 1.0116,
      "step": 35
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.9904,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.9896,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.851851851851852e-05,
      "loss": 0.9806,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.999978492141723e-05,
      "loss": 0.9673,
      "step": 55
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9992258142410335e-05,
      "loss": 0.9732,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.997398668423542e-05,
      "loss": 0.9526,
      "step": 65
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9944990194198758e-05,
      "loss": 0.9571,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9905299852237654e-05,
      "loss": 0.9498,
      "step": 75
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9854958337392654e-05,
      "loss": 0.959,
      "step": 80
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9794019781914764e-05,
      "loss": 0.9538,
      "step": 85
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9722549713057008e-05,
      "loss": 0.9449,
      "step": 90
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9640624982612943e-05,
      "loss": 0.9497,
      "step": 95
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.954833368427792e-05,
      "loss": 0.9595,
      "step": 100
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9445775058921856e-05,
      "loss": 0.9563,
      "step": 105
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9333059387875527e-05,
      "loss": 0.9415,
      "step": 110
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.921030787434499e-05,
      "loss": 0.9432,
      "step": 115
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.907765251308173e-05,
      "loss": 0.9484,
      "step": 120
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.8935235948448653e-05,
      "loss": 0.939,
      "step": 125
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8783211321034537e-05,
      "loss": 0.9326,
      "step": 130
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.8621742102981906e-05,
      "loss": 0.9485,
      "step": 135
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.845100192220537e-05,
      "loss": 0.9401,
      "step": 140
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.8271174375689454e-05,
      "loss": 0.9415,
      "step": 145
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.808245283206669e-05,
      "loss": 0.9439,
      "step": 150
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.7885040223688234e-05,
      "loss": 0.9423,
      "step": 155
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.767914882841067e-05,
      "loss": 0.9422,
      "step": 160
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.7465000041333496e-05,
      "loss": 0.933,
      "step": 165
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.724282413673291e-05,
      "loss": 0.9288,
      "step": 170
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.7012860020447797e-05,
      "loss": 0.937,
      "step": 175
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.677535497298416e-05,
      "loss": 0.9411,
      "step": 180
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.653056438361432e-05,
      "loss": 0.9327,
      "step": 185
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.6278751475756712e-05,
      "loss": 0.934,
      "step": 190
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.602018702393164e-05,
      "loss": 0.9242,
      "step": 195
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.5755149062597332e-05,
      "loss": 0.9264,
      "step": 200
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.5483922587179386e-05,
      "loss": 0.9343,
      "step": 205
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.5206799247615038e-05,
      "loss": 0.9194,
      "step": 210
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.4924077034741924e-05,
      "loss": 0.9306,
      "step": 215
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.4636059959868363e-05,
      "loss": 0.918,
      "step": 220
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.43430577278699e-05,
      "loss": 0.9193,
      "step": 225
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.4045385404163533e-05,
      "loss": 0.9259,
      "step": 230
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.3743363075917723e-05,
      "loss": 0.9247,
      "step": 235
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.3437315507862568e-05,
      "loss": 0.9267,
      "step": 240
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.312757179307012e-05,
      "loss": 0.9193,
      "step": 245
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.28144649990805e-05,
      "loss": 0.9263,
      "step": 250
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.2498331809754243e-05,
      "loss": 0.9172,
      "step": 255
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.2179512163235973e-05,
      "loss": 0.9223,
      "step": 260
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.1858348886418832e-05,
      "loss": 0.9196,
      "step": 265
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.153518732630253e-05,
      "loss": 0.9218,
      "step": 270
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.121037497864163e-05,
      "loss": 0.9213,
      "step": 275
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.088426111428319e-05,
      "loss": 0.9078,
      "step": 280
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.0557196403595689e-05,
      "loss": 0.9135,
      "step": 285
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.0229532539393051e-05,
      "loss": 0.9051,
      "step": 290
    },
    {
      "epoch": 0.54,
      "eval_loss": 0.8942756056785583,
      "eval_runtime": 214.7071,
      "eval_samples_per_second": 171.531,
      "eval_steps_per_second": 0.671,
      "step": 290
    },
    {
      "epoch": 0.54,
      "step": 290,
      "total_flos": 485917835919360.0,
      "train_loss": 0.9702501186009111,
      "train_runtime": 6614.4701,
      "train_samples_per_second": 41.278,
      "train_steps_per_second": 0.081
    }
  ],
  "logging_steps": 5,
  "max_steps": 533,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 485917835919360.0,
  "trial_name": null,
  "trial_params": null
}