{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07635336336565626,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.00019980267284282717,
      "loss": 2.374,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.6044,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001982287250728689,
      "loss": 1.0948,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001968583161128631,
      "loss": 0.835,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.7789,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019297764858882514,
      "loss": 0.7047,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019048270524660196,
      "loss": 0.7014,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.6807,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018443279255020152,
      "loss": 0.6856,
      "step": 90
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.6469,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00017705132427757895,
      "loss": 0.6406,
      "step": 110
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00017289686274214118,
      "loss": 0.6724,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016845471059286887,
      "loss": 0.6708,
      "step": 130
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000163742398974869,
      "loss": 0.6362,
      "step": 140
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.6356,
      "step": 150
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015358267949789966,
      "loss": 0.6422,
      "step": 160
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00014817536741017152,
      "loss": 0.6414,
      "step": 170
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00014257792915650728,
      "loss": 0.5947,
      "step": 180
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013681245526846783,
      "loss": 0.6238,
      "step": 190
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6221,
      "step": 200
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001248689887164855,
      "loss": 0.6059,
      "step": 210
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011873813145857249,
      "loss": 0.6132,
      "step": 220
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00011253332335643043,
      "loss": 0.6079,
      "step": 230
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00010627905195293135,
      "loss": 0.6215,
      "step": 240
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 0.5999,
      "step": 250
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.6346,
      "step": 260
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.746667664356956e-05,
      "loss": 0.6305,
      "step": 270
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.126186854142752e-05,
      "loss": 0.613,
      "step": 280
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.513101128351454e-05,
      "loss": 0.5864,
      "step": 290
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.6088,
      "step": 300
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.318754473153221e-05,
      "loss": 0.5992,
      "step": 310
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.6092,
      "step": 320
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.182463258982846e-05,
      "loss": 0.6022,
      "step": 330
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.6417320502100316e-05,
      "loss": 0.5862,
      "step": 340
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.5768,
      "step": 350
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.6257601025131026e-05,
      "loss": 0.5986,
      "step": 360
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.154528940713113e-05,
      "loss": 0.6203,
      "step": 370
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.5693,
      "step": 380
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.2948675722421086e-05,
      "loss": 0.5848,
      "step": 390
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.5812,
      "step": 400
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.5567207449798515e-05,
      "loss": 0.597,
      "step": 410
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.2369331995613665e-05,
      "loss": 0.5703,
      "step": 420
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.517294753398064e-06,
      "loss": 0.561,
      "step": 430
    },
    {
      "epoch": 0.07,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.5867,
      "step": 440
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.5813,
      "step": 450
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.1416838871368924e-06,
      "loss": 0.5883,
      "step": 460
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.771274927131139e-06,
      "loss": 0.6026,
      "step": 470
    },
    {
      "epoch": 0.07,
      "learning_rate": 7.885298685522235e-07,
      "loss": 0.5676,
      "step": 480
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.973271571728441e-07,
      "loss": 0.6015,
      "step": 490
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0,
      "loss": 0.5788,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 5718428677840896.0,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}