{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2675227394328518,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 7.3019086777975994,
      "learning_rate": 5e-06,
      "loss": 0.6939,
      "step": 10
    },
    {
      "epoch": 0.01,
      "grad_norm": 5.150989333266983,
      "learning_rate": 1e-05,
      "loss": 0.7167,
      "step": 20
    },
    {
      "epoch": 0.02,
      "grad_norm": 3.640558809610037,
      "learning_rate": 1.5e-05,
      "loss": 0.5683,
      "step": 30
    },
    {
      "epoch": 0.02,
      "grad_norm": 7.517999397731128,
      "learning_rate": 2e-05,
      "loss": 0.5472,
      "step": 40
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.9687061679463425,
      "learning_rate": 2.5e-05,
      "loss": 0.4439,
      "step": 50
    },
    {
      "epoch": 0.03,
      "grad_norm": 3.643479206523606,
      "learning_rate": 3e-05,
      "loss": 0.2486,
      "step": 60
    },
    {
      "epoch": 0.04,
      "grad_norm": 2.2754773308695095,
      "learning_rate": 3.5e-05,
      "loss": 0.2217,
      "step": 70
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.7144730049127388,
      "learning_rate": 4e-05,
      "loss": 0.169,
      "step": 80
    },
    {
      "epoch": 0.05,
      "grad_norm": 3.4702829704135114,
      "learning_rate": 4.5e-05,
      "loss": 0.1994,
      "step": 90
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.3985127340985621,
      "learning_rate": 5e-05,
      "loss": 0.1612,
      "step": 100
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.375992184386137,
      "learning_rate": 4.982758620689655e-05,
      "loss": 0.1576,
      "step": 110
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.9528635753013313,
      "learning_rate": 4.9655172413793107e-05,
      "loss": 0.1393,
      "step": 120
    },
    {
      "epoch": 0.07,
      "grad_norm": 4.075169010198401,
      "learning_rate": 4.9482758620689655e-05,
      "loss": 0.1969,
      "step": 130
    },
    {
      "epoch": 0.07,
      "grad_norm": 2.0953991165751207,
      "learning_rate": 4.931034482758621e-05,
      "loss": 0.1294,
      "step": 140
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.942660591044849,
      "learning_rate": 4.913793103448276e-05,
      "loss": 0.1306,
      "step": 150
    },
    {
      "epoch": 0.09,
      "grad_norm": 3.1508904015728345,
      "learning_rate": 4.896551724137931e-05,
      "loss": 0.1526,
      "step": 160
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.9862795165358471,
      "learning_rate": 4.8793103448275864e-05,
      "loss": 0.1186,
      "step": 170
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.633061833817991,
      "learning_rate": 4.862068965517241e-05,
      "loss": 0.1457,
      "step": 180
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.8017052368446178,
      "learning_rate": 4.844827586206897e-05,
      "loss": 0.1234,
      "step": 190
    },
    {
      "epoch": 0.11,
      "grad_norm": 2.1560694100709803,
      "learning_rate": 4.827586206896552e-05,
      "loss": 0.1346,
      "step": 200
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.5737689267430703,
      "learning_rate": 4.810344827586207e-05,
      "loss": 0.116,
      "step": 210
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.957864677854788,
      "learning_rate": 4.793103448275863e-05,
      "loss": 0.1692,
      "step": 220
    },
    {
      "epoch": 0.12,
      "grad_norm": 2.215039223521855,
      "learning_rate": 4.7758620689655176e-05,
      "loss": 0.1245,
      "step": 230
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.370517239734168,
      "learning_rate": 4.7586206896551725e-05,
      "loss": 0.1476,
      "step": 240
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.7341334563022532,
      "learning_rate": 4.741379310344828e-05,
      "loss": 0.1236,
      "step": 250
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.5994298113068974,
      "learning_rate": 4.724137931034483e-05,
      "loss": 0.1161,
      "step": 260
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.5317433190951963,
      "learning_rate": 4.7068965517241385e-05,
      "loss": 0.1035,
      "step": 270
    },
    {
      "epoch": 0.15,
      "grad_norm": 2.191977732539556,
      "learning_rate": 4.689655172413793e-05,
      "loss": 0.1427,
      "step": 280
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.6038667570691656,
      "learning_rate": 4.672413793103448e-05,
      "loss": 0.1225,
      "step": 290
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.577572731831179,
      "learning_rate": 4.655172413793104e-05,
      "loss": 0.1399,
      "step": 300
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.6199241001441385,
      "learning_rate": 4.6379310344827586e-05,
      "loss": 0.1242,
      "step": 310
    },
    {
      "epoch": 0.17,
      "grad_norm": 2.236577821186196,
      "learning_rate": 4.6206896551724135e-05,
      "loss": 0.1656,
      "step": 320
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.7294690605254757,
      "learning_rate": 4.603448275862069e-05,
      "loss": 0.1382,
      "step": 330
    },
    {
      "epoch": 0.18,
      "grad_norm": 2.196527516378511,
      "learning_rate": 4.586206896551724e-05,
      "loss": 0.1257,
      "step": 340
    },
    {
      "epoch": 0.19,
      "grad_norm": 2.1057444340221463,
      "learning_rate": 4.5689655172413794e-05,
      "loss": 0.1238,
      "step": 350
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.5409556870328274,
      "learning_rate": 4.551724137931035e-05,
      "loss": 0.1383,
      "step": 360
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.5204083616874053,
      "learning_rate": 4.53448275862069e-05,
      "loss": 0.1068,
      "step": 370
    },
    {
      "epoch": 0.2,
      "grad_norm": 2.3557725298931746,
      "learning_rate": 4.5172413793103454e-05,
      "loss": 0.1071,
      "step": 380
    },
    {
      "epoch": 0.21,
      "grad_norm": 3.2601538460418644,
      "learning_rate": 4.5e-05,
      "loss": 0.125,
      "step": 390
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.9031725385762286,
      "learning_rate": 4.482758620689655e-05,
      "loss": 0.0991,
      "step": 400
    },
    {
      "epoch": 0.22,
      "grad_norm": 1.3946050262183123,
      "learning_rate": 4.465517241379311e-05,
      "loss": 0.1156,
      "step": 410
    },
    {
      "epoch": 0.22,
      "grad_norm": 1.097644875106397,
      "learning_rate": 4.4482758620689656e-05,
      "loss": 0.1366,
      "step": 420
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.37846299019108,
      "learning_rate": 4.431034482758621e-05,
      "loss": 0.126,
      "step": 430
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.8340152889320331,
      "learning_rate": 4.413793103448276e-05,
      "loss": 0.1066,
      "step": 440
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.8304505611337867,
      "learning_rate": 4.396551724137931e-05,
      "loss": 0.0868,
      "step": 450
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.550196490898523,
      "learning_rate": 4.3793103448275864e-05,
      "loss": 0.1286,
      "step": 460
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.176112247796248,
      "learning_rate": 4.362068965517241e-05,
      "loss": 0.1206,
      "step": 470
    },
    {
      "epoch": 0.26,
      "grad_norm": 1.6589263894091213,
      "learning_rate": 4.344827586206897e-05,
      "loss": 0.1008,
      "step": 480
    },
    {
      "epoch": 0.26,
      "grad_norm": 1.8349611508902046,
      "learning_rate": 4.327586206896552e-05,
      "loss": 0.1198,
      "step": 490
    },
    {
      "epoch": 0.27,
      "grad_norm": 2.1218964920724126,
      "learning_rate": 4.3103448275862066e-05,
      "loss": 0.1166,
      "step": 500
    },
    {
      "epoch": 0.27,
      "eval_loss": 0.6078919172286987,
      "eval_runtime": 116.8471,
      "eval_samples_per_second": 11.288,
      "eval_steps_per_second": 2.824,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 3000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 14449508352000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}