{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 2994,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 0.00019989878688605225,
      "loss": 1.6802,
      "step": 50
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019959535242609772,
      "loss": 1.5884,
      "step": 100
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001990903108510678,
      "loss": 1.5617,
      "step": 150
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019838468449757217,
      "loss": 1.5139,
      "step": 200
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019747990173842118,
      "loss": 1.5259,
      "step": 250
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019637779409122493,
      "loss": 1.4783,
      "step": 300
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019508059251092087,
      "loss": 1.5202,
      "step": 350
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001935909228737363,
      "loss": 1.7727,
      "step": 400
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00019191180066172584,
      "loss": 1.8033,
      "step": 450
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00019004662485864503,
      "loss": 1.7674,
      "step": 500
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00018799917106951565,
      "loss": 1.3627,
      "step": 550
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00018577358387781095,
      "loss": 1.3747,
      "step": 600
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001833743684557316,
      "loss": 1.3806,
      "step": 650
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00018080638144455567,
      "loss": 1.3878,
      "step": 700
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00017807482112352263,
      "loss": 1.3824,
      "step": 750
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001751852168871531,
      "loss": 1.4058,
      "step": 800
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00017214341805230388,
      "loss": 1.4329,
      "step": 850
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001689555820176165,
      "loss": 1.4325,
      "step": 900
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00016562816179932748,
      "loss": 1.4175,
      "step": 950
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001621678929686709,
      "loss": 1.4092,
      "step": 1000
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00015858178001731577,
      "loss": 0.969,
      "step": 1050
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00015487708217843755,
      "loss": 0.9795,
      "step": 1100
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0001510612987321264,
      "loss": 0.991,
      "step": 1150
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00014714215382487735,
      "loss": 1.0001,
      "step": 1200
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00014312758083389192,
      "loss": 1.0092,
      "step": 1250
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00013902570630784184,
      "loss": 1.0274,
      "step": 1300
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.00013484483351660324,
      "loss": 1.0369,
      "step": 1350
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.00013059342564326052,
      "loss": 1.043,
      "step": 1400
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.00012628008865240412,
      "loss": 1.0355,
      "step": 1450
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.00012191355386940109,
      "loss": 1.0137,
      "step": 1500
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0001175912552720942,
      "loss": 0.5538,
      "step": 1550
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.00011314555233691659,
      "loss": 0.5644,
      "step": 1600
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.00010867323935600735,
      "loss": 0.5862,
      "step": 1650
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.00010418336946383338,
      "loss": 0.595,
      "step": 1700
    },
    {
      "epoch": 3.51,
      "learning_rate": 9.968503133465485e-05,
      "loss": 0.5974,
      "step": 1750
    },
    {
      "epoch": 3.61,
      "learning_rate": 9.518733078466463e-05,
      "loss": 0.5951,
      "step": 1800
    },
    {
      "epoch": 3.71,
      "learning_rate": 9.069937233942807e-05,
      "loss": 0.5998,
      "step": 1850
    },
    {
      "epoch": 3.81,
      "learning_rate": 8.623024080393546e-05,
      "loss": 0.5986,
      "step": 1900
    },
    {
      "epoch": 3.91,
      "learning_rate": 8.178898287257368e-05,
      "loss": 0.5888,
      "step": 1950
    },
    {
      "epoch": 4.01,
      "learning_rate": 7.738458881624441e-05,
      "loss": 0.576,
      "step": 2000
    },
    {
      "epoch": 4.11,
      "learning_rate": 7.302597428369742e-05,
      "loss": 0.271,
      "step": 2050
    },
    {
      "epoch": 4.21,
      "learning_rate": 6.872196225391955e-05,
      "loss": 0.2735,
      "step": 2100
    },
    {
      "epoch": 4.31,
      "learning_rate": 6.448126517611075e-05,
      "loss": 0.2818,
      "step": 2150
    },
    {
      "epoch": 4.41,
      "learning_rate": 6.031246733340219e-05,
      "loss": 0.2814,
      "step": 2200
    },
    {
      "epoch": 4.51,
      "learning_rate": 5.6224007466015405e-05,
      "loss": 0.277,
      "step": 2250
    },
    {
      "epoch": 4.61,
      "learning_rate": 5.2224161689038975e-05,
      "loss": 0.275,
      "step": 2300
    },
    {
      "epoch": 4.71,
      "learning_rate": 4.8321026739400875e-05,
      "loss": 0.2763,
      "step": 2350
    },
    {
      "epoch": 4.81,
      "learning_rate": 4.4522503585949327e-05,
      "loss": 0.2766,
      "step": 2400
    },
    {
      "epoch": 4.91,
      "learning_rate": 4.083628143581959e-05,
      "loss": 0.2775,
      "step": 2450
    },
    {
      "epoch": 5.01,
      "learning_rate": 3.726982216946203e-05,
      "loss": 0.264,
      "step": 2500
    },
    {
      "epoch": 5.11,
      "learning_rate": 3.383034523583898e-05,
      "loss": 0.1316,
      "step": 2550
    },
    {
      "epoch": 5.21,
      "learning_rate": 3.052481303836647e-05,
      "loss": 0.1326,
      "step": 2600
    },
    {
      "epoch": 5.31,
      "learning_rate": 2.7359916841183754e-05,
      "loss": 0.1349,
      "step": 2650
    },
    {
      "epoch": 5.41,
      "learning_rate": 2.4342063224279566e-05,
      "loss": 0.1344,
      "step": 2700
    },
    {
      "epoch": 5.51,
      "learning_rate": 2.1477361114894035e-05,
      "loss": 0.1326,
      "step": 2750
    },
    {
      "epoch": 5.61,
      "learning_rate": 1.8771609421447622e-05,
      "loss": 0.1278,
      "step": 2800
    },
    {
      "epoch": 5.71,
      "learning_rate": 1.6230285295029556e-05,
      "loss": 0.129,
      "step": 2850
    },
    {
      "epoch": 5.81,
      "learning_rate": 1.3858533042207633e-05,
      "loss": 0.1282,
      "step": 2900
    },
    {
      "epoch": 5.91,
      "learning_rate": 1.166115371160218e-05,
      "loss": 0.1285,
      "step": 2950
    }
  ],
  "logging_steps": 50,
  "max_steps": 3491,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 2.316912930642985e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}