{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4984025559105431,
  "eval_steps": 39,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 0.06435385346412659,
      "learning_rate": 1e-05,
      "loss": 0.6574,
      "step": 1
    },
    {
      "epoch": 0.01,
      "eval_loss": 0.7461566925048828,
      "eval_runtime": 151.7973,
      "eval_samples_per_second": 1.482,
      "eval_steps_per_second": 0.376,
      "step": 1
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.062134526669979095,
      "learning_rate": 2e-05,
      "loss": 0.6897,
      "step": 2
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.06962593644857407,
      "learning_rate": 3e-05,
      "loss": 0.6974,
      "step": 3
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.0730314701795578,
      "learning_rate": 4e-05,
      "loss": 0.7454,
      "step": 4
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.07659862190485,
      "learning_rate": 5e-05,
      "loss": 0.6962,
      "step": 5
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.07314729690551758,
      "learning_rate": 6e-05,
      "loss": 0.6602,
      "step": 6
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.0892895832657814,
      "learning_rate": 7e-05,
      "loss": 0.6594,
      "step": 7
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.11520648747682571,
      "learning_rate": 8e-05,
      "loss": 0.7406,
      "step": 8
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.1333557516336441,
      "learning_rate": 9e-05,
      "loss": 0.663,
      "step": 9
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.14017663896083832,
      "learning_rate": 0.0001,
      "loss": 0.6185,
      "step": 10
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.1453818678855896,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.602,
      "step": 11
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.14279265701770782,
      "learning_rate": 0.00012,
      "loss": 0.6151,
      "step": 12
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.11934962123632431,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.5085,
      "step": 13
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.11375121772289276,
      "learning_rate": 0.00014,
      "loss": 0.4823,
      "step": 14
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.09707039594650269,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.4281,
      "step": 15
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.11333765089511871,
      "learning_rate": 0.00016,
      "loss": 0.4417,
      "step": 16
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.09926053136587143,
      "learning_rate": 0.00017,
      "loss": 0.3654,
      "step": 17
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.1027929037809372,
      "learning_rate": 0.00018,
      "loss": 0.3748,
      "step": 18
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.09768980741500854,
      "learning_rate": 0.00019,
      "loss": 0.3306,
      "step": 19
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.08072198927402496,
      "learning_rate": 0.0002,
      "loss": 0.355,
      "step": 20
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.06444709748029709,
      "learning_rate": 0.00019997332081116373,
      "loss": 0.3152,
      "step": 21
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.0576409213244915,
      "learning_rate": 0.00019989329748023725,
      "loss": 0.2674,
      "step": 22
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.08624427020549774,
      "learning_rate": 0.0001997599727063717,
      "loss": 0.2807,
      "step": 23
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.08828990906476974,
      "learning_rate": 0.00019957341762950344,
      "loss": 0.2736,
      "step": 24
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.0641990676522255,
      "learning_rate": 0.00019933373179239502,
      "loss": 0.2427,
      "step": 25
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.05487390235066414,
      "learning_rate": 0.0001990410430875205,
      "loss": 0.2737,
      "step": 26
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.0666637197136879,
      "learning_rate": 0.00019869550768882455,
      "loss": 0.2806,
      "step": 27
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.053027719259262085,
      "learning_rate": 0.0001982973099683902,
      "loss": 0.2664,
      "step": 28
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.055217448621988297,
      "learning_rate": 0.0001978466623980609,
      "loss": 0.309,
      "step": 29
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.05493360385298729,
      "learning_rate": 0.0001973438054360693,
      "loss": 0.2318,
      "step": 30
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.0376153439283371,
      "learning_rate": 0.00019678900739873226,
      "loss": 0.2049,
      "step": 31
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.03811287507414818,
      "learning_rate": 0.00019618256431728194,
      "loss": 0.2771,
      "step": 32
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.04185184836387634,
      "learning_rate": 0.000195524799779908,
      "loss": 0.1843,
      "step": 33
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.04743755981326103,
      "learning_rate": 0.0001948160647590966,
      "loss": 0.2414,
      "step": 34
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.03343382850289345,
      "learning_rate": 0.00019405673742435678,
      "loss": 0.2007,
      "step": 35
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.03178093209862709,
      "learning_rate": 0.00019324722294043558,
      "loss": 0.1898,
      "step": 36
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.03482227399945259,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.2657,
      "step": 37
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.03727172687649727,
      "learning_rate": 0.0001914793868488021,
      "loss": 0.2185,
      "step": 38
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.0382206104695797,
      "learning_rate": 0.00019052200852974819,
      "loss": 0.1778,
      "step": 39
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.2122737020254135,
      "eval_runtime": 154.5774,
      "eval_samples_per_second": 1.456,
      "eval_steps_per_second": 0.369,
      "step": 39
    }
  ],
  "logging_steps": 1,
  "max_steps": 156,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 39,
  "total_flos": 5.128431174313574e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}