{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25103830179972314,
  "eval_steps": 500,
  "global_step": 34,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007383479464697739,
      "grad_norm": 1.9591929912567139,
      "learning_rate": 0.0,
      "loss": 1.6228,
      "memory/device_mem_reserved(gib)": 21.61,
      "memory/max_mem_active(gib)": 21.2,
      "memory/max_mem_allocated(gib)": 21.2,
      "step": 1
    },
    {
      "epoch": 0.014766958929395477,
      "grad_norm": 1.4523507356643677,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.5769,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 2
    },
    {
      "epoch": 0.022150438394093218,
      "grad_norm": 1.1918187141418457,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 1.5435,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 3
    },
    {
      "epoch": 0.029533917858790955,
      "grad_norm": 0.8260876536369324,
      "learning_rate": 4.615384615384616e-05,
      "loss": 1.6523,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 4
    },
    {
      "epoch": 0.03691739732348869,
      "grad_norm": 0.8584926128387451,
      "learning_rate": 6.153846153846155e-05,
      "loss": 1.5745,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 5
    },
    {
      "epoch": 0.044300876788186436,
      "grad_norm": 0.6466429829597473,
      "learning_rate": 7.692307692307693e-05,
      "loss": 1.4759,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 6
    },
    {
      "epoch": 0.05168435625288417,
      "grad_norm": 0.5014482140541077,
      "learning_rate": 9.230769230769232e-05,
      "loss": 1.602,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 7
    },
    {
      "epoch": 0.05906783571758191,
      "grad_norm": 0.6017433404922485,
      "learning_rate": 0.0001076923076923077,
      "loss": 1.4176,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 8
    },
    {
      "epoch": 0.06645131518227965,
      "grad_norm": 0.4612258970737457,
      "learning_rate": 0.0001230769230769231,
      "loss": 1.5819,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 9
    },
    {
      "epoch": 0.07383479464697738,
      "grad_norm": 0.4430214464664459,
      "learning_rate": 0.00013846153846153847,
      "loss": 1.561,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 10
    },
    {
      "epoch": 0.08121827411167512,
      "grad_norm": 0.3746771216392517,
      "learning_rate": 0.00015384615384615385,
      "loss": 1.6744,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 11
    },
    {
      "epoch": 0.08860175357637287,
      "grad_norm": 0.38248857855796814,
      "learning_rate": 0.00016923076923076923,
      "loss": 1.5629,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 12
    },
    {
      "epoch": 0.09598523304107061,
      "grad_norm": 0.515844464302063,
      "learning_rate": 0.00018461538461538463,
      "loss": 1.5264,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 13
    },
    {
      "epoch": 0.10336871250576835,
      "grad_norm": 0.3964424431324005,
      "learning_rate": 0.0002,
      "loss": 1.5398,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 14
    },
    {
      "epoch": 0.11075219197046608,
      "grad_norm": 0.4010593891143799,
      "learning_rate": 0.0001999668467514313,
      "loss": 1.4618,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 15
    },
    {
      "epoch": 0.11813567143516382,
      "grad_norm": 0.3192802965641022,
      "learning_rate": 0.00019986740898848306,
      "loss": 1.6994,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 16
    },
    {
      "epoch": 0.12551915089986157,
      "grad_norm": 0.410099059343338,
      "learning_rate": 0.00019970175264485266,
      "loss": 1.5913,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 17
    },
    {
      "epoch": 0.1329026303645593,
      "grad_norm": 0.312429815530777,
      "learning_rate": 0.0001994699875614589,
      "loss": 1.5701,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 18
    },
    {
      "epoch": 0.14028610982925704,
      "grad_norm": 0.2831230163574219,
      "learning_rate": 0.00019917226741361015,
      "loss": 1.5744,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 19
    },
    {
      "epoch": 0.14766958929395477,
      "grad_norm": 0.3618868291378021,
      "learning_rate": 0.00019880878960910772,
      "loss": 1.5185,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 20
    },
    {
      "epoch": 0.15505306875865252,
      "grad_norm": 0.3151628077030182,
      "learning_rate": 0.00019837979515735166,
      "loss": 1.5086,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 21
    },
    {
      "epoch": 0.16243654822335024,
      "grad_norm": 0.31955838203430176,
      "learning_rate": 0.0001978855685095358,
      "loss": 1.6329,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 22
    },
    {
      "epoch": 0.169820027688048,
      "grad_norm": 0.3030437231063843,
      "learning_rate": 0.00019732643737003827,
      "loss": 1.6697,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 23
    },
    {
      "epoch": 0.17720350715274574,
      "grad_norm": 0.41288134455680847,
      "learning_rate": 0.00019670277247913205,
      "loss": 1.7094,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 24
    },
    {
      "epoch": 0.18458698661744347,
      "grad_norm": 0.2887294888496399,
      "learning_rate": 0.00019601498736716017,
      "loss": 1.5554,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 25
    },
    {
      "epoch": 0.19197046608214122,
      "grad_norm": 0.3173791170120239,
      "learning_rate": 0.00019526353808033825,
      "loss": 1.4404,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 26
    },
    {
      "epoch": 0.19935394554683894,
      "grad_norm": 0.2877439558506012,
      "learning_rate": 0.00019444892287836613,
      "loss": 1.4766,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 27
    },
    {
      "epoch": 0.2067374250115367,
      "grad_norm": 0.29286038875579834,
      "learning_rate": 0.00019357168190404936,
      "loss": 1.5156,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 28
    },
    {
      "epoch": 0.2141209044762344,
      "grad_norm": 0.27713659405708313,
      "learning_rate": 0.00019263239682514952,
      "loss": 1.5153,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 29
    },
    {
      "epoch": 0.22150438394093216,
      "grad_norm": 0.29187655448913574,
      "learning_rate": 0.0001916316904487005,
      "loss": 1.6036,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 30
    },
    {
      "epoch": 0.22888786340562992,
      "grad_norm": 0.2671583890914917,
      "learning_rate": 0.00019057022630804716,
      "loss": 1.4675,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 31
    },
    {
      "epoch": 0.23627134287032764,
      "grad_norm": 0.2679831087589264,
      "learning_rate": 0.00018944870822287956,
      "loss": 1.581,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 32
    },
    {
      "epoch": 0.2436548223350254,
      "grad_norm": 0.26359617710113525,
      "learning_rate": 0.00018826787983255473,
      "loss": 1.4674,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 33
    },
    {
      "epoch": 0.25103830179972314,
      "grad_norm": 0.30446046590805054,
      "learning_rate": 0.00018702852410301554,
      "loss": 1.5038,
      "memory/device_mem_reserved(gib)": 21.8,
      "memory/max_mem_active(gib)": 21.55,
      "memory/max_mem_allocated(gib)": 21.55,
      "step": 34
    }
  ],
  "logging_steps": 1,
  "max_steps": 135,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 34,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.17292722381783e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}