{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32,
      "grad_norm": 0.18859412248721424,
      "learning_rate": 0.0,
      "loss": 1.855,
      "step": 1
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.19568499575347786,
      "learning_rate": 0.0005,
      "loss": 1.9926,
      "step": 2
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.29431554560314344,
      "learning_rate": 0.0004991893270335525,
      "loss": 1.927,
      "step": 3
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.29431554560314344,
      "learning_rate": 0.0004967625656594782,
      "loss": 1.8452,
      "step": 4
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.8266520153680488,
      "learning_rate": 0.000492735454356513,
      "loss": 1.6406,
      "step": 5
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.7594278037913929,
      "learning_rate": 0.00048713411048678635,
      "loss": 1.7403,
      "step": 6
    },
    {
      "epoch": 1.96,
      "grad_norm": 5.486762613373928,
      "learning_rate": 0.0004799948609147061,
      "loss": 1.8554,
      "step": 7
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.486762613373928,
      "learning_rate": 0.00047136400641330245,
      "loss": 1.4854,
      "step": 8
    },
    {
      "epoch": 2.32,
      "grad_norm": 2.071973329180764,
      "learning_rate": 0.00046129752138594874,
      "loss": 1.5481,
      "step": 9
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.6793052873736364,
      "learning_rate": 0.0004498606908508753,
      "loss": 1.5247,
      "step": 10
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.8977423000889911,
      "learning_rate": 0.00043712768704277526,
      "loss": 1.6431,
      "step": 11
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8977423000889911,
      "learning_rate": 0.00042318108837739987,
      "loss": 0.9422,
      "step": 12
    },
    {
      "epoch": 3.32,
      "grad_norm": 1.0958352799991686,
      "learning_rate": 0.0004081113438988443,
      "loss": 1.304,
      "step": 13
    },
    {
      "epoch": 3.64,
      "grad_norm": 1.5378951599262418,
      "learning_rate": 0.00039201618668278893,
      "loss": 1.3008,
      "step": 14
    },
    {
      "epoch": 3.96,
      "grad_norm": 0.8511977662468583,
      "learning_rate": 0.000375,
      "loss": 1.4582,
      "step": 15
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.8511977662468583,
      "learning_rate": 0.0003571731403507635,
      "loss": 0.4623,
      "step": 16
    },
    {
      "epoch": 4.32,
      "grad_norm": 0.9290144753914329,
      "learning_rate": 0.0003386512217606339,
      "loss": 1.0573,
      "step": 17
    },
    {
      "epoch": 4.64,
      "grad_norm": 0.6575317816896541,
      "learning_rate": 0.00031955436597911317,
      "loss": 0.9713,
      "step": 18
    },
    {
      "epoch": 4.96,
      "grad_norm": 1.2491458277203997,
      "learning_rate": 0.00030000642344401115,
      "loss": 1.1729,
      "step": 19
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.2491458277203997,
      "learning_rate": 0.0002801341700638307,
      "loss": 0.1771,
      "step": 20
    },
    {
      "epoch": 5.32,
      "grad_norm": 1.235857325955075,
      "learning_rate": 0.0002600664850273538,
      "loss": 0.8155,
      "step": 21
    },
    {
      "epoch": 5.64,
      "grad_norm": 0.6388932828526788,
      "learning_rate": 0.0002399335149726463,
      "loss": 0.7108,
      "step": 22
    },
    {
      "epoch": 5.96,
      "grad_norm": 0.7819931539727927,
      "learning_rate": 0.00021986582993616926,
      "loss": 0.8861,
      "step": 23
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7819931539727927,
      "learning_rate": 0.00019999357655598894,
      "loss": 0.0923,
      "step": 24
    },
    {
      "epoch": 6.32,
      "grad_norm": 0.8887080599954317,
      "learning_rate": 0.00018044563402088684,
      "loss": 0.6012,
      "step": 25
    },
    {
      "epoch": 6.64,
      "grad_norm": 0.5485487599439223,
      "learning_rate": 0.00016134877823936609,
      "loss": 0.5181,
      "step": 26
    },
    {
      "epoch": 6.96,
      "grad_norm": 0.4629969870334225,
      "learning_rate": 0.00014282685964923643,
      "loss": 0.6908,
      "step": 27
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.4629969870334225,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.0508,
      "step": 28
    },
    {
      "epoch": 7.32,
      "grad_norm": 0.6975915107338143,
      "learning_rate": 0.00010798381331721108,
      "loss": 0.4188,
      "step": 29
    },
    {
      "epoch": 7.64,
      "grad_norm": 0.49152358026000714,
      "learning_rate": 9.18886561011557e-05,
      "loss": 0.3578,
      "step": 30
    },
    {
      "epoch": 7.96,
      "grad_norm": 0.39011405587674003,
      "learning_rate": 7.681891162260016e-05,
      "loss": 0.4971,
      "step": 31
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.4820423853174385,
      "learning_rate": 6.28723129572247e-05,
      "loss": 0.0178,
      "step": 32
    },
    {
      "epoch": 8.32,
      "grad_norm": 0.4488361231595311,
      "learning_rate": 5.013930914912476e-05,
      "loss": 0.3,
      "step": 33
    },
    {
      "epoch": 8.64,
      "grad_norm": 0.41126028156234384,
      "learning_rate": 3.870247861405135e-05,
      "loss": 0.2649,
      "step": 34
    },
    {
      "epoch": 8.96,
      "grad_norm": 0.4394886240552755,
      "learning_rate": 2.863599358669755e-05,
      "loss": 0.3906,
      "step": 35
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.4394886240552755,
      "learning_rate": 2.0005139085293944e-05,
      "loss": 0.0116,
      "step": 36
    },
    {
      "epoch": 9.32,
      "grad_norm": 0.4003875847860307,
      "learning_rate": 1.286588951321363e-05,
      "loss": 0.2341,
      "step": 37
    },
    {
      "epoch": 9.64,
      "grad_norm": 0.5105097493195208,
      "learning_rate": 7.2645456434869975e-06,
      "loss": 0.2212,
      "step": 38
    },
    {
      "epoch": 9.96,
      "grad_norm": 0.4185656036067592,
      "learning_rate": 3.2374343405217886e-06,
      "loss": 0.3507,
      "step": 39
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.4185656036067592,
      "learning_rate": 8.106729664475177e-07,
      "loss": 0.0108,
      "step": 40
    },
    {
      "epoch": 10.0,
      "step": 40,
      "total_flos": 80308774895616.0,
      "train_loss": 0.8836164159234613,
      "train_runtime": 1608.8327,
      "train_samples_per_second": 0.615,
      "train_steps_per_second": 0.025
    }
  ],
  "logging_steps": 1,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 80308774895616.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}