{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9965397923875432,
  "eval_steps": 500,
  "global_step": 108,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00922722029988466,
      "grad_norm": 0.057699669152498245,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.1486,
      "mean_token_accuracy": 0.9603070467710495,
      "step": 1
    },
    {
      "epoch": 0.0461361014994233,
      "grad_norm": 0.057932183146476746,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.1521,
      "mean_token_accuracy": 0.9589259419590235,
      "step": 5
    },
    {
      "epoch": 0.0922722029988466,
      "grad_norm": 0.044771965593099594,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.1491,
      "mean_token_accuracy": 0.9586100548505783,
      "step": 10
    },
    {
      "epoch": 0.1384083044982699,
      "grad_norm": 0.04442073777318001,
      "learning_rate": 0.00019916201012264254,
      "loss": 0.1121,
      "mean_token_accuracy": 0.9675070151686669,
      "step": 15
    },
    {
      "epoch": 0.1845444059976932,
      "grad_norm": 0.05502348393201828,
      "learning_rate": 0.00019578173241879872,
      "loss": 0.0855,
      "mean_token_accuracy": 0.9732602819800377,
      "step": 20
    },
    {
      "epoch": 0.2306805074971165,
      "grad_norm": 0.040541354566812515,
      "learning_rate": 0.00018989517410853955,
      "loss": 0.0611,
      "mean_token_accuracy": 0.9792577132582665,
      "step": 25
    },
    {
      "epoch": 0.2768166089965398,
      "grad_norm": 0.03484530746936798,
      "learning_rate": 0.0001816563663057211,
      "loss": 0.0489,
      "mean_token_accuracy": 0.9825387537479401,
      "step": 30
    },
    {
      "epoch": 0.3229527104959631,
      "grad_norm": 0.04107120633125305,
      "learning_rate": 0.00017128089045468294,
      "loss": 0.0411,
      "mean_token_accuracy": 0.9843883469700814,
      "step": 35
    },
    {
      "epoch": 0.3690888119953864,
      "grad_norm": 0.03086032159626484,
      "learning_rate": 0.00015904023730059228,
      "loss": 0.0387,
      "mean_token_accuracy": 0.9855756282806396,
      "step": 40
    },
    {
      "epoch": 0.41522491349480967,
      "grad_norm": 0.029818393290042877,
      "learning_rate": 0.00014525470290445392,
      "loss": 0.036,
      "mean_token_accuracy": 0.9861921563744545,
      "step": 45
    },
    {
      "epoch": 0.461361014994233,
      "grad_norm": 0.032603517174720764,
      "learning_rate": 0.00013028500758979506,
      "loss": 0.033,
      "mean_token_accuracy": 0.9873641684651375,
      "step": 50
    },
    {
      "epoch": 0.5074971164936563,
      "grad_norm": 0.024502255022525787,
      "learning_rate": 0.00011452285712454904,
      "loss": 0.034,
      "mean_token_accuracy": 0.9869368731975555,
      "step": 55
    },
    {
      "epoch": 0.5536332179930796,
      "grad_norm": 0.028779158368706703,
      "learning_rate": 9.838069311974986e-05,
      "loss": 0.0385,
      "mean_token_accuracy": 0.9849224641919136,
      "step": 60
    },
    {
      "epoch": 0.5997693194925029,
      "grad_norm": 0.02729989029467106,
      "learning_rate": 8.228090084207774e-05,
      "loss": 0.0354,
      "mean_token_accuracy": 0.9860517591238022,
      "step": 65
    },
    {
      "epoch": 0.6459054209919262,
      "grad_norm": 0.029013721272349358,
      "learning_rate": 6.664475683491796e-05,
      "loss": 0.0344,
      "mean_token_accuracy": 0.986846213042736,
      "step": 70
    },
    {
      "epoch": 0.6920415224913494,
      "grad_norm": 0.02776612527668476,
      "learning_rate": 5.1881405550919493e-05,
      "loss": 0.0338,
      "mean_token_accuracy": 0.9866286054253578,
      "step": 75
    },
    {
      "epoch": 0.7381776239907728,
      "grad_norm": 0.031024280935525894,
      "learning_rate": 3.8377153439907266e-05,
      "loss": 0.0321,
      "mean_token_accuracy": 0.9873672261834144,
      "step": 80
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 0.02875332161784172,
      "learning_rate": 2.6485360629279987e-05,
      "loss": 0.0307,
      "mean_token_accuracy": 0.9876510694622993,
      "step": 85
    },
    {
      "epoch": 0.8304498269896193,
      "grad_norm": 0.02739580348134041,
      "learning_rate": 1.65171946970729e-05,
      "loss": 0.0281,
      "mean_token_accuracy": 0.9888536125421524,
      "step": 90
    },
    {
      "epoch": 0.8765859284890427,
      "grad_norm": 0.025241447612643242,
      "learning_rate": 8.733488479845997e-06,
      "loss": 0.032,
      "mean_token_accuracy": 0.9872176691889762,
      "step": 95
    },
    {
      "epoch": 0.922722029988466,
      "grad_norm": 0.024631677195429802,
      "learning_rate": 3.3379149687388867e-06,
      "loss": 0.0293,
      "mean_token_accuracy": 0.9884507328271865,
      "step": 100
    },
    {
      "epoch": 0.9688581314878892,
      "grad_norm": 0.029005141928792,
      "learning_rate": 4.7165788333860536e-07,
      "loss": 0.0363,
      "mean_token_accuracy": 0.9855603620409965,
      "step": 105
    },
    {
      "epoch": 0.9965397923875432,
      "mean_token_accuracy": 0.9884629423419634,
      "step": 108,
      "total_flos": 5.638661914125926e+16,
      "train_loss": 0.05270655032385279,
      "train_runtime": 2016.3955,
      "train_samples_per_second": 0.43,
      "train_steps_per_second": 0.054
    }
  ],
  "logging_steps": 5,
  "max_steps": 108,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 5.638661914125926e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}