{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 59.80732177263969,
  "eval_steps": 1164,
  "global_step": 11640,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.980732177263969,
      "grad_norm": 1.6488584280014038,
      "learning_rate": 9.00171821305842e-06,
      "loss": 2.4506,
      "step": 1164
    },
    {
      "epoch": 5.980732177263969,
      "eval_accuracy": 0.07356671740233384,
      "eval_loss": 2.987065315246582,
      "eval_runtime": 32.1198,
      "eval_samples_per_second": 245.456,
      "eval_steps_per_second": 12.298,
      "step": 1164
    },
    {
      "epoch": 11.961464354527939,
      "grad_norm": 4.022498607635498,
      "learning_rate": 8.00257731958763e-06,
      "loss": 2.3229,
      "step": 2328
    },
    {
      "epoch": 11.961464354527939,
      "eval_accuracy": 0.07331303906646372,
      "eval_loss": 3.1384434700012207,
      "eval_runtime": 28.9812,
      "eval_samples_per_second": 272.038,
      "eval_steps_per_second": 13.63,
      "step": 2328
    },
    {
      "epoch": 17.942196531791907,
      "grad_norm": 3.224060535430908,
      "learning_rate": 7.002577319587629e-06,
      "loss": 2.2364,
      "step": 3492
    },
    {
      "epoch": 17.942196531791907,
      "eval_accuracy": 0.07952815829528158,
      "eval_loss": 3.1919777393341064,
      "eval_runtime": 28.8853,
      "eval_samples_per_second": 272.942,
      "eval_steps_per_second": 13.675,
      "step": 3492
    },
    {
      "epoch": 23.922928709055878,
      "grad_norm": 3.2662484645843506,
      "learning_rate": 6.003436426116839e-06,
      "loss": 2.1589,
      "step": 4656
    },
    {
      "epoch": 23.922928709055878,
      "eval_accuracy": 0.0824771689497717,
      "eval_loss": 3.2666664123535156,
      "eval_runtime": 28.8936,
      "eval_samples_per_second": 272.863,
      "eval_steps_per_second": 13.671,
      "step": 4656
    },
    {
      "epoch": 29.903660886319845,
      "grad_norm": 4.750115394592285,
      "learning_rate": 5.003436426116839e-06,
      "loss": 2.1034,
      "step": 5820
    },
    {
      "epoch": 29.903660886319845,
      "eval_accuracy": 0.08351090816844242,
      "eval_loss": 3.2883238792419434,
      "eval_runtime": 28.8169,
      "eval_samples_per_second": 273.589,
      "eval_steps_per_second": 13.707,
      "step": 5820
    },
    {
      "epoch": 35.884393063583815,
      "grad_norm": 4.091363430023193,
      "learning_rate": 4.004295532646048e-06,
      "loss": 2.0555,
      "step": 6984
    },
    {
      "epoch": 35.884393063583815,
      "eval_accuracy": 0.08365043125317098,
      "eval_loss": 3.351201295852661,
      "eval_runtime": 28.9642,
      "eval_samples_per_second": 272.198,
      "eval_steps_per_second": 13.638,
      "step": 6984
    },
    {
      "epoch": 41.86512524084778,
      "grad_norm": 3.1545722484588623,
      "learning_rate": 3.004295532646048e-06,
      "loss": 2.0231,
      "step": 8148
    },
    {
      "epoch": 41.86512524084778,
      "eval_accuracy": 0.08360513155033703,
      "eval_loss": 3.4304280281066895,
      "eval_runtime": 28.8426,
      "eval_samples_per_second": 273.345,
      "eval_steps_per_second": 13.695,
      "step": 8148
    },
    {
      "epoch": 47.845857418111756,
      "grad_norm": 3.3551816940307617,
      "learning_rate": 2.005154639175258e-06,
      "loss": 2.0056,
      "step": 9312
    },
    {
      "epoch": 47.845857418111756,
      "eval_accuracy": 0.08306380010147134,
      "eval_loss": 3.553959369659424,
      "eval_runtime": 29.0501,
      "eval_samples_per_second": 271.393,
      "eval_steps_per_second": 13.597,
      "step": 9312
    },
    {
      "epoch": 53.82658959537572,
      "grad_norm": 3.364650249481201,
      "learning_rate": 1.005154639175258e-06,
      "loss": 1.9964,
      "step": 10476
    },
    {
      "epoch": 53.82658959537572,
      "eval_accuracy": 0.08203675517221941,
      "eval_loss": 3.589355230331421,
      "eval_runtime": 28.9839,
      "eval_samples_per_second": 272.014,
      "eval_steps_per_second": 13.628,
      "step": 10476
    },
    {
      "epoch": 59.80732177263969,
      "grad_norm": 5.201988697052002,
      "learning_rate": 6.0137457044673545e-09,
      "loss": 1.9848,
      "step": 11640
    },
    {
      "epoch": 59.80732177263969,
      "eval_accuracy": 0.08131659056316591,
      "eval_loss": 3.626406192779541,
      "eval_runtime": 29.0612,
      "eval_samples_per_second": 271.29,
      "eval_steps_per_second": 13.592,
      "step": 11640
    },
    {
      "epoch": 59.80732177263969,
      "step": 11640,
      "total_flos": 1.472280663793582e+18,
      "train_loss": 2.133767731656733,
      "train_runtime": 32669.9946,
      "train_samples_per_second": 114.321,
      "train_steps_per_second": 0.356
    }
  ],
  "logging_steps": 1164,
  "max_steps": 11640,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 60,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.472280663793582e+18,
  "train_batch_size": 40,
  "trial_name": null,
  "trial_params": null
}