{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 9040,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.19850963531373816,
      "eval_loss": 5.1191253662109375,
      "eval_runtime": 4.3448,
      "eval_samples_per_second": 46.723,
      "eval_steps_per_second": 1.611,
      "step": 904
    },
    {
      "epoch": 1.1061946902654867,
      "grad_norm": 12336.87109375,
      "learning_rate": 0.0005993999999999999,
      "loss": 1.2803,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.21601611830372205,
      "eval_loss": 4.903479099273682,
      "eval_runtime": 3.919,
      "eval_samples_per_second": 51.798,
      "eval_steps_per_second": 1.786,
      "step": 1808
    },
    {
      "epoch": 2.2123893805309733,
      "grad_norm": 17902.7421875,
      "learning_rate": 0.0005254477611940299,
      "loss": 1.1443,
      "step": 2000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.21898527951567967,
      "eval_loss": 4.8314008712768555,
      "eval_runtime": 3.9099,
      "eval_samples_per_second": 51.919,
      "eval_steps_per_second": 1.79,
      "step": 2712
    },
    {
      "epoch": 3.3185840707964602,
      "grad_norm": 28265.408203125,
      "learning_rate": 0.00045082089552238807,
      "loss": 1.1125,
      "step": 3000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.2254923698340933,
      "eval_loss": 4.771282196044922,
      "eval_runtime": 3.9059,
      "eval_samples_per_second": 51.973,
      "eval_steps_per_second": 1.792,
      "step": 3616
    },
    {
      "epoch": 4.424778761061947,
      "grad_norm": 25827.923828125,
      "learning_rate": 0.0003761940298507462,
      "loss": 1.099,
      "step": 4000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.23474689828694822,
      "eval_loss": 4.695719242095947,
      "eval_runtime": 3.9271,
      "eval_samples_per_second": 51.692,
      "eval_steps_per_second": 1.782,
      "step": 4520
    },
    {
      "epoch": 5.530973451327434,
      "grad_norm": 29887.09765625,
      "learning_rate": 0.00030156716417910443,
      "loss": 1.0789,
      "step": 5000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.24265180800709513,
      "eval_loss": 4.621862888336182,
      "eval_runtime": 3.9341,
      "eval_samples_per_second": 51.6,
      "eval_steps_per_second": 1.779,
      "step": 5424
    },
    {
      "epoch": 6.6371681415929205,
      "grad_norm": 21937.826171875,
      "learning_rate": 0.0002269402985074627,
      "loss": 1.0579,
      "step": 6000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.250710959868123,
      "eval_loss": 4.546590805053711,
      "eval_runtime": 3.9246,
      "eval_samples_per_second": 51.725,
      "eval_steps_per_second": 1.784,
      "step": 6328
    },
    {
      "epoch": 7.743362831858407,
      "grad_norm": 15053.748046875,
      "learning_rate": 0.00015231343283582087,
      "loss": 1.0332,
      "step": 7000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.2598980073843425,
      "eval_loss": 4.459190845489502,
      "eval_runtime": 3.9202,
      "eval_samples_per_second": 51.784,
      "eval_steps_per_second": 1.786,
      "step": 7232
    },
    {
      "epoch": 8.849557522123893,
      "grad_norm": 13792.96484375,
      "learning_rate": 7.76865671641791e-05,
      "loss": 1.0096,
      "step": 8000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.2669931458648646,
      "eval_loss": 4.392664909362793,
      "eval_runtime": 3.9151,
      "eval_samples_per_second": 51.851,
      "eval_steps_per_second": 1.788,
      "step": 8136
    },
    {
      "epoch": 9.955752212389381,
      "grad_norm": 12945.439453125,
      "learning_rate": 3.0597014925373133e-06,
      "loss": 0.9929,
      "step": 9000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.2705117947037105,
      "eval_loss": 4.354263782501221,
      "eval_runtime": 3.9272,
      "eval_samples_per_second": 51.691,
      "eval_steps_per_second": 1.782,
      "step": 9040
    },
    {
      "epoch": 10.0,
      "step": 9040,
      "total_flos": 7.55264618496e+16,
      "train_loss": 1.0894328868494625,
      "train_runtime": 8807.3219,
      "train_samples_per_second": 32.819,
      "train_steps_per_second": 1.026
    }
  ],
  "logging_steps": 1000,
  "max_steps": 9040,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 7.55264618496e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}