{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 59.922928709055874,
  "eval_steps": 1866,
  "global_step": 18660,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.992292870905588,
      "grad_norm": 1.8218445777893066,
      "learning_rate": 9.002143622722401e-06,
      "loss": 2.4434,
      "step": 1866
    },
    {
      "epoch": 5.992292870905588,
      "eval_accuracy": 0.03163401873707264,
      "eval_loss": 3.7035000324249268,
      "eval_runtime": 31.9522,
      "eval_samples_per_second": 257.228,
      "eval_steps_per_second": 6.447,
      "step": 1866
    },
    {
      "epoch": 11.984585741811175,
      "grad_norm": 4.5330424308776855,
      "learning_rate": 8.0021436227224e-06,
      "loss": 2.2689,
      "step": 3732
    },
    {
      "epoch": 11.984585741811175,
      "eval_accuracy": 0.031208176177150503,
      "eval_loss": 3.9282093048095703,
      "eval_runtime": 32.0567,
      "eval_samples_per_second": 256.39,
      "eval_steps_per_second": 6.426,
      "step": 3732
    },
    {
      "epoch": 17.976878612716764,
      "grad_norm": 7.768856048583984,
      "learning_rate": 7.002143622722402e-06,
      "loss": 2.1311,
      "step": 5598
    },
    {
      "epoch": 17.976878612716764,
      "eval_accuracy": 0.0324045909883603,
      "eval_loss": 4.188955307006836,
      "eval_runtime": 31.9998,
      "eval_samples_per_second": 256.845,
      "eval_steps_per_second": 6.438,
      "step": 5598
    },
    {
      "epoch": 23.96917148362235,
      "grad_norm": 4.701458930969238,
      "learning_rate": 6.002679528403002e-06,
      "loss": 2.0473,
      "step": 7464
    },
    {
      "epoch": 23.96917148362235,
      "eval_accuracy": 0.03166443606278136,
      "eval_loss": 4.221826076507568,
      "eval_runtime": 31.9366,
      "eval_samples_per_second": 257.353,
      "eval_steps_per_second": 6.45,
      "step": 7464
    },
    {
      "epoch": 29.961464354527937,
      "grad_norm": 4.455111503601074,
      "learning_rate": 5.003215434083602e-06,
      "loss": 2.0065,
      "step": 9330
    },
    {
      "epoch": 29.961464354527937,
      "eval_accuracy": 0.03170702031877357,
      "eval_loss": 4.196821212768555,
      "eval_runtime": 31.9205,
      "eval_samples_per_second": 257.484,
      "eval_steps_per_second": 6.454,
      "step": 9330
    },
    {
      "epoch": 35.95375722543353,
      "grad_norm": 4.213284492492676,
      "learning_rate": 4.003751339764202e-06,
      "loss": 1.9816,
      "step": 11196
    },
    {
      "epoch": 35.95375722543353,
      "eval_accuracy": 0.031127063308593907,
      "eval_loss": 4.327696323394775,
      "eval_runtime": 32.0629,
      "eval_samples_per_second": 256.34,
      "eval_steps_per_second": 6.425,
      "step": 11196
    },
    {
      "epoch": 41.946050096339114,
      "grad_norm": 4.925486087799072,
      "learning_rate": 3.004287245444802e-06,
      "loss": 1.9593,
      "step": 13062
    },
    {
      "epoch": 41.946050096339114,
      "eval_accuracy": 0.031164722854709472,
      "eval_loss": 4.440001487731934,
      "eval_runtime": 31.9997,
      "eval_samples_per_second": 256.846,
      "eval_steps_per_second": 6.438,
      "step": 13062
    },
    {
      "epoch": 47.9383429672447,
      "grad_norm": 3.112938404083252,
      "learning_rate": 2.004823151125402e-06,
      "loss": 1.9448,
      "step": 14928
    },
    {
      "epoch": 47.9383429672447,
      "eval_accuracy": 0.031116924200024335,
      "eval_loss": 4.489612102508545,
      "eval_runtime": 31.9592,
      "eval_samples_per_second": 257.172,
      "eval_steps_per_second": 6.446,
      "step": 14928
    },
    {
      "epoch": 53.93063583815029,
      "grad_norm": 1.5867228507995605,
      "learning_rate": 1.005359056806002e-06,
      "loss": 1.9352,
      "step": 16794
    },
    {
      "epoch": 53.93063583815029,
      "eval_accuracy": 0.03109326628002866,
      "eval_loss": 4.571017265319824,
      "eval_runtime": 31.9814,
      "eval_samples_per_second": 256.993,
      "eval_steps_per_second": 6.441,
      "step": 16794
    },
    {
      "epoch": 59.922928709055874,
      "grad_norm": 4.193638801574707,
      "learning_rate": 5.894962486602358e-09,
      "loss": 1.9342,
      "step": 18660
    },
    {
      "epoch": 59.922928709055874,
      "eval_accuracy": 0.031013505292614672,
      "eval_loss": 4.6299943923950195,
      "eval_runtime": 31.9345,
      "eval_samples_per_second": 257.37,
      "eval_steps_per_second": 6.451,
      "step": 18660
    },
    {
      "epoch": 59.922928709055874,
      "step": 18660,
      "total_flos": 1.4737892295759744e+18,
      "train_loss": 2.0652262108118973,
      "train_runtime": 33416.7253,
      "train_samples_per_second": 111.779,
      "train_steps_per_second": 0.558
    }
  ],
  "logging_steps": 1866,
  "max_steps": 18660,
  "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": 1.4737892295759744e+18,
  "train_batch_size": 40,
  "trial_name": null,
  "trial_params": null
}