{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.066603460535672,
  "eval_steps": 1500,
  "global_step": 4500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0711068973690448,
      "grad_norm": 1.3703839778900146,
      "learning_rate": 1.4218009478672987e-05,
      "loss": 1.6599,
      "step": 300
    },
    {
      "epoch": 0.1422137947380896,
      "grad_norm": 1.2324339151382446,
      "learning_rate": 1.9975676940479608e-05,
      "loss": 1.6611,
      "step": 600
    },
    {
      "epoch": 0.2133206921071344,
      "grad_norm": 1.3222817182540894,
      "learning_rate": 1.9825039649994836e-05,
      "loss": 1.6619,
      "step": 900
    },
    {
      "epoch": 0.2844275894761792,
      "grad_norm": 1.1514230966567993,
      "learning_rate": 1.953873955447588e-05,
      "loss": 1.6576,
      "step": 1200
    },
    {
      "epoch": 0.355534486845224,
      "grad_norm": 1.0430920124053955,
      "learning_rate": 1.9120729846522797e-05,
      "loss": 1.6591,
      "step": 1500
    },
    {
      "epoch": 0.355534486845224,
      "eval_loss": 1.6568845510482788,
      "eval_runtime": 2223.4322,
      "eval_samples_per_second": 6.746,
      "eval_steps_per_second": 6.746,
      "step": 1500
    },
    {
      "epoch": 0.4266413842142688,
      "grad_norm": 1.1808266639709473,
      "learning_rate": 1.857678234706788e-05,
      "loss": 1.6534,
      "step": 1800
    },
    {
      "epoch": 0.4977482815833136,
      "grad_norm": 1.1664097309112549,
      "learning_rate": 1.7914407808860857e-05,
      "loss": 1.6546,
      "step": 2100
    },
    {
      "epoch": 0.5688551789523584,
      "grad_norm": 1.255988359451294,
      "learning_rate": 1.714275220902116e-05,
      "loss": 1.648,
      "step": 2400
    },
    {
      "epoch": 0.6399620763214032,
      "grad_norm": 1.406730055809021,
      "learning_rate": 1.627247046263554e-05,
      "loss": 1.6505,
      "step": 2700
    },
    {
      "epoch": 0.711068973690448,
      "grad_norm": 1.4758352041244507,
      "learning_rate": 1.531557930114637e-05,
      "loss": 1.6504,
      "step": 3000
    },
    {
      "epoch": 0.711068973690448,
      "eval_loss": 1.6482607126235962,
      "eval_runtime": 2220.8948,
      "eval_samples_per_second": 6.754,
      "eval_steps_per_second": 6.754,
      "step": 3000
    },
    {
      "epoch": 0.7821758710594928,
      "grad_norm": 1.4238367080688477,
      "learning_rate": 1.4285291346965831e-05,
      "loss": 1.646,
      "step": 3300
    },
    {
      "epoch": 0.8532827684285376,
      "grad_norm": 1.1593595743179321,
      "learning_rate": 1.319583267539094e-05,
      "loss": 1.6454,
      "step": 3600
    },
    {
      "epoch": 0.9243896657975824,
      "grad_norm": 1.1607190370559692,
      "learning_rate": 1.2062246382899667e-05,
      "loss": 1.6429,
      "step": 3900
    },
    {
      "epoch": 0.9954965631666272,
      "grad_norm": 1.341468334197998,
      "learning_rate": 1.0900184874130164e-05,
      "loss": 1.6381,
      "step": 4200
    },
    {
      "epoch": 1.066603460535672,
      "grad_norm": 1.3884109258651733,
      "learning_rate": 9.725693735616222e-06,
      "loss": 1.6038,
      "step": 4500
    },
    {
      "epoch": 1.066603460535672,
      "eval_loss": 1.642856478691101,
      "eval_runtime": 2220.4526,
      "eval_samples_per_second": 6.755,
      "eval_steps_per_second": 6.755,
      "step": 4500
    }
  ],
  "logging_steps": 300,
  "max_steps": 8438,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1996706885823365e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}