{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.509433962264151,
  "eval_steps": 20,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018867924528301886,
      "eval_loss": 1.9572468996047974,
      "eval_runtime": 19.4145,
      "eval_samples_per_second": 77.313,
      "eval_steps_per_second": 4.842,
      "step": 1
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 1.59375,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.6912,
      "step": 10
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.6237,
      "step": 20
    },
    {
      "epoch": 0.37735849056603776,
      "eval_loss": 1.5020643472671509,
      "eval_runtime": 18.3981,
      "eval_samples_per_second": 81.584,
      "eval_steps_per_second": 5.109,
      "step": 20
    },
    {
      "epoch": 0.5660377358490566,
      "grad_norm": 1.3828125,
      "learning_rate": 0.0002,
      "loss": 1.7306,
      "step": 30
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.8203125,
      "learning_rate": 0.00019984815164333163,
      "loss": 1.6944,
      "step": 40
    },
    {
      "epoch": 0.7547169811320755,
      "eval_loss": 1.5448347330093384,
      "eval_runtime": 28.537,
      "eval_samples_per_second": 52.598,
      "eval_steps_per_second": 3.294,
      "step": 40
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 0.859375,
      "learning_rate": 0.00019939306773179497,
      "loss": 1.6815,
      "step": 50
    },
    {
      "epoch": 1.1320754716981132,
      "grad_norm": 0.91796875,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.2718,
      "step": 60
    },
    {
      "epoch": 1.1320754716981132,
      "eval_loss": 1.6332371234893799,
      "eval_runtime": 18.8135,
      "eval_samples_per_second": 79.783,
      "eval_steps_per_second": 4.996,
      "step": 60
    },
    {
      "epoch": 1.320754716981132,
      "grad_norm": 0.859375,
      "learning_rate": 0.00019757963826274357,
      "loss": 1.1934,
      "step": 70
    },
    {
      "epoch": 1.509433962264151,
      "grad_norm": 0.83203125,
      "learning_rate": 0.00019622680003092503,
      "loss": 1.0234,
      "step": 80
    },
    {
      "epoch": 1.509433962264151,
      "eval_loss": 1.704294204711914,
      "eval_runtime": 18.5821,
      "eval_samples_per_second": 80.777,
      "eval_steps_per_second": 5.059,
      "step": 80
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.850280234267443e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}