{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8867924528301887,
  "eval_steps": 20,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018867924528301886,
      "eval_loss": 1.91287362575531,
      "eval_runtime": 19.9916,
      "eval_samples_per_second": 75.082,
      "eval_steps_per_second": 4.702,
      "step": 1
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 1.6953125,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.7788,
      "step": 10
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 1.1875,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.6758,
      "step": 20
    },
    {
      "epoch": 0.37735849056603776,
      "eval_loss": 1.5468029975891113,
      "eval_runtime": 19.2466,
      "eval_samples_per_second": 77.988,
      "eval_steps_per_second": 4.884,
      "step": 20
    },
    {
      "epoch": 0.5660377358490566,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0002,
      "loss": 1.7428,
      "step": 30
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.9609375,
      "learning_rate": 0.00019984815164333163,
      "loss": 1.7482,
      "step": 40
    },
    {
      "epoch": 0.7547169811320755,
      "eval_loss": 1.5930224657058716,
      "eval_runtime": 20.8935,
      "eval_samples_per_second": 71.84,
      "eval_steps_per_second": 4.499,
      "step": 40
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00019939306773179497,
      "loss": 1.7373,
      "step": 50
    },
    {
      "epoch": 1.1320754716981132,
      "grad_norm": 1.015625,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.3262,
      "step": 60
    },
    {
      "epoch": 1.1320754716981132,
      "eval_loss": 1.694644570350647,
      "eval_runtime": 19.8369,
      "eval_samples_per_second": 75.667,
      "eval_steps_per_second": 4.739,
      "step": 60
    },
    {
      "epoch": 1.320754716981132,
      "grad_norm": 0.8671875,
      "learning_rate": 0.00019757963826274357,
      "loss": 1.2568,
      "step": 70
    },
    {
      "epoch": 1.509433962264151,
      "grad_norm": 0.90234375,
      "learning_rate": 0.00019622680003092503,
      "loss": 1.072,
      "step": 80
    },
    {
      "epoch": 1.509433962264151,
      "eval_loss": 1.7398728132247925,
      "eval_runtime": 28.2186,
      "eval_samples_per_second": 53.192,
      "eval_steps_per_second": 3.331,
      "step": 80
    },
    {
      "epoch": 1.6981132075471699,
      "grad_norm": 0.85546875,
      "learning_rate": 0.00019458172417006347,
      "loss": 1.0807,
      "step": 90
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": 0.80859375,
      "learning_rate": 0.00019264940672148018,
      "loss": 1.3163,
      "step": 100
    },
    {
      "epoch": 1.8867924528301887,
      "eval_loss": 1.7708204984664917,
      "eval_runtime": 19.9313,
      "eval_samples_per_second": 75.309,
      "eval_steps_per_second": 4.716,
      "step": 100
    }
  ],
  "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": 7.313993814455091e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}