{
  "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": 2.0760505199432373,
      "eval_runtime": 19.9612,
      "eval_samples_per_second": 75.196,
      "eval_steps_per_second": 4.709,
      "step": 1
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 2.0625,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.8165,
      "step": 10
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.6773,
      "step": 20
    },
    {
      "epoch": 0.37735849056603776,
      "eval_loss": 1.5448647737503052,
      "eval_runtime": 19.4232,
      "eval_samples_per_second": 77.279,
      "eval_steps_per_second": 4.84,
      "step": 20
    },
    {
      "epoch": 0.5660377358490566,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0002,
      "loss": 1.7454,
      "step": 30
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.96875,
      "learning_rate": 0.00019984815164333163,
      "loss": 1.752,
      "step": 40
    },
    {
      "epoch": 0.7547169811320755,
      "eval_loss": 1.5965954065322876,
      "eval_runtime": 29.2724,
      "eval_samples_per_second": 51.277,
      "eval_steps_per_second": 3.211,
      "step": 40
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 0.96875,
      "learning_rate": 0.00019939306773179497,
      "loss": 1.7421,
      "step": 50
    },
    {
      "epoch": 1.1320754716981132,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.3307,
      "step": 60
    },
    {
      "epoch": 1.1320754716981132,
      "eval_loss": 1.6943310499191284,
      "eval_runtime": 21.4164,
      "eval_samples_per_second": 70.087,
      "eval_steps_per_second": 4.389,
      "step": 60
    },
    {
      "epoch": 1.320754716981132,
      "grad_norm": 0.85546875,
      "learning_rate": 0.00019757963826274357,
      "loss": 1.2583,
      "step": 70
    },
    {
      "epoch": 1.509433962264151,
      "grad_norm": 0.90625,
      "learning_rate": 0.00019622680003092503,
      "loss": 1.0736,
      "step": 80
    },
    {
      "epoch": 1.509433962264151,
      "eval_loss": 1.7416529655456543,
      "eval_runtime": 32.0268,
      "eval_samples_per_second": 46.867,
      "eval_steps_per_second": 2.935,
      "step": 80
    },
    {
      "epoch": 1.6981132075471699,
      "grad_norm": 0.86328125,
      "learning_rate": 0.00019458172417006347,
      "loss": 1.0759,
      "step": 90
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": 0.828125,
      "learning_rate": 0.00019264940672148018,
      "loss": 1.2902,
      "step": 100
    },
    {
      "epoch": 1.8867924528301887,
      "eval_loss": 1.7835454940795898,
      "eval_runtime": 20.8305,
      "eval_samples_per_second": 72.058,
      "eval_steps_per_second": 4.513,
      "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
}