{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14201183431952663,
  "eval_steps": 20,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001183431952662722,
      "eval_loss": 10.566378593444824,
      "eval_runtime": 1.9917,
      "eval_samples_per_second": 754.145,
      "eval_steps_per_second": 47.197,
      "step": 1
    },
    {
      "epoch": 0.011834319526627219,
      "grad_norm": 6.460504531860352,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 10.5689,
      "step": 10
    },
    {
      "epoch": 0.023668639053254437,
      "grad_norm": 4.217194557189941,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 10.5293,
      "step": 20
    },
    {
      "epoch": 0.023668639053254437,
      "eval_loss": 10.470946311950684,
      "eval_runtime": 1.962,
      "eval_samples_per_second": 765.537,
      "eval_steps_per_second": 47.91,
      "step": 20
    },
    {
      "epoch": 0.03550295857988166,
      "grad_norm": 7.088407039642334,
      "learning_rate": 4.8e-05,
      "loss": 10.3793,
      "step": 30
    },
    {
      "epoch": 0.047337278106508875,
      "grad_norm": 4.761963844299316,
      "learning_rate": 6.400000000000001e-05,
      "loss": 9.924,
      "step": 40
    },
    {
      "epoch": 0.047337278106508875,
      "eval_loss": 9.448060035705566,
      "eval_runtime": 2.0352,
      "eval_samples_per_second": 738.016,
      "eval_steps_per_second": 46.187,
      "step": 40
    },
    {
      "epoch": 0.05917159763313609,
      "grad_norm": 5.449029922485352,
      "learning_rate": 8e-05,
      "loss": 8.9682,
      "step": 50
    },
    {
      "epoch": 0.07100591715976332,
      "grad_norm": 2.087066173553467,
      "learning_rate": 9.6e-05,
      "loss": 8.2576,
      "step": 60
    },
    {
      "epoch": 0.07100591715976332,
      "eval_loss": 7.836277961730957,
      "eval_runtime": 2.012,
      "eval_samples_per_second": 746.529,
      "eval_steps_per_second": 46.72,
      "step": 60
    },
    {
      "epoch": 0.08284023668639054,
      "grad_norm": 1.812099575996399,
      "learning_rate": 0.00011200000000000001,
      "loss": 7.6596,
      "step": 70
    },
    {
      "epoch": 0.09467455621301775,
      "grad_norm": 2.425971269607544,
      "learning_rate": 0.00012800000000000002,
      "loss": 7.4757,
      "step": 80
    },
    {
      "epoch": 0.09467455621301775,
      "eval_loss": 7.445075988769531,
      "eval_runtime": 2.0477,
      "eval_samples_per_second": 733.507,
      "eval_steps_per_second": 45.905,
      "step": 80
    },
    {
      "epoch": 0.10650887573964497,
      "grad_norm": 1.7427077293395996,
      "learning_rate": 0.000144,
      "loss": 7.4227,
      "step": 90
    },
    {
      "epoch": 0.11834319526627218,
      "grad_norm": 5.246922492980957,
      "learning_rate": 0.00016,
      "loss": 7.2513,
      "step": 100
    },
    {
      "epoch": 0.11834319526627218,
      "eval_loss": 7.342855930328369,
      "eval_runtime": 1.997,
      "eval_samples_per_second": 752.143,
      "eval_steps_per_second": 47.072,
      "step": 100
    },
    {
      "epoch": 0.1301775147928994,
      "grad_norm": 2.3408617973327637,
      "learning_rate": 0.00017600000000000002,
      "loss": 7.3941,
      "step": 110
    },
    {
      "epoch": 0.14201183431952663,
      "grad_norm": 2.138099431991577,
      "learning_rate": 0.000192,
      "loss": 7.1604,
      "step": 120
    },
    {
      "epoch": 0.14201183431952663,
      "eval_loss": 7.194538593292236,
      "eval_runtime": 1.9979,
      "eval_samples_per_second": 751.783,
      "eval_steps_per_second": 47.049,
      "step": 120
    }
  ],
  "logging_steps": 10,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5058714486702080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}