{
  "best_global_step": 360,
  "best_metric": 0.36397936940193176,
  "best_model_checkpoint": null,
  "epoch": 0.4540295119182747,
  "eval_steps": 40,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04540295119182747,
      "grad_norm": 5.84375,
      "learning_rate": 9.75e-06,
      "loss": 2.131,
      "step": 40
    },
    {
      "epoch": 0.04540295119182747,
      "eval_loss": 1.8176805973052979,
      "eval_model_preparation_time": 0.0081,
      "eval_runtime": 12.8325,
      "eval_samples_per_second": 79.798,
      "eval_steps_per_second": 2.494,
      "step": 40
    },
    {
      "epoch": 0.09080590238365494,
      "grad_norm": 10.5625,
      "learning_rate": 9.713207455460893e-06,
      "loss": 1.4527,
      "step": 80
    },
    {
      "epoch": 0.09080590238365494,
      "eval_loss": 1.1334214210510254,
      "eval_model_preparation_time": 0.0081,
      "eval_runtime": 12.7653,
      "eval_samples_per_second": 80.218,
      "eval_steps_per_second": 2.507,
      "step": 80
    },
    {
      "epoch": 0.1362088535754824,
      "grad_norm": 4.09375,
      "learning_rate": 8.858122916938601e-06,
      "loss": 0.9438,
      "step": 120
    },
    {
      "epoch": 0.1362088535754824,
      "eval_loss": 0.7638623714447021,
      "eval_model_preparation_time": 0.0081,
      "eval_runtime": 12.8084,
      "eval_samples_per_second": 79.947,
      "eval_steps_per_second": 2.498,
      "step": 120
    },
    {
      "epoch": 0.18161180476730987,
      "grad_norm": 2.734375,
      "learning_rate": 7.537691814803522e-06,
      "loss": 0.6657,
      "step": 160
    },
    {
      "epoch": 0.18161180476730987,
      "eval_loss": 0.5563021898269653,
      "eval_model_preparation_time": 0.0081,
      "eval_runtime": 12.785,
      "eval_samples_per_second": 80.094,
      "eval_steps_per_second": 2.503,
      "step": 160
    },
    {
      "epoch": 0.22701475595913734,
      "grad_norm": 2.65625,
      "learning_rate": 5.911177627460739e-06,
      "loss": 0.4941,
      "step": 200
    },
    {
      "epoch": 0.22701475595913734,
      "eval_loss": 0.4392661154270172,
      "eval_model_preparation_time": 0.0081,
      "eval_runtime": 12.8151,
      "eval_samples_per_second": 79.906,
      "eval_steps_per_second": 2.497,
      "step": 200
    },
    {
      "epoch": 0.2724177071509648,
      "grad_norm": 1.9921875,
      "learning_rate": 4.174761970696612e-06,
      "loss": 0.4092,
      "step": 240
    },
    {
      "epoch": 0.2724177071509648,
      "eval_loss": 0.3819335103034973,
      "eval_model_preparation_time": 0.0081,
      "eval_runtime": 12.831,
      "eval_samples_per_second": 79.807,
      "eval_steps_per_second": 2.494,
      "step": 240
    },
    {
      "epoch": 0.3178206583427923,
      "grad_norm": 1.625,
      "learning_rate": 2.5378821994826654e-06,
      "loss": 0.3775,
      "step": 280
    },
    {
      "epoch": 0.3178206583427923,
      "eval_loss": 0.3678199350833893,
      "eval_model_preparation_time": 0.0081,
      "eval_runtime": 12.8047,
      "eval_samples_per_second": 79.971,
      "eval_steps_per_second": 2.499,
      "step": 280
    },
    {
      "epoch": 0.36322360953461974,
      "grad_norm": 1.71875,
      "learning_rate": 1.1979701719998454e-06,
      "loss": 0.3693,
      "step": 320
    },
    {
      "epoch": 0.36322360953461974,
      "eval_loss": 0.36460334062576294,
      "eval_model_preparation_time": 0.0081,
      "eval_runtime": 12.7939,
      "eval_samples_per_second": 80.038,
      "eval_steps_per_second": 2.501,
      "step": 320
    },
    {
      "epoch": 0.4086265607264472,
      "grad_norm": 2.25,
      "learning_rate": 3.166390537580122e-07,
      "loss": 0.3772,
      "step": 360
    },
    {
      "epoch": 0.4086265607264472,
      "eval_loss": 0.36397936940193176,
      "eval_model_preparation_time": 0.0081,
      "eval_runtime": 12.7983,
      "eval_samples_per_second": 80.011,
      "eval_steps_per_second": 2.5,
      "step": 360
    },
    {
      "epoch": 0.4540295119182747,
      "grad_norm": 1.734375,
      "learning_rate": 1.903846791434516e-10,
      "loss": 0.3684,
      "step": 400
    },
    {
      "epoch": 0.4540295119182747,
      "eval_loss": 0.36452436447143555,
      "eval_model_preparation_time": 0.0081,
      "eval_runtime": 12.7892,
      "eval_samples_per_second": 80.067,
      "eval_steps_per_second": 2.502,
      "step": 400
    }
  ],
  "logging_steps": 40,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.208164803588915e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}