{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9473684210526314,
  "eval_steps": 500,
  "global_step": 126,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 0.5355339646339417,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.6537,
      "step": 10
    },
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 0.20671233534812927,
      "learning_rate": 4.975884657667922e-05,
      "loss": 0.5325,
      "step": 20
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.22667203843593597,
      "learning_rate": 4.7857443822096905e-05,
      "loss": 0.4695,
      "step": 30
    },
    {
      "epoch": 0.935672514619883,
      "grad_norm": 0.1748281568288803,
      "learning_rate": 4.420066015704105e-05,
      "loss": 0.4714,
      "step": 40
    },
    {
      "epoch": 1.1695906432748537,
      "grad_norm": 0.2946503460407257,
      "learning_rate": 3.9069325244239095e-05,
      "loss": 0.3367,
      "step": 50
    },
    {
      "epoch": 1.4035087719298245,
      "grad_norm": 0.42143750190734863,
      "learning_rate": 3.285750971649167e-05,
      "loss": 0.2901,
      "step": 60
    },
    {
      "epoch": 1.6374269005847952,
      "grad_norm": 0.2530311942100525,
      "learning_rate": 2.6736207876813646e-05,
      "loss": 0.3032,
      "step": 70
    },
    {
      "epoch": 1.871345029239766,
      "grad_norm": 0.1768988072872162,
      "learning_rate": 1.982487176740627e-05,
      "loss": 0.2853,
      "step": 80
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.3087441325187683,
      "learning_rate": 1.3929797833664013e-05,
      "loss": 0.2695,
      "step": 90
    },
    {
      "epoch": 2.3391812865497075,
      "grad_norm": 0.2012886106967926,
      "learning_rate": 8.202980953574735e-06,
      "loss": 0.1931,
      "step": 100
    },
    {
      "epoch": 2.573099415204678,
      "grad_norm": 0.148341104388237,
      "learning_rate": 3.7661231264943086e-06,
      "loss": 0.1779,
      "step": 110
    },
    {
      "epoch": 2.807017543859649,
      "grad_norm": 0.17457139492034912,
      "learning_rate": 9.599612953967746e-07,
      "loss": 0.1911,
      "step": 120
    },
    {
      "epoch": 2.9473684210526314,
      "step": 126,
      "total_flos": 1.7234812004519117e+18,
      "train_loss": 0.3399257877516368,
      "train_runtime": 10447.3037,
      "train_samples_per_second": 0.393,
      "train_steps_per_second": 0.012
    }
  ],
  "logging_steps": 10,
  "max_steps": 126,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7234812004519117e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}