{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.028429282160625444,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005685856432125089,
      "eval_loss": 1.8247241973876953,
      "eval_runtime": 60.082,
      "eval_samples_per_second": 12.333,
      "eval_steps_per_second": 6.175,
      "step": 1
    },
    {
      "epoch": 0.0028429282160625444,
      "grad_norm": 38.031349182128906,
      "learning_rate": 5e-05,
      "loss": 8.059,
      "step": 5
    },
    {
      "epoch": 0.005685856432125089,
      "grad_norm": 21.300106048583984,
      "learning_rate": 0.0001,
      "loss": 8.0232,
      "step": 10
    },
    {
      "epoch": 0.005685856432125089,
      "eval_loss": 1.6558767557144165,
      "eval_runtime": 60.536,
      "eval_samples_per_second": 12.241,
      "eval_steps_per_second": 6.129,
      "step": 10
    },
    {
      "epoch": 0.008528784648187633,
      "grad_norm": 17.596519470214844,
      "learning_rate": 9.619397662556435e-05,
      "loss": 6.7449,
      "step": 15
    },
    {
      "epoch": 0.011371712864250177,
      "grad_norm": 16.79132080078125,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.9149,
      "step": 20
    },
    {
      "epoch": 0.011371712864250177,
      "eval_loss": 1.564450979232788,
      "eval_runtime": 60.9336,
      "eval_samples_per_second": 12.161,
      "eval_steps_per_second": 6.089,
      "step": 20
    },
    {
      "epoch": 0.014214641080312722,
      "grad_norm": 15.55430793762207,
      "learning_rate": 6.91341716182545e-05,
      "loss": 5.6261,
      "step": 25
    },
    {
      "epoch": 0.017057569296375266,
      "grad_norm": 19.65045738220215,
      "learning_rate": 5e-05,
      "loss": 6.2795,
      "step": 30
    },
    {
      "epoch": 0.017057569296375266,
      "eval_loss": 1.5391863584518433,
      "eval_runtime": 60.8685,
      "eval_samples_per_second": 12.174,
      "eval_steps_per_second": 6.095,
      "step": 30
    },
    {
      "epoch": 0.01990049751243781,
      "grad_norm": 10.385039329528809,
      "learning_rate": 3.086582838174551e-05,
      "loss": 5.5755,
      "step": 35
    },
    {
      "epoch": 0.022743425728500355,
      "grad_norm": 17.608741760253906,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 6.4154,
      "step": 40
    },
    {
      "epoch": 0.022743425728500355,
      "eval_loss": 1.5208227634429932,
      "eval_runtime": 61.1128,
      "eval_samples_per_second": 12.125,
      "eval_steps_per_second": 6.071,
      "step": 40
    },
    {
      "epoch": 0.0255863539445629,
      "grad_norm": 11.478259086608887,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 6.3918,
      "step": 45
    },
    {
      "epoch": 0.028429282160625444,
      "grad_norm": 11.493557929992676,
      "learning_rate": 0.0,
      "loss": 5.6759,
      "step": 50
    },
    {
      "epoch": 0.028429282160625444,
      "eval_loss": 1.5186352729797363,
      "eval_runtime": 60.8233,
      "eval_samples_per_second": 12.183,
      "eval_steps_per_second": 6.1,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1436183489871872e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}