{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06956521739130435,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01391304347826087,
      "grad_norm": 0.006644553504884243,
      "learning_rate": 1e-05,
      "loss": 11.9327,
      "step": 1
    },
    {
      "epoch": 0.01391304347826087,
      "eval_loss": 11.931827545166016,
      "eval_runtime": 14.036,
      "eval_samples_per_second": 8.621,
      "eval_steps_per_second": 4.346,
      "step": 1
    },
    {
      "epoch": 0.02782608695652174,
      "grad_norm": 0.010138041339814663,
      "learning_rate": 2e-05,
      "loss": 11.9294,
      "step": 2
    },
    {
      "epoch": 0.02782608695652174,
      "eval_loss": 11.9318265914917,
      "eval_runtime": 0.1907,
      "eval_samples_per_second": 634.519,
      "eval_steps_per_second": 319.882,
      "step": 2
    },
    {
      "epoch": 0.04173913043478261,
      "grad_norm": 0.008350933901965618,
      "learning_rate": 3e-05,
      "loss": 11.9339,
      "step": 3
    },
    {
      "epoch": 0.05565217391304348,
      "grad_norm": 0.005904448218643665,
      "learning_rate": 4e-05,
      "loss": 11.9335,
      "step": 4
    },
    {
      "epoch": 0.05565217391304348,
      "eval_loss": 11.931821823120117,
      "eval_runtime": 0.2125,
      "eval_samples_per_second": 569.45,
      "eval_steps_per_second": 287.078,
      "step": 4
    },
    {
      "epoch": 0.06956521739130435,
      "grad_norm": 0.00795205682516098,
      "learning_rate": 5e-05,
      "loss": 11.9293,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2363228160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}