{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006861181152335374,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.861181152335375e-05,
      "grad_norm": 2.1441073417663574,
      "learning_rate": 2e-05,
      "loss": 4.9116,
      "step": 1
    },
    {
      "epoch": 6.861181152335375e-05,
      "eval_loss": 4.604319095611572,
      "eval_runtime": 233.9836,
      "eval_samples_per_second": 26.228,
      "eval_steps_per_second": 13.116,
      "step": 1
    },
    {
      "epoch": 0.0001372236230467075,
      "grad_norm": 1.9458142518997192,
      "learning_rate": 4e-05,
      "loss": 4.5221,
      "step": 2
    },
    {
      "epoch": 0.00020583543457006125,
      "grad_norm": 2.0711398124694824,
      "learning_rate": 6e-05,
      "loss": 4.8797,
      "step": 3
    },
    {
      "epoch": 0.00020583543457006125,
      "eval_loss": 4.589332580566406,
      "eval_runtime": 231.9652,
      "eval_samples_per_second": 26.457,
      "eval_steps_per_second": 13.23,
      "step": 3
    },
    {
      "epoch": 0.000274447246093415,
      "grad_norm": 1.8909467458724976,
      "learning_rate": 8e-05,
      "loss": 4.5326,
      "step": 4
    },
    {
      "epoch": 0.0003430590576167687,
      "grad_norm": 2.2932982444763184,
      "learning_rate": 0.0001,
      "loss": 4.8023,
      "step": 5
    },
    {
      "epoch": 0.0004116708691401225,
      "grad_norm": 2.753103494644165,
      "learning_rate": 0.00012,
      "loss": 4.4773,
      "step": 6
    },
    {
      "epoch": 0.0004116708691401225,
      "eval_loss": 4.165267467498779,
      "eval_runtime": 232.0307,
      "eval_samples_per_second": 26.449,
      "eval_steps_per_second": 13.227,
      "step": 6
    },
    {
      "epoch": 0.0004802826806634762,
      "grad_norm": 2.441800355911255,
      "learning_rate": 0.00014,
      "loss": 3.8999,
      "step": 7
    },
    {
      "epoch": 0.00054889449218683,
      "grad_norm": 3.2049639225006104,
      "learning_rate": 0.00016,
      "loss": 3.5331,
      "step": 8
    },
    {
      "epoch": 0.0006175063037101837,
      "grad_norm": 2.61136531829834,
      "learning_rate": 0.00018,
      "loss": 3.4902,
      "step": 9
    },
    {
      "epoch": 0.0006175063037101837,
      "eval_loss": 2.9883694648742676,
      "eval_runtime": 232.1027,
      "eval_samples_per_second": 26.441,
      "eval_steps_per_second": 13.223,
      "step": 9
    },
    {
      "epoch": 0.0006861181152335374,
      "grad_norm": 2.8295400142669678,
      "learning_rate": 0.0002,
      "loss": 2.9575,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2570388167983104.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}