{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008592910848549946,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "grad_norm": 0.6365009546279907,
      "learning_rate": 2e-05,
      "loss": 9.1012,
      "step": 1
    },
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 2.3472936153411865,
      "eval_runtime": 5.8059,
      "eval_samples_per_second": 84.397,
      "eval_steps_per_second": 42.199,
      "step": 1
    },
    {
      "epoch": 0.0017185821697099893,
      "grad_norm": 0.6434097290039062,
      "learning_rate": 4e-05,
      "loss": 9.1565,
      "step": 2
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 0.5617024302482605,
      "learning_rate": 6e-05,
      "loss": 8.994,
      "step": 3
    },
    {
      "epoch": 0.0025778732545649837,
      "eval_loss": 2.347203016281128,
      "eval_runtime": 5.7549,
      "eval_samples_per_second": 85.145,
      "eval_steps_per_second": 42.573,
      "step": 3
    },
    {
      "epoch": 0.0034371643394199786,
      "grad_norm": 0.5764390230178833,
      "learning_rate": 8e-05,
      "loss": 9.6451,
      "step": 4
    },
    {
      "epoch": 0.004296455424274973,
      "grad_norm": 0.6233522891998291,
      "learning_rate": 0.0001,
      "loss": 9.2905,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 0.6683151125907898,
      "learning_rate": 0.00012,
      "loss": 9.4995,
      "step": 6
    },
    {
      "epoch": 0.0051557465091299675,
      "eval_loss": 2.344770669937134,
      "eval_runtime": 5.9643,
      "eval_samples_per_second": 82.156,
      "eval_steps_per_second": 41.078,
      "step": 6
    },
    {
      "epoch": 0.006015037593984963,
      "grad_norm": 0.6831635236740112,
      "learning_rate": 0.00014,
      "loss": 8.5867,
      "step": 7
    },
    {
      "epoch": 0.006874328678839957,
      "grad_norm": 0.7074967622756958,
      "learning_rate": 0.00016,
      "loss": 9.2918,
      "step": 8
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 0.6262189149856567,
      "learning_rate": 0.00018,
      "loss": 8.5916,
      "step": 9
    },
    {
      "epoch": 0.007733619763694952,
      "eval_loss": 2.335700750350952,
      "eval_runtime": 5.9388,
      "eval_samples_per_second": 82.509,
      "eval_steps_per_second": 41.254,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "grad_norm": 0.9625266790390015,
      "learning_rate": 0.0002,
      "loss": 9.5679,
      "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": 42445433733120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}